c3e03886d6
Model: fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
30090 lines
825 KiB
JSON
30090 lines
825 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.36066763425254,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.872125720977783,
|
|
"epoch": 0.27258708272859217,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996263683987316,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.1507551245391369,
|
|
"num_tokens": 6226264.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.812562322616577,
|
|
"epoch": 0.2730406386066763,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996245021631033,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15249016731977463,
|
|
"num_tokens": 6235137.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.790219068527222,
|
|
"epoch": 0.27349419448476053,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499622631282183,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.15375427156686783,
|
|
"num_tokens": 6245411.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.873235607147217,
|
|
"epoch": 0.2739477503628447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996207557560095,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.14681091234087945,
|
|
"num_tokens": 6255633.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.818582916259766,
|
|
"epoch": 0.2744013062409289,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996188755846216,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.1482468992471695,
|
|
"num_tokens": 6265109.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.841054964065552,
|
|
"epoch": 0.27485486211901305,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499616990768058,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.14764970988035203,
|
|
"num_tokens": 6275241.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.906813526153565,
|
|
"epoch": 0.27530841799709727,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996151013063579,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.14210136905312537,
|
|
"num_tokens": 6286603.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.801692199707031,
|
|
"epoch": 0.2757619738751814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996132071995601,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.1628328561782837,
|
|
"num_tokens": 6297219.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.741138601303101,
|
|
"epoch": 0.2762155297532656,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996113084477042,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.1547319009900093,
|
|
"num_tokens": 6307694.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.750327444076538,
|
|
"epoch": 0.2766690856313498,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996094050508291,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.15616930574178695,
|
|
"num_tokens": 6317384.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.863014984130859,
|
|
"epoch": 0.27712264150943394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996074970089741,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14901937842369078,
|
|
"num_tokens": 6327558.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.802416276931763,
|
|
"epoch": 0.27757619738751815,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996055843221789,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.16094797402620314,
|
|
"num_tokens": 6337828.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.804899978637695,
|
|
"epoch": 0.2780297532656023,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996036669904831,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.1513446494936943,
|
|
"num_tokens": 6348678.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.784188747406006,
|
|
"epoch": 0.2784833091436865,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996017450139261,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.1463714897632599,
|
|
"num_tokens": 6359670.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.87315411567688,
|
|
"epoch": 0.2789368650217707,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995998183925478,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.15490294694900514,
|
|
"num_tokens": 6371034.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.775865983963013,
|
|
"epoch": 0.2793904208998549,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995978871263881,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.1566627189517021,
|
|
"num_tokens": 6380672.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.811061096191406,
|
|
"epoch": 0.27984397677793904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995959512154868,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.1400656595826149,
|
|
"num_tokens": 6390799.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.772877502441406,
|
|
"epoch": 0.2802975326560232,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499594010659884,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.15223535746335984,
|
|
"num_tokens": 6400965.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.814068937301636,
|
|
"epoch": 0.2807510885341074,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995920654596199,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.14599630907177924,
|
|
"num_tokens": 6411567.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.83027400970459,
|
|
"epoch": 0.28120464441219156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995901156147345,
|
|
"loss": 5.804,
|
|
"mean_token_accuracy": 0.1567014843225479,
|
|
"num_tokens": 6421193.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.850267601013184,
|
|
"epoch": 0.2816582002902758,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995881611252684,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.15475278794765474,
|
|
"num_tokens": 6430281.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.7939496517181395,
|
|
"epoch": 0.28211175616835993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995862019912619,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.146951512247324,
|
|
"num_tokens": 6441055.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.824093437194824,
|
|
"epoch": 0.28256531204644414,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995842382127555,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.15018295422196387,
|
|
"num_tokens": 6451082.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.802210283279419,
|
|
"epoch": 0.2830188679245283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995822697897897,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.14790797382593154,
|
|
"num_tokens": 6461617.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.898024320602417,
|
|
"epoch": 0.2834724238026125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995802967224056,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.14873994886875153,
|
|
"num_tokens": 6472780.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.7456702709198,
|
|
"epoch": 0.28392597968069666,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995783190106434,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.15184671580791473,
|
|
"num_tokens": 6484078.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.8592980861663815,
|
|
"epoch": 0.2843795355587808,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995763366545445,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.14368489608168603,
|
|
"num_tokens": 6494366.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.727130985260009,
|
|
"epoch": 0.284833091436865,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995743496541497,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.15323618352413176,
|
|
"num_tokens": 6505461.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.864217281341553,
|
|
"epoch": 0.2852866473149492,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995723580095001,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.15169936046004295,
|
|
"num_tokens": 6516141.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.699955415725708,
|
|
"epoch": 0.2857402031930334,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499570361720637,
|
|
"loss": 5.7494,
|
|
"mean_token_accuracy": 0.15026842653751374,
|
|
"num_tokens": 6525536.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.858482599258423,
|
|
"epoch": 0.28619375907111755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995683607876015,
|
|
"loss": 5.807,
|
|
"mean_token_accuracy": 0.1474149063229561,
|
|
"num_tokens": 6535852.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.877813768386841,
|
|
"epoch": 0.28664731494920176,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995663552104352,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.15658673495054246,
|
|
"num_tokens": 6546353.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.71932168006897,
|
|
"epoch": 0.2871008708272859,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995643449891793,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.15023708939552308,
|
|
"num_tokens": 6557782.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.821673774719239,
|
|
"epoch": 0.2875544267053701,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995623301238757,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.15660330504179001,
|
|
"num_tokens": 6568100.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.765221214294433,
|
|
"epoch": 0.2880079825834543,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995603106145657,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.14751623272895814,
|
|
"num_tokens": 6578698.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.8275402069091795,
|
|
"epoch": 0.28846153846153844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995582864612913,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.14643221199512482,
|
|
"num_tokens": 6588908.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.737450218200683,
|
|
"epoch": 0.28891509433962265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995562576640943,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15332392156124114,
|
|
"num_tokens": 6599445.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.767725610733033,
|
|
"epoch": 0.2893686502177068,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995542242230167,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.15147417038679123,
|
|
"num_tokens": 6610246.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.761809396743774,
|
|
"epoch": 0.289822206095791,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995521861381006,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.1523432895541191,
|
|
"num_tokens": 6620501.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.912834644317627,
|
|
"epoch": 0.29027576197387517,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499550143409388,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.14403355419635772,
|
|
"num_tokens": 6631206.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.721426582336425,
|
|
"epoch": 0.2907293178519594,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995480960369211,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.14767736345529556,
|
|
"num_tokens": 6641600.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.808769845962525,
|
|
"epoch": 0.29118287373004353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995460440207425,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.14944822043180467,
|
|
"num_tokens": 6652319.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.869615316390991,
|
|
"epoch": 0.29163642960812775,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995439873608945,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.1475253716111183,
|
|
"num_tokens": 6663702.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.792519235610962,
|
|
"epoch": 0.2920899854862119,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995419260574196,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.1453598067164421,
|
|
"num_tokens": 6673908.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.787820816040039,
|
|
"epoch": 0.29254354136429606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995398601103603,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.15197647958993912,
|
|
"num_tokens": 6683237.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.817029237747192,
|
|
"epoch": 0.29299709724238027,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995377895197597,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15499222725629808,
|
|
"num_tokens": 6693451.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.665473747253418,
|
|
"epoch": 0.2934506531204644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995357142856602,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.15413334965705872,
|
|
"num_tokens": 6703479.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.710675239562988,
|
|
"epoch": 0.29390420899854863,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499533634408105,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.15576022118330002,
|
|
"num_tokens": 6715321.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.783253860473633,
|
|
"epoch": 0.2943577648766328,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499531549887137,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15394483953714372,
|
|
"num_tokens": 6725541.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.759927129745483,
|
|
"epoch": 0.294811320754717,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995294607227993,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.1588973805308342,
|
|
"num_tokens": 6735165.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.8403795719146725,
|
|
"epoch": 0.29526487663280115,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995273669151351,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.15932275354862213,
|
|
"num_tokens": 6744245.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.75037317276001,
|
|
"epoch": 0.29571843251088537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499525268464188,
|
|
"loss": 5.7239,
|
|
"mean_token_accuracy": 0.1572644904255867,
|
|
"num_tokens": 6754894.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.779234743118286,
|
|
"epoch": 0.2961719883889695,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995231653700009,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.14348074272274972,
|
|
"num_tokens": 6764442.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.824223375320434,
|
|
"epoch": 0.2966255442670537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995210576326176,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.14877086579799653,
|
|
"num_tokens": 6775054.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.795979833602905,
|
|
"epoch": 0.2970791001451379,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995189452520816,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.1630966395139694,
|
|
"num_tokens": 6784825.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.796776056289673,
|
|
"epoch": 0.29753265602322204,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995168282284366,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.15851086676120757,
|
|
"num_tokens": 6795928.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.693297910690307,
|
|
"epoch": 0.29798621190130625,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995147065617263,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.1500129833817482,
|
|
"num_tokens": 6805456.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.815392637252808,
|
|
"epoch": 0.2984397677793904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995125802519946,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.15002186894416808,
|
|
"num_tokens": 6816215.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.834223985671997,
|
|
"epoch": 0.2988933236574746,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995104492992857,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.14767192974686622,
|
|
"num_tokens": 6826545.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.70528507232666,
|
|
"epoch": 0.2993468795355588,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995083137036434,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.15581652522087097,
|
|
"num_tokens": 6836184.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.8633002758026125,
|
|
"epoch": 0.299800435413643,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995061734651121,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.15215000808238982,
|
|
"num_tokens": 6846646.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.830773496627808,
|
|
"epoch": 0.30025399129172714,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995040285837358,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.16062179654836656,
|
|
"num_tokens": 6857597.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.789421701431275,
|
|
"epoch": 0.3007075471698113,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995018790595589,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.15099546015262605,
|
|
"num_tokens": 6867523.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.900367307662964,
|
|
"epoch": 0.3011611030478955,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994997248926261,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.14628595039248465,
|
|
"num_tokens": 6878190.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.762005186080932,
|
|
"epoch": 0.30161465892597966,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994975660829817,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.16212552934885024,
|
|
"num_tokens": 6888483.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.688748073577881,
|
|
"epoch": 0.3020682148040639,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994954026306705,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.15575181618332862,
|
|
"num_tokens": 6898337.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.831185674667358,
|
|
"epoch": 0.30252177068214803,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994932345357371,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.1522991269826889,
|
|
"num_tokens": 6909131.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.75893816947937,
|
|
"epoch": 0.30297532656023224,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994910617982264,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.14802005887031555,
|
|
"num_tokens": 6919790.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.829823637008667,
|
|
"epoch": 0.3034288824383164,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994888844181833,
|
|
"loss": 5.7614,
|
|
"mean_token_accuracy": 0.1517559289932251,
|
|
"num_tokens": 6930072.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.741778373718262,
|
|
"epoch": 0.3038824383164006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994867023956529,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.15023863464593887,
|
|
"num_tokens": 6940646.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.6631731510162355,
|
|
"epoch": 0.30433599419448476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994845157306803,
|
|
"loss": 5.6513,
|
|
"mean_token_accuracy": 0.15208848789334298,
|
|
"num_tokens": 6951645.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.856181573867798,
|
|
"epoch": 0.3047895500725689,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994823244233107,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15186134427785875,
|
|
"num_tokens": 6963020.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.821042013168335,
|
|
"epoch": 0.3052431059506531,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994801284735895,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.15716724395751952,
|
|
"num_tokens": 6972895.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.8223480701446535,
|
|
"epoch": 0.3056966618287373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994779278815619,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.14308758080005646,
|
|
"num_tokens": 6985363.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.8458006381988525,
|
|
"epoch": 0.3061502177068215,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004994757226472736,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.15202625691890717,
|
|
"num_tokens": 6997040.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.806244993209839,
|
|
"epoch": 0.30660377358490565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994735127707702,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.15390410125255585,
|
|
"num_tokens": 7007591.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.826634693145752,
|
|
"epoch": 0.30705732946298986,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994712982520972,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.16007999330759048,
|
|
"num_tokens": 7017858.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.678028774261475,
|
|
"epoch": 0.307510885341074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994690790913008,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.15252023860812186,
|
|
"num_tokens": 7027365.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.743245077133179,
|
|
"epoch": 0.3079644412191582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994668552884265,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.15393923968076706,
|
|
"num_tokens": 7038728.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.860477924346924,
|
|
"epoch": 0.3084179970972424,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994646268435204,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.15698569566011428,
|
|
"num_tokens": 7048736.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.672683954238892,
|
|
"epoch": 0.30887155297532654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994623937566286,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.15398403406143188,
|
|
"num_tokens": 7059205.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.810827445983887,
|
|
"epoch": 0.30932510885341075,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994601560277974,
|
|
"loss": 5.7705,
|
|
"mean_token_accuracy": 0.151111601293087,
|
|
"num_tokens": 7069513.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.794088840484619,
|
|
"epoch": 0.3097786647314949,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499457913657073,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.15149736255407334,
|
|
"num_tokens": 7079940.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.805775165557861,
|
|
"epoch": 0.3102322206095791,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994556666445016,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.1570603534579277,
|
|
"num_tokens": 7090792.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.662250566482544,
|
|
"epoch": 0.31068577648766327,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994534149901299,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15090260058641433,
|
|
"num_tokens": 7101964.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.749277830123901,
|
|
"epoch": 0.3111393323657475,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994511586940044,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.15125103592872619,
|
|
"num_tokens": 7113332.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.871686697006226,
|
|
"epoch": 0.31159288824383163,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994488977561717,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.14723959863185881,
|
|
"num_tokens": 7123481.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.696882629394532,
|
|
"epoch": 0.31204644412191584,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994466321766786,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.15849945396184922,
|
|
"num_tokens": 7133694.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.741990947723389,
|
|
"epoch": 0.3125,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499444361955572,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.15803271979093553,
|
|
"num_tokens": 7144491.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.9043221950531,
|
|
"epoch": 0.31295355587808416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994420870928988,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.14943068027496337,
|
|
"num_tokens": 7154716.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.81868691444397,
|
|
"epoch": 0.31340711175616837,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994398075887059,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.14441180527210234,
|
|
"num_tokens": 7164258.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.822063636779785,
|
|
"epoch": 0.3138606676342525,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994375234430407,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.15146763920783995,
|
|
"num_tokens": 7175098.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.750956344604492,
|
|
"epoch": 0.31431422351233673,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994352346559504,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.15109349340200423,
|
|
"num_tokens": 7186480.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.7146683692932125,
|
|
"epoch": 0.3147677793904209,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994329412274821,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.15527350157499314,
|
|
"num_tokens": 7197056.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.814749813079834,
|
|
"epoch": 0.3152213352685051,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994306431576835,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.14993275180459023,
|
|
"num_tokens": 7206040.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.851417589187622,
|
|
"epoch": 0.31567489114658925,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499428340446602,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.15531422793865204,
|
|
"num_tokens": 7216344.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.784599637985229,
|
|
"epoch": 0.31612844702467346,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994260330942851,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.1495263546705246,
|
|
"num_tokens": 7226729.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.67893795967102,
|
|
"epoch": 0.3165820029027576,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994237211007808,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15380621552467347,
|
|
"num_tokens": 7237616.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.821342611312867,
|
|
"epoch": 0.3170355587808418,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994214044661367,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.1568485826253891,
|
|
"num_tokens": 7247857.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.650297212600708,
|
|
"epoch": 0.317489114658926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994190831904007,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.16020147651433944,
|
|
"num_tokens": 7257858.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.652521848678589,
|
|
"epoch": 0.31794267053701014,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499416757273621,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.15801683515310289,
|
|
"num_tokens": 7268440.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.8561008930206295,
|
|
"epoch": 0.31839622641509435,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994144267158454,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15808832198381423,
|
|
"num_tokens": 7278560.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.721616554260254,
|
|
"epoch": 0.3188497822931785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994120915171224,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15598661005496978,
|
|
"num_tokens": 7288422.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.822176361083985,
|
|
"epoch": 0.3193033381712627,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994097516775002,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.1543071150779724,
|
|
"num_tokens": 7298613.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.81471004486084,
|
|
"epoch": 0.3197568940493469,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994074071970271,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.1467634655535221,
|
|
"num_tokens": 7309509.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.774685192108154,
|
|
"epoch": 0.3202104499274311,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994050580757515,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.15079469233751297,
|
|
"num_tokens": 7319015.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.718948554992676,
|
|
"epoch": 0.32066400580551524,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994027043137223,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.16023388206958772,
|
|
"num_tokens": 7329026.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.813447046279907,
|
|
"epoch": 0.3211175616835994,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994003459109879,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.1511634275317192,
|
|
"num_tokens": 7339638.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.781355905532837,
|
|
"epoch": 0.3215711175616836,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993979828675972,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.15422995537519454,
|
|
"num_tokens": 7349979.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.67366590499878,
|
|
"epoch": 0.32202467343976776,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499395615183599,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.1652266263961792,
|
|
"num_tokens": 7359398.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.656069612503051,
|
|
"epoch": 0.32247822931785197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993932428590422,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.15403880178928375,
|
|
"num_tokens": 7370418.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.780758047103882,
|
|
"epoch": 0.3229317851959361,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993908658939762,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.1502725899219513,
|
|
"num_tokens": 7380461.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.806817102432251,
|
|
"epoch": 0.32338534107402034,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993884842884496,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.15863013118505478,
|
|
"num_tokens": 7390646.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.747936010360718,
|
|
"epoch": 0.3238388969521045,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993860980425121,
|
|
"loss": 5.8076,
|
|
"mean_token_accuracy": 0.155539433658123,
|
|
"num_tokens": 7402106.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.781191968917847,
|
|
"epoch": 0.3242924528301887,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993837071562131,
|
|
"loss": 5.7951,
|
|
"mean_token_accuracy": 0.15347181856632233,
|
|
"num_tokens": 7412936.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.744540643692017,
|
|
"epoch": 0.32474600870827286,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993813116296017,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.15949824452400208,
|
|
"num_tokens": 7422303.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.784517669677735,
|
|
"epoch": 0.325199564586357,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993789114627275,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.15309756696224214,
|
|
"num_tokens": 7432829.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.81943531036377,
|
|
"epoch": 0.3256531204644412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993765066556403,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.15031561404466628,
|
|
"num_tokens": 7443218.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.7325328350067135,
|
|
"epoch": 0.3261066763425254,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993740972083899,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.15189058780670167,
|
|
"num_tokens": 7454531.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.796178579330444,
|
|
"epoch": 0.3265602322206096,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993716831210259,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.1558135211467743,
|
|
"num_tokens": 7464993.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.710817050933838,
|
|
"epoch": 0.32701378809869375,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993692643935983,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.15145019814372063,
|
|
"num_tokens": 7475755.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.791586971282959,
|
|
"epoch": 0.32746734397677796,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993668410261571,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.15512488633394242,
|
|
"num_tokens": 7486778.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.883192777633667,
|
|
"epoch": 0.3279208998548621,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993644130187525,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.15393500328063964,
|
|
"num_tokens": 7497439.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.713404703140259,
|
|
"epoch": 0.3283744557329463,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993619803714347,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.149221783131361,
|
|
"num_tokens": 7508274.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.824280738830566,
|
|
"epoch": 0.3288280116110305,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993595430842539,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.15261871069669725,
|
|
"num_tokens": 7519315.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.868468761444092,
|
|
"epoch": 0.32928156748911463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993571011572606,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.15521898567676545,
|
|
"num_tokens": 7529910.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.664683103561401,
|
|
"epoch": 0.32973512336719885,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993546545905053,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.15814965665340425,
|
|
"num_tokens": 7538966.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.843475103378296,
|
|
"epoch": 0.330188679245283,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993522033840386,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.14933252111077308,
|
|
"num_tokens": 7549683.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.716665935516358,
|
|
"epoch": 0.3306422351233672,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499349747537911,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.15621910542249678,
|
|
"num_tokens": 7560629.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.719961214065552,
|
|
"epoch": 0.33109579100145137,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993472870521736,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.1616758957505226,
|
|
"num_tokens": 7570613.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.70309534072876,
|
|
"epoch": 0.3315493468795356,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993448219268771,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.15617789477109909,
|
|
"num_tokens": 7580640.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.7273846626281735,
|
|
"epoch": 0.33200290275761973,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993423521620726,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.1586635485291481,
|
|
"num_tokens": 7590164.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.818833351135254,
|
|
"epoch": 0.33245645863570394,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993398777578109,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.15034616962075234,
|
|
"num_tokens": 7600173.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.7085833072662355,
|
|
"epoch": 0.3329100145137881,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993373987141435,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.16563706398010253,
|
|
"num_tokens": 7609958.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.732572078704834,
|
|
"epoch": 0.33336357039187225,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993349150311214,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.15159249901771546,
|
|
"num_tokens": 7620237.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.698968887329102,
|
|
"epoch": 0.33381712626995647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993324267087962,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.1608090043067932,
|
|
"num_tokens": 7629886.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.755589199066162,
|
|
"epoch": 0.3342706821480406,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993299337472192,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.15914253294467925,
|
|
"num_tokens": 7640057.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.7210606098175045,
|
|
"epoch": 0.33472423802612483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499327436146442,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15623899549245834,
|
|
"num_tokens": 7649766.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.704188871383667,
|
|
"epoch": 0.335177793904209,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993249339065162,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.15833286568522453,
|
|
"num_tokens": 7660890.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.789506959915161,
|
|
"epoch": 0.3356313497822932,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993224270274937,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.15361475795507432,
|
|
"num_tokens": 7670737.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.6635422706604,
|
|
"epoch": 0.33608490566037735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993199155094263,
|
|
"loss": 5.6866,
|
|
"mean_token_accuracy": 0.15698174983263016,
|
|
"num_tokens": 7681407.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.730187511444091,
|
|
"epoch": 0.33653846153846156,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993173993523658,
|
|
"loss": 5.6158,
|
|
"mean_token_accuracy": 0.16286221295595169,
|
|
"num_tokens": 7691758.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.675654602050781,
|
|
"epoch": 0.3369920174165457,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993148785563643,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15679143369197845,
|
|
"num_tokens": 7702934.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.694839334487915,
|
|
"epoch": 0.3374455732946299,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499312353121474,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.15497201532125474,
|
|
"num_tokens": 7713001.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.801605463027954,
|
|
"epoch": 0.3378991291727141,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993098230477471,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.14621546119451523,
|
|
"num_tokens": 7724005.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.722197771072388,
|
|
"epoch": 0.33835268505079824,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993072883352358,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.15557765886187552,
|
|
"num_tokens": 7733743.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.782563161849976,
|
|
"epoch": 0.33880624092888245,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993047489839927,
|
|
"loss": 5.8425,
|
|
"mean_token_accuracy": 0.1471106566488743,
|
|
"num_tokens": 7743762.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.88274621963501,
|
|
"epoch": 0.3392597968069666,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993022049940702,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.15454336851835251,
|
|
"num_tokens": 7753758.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.700439834594727,
|
|
"epoch": 0.3397133526850508,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992996563655209,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.15768471136689186,
|
|
"num_tokens": 7764692.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.702702379226684,
|
|
"epoch": 0.340166908563135,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992971030983975,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.155170801281929,
|
|
"num_tokens": 7776892.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.838658714294434,
|
|
"epoch": 0.3406204644412192,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992945451927531,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.15279003530740737,
|
|
"num_tokens": 7787143.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.725220155715943,
|
|
"epoch": 0.34107402031930334,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992919826486402,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.1564330369234085,
|
|
"num_tokens": 7798537.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.685366582870484,
|
|
"epoch": 0.3415275761973875,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992894154661118,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.1586100533604622,
|
|
"num_tokens": 7808434.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.7612800121307375,
|
|
"epoch": 0.3419811320754717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992868436452213,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.15543903708457946,
|
|
"num_tokens": 7819592.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.801908349990844,
|
|
"epoch": 0.34243468795355586,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992842671860217,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.16048139780759813,
|
|
"num_tokens": 7830602.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.761849641799927,
|
|
"epoch": 0.34288824383164007,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992816860885662,
|
|
"loss": 5.8073,
|
|
"mean_token_accuracy": 0.1533203274011612,
|
|
"num_tokens": 7840850.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.884047603607177,
|
|
"epoch": 0.3433417997097242,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992791003529084,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.14962777942419053,
|
|
"num_tokens": 7852371.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.735295009613037,
|
|
"epoch": 0.34379535558780844,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992765099791017,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.1477210432291031,
|
|
"num_tokens": 7863290.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.721421813964843,
|
|
"epoch": 0.3442489114658926,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992739149671995,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.15730728954076767,
|
|
"num_tokens": 7873927.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.7242011547088625,
|
|
"epoch": 0.3447024673439768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992713153172556,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15784906297922136,
|
|
"num_tokens": 7884977.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.627726364135742,
|
|
"epoch": 0.34515602322206096,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992687110293238,
|
|
"loss": 5.7255,
|
|
"mean_token_accuracy": 0.16205305680632592,
|
|
"num_tokens": 7894620.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.740850877761841,
|
|
"epoch": 0.3456095791001451,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992661021034579,
|
|
"loss": 5.6443,
|
|
"mean_token_accuracy": 0.15828863084316253,
|
|
"num_tokens": 7904541.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.705569267272949,
|
|
"epoch": 0.3460631349782293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992634885397118,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.1567293658852577,
|
|
"num_tokens": 7915435.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.717358255386353,
|
|
"epoch": 0.3465166908563135,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992608703381396,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15847330242395402,
|
|
"num_tokens": 7925870.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.707509326934814,
|
|
"epoch": 0.3469702467343977,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992582474987955,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.151695054769516,
|
|
"num_tokens": 7937046.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.682017850875854,
|
|
"epoch": 0.34742380261248185,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992556200217337,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.15659248381853103,
|
|
"num_tokens": 7947150.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.776818370819091,
|
|
"epoch": 0.34787735849056606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992529879070085,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.15769558846950532,
|
|
"num_tokens": 7956815.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.83626880645752,
|
|
"epoch": 0.3483309143686502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992503511546745,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.15489998310804368,
|
|
"num_tokens": 7968114.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.773981189727783,
|
|
"epoch": 0.3487844702467344,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992477097647859,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15163280665874482,
|
|
"num_tokens": 7977840.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.754621744155884,
|
|
"epoch": 0.3492380261248186,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992450637373976,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.1560756802558899,
|
|
"num_tokens": 7988663.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.654491233825683,
|
|
"epoch": 0.34969158200290273,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992424130725642,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.15517864674329757,
|
|
"num_tokens": 7999693.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.813797044754028,
|
|
"epoch": 0.35014513788098695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992397577703406,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.1493635967373848,
|
|
"num_tokens": 8010154.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.859886837005615,
|
|
"epoch": 0.3505986937590711,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992370978307816,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.15075698494911194,
|
|
"num_tokens": 8020921.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.7340294361114506,
|
|
"epoch": 0.3510522496371553,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992344332539424,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1617124542593956,
|
|
"num_tokens": 8031404.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.685090446472168,
|
|
"epoch": 0.35150580551523947,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992317640398779,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.16097560971975328,
|
|
"num_tokens": 8041310.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.719081544876099,
|
|
"epoch": 0.3519593613933237,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992290901886434,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.15827004760503768,
|
|
"num_tokens": 8051054.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.7040183544158936,
|
|
"epoch": 0.35241291727140783,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499226411700294,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.16001638025045395,
|
|
"num_tokens": 8061063.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.758534955978393,
|
|
"epoch": 0.35286647314949204,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992237285748855,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.15772127062082292,
|
|
"num_tokens": 8071715.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.806764888763428,
|
|
"epoch": 0.3533200290275762,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992210408124731,
|
|
"loss": 5.7353,
|
|
"mean_token_accuracy": 0.14987001866102218,
|
|
"num_tokens": 8082679.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.712429571151733,
|
|
"epoch": 0.35377358490566035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992183484131123,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.1527717225253582,
|
|
"num_tokens": 8093785.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.746983051300049,
|
|
"epoch": 0.35422714078374457,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992156513768591,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.1591253861784935,
|
|
"num_tokens": 8105822.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.720091438293457,
|
|
"epoch": 0.3546806966618287,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499212949703769,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.1609518736600876,
|
|
"num_tokens": 8115521.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.691662406921386,
|
|
"epoch": 0.35513425253991293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992102433938981,
|
|
"loss": 5.672,
|
|
"mean_token_accuracy": 0.1599155269563198,
|
|
"num_tokens": 8125524.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.70084958076477,
|
|
"epoch": 0.3555878084179971,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992075324473021,
|
|
"loss": 5.5852,
|
|
"mean_token_accuracy": 0.16763251274824142,
|
|
"num_tokens": 8135552.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.827421236038208,
|
|
"epoch": 0.3560413642960813,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992048168640371,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.15760034322738647,
|
|
"num_tokens": 8145617.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.698878335952759,
|
|
"epoch": 0.35649492017416545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992020966441595,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.15130315870046615,
|
|
"num_tokens": 8156729.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.716935110092163,
|
|
"epoch": 0.35694847605224966,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991993717877254,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.15315268635749818,
|
|
"num_tokens": 8167637.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.789372968673706,
|
|
"epoch": 0.3574020319303338,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991966422947911,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.16331233233213424,
|
|
"num_tokens": 8177354.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.685820865631103,
|
|
"epoch": 0.357855587808418,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991939081654132,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.1660743162035942,
|
|
"num_tokens": 8187580.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.716048860549927,
|
|
"epoch": 0.3583091436865022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499191169399648,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.15225303024053574,
|
|
"num_tokens": 8199382.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.73907208442688,
|
|
"epoch": 0.35876269956458634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991884259975525,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15740728080272676,
|
|
"num_tokens": 8208484.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.742117643356323,
|
|
"epoch": 0.35921625544267055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499185677959183,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.15358153730630875,
|
|
"num_tokens": 8219056.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.73494143486023,
|
|
"epoch": 0.3596698113207547,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991829252845966,
|
|
"loss": 5.686,
|
|
"mean_token_accuracy": 0.152549646794796,
|
|
"num_tokens": 8230149.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.730507802963257,
|
|
"epoch": 0.3601233671988389,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991801679738502,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.14736442565917968,
|
|
"num_tokens": 8240803.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.757702302932739,
|
|
"epoch": 0.3605769230769231,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991774060270008,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.14796190112829208,
|
|
"num_tokens": 8251563.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.680777549743652,
|
|
"epoch": 0.3610304789550073,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991746394441055,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.15206940174102784,
|
|
"num_tokens": 8261342.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.735341548919678,
|
|
"epoch": 0.36148403483309144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991718682252216,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.15018298774957656,
|
|
"num_tokens": 8271540.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.823741292953491,
|
|
"epoch": 0.3619375907111756,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991690923704063,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.15624243170022964,
|
|
"num_tokens": 8280593.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.720953178405762,
|
|
"epoch": 0.3623911465892598,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991663118797171,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.15814144015312195,
|
|
"num_tokens": 8290126.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.742925214767456,
|
|
"epoch": 0.36284470246734396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991635267532113,
|
|
"loss": 5.637,
|
|
"mean_token_accuracy": 0.1533143252134323,
|
|
"num_tokens": 8301416.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.761494159698486,
|
|
"epoch": 0.36329825834542817,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991607369909468,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.1542692556977272,
|
|
"num_tokens": 8311034.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.755333518981933,
|
|
"epoch": 0.3637518142235123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991579425929811,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.1533808723092079,
|
|
"num_tokens": 8322203.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.734006357192993,
|
|
"epoch": 0.36420537010159654,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499155143559372,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.15972371846437455,
|
|
"num_tokens": 8330981.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.595567846298218,
|
|
"epoch": 0.3646589259796807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991523398901773,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.15632233768701553,
|
|
"num_tokens": 8341294.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.888984680175781,
|
|
"epoch": 0.3651124818577649,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991495315854553,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.14876558110117913,
|
|
"num_tokens": 8351824.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.706782484054566,
|
|
"epoch": 0.36556603773584906,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991467186452637,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.1557074546813965,
|
|
"num_tokens": 8361975.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.656030082702637,
|
|
"epoch": 0.3660195936139332,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991439010696609,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16090150475502013,
|
|
"num_tokens": 8372145.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.77086763381958,
|
|
"epoch": 0.3664731494920174,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991410788587051,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.1525834932923317,
|
|
"num_tokens": 8382542.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.766021776199341,
|
|
"epoch": 0.3669267053701016,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991382520124547,
|
|
"loss": 5.695,
|
|
"mean_token_accuracy": 0.15353819727897644,
|
|
"num_tokens": 8393450.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.739769554138183,
|
|
"epoch": 0.3673802612481858,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991354205309681,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15330485254526138,
|
|
"num_tokens": 8404929.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.684649848937989,
|
|
"epoch": 0.36783381712626995,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499132584414304,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.1600140005350113,
|
|
"num_tokens": 8415703.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.716530799865723,
|
|
"epoch": 0.36828737300435416,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991297436625207,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.15426832735538482,
|
|
"num_tokens": 8426220.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.657416963577271,
|
|
"epoch": 0.3687409288824383,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991268982756774,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.1579454243183136,
|
|
"num_tokens": 8436220.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.7623128414154055,
|
|
"epoch": 0.3691944847605225,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991240482538327,
|
|
"loss": 5.7639,
|
|
"mean_token_accuracy": 0.1493281066417694,
|
|
"num_tokens": 8446724.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.762617349624634,
|
|
"epoch": 0.3696480406386067,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991211935970455,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.15606819838285446,
|
|
"num_tokens": 8457270.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.686959457397461,
|
|
"epoch": 0.37010159651669083,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991183343053748,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.15353127270936967,
|
|
"num_tokens": 8468137.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.741979169845581,
|
|
"epoch": 0.37055515239477504,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049911547037888,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15946190059185028,
|
|
"num_tokens": 8477574.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.722776651382446,
|
|
"epoch": 0.3710087082728592,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991126018176202,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15095608532428742,
|
|
"num_tokens": 8487268.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.846265125274658,
|
|
"epoch": 0.3714622641509434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991097286216545,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.15681469887495042,
|
|
"num_tokens": 8497785.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.764314413070679,
|
|
"epoch": 0.37191582002902757,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991068507910427,
|
|
"loss": 5.637,
|
|
"mean_token_accuracy": 0.1572082445025444,
|
|
"num_tokens": 8508169.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.668509101867675,
|
|
"epoch": 0.3723693759071118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499103968325844,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.15181283801794052,
|
|
"num_tokens": 8519201.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.773807764053345,
|
|
"epoch": 0.37282293178519593,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991010812261181,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.15204160511493683,
|
|
"num_tokens": 8531093.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.656918621063232,
|
|
"epoch": 0.37327648766328014,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990981894919248,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.15744011104106903,
|
|
"num_tokens": 8541730.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.677169275283814,
|
|
"epoch": 0.3737300435413643,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990952931233238,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15572711825370789,
|
|
"num_tokens": 8552570.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.765596532821656,
|
|
"epoch": 0.37418359941944845,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499092392120375,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1613634631037712,
|
|
"num_tokens": 8562340.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.75891342163086,
|
|
"epoch": 0.37463715529753266,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990894864831385,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.14843543320894242,
|
|
"num_tokens": 8573240.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.706006050109863,
|
|
"epoch": 0.3750907111756168,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990865762116743,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.16231092363595961,
|
|
"num_tokens": 8583194.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.76061520576477,
|
|
"epoch": 0.37554426705370103,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990836613060426,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.15307701751589775,
|
|
"num_tokens": 8593603.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.7104448795318605,
|
|
"epoch": 0.3759978229317852,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990807417663036,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15583582669496537,
|
|
"num_tokens": 8603176.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.770629453659057,
|
|
"epoch": 0.3764513788098694,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990778175925179,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.15750074684619902,
|
|
"num_tokens": 8614801.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.818771934509277,
|
|
"epoch": 0.37690493468795355,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990748887847457,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.15358437448740006,
|
|
"num_tokens": 8624999.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.697445487976074,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990719553430477,
|
|
"loss": 5.5989,
|
|
"mean_token_accuracy": 0.16195421367883683,
|
|
"num_tokens": 8635358.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.751416826248169,
|
|
"epoch": 0.3778120464441219,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990690172674847,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.1510378047823906,
|
|
"num_tokens": 8645430.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.774804925918579,
|
|
"epoch": 0.3782656023222061,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990660745581172,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.16380622684955598,
|
|
"num_tokens": 8655115.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.644221448898316,
|
|
"epoch": 0.3787191582002903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990631272150062,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.1576675742864609,
|
|
"num_tokens": 8665391.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.724270439147949,
|
|
"epoch": 0.37917271407837444,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990601752382127,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.1531612053513527,
|
|
"num_tokens": 8676819.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.810973405838013,
|
|
"epoch": 0.37962626995645865,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990572186277975,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.16196503043174743,
|
|
"num_tokens": 8687052.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.741652250289917,
|
|
"epoch": 0.3800798258345428,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990542573838221,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.14744316637516022,
|
|
"num_tokens": 8697756.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.6437897205352785,
|
|
"epoch": 0.380533381712627,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990512915063475,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.16152960807085037,
|
|
"num_tokens": 8708388.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.822674703598023,
|
|
"epoch": 0.38098693759071117,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004990483209954352,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.14884860962629318,
|
|
"num_tokens": 8719475.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.752110195159912,
|
|
"epoch": 0.3814404934687954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990453458511464,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.16833294183015823,
|
|
"num_tokens": 8729395.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.708733367919922,
|
|
"epoch": 0.38189404934687954,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990423660735428,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15839240252971648,
|
|
"num_tokens": 8740351.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.7155640602111815,
|
|
"epoch": 0.3823476052249637,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499039381662686,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.16292448043823243,
|
|
"num_tokens": 8749260.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.792791223526001,
|
|
"epoch": 0.3828011611030479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990363926186377,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.1454516589641571,
|
|
"num_tokens": 8759604.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.777758598327637,
|
|
"epoch": 0.38325471698113206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990333989414597,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.15234508663415908,
|
|
"num_tokens": 8769815.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.728119850158691,
|
|
"epoch": 0.38370827285921627,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990304006312138,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.1551062658429146,
|
|
"num_tokens": 8780557.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.733680391311646,
|
|
"epoch": 0.3841618287373004,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004990273976879622,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.1641158416867256,
|
|
"num_tokens": 8790993.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.759084987640381,
|
|
"epoch": 0.38461538461538464,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990243901117669,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.15187538415193558,
|
|
"num_tokens": 8800657.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.6477912902832035,
|
|
"epoch": 0.3850689404934688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990213779026903,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.1512046605348587,
|
|
"num_tokens": 8812983.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.851211357116699,
|
|
"epoch": 0.385522496371553,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990183610607944,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.1610846310853958,
|
|
"num_tokens": 8822980.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.713478326797485,
|
|
"epoch": 0.38597605224963716,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004990153395861415,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.161063851416111,
|
|
"num_tokens": 8833821.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.584740400314331,
|
|
"epoch": 0.3864296081277213,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990123134787946,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.15470565110445023,
|
|
"num_tokens": 8843929.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.697726917266846,
|
|
"epoch": 0.3868831640058055,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990092827388159,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.1604609251022339,
|
|
"num_tokens": 8854180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.631396293640137,
|
|
"epoch": 0.3873367198838897,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990062473662681,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.16301485896110535,
|
|
"num_tokens": 8865018.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.728056001663208,
|
|
"epoch": 0.3877902757619739,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499003207361214,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.1480627566576004,
|
|
"num_tokens": 8875423.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.879735326766967,
|
|
"epoch": 0.38824383164005805,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990001627237165,
|
|
"loss": 5.7072,
|
|
"mean_token_accuracy": 0.15677697360515594,
|
|
"num_tokens": 8887850.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.671970367431641,
|
|
"epoch": 0.38869738751814226,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989971134538386,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.15710368007421494,
|
|
"num_tokens": 8897429.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.6937713623046875,
|
|
"epoch": 0.3891509433962264,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989940595516432,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.15821060836315154,
|
|
"num_tokens": 8907048.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.72869644165039,
|
|
"epoch": 0.3896044992743106,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989910010171938,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.15163719207048415,
|
|
"num_tokens": 8917987.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.723460674285889,
|
|
"epoch": 0.3900580551523948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989879378505532,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.15756893455982207,
|
|
"num_tokens": 8929339.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.622553491592408,
|
|
"epoch": 0.39051161103047893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989848700517849,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.155763378739357,
|
|
"num_tokens": 8939473.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.663455677032471,
|
|
"epoch": 0.39096516690856314,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989817976209526,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1591288760304451,
|
|
"num_tokens": 8949173.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.7296106815338135,
|
|
"epoch": 0.3914187227866473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989787205581196,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.1606694459915161,
|
|
"num_tokens": 8959879.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.717441272735596,
|
|
"epoch": 0.3918722786647315,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004989756388633496,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.15467706620693206,
|
|
"num_tokens": 8970643.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.686373376846314,
|
|
"epoch": 0.39232583454281567,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989725525367063,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.1609751895070076,
|
|
"num_tokens": 8979882.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.7686194896698,
|
|
"epoch": 0.3927793904208999,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989694615782534,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.15228137522935867,
|
|
"num_tokens": 8990925.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.746078300476074,
|
|
"epoch": 0.39323294629898403,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989663659880552,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1520710125565529,
|
|
"num_tokens": 9001365.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.773279905319214,
|
|
"epoch": 0.3936865021770682,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989632657661754,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.15934449434280396,
|
|
"num_tokens": 9011942.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.776633024215698,
|
|
"epoch": 0.3941400580551524,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498960160912678,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.15434861183166504,
|
|
"num_tokens": 9022610.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.718952655792236,
|
|
"epoch": 0.39459361393323655,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989570514276276,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.15780188590288163,
|
|
"num_tokens": 9033034.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.699564695358276,
|
|
"epoch": 0.39504716981132076,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989539373110883,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.15199518352746963,
|
|
"num_tokens": 9043418.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.812909030914307,
|
|
"epoch": 0.3955007256894049,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989508185631245,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.1541099339723587,
|
|
"num_tokens": 9052708.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.673247146606445,
|
|
"epoch": 0.39595428156748913,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989476951838006,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.1546905130147934,
|
|
"num_tokens": 9062883.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.740717458724975,
|
|
"epoch": 0.3964078374455733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989445671731814,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.1623426467180252,
|
|
"num_tokens": 9072830.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.605792236328125,
|
|
"epoch": 0.3968613933236575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989414345313315,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.15586361438035964,
|
|
"num_tokens": 9082749.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.7155884265899655,
|
|
"epoch": 0.39731494920174165,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989382972583156,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.15358513742685317,
|
|
"num_tokens": 9094188.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.6907202243804935,
|
|
"epoch": 0.3977685050798258,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989351553541986,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.15161869078874587,
|
|
"num_tokens": 9105023.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.616463232040405,
|
|
"epoch": 0.39822206095791,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004989320088190456,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.15799364000558852,
|
|
"num_tokens": 9115563.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.691041946411133,
|
|
"epoch": 0.3986756168359942,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989288576529216,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.15247485041618347,
|
|
"num_tokens": 9125394.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.73917670249939,
|
|
"epoch": 0.3991291727140784,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989257018558917,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.15650943666696548,
|
|
"num_tokens": 9137061.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.713806009292602,
|
|
"epoch": 0.39958272859216254,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989225414280213,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1589561104774475,
|
|
"num_tokens": 9148196.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.646256589889527,
|
|
"epoch": 0.40003628447024675,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989193763693756,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.16273730546236037,
|
|
"num_tokens": 9158013.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.649022006988526,
|
|
"epoch": 0.4004898403483309,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989162066800202,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.15886689722537994,
|
|
"num_tokens": 9167813.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.624588108062744,
|
|
"epoch": 0.4009433962264151,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989130323600205,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.16580986827611924,
|
|
"num_tokens": 9177783.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.660892677307129,
|
|
"epoch": 0.40139695210449927,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989098534094424,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.1579426884651184,
|
|
"num_tokens": 9187556.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.729719161987305,
|
|
"epoch": 0.4018505079825834,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989066698283512,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.15310224890708923,
|
|
"num_tokens": 9198659.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.774732494354248,
|
|
"epoch": 0.40230406386066764,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989034816168132,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.16033934354782103,
|
|
"num_tokens": 9209546.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.666764545440674,
|
|
"epoch": 0.4027576197387518,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989002887748941,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.16027882397174836,
|
|
"num_tokens": 9219339.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.718165111541748,
|
|
"epoch": 0.403211175616836,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988970913026601,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.15176644548773766,
|
|
"num_tokens": 9230364.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.744258975982666,
|
|
"epoch": 0.40366473149492016,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004988938892001771,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1577327385544777,
|
|
"num_tokens": 9240732.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.651133108139038,
|
|
"epoch": 0.40411828737300437,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988906824675113,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.1604924499988556,
|
|
"num_tokens": 9251049.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.6878711700439455,
|
|
"epoch": 0.4045718432510885,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004988874711047293,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.16183407455682755,
|
|
"num_tokens": 9261660.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.727019739151001,
|
|
"epoch": 0.40502539912917274,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004988842551118972,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.16216951757669448,
|
|
"num_tokens": 9272114.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.788266038894653,
|
|
"epoch": 0.4054789550072569,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988810344890818,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.15519319474697113,
|
|
"num_tokens": 9282125.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.740830755233764,
|
|
"epoch": 0.40593251088534105,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004988778092363494,
|
|
"loss": 5.6799,
|
|
"mean_token_accuracy": 0.15653618425130844,
|
|
"num_tokens": 9294078.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.690979671478272,
|
|
"epoch": 0.40638606676342526,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988745793537671,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.15408705770969391,
|
|
"num_tokens": 9304026.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.729645156860352,
|
|
"epoch": 0.4068396226415094,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004988713448414011,
|
|
"loss": 5.6865,
|
|
"mean_token_accuracy": 0.16053041964769363,
|
|
"num_tokens": 9313933.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.719425439834595,
|
|
"epoch": 0.4072931785195936,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498868105699319,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.15748196542263032,
|
|
"num_tokens": 9323932.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.604436445236206,
|
|
"epoch": 0.4077467343976778,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988648619275872,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.171552175283432,
|
|
"num_tokens": 9333467.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.745215559005738,
|
|
"epoch": 0.408200290275762,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988616135262729,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.15075961947441102,
|
|
"num_tokens": 9344909.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.866862964630127,
|
|
"epoch": 0.40865384615384615,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988583604954436,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.152850903570652,
|
|
"num_tokens": 9355630.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.665213871002197,
|
|
"epoch": 0.40910740203193036,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988551028351663,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.15456879287958145,
|
|
"num_tokens": 9365700.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.628423118591309,
|
|
"epoch": 0.4095609579100145,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004988518405455084,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.1484757512807846,
|
|
"num_tokens": 9377088.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.7334541320800785,
|
|
"epoch": 0.41001451378809867,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988485736265374,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.16351988762617112,
|
|
"num_tokens": 9386855.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.731301927566529,
|
|
"epoch": 0.4104680696661829,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000498845302078321,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15784264355897903,
|
|
"num_tokens": 9398661.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.735857725143433,
|
|
"epoch": 0.41092162554426703,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004988420259009266,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.1608929917216301,
|
|
"num_tokens": 9408670.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.7451990127563475,
|
|
"epoch": 0.41137518142235124,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498838745094422,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.15440730154514312,
|
|
"num_tokens": 9418740.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.706992340087891,
|
|
"epoch": 0.4118287373004354,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004988354596588751,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.15828332751989366,
|
|
"num_tokens": 9429339.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.724893856048584,
|
|
"epoch": 0.4122822931785196,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988321695943539,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.16610953062772751,
|
|
"num_tokens": 9438996.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.666243076324463,
|
|
"epoch": 0.41273584905660377,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988288749009264,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.16006203293800353,
|
|
"num_tokens": 9448669.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.654767560958862,
|
|
"epoch": 0.413189404934688,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004988255755786608,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.16067843437194823,
|
|
"num_tokens": 9458857.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.69340295791626,
|
|
"epoch": 0.41364296081277213,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988222716276251,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.16045788377523423,
|
|
"num_tokens": 9470241.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.792037296295166,
|
|
"epoch": 0.4140965166908563,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498818963047888,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.1541075199842453,
|
|
"num_tokens": 9480528.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.792665910720825,
|
|
"epoch": 0.4145500725689405,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004988156498395176,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.15965667963027955,
|
|
"num_tokens": 9491000.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.717759847640991,
|
|
"epoch": 0.41500362844702465,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004988123320025825,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.16161510795354844,
|
|
"num_tokens": 9501612.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.71904559135437,
|
|
"epoch": 0.41545718432510886,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004988090095371514,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.15754791498184204,
|
|
"num_tokens": 9513999.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.719426965713501,
|
|
"epoch": 0.415910740203193,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988056824432928,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.15234914422035217,
|
|
"num_tokens": 9524392.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.748761129379273,
|
|
"epoch": 0.41636429608127723,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004988023507210758,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.15767379999160766,
|
|
"num_tokens": 9534227.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.687965345382691,
|
|
"epoch": 0.4168178519593614,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004987990143705692,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.16447580456733704,
|
|
"num_tokens": 9544242.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.6869677066802975,
|
|
"epoch": 0.4172714078374456,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004987956733918418,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.15838005393743515,
|
|
"num_tokens": 9553921.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.648387908935547,
|
|
"epoch": 0.41772496371552975,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987923277849629,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.1557765543460846,
|
|
"num_tokens": 9564768.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.73125262260437,
|
|
"epoch": 0.4181785195936139,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987889775500017,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.15236683785915375,
|
|
"num_tokens": 9576360.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.753176498413086,
|
|
"epoch": 0.4186320754716981,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004987856226870272,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.15639690160751343,
|
|
"num_tokens": 9587623.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.70543532371521,
|
|
"epoch": 0.4190856313497823,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987822631961092,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.15374598652124405,
|
|
"num_tokens": 9597837.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.706055736541748,
|
|
"epoch": 0.4195391872278665,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498778899077317,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.15881578475236893,
|
|
"num_tokens": 9609509.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.7174797534942625,
|
|
"epoch": 0.41999274310595064,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00049877553033072,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.15826885551214218,
|
|
"num_tokens": 9619954.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.679054498672485,
|
|
"epoch": 0.42044629898403485,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004987721569563882,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.15558764338493347,
|
|
"num_tokens": 9629742.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.683841419219971,
|
|
"epoch": 0.420899854862119,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498768778954391,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.16237951517105104,
|
|
"num_tokens": 9641378.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.763059043884278,
|
|
"epoch": 0.4213534107402032,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987653963247985,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.16142413020133972,
|
|
"num_tokens": 9652279.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.770412397384644,
|
|
"epoch": 0.42180696661828737,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004987620090676805,
|
|
"loss": 5.7089,
|
|
"mean_token_accuracy": 0.1528452843427658,
|
|
"num_tokens": 9663416.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.7631096839904785,
|
|
"epoch": 0.4222605224963715,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987586171831072,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.15435225814580916,
|
|
"num_tokens": 9674647.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.690637016296387,
|
|
"epoch": 0.42271407837445574,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987552206711487,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.15983799695968628,
|
|
"num_tokens": 9685084.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.581456327438355,
|
|
"epoch": 0.4231676342525399,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987518195318752,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.15758123695850373,
|
|
"num_tokens": 9695661.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.736875104904175,
|
|
"epoch": 0.4236211901306241,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498748413765357,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.15394429713487626,
|
|
"num_tokens": 9705773.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.76428861618042,
|
|
"epoch": 0.42407474600870826,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987450033716646,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.15749599486589433,
|
|
"num_tokens": 9715799.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.718335390090942,
|
|
"epoch": 0.42452830188679247,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987415883508686,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.16066358387470245,
|
|
"num_tokens": 9727012.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.74974217414856,
|
|
"epoch": 0.4249818577648766,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004987381687030394,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.15791599750518798,
|
|
"num_tokens": 9737044.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.817522478103638,
|
|
"epoch": 0.42543541364296084,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004987347444282479,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.14861048609018326,
|
|
"num_tokens": 9747648.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.656645727157593,
|
|
"epoch": 0.425888969521045,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987313155265649,
|
|
"loss": 5.637,
|
|
"mean_token_accuracy": 0.15445875972509385,
|
|
"num_tokens": 9757812.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.77165412902832,
|
|
"epoch": 0.42634252539912915,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987278819980613,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15808448195457458,
|
|
"num_tokens": 9768337.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.789901208877564,
|
|
"epoch": 0.42679608127721336,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004987244438428081,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.14943017363548278,
|
|
"num_tokens": 9779433.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.658951282501221,
|
|
"epoch": 0.4272496371552975,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004987210010608764,
|
|
"loss": 5.5923,
|
|
"mean_token_accuracy": 0.1585081249475479,
|
|
"num_tokens": 9790069.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.642023754119873,
|
|
"epoch": 0.4277031930333817,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004987175536523373,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.16363361924886705,
|
|
"num_tokens": 9799669.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.639230585098266,
|
|
"epoch": 0.4281567489114659,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004987141016172622,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.16178745478391648,
|
|
"num_tokens": 9809615.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.680355024337769,
|
|
"epoch": 0.4286103047895501,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987106449557225,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.15792733579874038,
|
|
"num_tokens": 9819666.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.779202842712403,
|
|
"epoch": 0.42906386066763424,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987071836677896,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.15531140714883804,
|
|
"num_tokens": 9831015.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.685993623733521,
|
|
"epoch": 0.42951741654571846,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987037177535353,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.15545632392168046,
|
|
"num_tokens": 9841354.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.646900415420532,
|
|
"epoch": 0.4299709724238026,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004987002472130309,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.153756807744503,
|
|
"num_tokens": 9850467.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.784751653671265,
|
|
"epoch": 0.43042452830188677,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004986967720463485,
|
|
"loss": 5.6621,
|
|
"mean_token_accuracy": 0.1529627487063408,
|
|
"num_tokens": 9861115.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.768982076644898,
|
|
"epoch": 0.430878084179971,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986932922535598,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.15878958255052567,
|
|
"num_tokens": 9871172.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.647015523910523,
|
|
"epoch": 0.43133164005805513,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004986898078347368,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.15951561331748962,
|
|
"num_tokens": 9881997.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.6569263458251955,
|
|
"epoch": 0.43178519593613934,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986863187899516,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.16232846826314926,
|
|
"num_tokens": 9892310.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.64468412399292,
|
|
"epoch": 0.4322387518142235,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986828251192764,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.15712934285402297,
|
|
"num_tokens": 9902664.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.7097142219543455,
|
|
"epoch": 0.4326923076923077,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986793268227833,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.1599283143877983,
|
|
"num_tokens": 9912491.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.671255397796631,
|
|
"epoch": 0.43314586357039186,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986758239005448,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.16305184960365296,
|
|
"num_tokens": 9922057.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.632063341140747,
|
|
"epoch": 0.4335994194484761,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986723163526331,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.15621958673000336,
|
|
"num_tokens": 9933661.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.657237720489502,
|
|
"epoch": 0.43405297532656023,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986688041791209,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.15300980508327483,
|
|
"num_tokens": 9945177.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.710802459716797,
|
|
"epoch": 0.4345065312046444,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000498665287380081,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.15459759831428527,
|
|
"num_tokens": 9956226.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.701862812042236,
|
|
"epoch": 0.4349600870827286,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986617659555859,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.15917366743087769,
|
|
"num_tokens": 9965877.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.690611982345581,
|
|
"epoch": 0.43541364296081275,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986582399057085,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.1667877346277237,
|
|
"num_tokens": 9975592.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.775518417358398,
|
|
"epoch": 0.43586719883889696,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986547092305216,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.15770362168550492,
|
|
"num_tokens": 9986094.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.735955429077149,
|
|
"epoch": 0.4363207547169811,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004986511739300984,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.1539325311779976,
|
|
"num_tokens": 9997241.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.640730094909668,
|
|
"epoch": 0.43677431059506533,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986476340045119,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.15729670077562333,
|
|
"num_tokens": 10008091.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.661537456512451,
|
|
"epoch": 0.4372278664731495,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986440894538354,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.15475862249732017,
|
|
"num_tokens": 10018794.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.731957864761353,
|
|
"epoch": 0.4376814223512337,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986405402781421,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.1584927648305893,
|
|
"num_tokens": 10028414.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.750116586685181,
|
|
"epoch": 0.43813497822931785,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986369864775054,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15727464854717255,
|
|
"num_tokens": 10038749.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.720384407043457,
|
|
"epoch": 0.438588534107402,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004986334280519989,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.1561151698231697,
|
|
"num_tokens": 10049866.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.676847696304321,
|
|
"epoch": 0.4390420899854862,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000498629865001696,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.16333256363868714,
|
|
"num_tokens": 10060680.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.776250123977661,
|
|
"epoch": 0.43949564586357037,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986262973266706,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1555226355791092,
|
|
"num_tokens": 10070931.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.693648958206177,
|
|
"epoch": 0.4399492017416546,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004986227250269964,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.1558353751897812,
|
|
"num_tokens": 10080189.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.716169309616089,
|
|
"epoch": 0.44040275761973874,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004986191481027472,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.1630585163831711,
|
|
"num_tokens": 10088813.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.719408226013184,
|
|
"epoch": 0.44085631349782295,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004986155665539971,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.15667377263307572,
|
|
"num_tokens": 10098125.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.71316180229187,
|
|
"epoch": 0.4413098693759071,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00049861198038082,
|
|
"loss": 5.6213,
|
|
"mean_token_accuracy": 0.15492214560508727,
|
|
"num_tokens": 10109125.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.656546688079834,
|
|
"epoch": 0.4417634252539913,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004986083895832903,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.15925385057926178,
|
|
"num_tokens": 10120182.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.681136751174927,
|
|
"epoch": 0.44221698113207547,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986047941614821,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.15356798693537713,
|
|
"num_tokens": 10130941.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.768857765197754,
|
|
"epoch": 0.4426705370101596,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986011941154696,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.15759876668453215,
|
|
"num_tokens": 10141708.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.660665369033813,
|
|
"epoch": 0.44312409288824384,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985975894453275,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.1579940661787987,
|
|
"num_tokens": 10151816.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.685306549072266,
|
|
"epoch": 0.443577648766328,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985939801511304,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.15800520777702332,
|
|
"num_tokens": 10162470.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.720489025115967,
|
|
"epoch": 0.4440312046444122,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985903662329527,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.1637508600950241,
|
|
"num_tokens": 10173171.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.6964959621429445,
|
|
"epoch": 0.44448476052249636,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985867476908693,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.16020630449056625,
|
|
"num_tokens": 10184185.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.72540864944458,
|
|
"epoch": 0.44493831640058057,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004985831245249549,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.15526049435138703,
|
|
"num_tokens": 10195516.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.693022298812866,
|
|
"epoch": 0.4453918722786647,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004985794967352846,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.1589369460940361,
|
|
"num_tokens": 10204936.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.758884763717651,
|
|
"epoch": 0.44584542815674894,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985758643219334,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15786018073558808,
|
|
"num_tokens": 10216218.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.800872135162353,
|
|
"epoch": 0.4462989840348331,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985722272849762,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.15207151025533677,
|
|
"num_tokens": 10226370.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.575708436965942,
|
|
"epoch": 0.44675253991291725,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004985685856244884,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.16749200075864792,
|
|
"num_tokens": 10236170.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.689274263381958,
|
|
"epoch": 0.44720609579100146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985649393405453,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.15733460038900376,
|
|
"num_tokens": 10246119.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.70348482131958,
|
|
"epoch": 0.4476596516690856,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985612884332223,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15208822041749953,
|
|
"num_tokens": 10256762.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.65702223777771,
|
|
"epoch": 0.4481132075471698,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004985576329025949,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.16472743451595306,
|
|
"num_tokens": 10267317.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.779310035705566,
|
|
"epoch": 0.448566763425254,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985539727487385,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.14801670163869857,
|
|
"num_tokens": 10279111.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.705371475219726,
|
|
"epoch": 0.4490203193033382,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985503079717292,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.16035750806331633,
|
|
"num_tokens": 10289383.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.721146535873413,
|
|
"epoch": 0.44947387518142234,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985466385716425,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.16319389194250106,
|
|
"num_tokens": 10299806.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.655878496170044,
|
|
"epoch": 0.44992743105950656,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004985429645485543,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.15566550940275192,
|
|
"num_tokens": 10310348.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.761146450042725,
|
|
"epoch": 0.4503809869375907,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004985392859025407,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.16084989458322524,
|
|
"num_tokens": 10320354.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.67796630859375,
|
|
"epoch": 0.45083454281567487,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985356026336776,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.1607133001089096,
|
|
"num_tokens": 10330292.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.622106838226318,
|
|
"epoch": 0.4512880986937591,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985319147420414,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.16529798954725267,
|
|
"num_tokens": 10340449.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.677884149551391,
|
|
"epoch": 0.45174165457184323,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985282222277082,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.15833908766508104,
|
|
"num_tokens": 10350637.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.6070215702056885,
|
|
"epoch": 0.45219521044992744,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985245250907544,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.16214152425527573,
|
|
"num_tokens": 10361548.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.6438604354858395,
|
|
"epoch": 0.4526487663280116,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004985208233312564,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.15428854525089264,
|
|
"num_tokens": 10371765.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.7256732940673825,
|
|
"epoch": 0.4531023222060958,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985171169492908,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.16112247854471207,
|
|
"num_tokens": 10382108.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.667687511444091,
|
|
"epoch": 0.45355587808417996,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985134059449344,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.16138881593942642,
|
|
"num_tokens": 10392390.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.645096778869629,
|
|
"epoch": 0.4540094339622642,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985096903182637,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.16399622708559036,
|
|
"num_tokens": 10402094.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.71685528755188,
|
|
"epoch": 0.45446298984034833,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985059700693557,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.15897753685712815,
|
|
"num_tokens": 10413350.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.757471227645874,
|
|
"epoch": 0.4549165457184325,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985022451982872,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.14736578613519669,
|
|
"num_tokens": 10424292.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.805013990402221,
|
|
"epoch": 0.4553701015965167,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984985157051354,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.15852102637290955,
|
|
"num_tokens": 10433724.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.681409645080566,
|
|
"epoch": 0.45582365747460085,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984947815899774,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.15463263988494874,
|
|
"num_tokens": 10444724.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.689796447753906,
|
|
"epoch": 0.45627721335268506,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984910428528902,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.16503604203462602,
|
|
"num_tokens": 10455086.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.637588691711426,
|
|
"epoch": 0.4567307692307692,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984872994939514,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1577824205160141,
|
|
"num_tokens": 10465076.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.698536729812622,
|
|
"epoch": 0.45718432510885343,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984835515132382,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.16402017027139665,
|
|
"num_tokens": 10474817.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.690934658050537,
|
|
"epoch": 0.4576378809869376,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984797989108282,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.15358709692955017,
|
|
"num_tokens": 10485735.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.629631233215332,
|
|
"epoch": 0.4580914368650218,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984760416867991,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.1563015177845955,
|
|
"num_tokens": 10496731.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.68785285949707,
|
|
"epoch": 0.45854499274310595,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984722798412286,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.1587032288312912,
|
|
"num_tokens": 10506787.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.730269145965576,
|
|
"epoch": 0.4589985486211901,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984685133741941,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.16047224551439285,
|
|
"num_tokens": 10517170.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.651216459274292,
|
|
"epoch": 0.4594521044992743,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000498464742285774,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15768254101276397,
|
|
"num_tokens": 10527342.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.672451400756836,
|
|
"epoch": 0.45990566037735847,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498460966576046,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.1630593493580818,
|
|
"num_tokens": 10537253.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.677005481719971,
|
|
"epoch": 0.4603592162554427,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984571862450884,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.160668021440506,
|
|
"num_tokens": 10547249.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.756367826461792,
|
|
"epoch": 0.46081277213352684,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004984534012929791,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.1614480659365654,
|
|
"num_tokens": 10558174.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.753311634063721,
|
|
"epoch": 0.46126632801161105,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004984496117197967,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.16208672225475312,
|
|
"num_tokens": 10567610.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.646350717544555,
|
|
"epoch": 0.4617198838896952,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984458175256193,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.15640690922737122,
|
|
"num_tokens": 10578494.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.7145490646362305,
|
|
"epoch": 0.4621734397677794,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984420187105253,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.1579895183444023,
|
|
"num_tokens": 10589482.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.78198881149292,
|
|
"epoch": 0.46262699564586357,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984382152745936,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.15277581810951232,
|
|
"num_tokens": 10599965.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.71567816734314,
|
|
"epoch": 0.4630805515239477,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984344072179026,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.15894951820373535,
|
|
"num_tokens": 10610500.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.731478691101074,
|
|
"epoch": 0.46353410740203194,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984305945405312,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.15854529589414595,
|
|
"num_tokens": 10619843.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.73313536643982,
|
|
"epoch": 0.4639876632801161,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498426777242558,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.16565094739198685,
|
|
"num_tokens": 10631026.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.546000003814697,
|
|
"epoch": 0.4644412191582003,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984229553240623,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.16317055374383926,
|
|
"num_tokens": 10641130.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.704706859588623,
|
|
"epoch": 0.46489477503628446,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004984191287851228,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.15852320194244385,
|
|
"num_tokens": 10652305.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.781041049957276,
|
|
"epoch": 0.46534833091436867,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984152976258188,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.16050119698047638,
|
|
"num_tokens": 10663083.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.711477136611938,
|
|
"epoch": 0.4658018867924528,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984114618462296,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.15250758677721024,
|
|
"num_tokens": 10673602.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.701936101913452,
|
|
"epoch": 0.46625544267053703,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004984076214464343,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.1663011431694031,
|
|
"num_tokens": 10684622.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.676464653015136,
|
|
"epoch": 0.4667089985486212,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984037764265126,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.15928329527378082,
|
|
"num_tokens": 10695129.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.592328977584839,
|
|
"epoch": 0.46716255442670535,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983999267865438,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.1723786011338234,
|
|
"num_tokens": 10705236.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.653973770141602,
|
|
"epoch": 0.46761611030478956,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004983960725266078,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.16147854626178743,
|
|
"num_tokens": 10715748.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.631850051879883,
|
|
"epoch": 0.4680696661828737,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004983922136467838,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.16219267398118972,
|
|
"num_tokens": 10725799.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.688706350326538,
|
|
"epoch": 0.4685232220609579,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000498388350147152,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.15641454756259918,
|
|
"num_tokens": 10735668.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.798784685134888,
|
|
"epoch": 0.4689767779390421,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983844820277922,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.15428698062896729,
|
|
"num_tokens": 10746466.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.826989364624024,
|
|
"epoch": 0.4694303338171263,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004983806092887843,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.1553424969315529,
|
|
"num_tokens": 10756724.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.670391082763672,
|
|
"epoch": 0.46988388969521044,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004983767319302086,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.15869035348296165,
|
|
"num_tokens": 10766919.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.573981809616089,
|
|
"epoch": 0.47033744557329465,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983728499521451,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.16845543682575226,
|
|
"num_tokens": 10777550.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.641195344924927,
|
|
"epoch": 0.4707910014513788,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983689633546741,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.15530664175748826,
|
|
"num_tokens": 10788456.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.667837238311767,
|
|
"epoch": 0.47124455732946297,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983650721378761,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.15722571164369584,
|
|
"num_tokens": 10800049.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.690346145629883,
|
|
"epoch": 0.4716981132075472,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983611763018314,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.15779779106378555,
|
|
"num_tokens": 10810743.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.8374152183532715,
|
|
"epoch": 0.47215166908563133,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983572758466208,
|
|
"loss": 5.7976,
|
|
"mean_token_accuracy": 0.15054364502429962,
|
|
"num_tokens": 10821897.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.762923002243042,
|
|
"epoch": 0.47260522496371554,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983533707723247,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.15647778511047364,
|
|
"num_tokens": 10831589.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.68774905204773,
|
|
"epoch": 0.4730587808417997,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983494610790241,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15626207888126373,
|
|
"num_tokens": 10841404.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.646328639984131,
|
|
"epoch": 0.4735123367198839,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983455467667996,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.15539631098508835,
|
|
"num_tokens": 10851577.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.65619740486145,
|
|
"epoch": 0.47396589259796806,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983416278357322,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.16633753776550292,
|
|
"num_tokens": 10861403.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.6497701644897464,
|
|
"epoch": 0.4744194484760523,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004983377042859032,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.1568841502070427,
|
|
"num_tokens": 10871933.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.693173456192016,
|
|
"epoch": 0.47487300435413643,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983337761173936,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.1571093514561653,
|
|
"num_tokens": 10881800.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.7815196990966795,
|
|
"epoch": 0.4753265602322206,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983298433302843,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.16028908640146255,
|
|
"num_tokens": 10891830.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.634613370895385,
|
|
"epoch": 0.4757801161103048,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983259059246572,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.16579733341932296,
|
|
"num_tokens": 10901557.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.5637064456939695,
|
|
"epoch": 0.47623367198838895,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983219639005934,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.1479102648794651,
|
|
"num_tokens": 10912155.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.665174531936645,
|
|
"epoch": 0.47668722786647316,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983180172581745,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.16128475666046144,
|
|
"num_tokens": 10922291.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.754207944869995,
|
|
"epoch": 0.4771407837445573,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983140659974819,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.15364252179861068,
|
|
"num_tokens": 10933176.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.72802848815918,
|
|
"epoch": 0.47759433962264153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983101101185977,
|
|
"loss": 5.7016,
|
|
"mean_token_accuracy": 0.15314582884311675,
|
|
"num_tokens": 10944049.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.698485708236694,
|
|
"epoch": 0.4780478955007257,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983061496216035,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.16470168977975846,
|
|
"num_tokens": 10954347.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.628724670410156,
|
|
"epoch": 0.4785014513788099,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983021845065812,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.16007599085569382,
|
|
"num_tokens": 10965123.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.607919788360595,
|
|
"epoch": 0.47895500725689405,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004982982147736128,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.16313560605049132,
|
|
"num_tokens": 10976395.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.689217376708984,
|
|
"epoch": 0.4794085631349782,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004982942404227805,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.1574721962213516,
|
|
"num_tokens": 10986797.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.7448052883148195,
|
|
"epoch": 0.4798621190130624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982902614541662,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.15480213314294816,
|
|
"num_tokens": 10997229.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.632512140274048,
|
|
"epoch": 0.48031567489114657,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982862778678526,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.16841159462928773,
|
|
"num_tokens": 11008180.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.69216685295105,
|
|
"epoch": 0.4807692307692308,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982822896639218,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.16379621475934983,
|
|
"num_tokens": 11019248.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.631191778182983,
|
|
"epoch": 0.48122278664731494,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982782968424563,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.16136889904737473,
|
|
"num_tokens": 11029760.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.595670461654663,
|
|
"epoch": 0.48167634252539915,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004982742994035388,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.1590326741337776,
|
|
"num_tokens": 11039211.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.633118486404419,
|
|
"epoch": 0.4821298984034833,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982702973472518,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.1575867161154747,
|
|
"num_tokens": 11049892.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.752400588989258,
|
|
"epoch": 0.4825834542815675,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982662906736783,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.15781162232160567,
|
|
"num_tokens": 11060823.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.606657981872559,
|
|
"epoch": 0.48303701015965167,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982622793829009,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.15996954441070557,
|
|
"num_tokens": 11072353.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.680554294586182,
|
|
"epoch": 0.4834905660377358,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004982582634750027,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.15869979858398436,
|
|
"num_tokens": 11082655.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.679764032363892,
|
|
"epoch": 0.48394412191582004,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982542429500667,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.16280234158039092,
|
|
"num_tokens": 11093315.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.555749750137329,
|
|
"epoch": 0.4843976777939042,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004982502178081761,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.16128282994031906,
|
|
"num_tokens": 11103074.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.700632524490357,
|
|
"epoch": 0.4848512336719884,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004982461880494141,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.16219093054533004,
|
|
"num_tokens": 11113636.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.656824111938477,
|
|
"epoch": 0.48530478955007256,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498242153673864,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.16639752238988875,
|
|
"num_tokens": 11123509.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.632119607925415,
|
|
"epoch": 0.48575834542815677,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982381146816094,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.1564563274383545,
|
|
"num_tokens": 11133405.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.721227788925171,
|
|
"epoch": 0.4862119013062409,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982340710727336,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.15045734122395515,
|
|
"num_tokens": 11144725.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.666970729827881,
|
|
"epoch": 0.48666545718432513,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004982300228473203,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.1582345709204674,
|
|
"num_tokens": 11155446.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.663780879974365,
|
|
"epoch": 0.4871190130624093,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004982259700054533,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.16389473974704744,
|
|
"num_tokens": 11165380.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.712706756591797,
|
|
"epoch": 0.48757256894049344,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982219125472163,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.1558239132165909,
|
|
"num_tokens": 11175641.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.7976789474487305,
|
|
"epoch": 0.48802612481857766,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004982178504726933,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.1573277808725834,
|
|
"num_tokens": 11186257.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.710126447677612,
|
|
"epoch": 0.4884796806966618,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004982137837819682,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.1532593734562397,
|
|
"num_tokens": 11197284.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.758053302764893,
|
|
"epoch": 0.488933236574746,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982097124751252,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.16171942353248597,
|
|
"num_tokens": 11208413.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.615036535263061,
|
|
"epoch": 0.4893867924528302,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982056365522486,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.16109529733657837,
|
|
"num_tokens": 11219016.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.637114524841309,
|
|
"epoch": 0.4898403483309144,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982015560134225,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.1623409003019333,
|
|
"num_tokens": 11228934.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.671698760986328,
|
|
"epoch": 0.49029390420899854,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981974708587312,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.16479768455028534,
|
|
"num_tokens": 11239596.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.5890604019165036,
|
|
"epoch": 0.49074746008708275,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981933810882594,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.1588309571146965,
|
|
"num_tokens": 11249560.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.677786207199096,
|
|
"epoch": 0.4912010159651669,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004981892867020917,
|
|
"loss": 5.6842,
|
|
"mean_token_accuracy": 0.15366458296775817,
|
|
"num_tokens": 11259787.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.762712717056274,
|
|
"epoch": 0.49165457184325106,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004981851877003125,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.16309960931539536,
|
|
"num_tokens": 11269717.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.639627838134766,
|
|
"epoch": 0.4921081277213353,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981810840830068,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.16716673821210862,
|
|
"num_tokens": 11279863.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.685359144210816,
|
|
"epoch": 0.49256168359941943,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981769758502596,
|
|
"loss": 5.7219,
|
|
"mean_token_accuracy": 0.14935771152377128,
|
|
"num_tokens": 11291161.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.661555337905884,
|
|
"epoch": 0.49301523947750364,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981728630021555,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.161973038315773,
|
|
"num_tokens": 11301151.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.631797122955322,
|
|
"epoch": 0.4934687953555878,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981687455387797,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.1609097644686699,
|
|
"num_tokens": 11311466.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.667022657394409,
|
|
"epoch": 0.493922351233672,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981646234602173,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.16592205464839935,
|
|
"num_tokens": 11321522.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.712038326263428,
|
|
"epoch": 0.49437590711175616,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981604967665539,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.1631213590502739,
|
|
"num_tokens": 11332317.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.616385984420776,
|
|
"epoch": 0.4948294629898404,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981563654578743,
|
|
"loss": 5.5578,
|
|
"mean_token_accuracy": 0.15613383799791336,
|
|
"num_tokens": 11343024.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.598169612884521,
|
|
"epoch": 0.49528301886792453,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004981522295342643,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.1637219548225403,
|
|
"num_tokens": 11353114.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.679735422134399,
|
|
"epoch": 0.4957365747460087,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004981480889958092,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.16203076988458634,
|
|
"num_tokens": 11363446.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.638913345336914,
|
|
"epoch": 0.4961901306240929,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981439438425949,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.16449467986822128,
|
|
"num_tokens": 11373413.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.596277523040771,
|
|
"epoch": 0.49664368650217705,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000498139794074707,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16666698157787324,
|
|
"num_tokens": 11383142.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.6968464851379395,
|
|
"epoch": 0.49709724238026126,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004981356396922313,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.16057899594306946,
|
|
"num_tokens": 11394635.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.642231130599976,
|
|
"epoch": 0.4975507982583454,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004981314806952535,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.16755957901477814,
|
|
"num_tokens": 11404442.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.574909734725952,
|
|
"epoch": 0.49800435413642963,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00049812731708386,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16344375908374786,
|
|
"num_tokens": 11414217.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.713902139663697,
|
|
"epoch": 0.4984579100145138,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004981231488581367,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.1595131129026413,
|
|
"num_tokens": 11423834.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.563067150115967,
|
|
"epoch": 0.498911465892598,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004981189760181699,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.16150647401809692,
|
|
"num_tokens": 11433613.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.617917442321778,
|
|
"epoch": 0.49936502177068215,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981147985640456,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.1645784094929695,
|
|
"num_tokens": 11443915.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.798919534683227,
|
|
"epoch": 0.4998185776487663,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981106164958506,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.1555358052253723,
|
|
"num_tokens": 11454588.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.619657421112061,
|
|
"epoch": 0.5002721335268505,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004981064298136712,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15784326046705247,
|
|
"num_tokens": 11465533.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.677310466766357,
|
|
"epoch": 0.5007256894049347,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004981022385175939,
|
|
"loss": 5.5938,
|
|
"mean_token_accuracy": 0.1527741253376007,
|
|
"num_tokens": 11475776.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.728420829772949,
|
|
"epoch": 0.5011792452830188,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980980426077054,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.16829029023647307,
|
|
"num_tokens": 11486200.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.639609622955322,
|
|
"epoch": 0.5016328011611031,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004980938420840926,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.1582867532968521,
|
|
"num_tokens": 11496768.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.645894479751587,
|
|
"epoch": 0.5020863570391872,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980896369468423,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.16483985483646393,
|
|
"num_tokens": 11507096.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.664897155761719,
|
|
"epoch": 0.5025399129172714,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980854271960415,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.15945658534765245,
|
|
"num_tokens": 11517301.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.730061626434326,
|
|
"epoch": 0.5029934687953556,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004980812128317772,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.16360202729701995,
|
|
"num_tokens": 11528616.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.749828433990478,
|
|
"epoch": 0.5034470246734397,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004980769938541364,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.16737237572669983,
|
|
"num_tokens": 11539344.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.668318414688111,
|
|
"epoch": 0.503900580551524,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004980727702632066,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.15578173995018005,
|
|
"num_tokens": 11549511.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.656678009033203,
|
|
"epoch": 0.5043541364296081,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004980685420590752,
|
|
"loss": 5.5735,
|
|
"mean_token_accuracy": 0.15664219707250596,
|
|
"num_tokens": 11559425.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.761865758895874,
|
|
"epoch": 0.5048076923076923,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980643092418294,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.15531755238771439,
|
|
"num_tokens": 11570406.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.6483618259429935,
|
|
"epoch": 0.5052612481857764,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980600718115568,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.1617144003510475,
|
|
"num_tokens": 11580509.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.649977540969848,
|
|
"epoch": 0.5057148040638607,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004980558297683452,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.162077334523201,
|
|
"num_tokens": 11590860.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.675752067565918,
|
|
"epoch": 0.5061683599419449,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004980515831122822,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.16118255853652955,
|
|
"num_tokens": 11601954.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.675711917877197,
|
|
"epoch": 0.506621915820029,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004980473318434555,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.15900284945964813,
|
|
"num_tokens": 11612581.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.614867401123047,
|
|
"epoch": 0.5070754716981132,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004980430759619532,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.16224440485239028,
|
|
"num_tokens": 11622599.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.6130211353302,
|
|
"epoch": 0.5075290275761973,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980388154678633,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.159950090944767,
|
|
"num_tokens": 11633611.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.590432405471802,
|
|
"epoch": 0.5079825834542816,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004980345503612738,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.16368415355682372,
|
|
"num_tokens": 11643159.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.688422393798828,
|
|
"epoch": 0.5084361393323658,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004980302806422729,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.16657138168811797,
|
|
"num_tokens": 11653174.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.689723253250122,
|
|
"epoch": 0.5088896952104499,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980260063109491,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.16194719970226287,
|
|
"num_tokens": 11662621.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.531690263748169,
|
|
"epoch": 0.5093432510885341,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004980217273673906,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.1628020793199539,
|
|
"num_tokens": 11673538.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.670006513595581,
|
|
"epoch": 0.5097968069666183,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980174438116859,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.16596334427595139,
|
|
"num_tokens": 11683203.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.5967333793640135,
|
|
"epoch": 0.5102503628447025,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980131556439236,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.16600242257118225,
|
|
"num_tokens": 11693313.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.628219795227051,
|
|
"epoch": 0.5107039187227866,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004980088628641925,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.16239438205957413,
|
|
"num_tokens": 11704194.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.6606667041778564,
|
|
"epoch": 0.5111574746008708,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980045654725812,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.16957058012485504,
|
|
"num_tokens": 11715109.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.587406253814697,
|
|
"epoch": 0.511611030478955,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004980002634691787,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.16856465935707093,
|
|
"num_tokens": 11724961.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.55975661277771,
|
|
"epoch": 0.5120645863570392,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497995956854074,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.16654812693595886,
|
|
"num_tokens": 11735334.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.60379810333252,
|
|
"epoch": 0.5125181422351234,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004979916456273561,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.15964554995298386,
|
|
"num_tokens": 11746858.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.744812774658203,
|
|
"epoch": 0.5129716981132075,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004979873297891141,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.1556268513202667,
|
|
"num_tokens": 11757819.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.700674200057984,
|
|
"epoch": 0.5134252539912917,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004979830093394372,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.16144313663244247,
|
|
"num_tokens": 11767470.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.652323913574219,
|
|
"epoch": 0.513878809869376,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004979786842784149,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.17092576026916503,
|
|
"num_tokens": 11777060.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.565343761444092,
|
|
"epoch": 0.5143323657474601,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979743546061366,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.1668785184621811,
|
|
"num_tokens": 11787176.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.527346277236939,
|
|
"epoch": 0.5147859216255443,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004979700203226918,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.16941867619752884,
|
|
"num_tokens": 11796419.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.734120464324951,
|
|
"epoch": 0.5152394775036284,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979656814281702,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.15707888454198837,
|
|
"num_tokens": 11807279.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.68532247543335,
|
|
"epoch": 0.5156930333817126,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004979613379226615,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.16275421977043153,
|
|
"num_tokens": 11817669.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.599370241165161,
|
|
"epoch": 0.5161465892597968,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004979569898062554,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.16634066104888917,
|
|
"num_tokens": 11827247.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.653990411758423,
|
|
"epoch": 0.516600145137881,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000497952637079042,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.15918290764093398,
|
|
"num_tokens": 11838201.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.628846836090088,
|
|
"epoch": 0.5170537010159652,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004979482797411114,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.17014151364564895,
|
|
"num_tokens": 11847561.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.6203492164611815,
|
|
"epoch": 0.5175072568940493,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004979439177925534,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.16502239555120468,
|
|
"num_tokens": 11858272.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.693549585342407,
|
|
"epoch": 0.5179608127721336,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004979395512334584,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.15832090377807617,
|
|
"num_tokens": 11869660.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.728826475143433,
|
|
"epoch": 0.5184143686502177,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004979351800639166,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.15534287691116333,
|
|
"num_tokens": 11880239.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.7823890209197994,
|
|
"epoch": 0.5188679245283019,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004979308042840186,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15747978836297988,
|
|
"num_tokens": 11890630.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.736940622329712,
|
|
"epoch": 0.519321480406386,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004979264238938547,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.15597223192453386,
|
|
"num_tokens": 11900948.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.611868143081665,
|
|
"epoch": 0.5197750362844702,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004979220388935155,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.1591492623090744,
|
|
"num_tokens": 11912528.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.612641048431397,
|
|
"epoch": 0.5202285921625545,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004979176492830918,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.16271282583475113,
|
|
"num_tokens": 11922211.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.666022205352784,
|
|
"epoch": 0.5206821480406386,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004979132550626742,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.16144200712442397,
|
|
"num_tokens": 11932520.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.680260562896729,
|
|
"epoch": 0.5211357039187228,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004979088562323538,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.1675450712442398,
|
|
"num_tokens": 11943312.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.60998158454895,
|
|
"epoch": 0.5215892597968069,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004979044527922214,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.1593760222196579,
|
|
"num_tokens": 11954455.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.657192420959473,
|
|
"epoch": 0.5220428156748912,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004979000447423681,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.16424417793750762,
|
|
"num_tokens": 11964650.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.650221443176269,
|
|
"epoch": 0.5224963715529753,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978956320828851,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.16050074696540834,
|
|
"num_tokens": 11975134.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.661907148361206,
|
|
"epoch": 0.5229499274310595,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004978912148138637,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.15903744250535964,
|
|
"num_tokens": 11986486.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.7855431079864506,
|
|
"epoch": 0.5234034833091437,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497886792935395,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.1529120087623596,
|
|
"num_tokens": 11998045.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.768364191055298,
|
|
"epoch": 0.5238570391872278,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004978823664475707,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.1632813185453415,
|
|
"num_tokens": 12008130.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.649330568313599,
|
|
"epoch": 0.5243105950653121,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004978779353504824,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.1525845743715763,
|
|
"num_tokens": 12018753.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.679066848754883,
|
|
"epoch": 0.5247641509433962,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004978734996442214,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.16855039298534394,
|
|
"num_tokens": 12028202.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.69135422706604,
|
|
"epoch": 0.5252177068214804,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004978690593288798,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.16048222556710243,
|
|
"num_tokens": 12039652.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.696301746368408,
|
|
"epoch": 0.5256712626995645,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004978646144045491,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.1572120249271393,
|
|
"num_tokens": 12051269.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.570094633102417,
|
|
"epoch": 0.5261248185776488,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004978601648713215,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.16403459310531615,
|
|
"num_tokens": 12060647.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.623483562469483,
|
|
"epoch": 0.526578374455733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978557107292889,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16484973430633545,
|
|
"num_tokens": 12071669.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.572929716110229,
|
|
"epoch": 0.5270319303338171,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004978512519785433,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.16810268610715867,
|
|
"num_tokens": 12081971.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.587448024749756,
|
|
"epoch": 0.5274854862119013,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000497846788619177,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.1635736644268036,
|
|
"num_tokens": 12092465.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.7142359733581545,
|
|
"epoch": 0.5279390420899854,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004978423206512825,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1615642175078392,
|
|
"num_tokens": 12101752.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.731019115447998,
|
|
"epoch": 0.5283925979680697,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000497837848074952,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1558190815150738,
|
|
"num_tokens": 12111805.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.712796831130982,
|
|
"epoch": 0.5288461538461539,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497833370890278,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.16041593104600907,
|
|
"num_tokens": 12122511.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.646581935882568,
|
|
"epoch": 0.529299709724238,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004978288890973529,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.16504603922367095,
|
|
"num_tokens": 12132510.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.560458707809448,
|
|
"epoch": 0.5297532656023222,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004978244026962698,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.160628604888916,
|
|
"num_tokens": 12142419.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.665068292617798,
|
|
"epoch": 0.5302068214804064,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004978199116871212,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.15784812569618226,
|
|
"num_tokens": 12152759.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.674602031707764,
|
|
"epoch": 0.5306603773584906,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00049781541607,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.16014756113290787,
|
|
"num_tokens": 12162758.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.650653648376465,
|
|
"epoch": 0.5311139332365747,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004978109158449993,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.15944256633520126,
|
|
"num_tokens": 12172664.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.6479345798492435,
|
|
"epoch": 0.5315674891146589,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004978064110122121,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.1643272027373314,
|
|
"num_tokens": 12182028.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.698169708251953,
|
|
"epoch": 0.532021044992743,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004978019015717314,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16326664686203002,
|
|
"num_tokens": 12192168.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.559962463378906,
|
|
"epoch": 0.5324746008708273,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977973875236508,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.16042792201042175,
|
|
"num_tokens": 12202889.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.602790117263794,
|
|
"epoch": 0.5329281567489115,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977928688680634,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.16603052914142608,
|
|
"num_tokens": 12212514.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.641613245010376,
|
|
"epoch": 0.5333817126269956,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977883456050626,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.1707530677318573,
|
|
"num_tokens": 12222353.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.693383884429932,
|
|
"epoch": 0.5338352685050798,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497783817734742,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.1538747400045395,
|
|
"num_tokens": 12232845.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.656322717666626,
|
|
"epoch": 0.534288824383164,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004977792852571954,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.15664656311273575,
|
|
"num_tokens": 12242950.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.683221960067749,
|
|
"epoch": 0.5347423802612482,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004977747481725164,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.15758552253246308,
|
|
"num_tokens": 12253132.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.648868751525879,
|
|
"epoch": 0.5351959361393324,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977702064807987,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.16616235822439193,
|
|
"num_tokens": 12263214.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.588494825363159,
|
|
"epoch": 0.5356494920174165,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004977656601821366,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.17042534202337264,
|
|
"num_tokens": 12273250.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.783517217636108,
|
|
"epoch": 0.5361030478955007,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977611092766238,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.16542720496654512,
|
|
"num_tokens": 12283767.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.619170093536377,
|
|
"epoch": 0.5365566037735849,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004977565537643544,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.15744243562221527,
|
|
"num_tokens": 12294612.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.574744081497192,
|
|
"epoch": 0.5370101596516691,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004977519936454227,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.16173869967460633,
|
|
"num_tokens": 12305614.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.6041184425354,
|
|
"epoch": 0.5374637155297532,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004977474289199231,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1602635309100151,
|
|
"num_tokens": 12316152.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.607742023468018,
|
|
"epoch": 0.5379172714078374,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004977428595879499,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.16442461162805558,
|
|
"num_tokens": 12325940.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.586103534698486,
|
|
"epoch": 0.5383708272859217,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004977382856495975,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.1628282383084297,
|
|
"num_tokens": 12335482.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.7526442527771,
|
|
"epoch": 0.5388243831640058,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977337071049606,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.1566042810678482,
|
|
"num_tokens": 12346386.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.743467712402344,
|
|
"epoch": 0.53927793904209,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497729123954134,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16442530900239943,
|
|
"num_tokens": 12356282.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.566780138015747,
|
|
"epoch": 0.5397314949201741,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004977245361972123,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.16320088356733323,
|
|
"num_tokens": 12366994.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.675820970535279,
|
|
"epoch": 0.5401850507982583,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004977199438342904,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.16420960426330566,
|
|
"num_tokens": 12377524.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.647736883163452,
|
|
"epoch": 0.5406386066763426,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004977153468654634,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.16150177270174026,
|
|
"num_tokens": 12387593.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.665026760101318,
|
|
"epoch": 0.5410921625544267,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004977107452908262,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.16269752979278565,
|
|
"num_tokens": 12398732.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.676980781555176,
|
|
"epoch": 0.5415457184325109,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000497706139110474,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.16847805306315422,
|
|
"num_tokens": 12409821.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.6549646854400635,
|
|
"epoch": 0.541999274310595,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004977015283245021,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.15639931112527847,
|
|
"num_tokens": 12420044.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.526405477523804,
|
|
"epoch": 0.5424528301886793,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004976969129330059,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.15921124070882797,
|
|
"num_tokens": 12430980.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.622525978088379,
|
|
"epoch": 0.5429063860667634,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004976922929360808,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.16727575212717055,
|
|
"num_tokens": 12441999.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.723354196548462,
|
|
"epoch": 0.5433599419448476,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004976876683338222,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.15907001495361328,
|
|
"num_tokens": 12452837.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.6485847473144535,
|
|
"epoch": 0.5438134978229318,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000497683039126326,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.16824455857276915,
|
|
"num_tokens": 12462142.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.643194198608398,
|
|
"epoch": 0.5442670537010159,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976784053136878,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.16665686517953873,
|
|
"num_tokens": 12472756.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5442670537010159,
|
|
"eval_entropy": 5.472823539039129,
|
|
"eval_loss": 5.589262962341309,
|
|
"eval_mean_token_accuracy": 0.16745942614938877,
|
|
"eval_num_tokens": 12472756.0,
|
|
"eval_runtime": 26.5027,
|
|
"eval_samples_per_second": 1334.206,
|
|
"eval_steps_per_second": 166.776,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.670133972167969,
|
|
"epoch": 0.5447206095791002,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004976737668960034,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.1545624852180481,
|
|
"num_tokens": 12483115.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.66155514717102,
|
|
"epoch": 0.5451741654571843,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976691238733688,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.1589282423257828,
|
|
"num_tokens": 12493280.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.693755388259888,
|
|
"epoch": 0.5456277213352685,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049766447624588,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.16183248460292815,
|
|
"num_tokens": 12503665.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.695195531845092,
|
|
"epoch": 0.5460812772133526,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497659824013633,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.1570957064628601,
|
|
"num_tokens": 12513381.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.753922653198242,
|
|
"epoch": 0.5465348330914369,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004976551671767241,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.16156743764877318,
|
|
"num_tokens": 12524121.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.648118257522583,
|
|
"epoch": 0.5469883889695211,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004976505057352496,
|
|
"loss": 5.5566,
|
|
"mean_token_accuracy": 0.16416458934545516,
|
|
"num_tokens": 12533972.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.698191070556641,
|
|
"epoch": 0.5474419448476052,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004976458396893059,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.1542829692363739,
|
|
"num_tokens": 12544110.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.691080808639526,
|
|
"epoch": 0.5478955007256894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976411690389896,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.15873684734106064,
|
|
"num_tokens": 12554273.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.705283308029175,
|
|
"epoch": 0.5483490566037735,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000497636493784397,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.16140856519341468,
|
|
"num_tokens": 12564633.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.645505380630493,
|
|
"epoch": 0.5488026124818578,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004976318139256251,
|
|
"loss": 5.5151,
|
|
"mean_token_accuracy": 0.1661514475941658,
|
|
"num_tokens": 12573790.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.6294355392456055,
|
|
"epoch": 0.549256168359942,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004976271294627706,
|
|
"loss": 5.5808,
|
|
"mean_token_accuracy": 0.15535681694746017,
|
|
"num_tokens": 12584265.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.621347236633301,
|
|
"epoch": 0.5497097242380261,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004976224403959303,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.16849451810121535,
|
|
"num_tokens": 12594413.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.657793998718262,
|
|
"epoch": 0.5501632801161103,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976177467252012,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.1673310860991478,
|
|
"num_tokens": 12604637.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.661483812332153,
|
|
"epoch": 0.5506168359941945,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004976130484506804,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.1647314742207527,
|
|
"num_tokens": 12614873.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.6395495414733885,
|
|
"epoch": 0.5510703918722787,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004976083455724649,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1589552417397499,
|
|
"num_tokens": 12626182.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.614484357833862,
|
|
"epoch": 0.5515239477503628,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004976036380906523,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.16557910591363906,
|
|
"num_tokens": 12635418.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.648619842529297,
|
|
"epoch": 0.551977503628447,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004975989260053395,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.1543217584490776,
|
|
"num_tokens": 12645942.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.660171985626221,
|
|
"epoch": 0.5524310595065312,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975942093166242,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.16052016615867615,
|
|
"num_tokens": 12656460.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.695255470275879,
|
|
"epoch": 0.5528846153846154,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004975894880246041,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.16347223967313768,
|
|
"num_tokens": 12666916.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.601450824737549,
|
|
"epoch": 0.5533381712626996,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004975847621293766,
|
|
"loss": 5.5431,
|
|
"mean_token_accuracy": 0.1696389064192772,
|
|
"num_tokens": 12677562.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.63624677658081,
|
|
"epoch": 0.5537917271407837,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004975800316310394,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.16171834021806716,
|
|
"num_tokens": 12687349.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.649888229370117,
|
|
"epoch": 0.5542452830188679,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004975752965296906,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.1648343488574028,
|
|
"num_tokens": 12697850.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.612441205978394,
|
|
"epoch": 0.5546988388969522,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004975705568254278,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.16573707461357118,
|
|
"num_tokens": 12708283.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.648651742935181,
|
|
"epoch": 0.5551523947750363,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004975658125183493,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.1632908210158348,
|
|
"num_tokens": 12718201.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.60323486328125,
|
|
"epoch": 0.5556059506531205,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000497561063608553,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.1683592066168785,
|
|
"num_tokens": 12728860.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.626165914535522,
|
|
"epoch": 0.5560595065312046,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975563100961372,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.15690662562847138,
|
|
"num_tokens": 12739007.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.606911945343017,
|
|
"epoch": 0.5565130624092888,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004975515519812002,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.17006937563419341,
|
|
"num_tokens": 12749004.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.596025609970093,
|
|
"epoch": 0.556966618287373,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004975467892638402,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16381375193595887,
|
|
"num_tokens": 12760085.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.645767450332642,
|
|
"epoch": 0.5574201741654572,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004975420219441561,
|
|
"loss": 5.5069,
|
|
"mean_token_accuracy": 0.17016789615154265,
|
|
"num_tokens": 12770303.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.661552429199219,
|
|
"epoch": 0.5578737300435413,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004975372500222462,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.16546058803796768,
|
|
"num_tokens": 12780334.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.6559959888458256,
|
|
"epoch": 0.5583272859216255,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004975324734982094,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.16141054183244705,
|
|
"num_tokens": 12790980.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.643654870986938,
|
|
"epoch": 0.5587808417997098,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004975276923721442,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.15867158025503159,
|
|
"num_tokens": 12801713.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.699330234527588,
|
|
"epoch": 0.5592343976777939,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004975229066441496,
|
|
"loss": 5.6061,
|
|
"mean_token_accuracy": 0.15926154106855392,
|
|
"num_tokens": 12813040.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.693249845504761,
|
|
"epoch": 0.5596879535558781,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004975181163143247,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.15429083853960038,
|
|
"num_tokens": 12824048.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.656903409957886,
|
|
"epoch": 0.5601415094339622,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004975133213827684,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.15892634391784669,
|
|
"num_tokens": 12834297.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.745335054397583,
|
|
"epoch": 0.5605950653120464,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004975085218495798,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.16047458797693254,
|
|
"num_tokens": 12844574.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.560383129119873,
|
|
"epoch": 0.5610486211901307,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004975037177148585,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.1610662505030632,
|
|
"num_tokens": 12854670.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.561988258361817,
|
|
"epoch": 0.5615021770682148,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004974989089787035,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.1686451852321625,
|
|
"num_tokens": 12865281.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.702982187271118,
|
|
"epoch": 0.561955732946299,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004974940956412143,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.1641027018427849,
|
|
"num_tokens": 12875222.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.816201686859131,
|
|
"epoch": 0.5624092888243831,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974892777024905,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.15752922147512435,
|
|
"num_tokens": 12885079.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.67298469543457,
|
|
"epoch": 0.5628628447024674,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004974844551626318,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.1641029268503189,
|
|
"num_tokens": 12896402.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.614017629623413,
|
|
"epoch": 0.5633164005805515,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004974796280217379,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.16557157337665557,
|
|
"num_tokens": 12906403.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.71490626335144,
|
|
"epoch": 0.5637699564586357,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004974747962799086,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.1579867884516716,
|
|
"num_tokens": 12917061.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.656363534927368,
|
|
"epoch": 0.5642235123367199,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004974699599372437,
|
|
"loss": 5.5807,
|
|
"mean_token_accuracy": 0.16344264447689055,
|
|
"num_tokens": 12927182.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.624368143081665,
|
|
"epoch": 0.564677068214804,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004974651189938434,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.16056101471185685,
|
|
"num_tokens": 12937371.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.70891375541687,
|
|
"epoch": 0.5651306240928883,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004974602734498079,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.15544345378875732,
|
|
"num_tokens": 12948569.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.741915559768676,
|
|
"epoch": 0.5655841799709724,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000497455423305237,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.15569789856672286,
|
|
"num_tokens": 12958503.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.718269109725952,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974505685602314,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.15982589423656463,
|
|
"num_tokens": 12968714.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.644350957870484,
|
|
"epoch": 0.5664912917271407,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004974457092148912,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.16113034933805465,
|
|
"num_tokens": 12978857.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.7991985321044925,
|
|
"epoch": 0.566944847605225,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004974408452693172,
|
|
"loss": 5.7043,
|
|
"mean_token_accuracy": 0.1546899065375328,
|
|
"num_tokens": 12989863.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.7228484630584715,
|
|
"epoch": 0.5673984034833092,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004974359767236099,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.16300520449876785,
|
|
"num_tokens": 13000307.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.664002227783203,
|
|
"epoch": 0.5678519593613933,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004974311035778698,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.16984948217868806,
|
|
"num_tokens": 13009053.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.61906361579895,
|
|
"epoch": 0.5683055152394775,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004974262258321979,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.15511150807142257,
|
|
"num_tokens": 13019136.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.743262004852295,
|
|
"epoch": 0.5687590711175616,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004974213434866949,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.15917437374591828,
|
|
"num_tokens": 13030356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.682684850692749,
|
|
"epoch": 0.5692126269956459,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004974164565414617,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16206429302692413,
|
|
"num_tokens": 13040477.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.6901579856872555,
|
|
"epoch": 0.56966618287373,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004974115649965998,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1673882707953453,
|
|
"num_tokens": 13051755.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.739024353027344,
|
|
"epoch": 0.5701197387518142,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004974066688522098,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.17134420275688172,
|
|
"num_tokens": 13061670.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.634558582305909,
|
|
"epoch": 0.5705732946298984,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974017681083934,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.1640141114592552,
|
|
"num_tokens": 13070917.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.620419692993164,
|
|
"epoch": 0.5710268505079826,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004973968627652516,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.16330747306346893,
|
|
"num_tokens": 13080577.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.691771507263184,
|
|
"epoch": 0.5714804063860668,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000497391952822886,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.16383007168769836,
|
|
"num_tokens": 13091446.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.720631074905396,
|
|
"epoch": 0.5719339622641509,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004973870382813983,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.1649190291762352,
|
|
"num_tokens": 13102752.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.738799524307251,
|
|
"epoch": 0.5723875181422351,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004973821191408899,
|
|
"loss": 5.6321,
|
|
"mean_token_accuracy": 0.1576658844947815,
|
|
"num_tokens": 13113944.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.651340627670288,
|
|
"epoch": 0.5728410740203193,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004973771954014626,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.15872492641210556,
|
|
"num_tokens": 13124316.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.741772079467774,
|
|
"epoch": 0.5732946298984035,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004973722670632182,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.15541704148054122,
|
|
"num_tokens": 13133567.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.67438702583313,
|
|
"epoch": 0.5737481857764877,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004973673341262587,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.16231633573770524,
|
|
"num_tokens": 13144279.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.728409671783448,
|
|
"epoch": 0.5742017416545718,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000497362396590686,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.16435034647583963,
|
|
"num_tokens": 13154463.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.754732084274292,
|
|
"epoch": 0.574655297532656,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004973574544566024,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.15627192705869675,
|
|
"num_tokens": 13165565.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.630088138580322,
|
|
"epoch": 0.5751088534107403,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004973525077241098,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.16437099426984786,
|
|
"num_tokens": 13175839.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.612335538864135,
|
|
"epoch": 0.5755624092888244,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004973475563933109,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.16129760444164276,
|
|
"num_tokens": 13186372.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.63255467414856,
|
|
"epoch": 0.5760159651669086,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973426004643077,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.16001515984535217,
|
|
"num_tokens": 13196259.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.689817476272583,
|
|
"epoch": 0.5764695210449927,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004973376399372029,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.16678900122642518,
|
|
"num_tokens": 13206497.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.654291391372681,
|
|
"epoch": 0.5769230769230769,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004973326748120991,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.16469015628099443,
|
|
"num_tokens": 13217188.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.670374917984009,
|
|
"epoch": 0.5773766328011611,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004973277050890988,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.16094538420438767,
|
|
"num_tokens": 13226544.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.710937643051148,
|
|
"epoch": 0.5778301886792453,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004973227307683049,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.15699274688959122,
|
|
"num_tokens": 13236572.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.80208945274353,
|
|
"epoch": 0.5782837445573294,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004973177518498204,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.16148673593997956,
|
|
"num_tokens": 13247958.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.642516231536865,
|
|
"epoch": 0.5787373004354136,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973127683337482,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.1633951857686043,
|
|
"num_tokens": 13258255.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.5757979393005375,
|
|
"epoch": 0.5791908563134979,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973077802201911,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1615252360701561,
|
|
"num_tokens": 13268416.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.58531641960144,
|
|
"epoch": 0.579644412191582,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004973027875092526,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.16312111020088196,
|
|
"num_tokens": 13278087.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.604562997817993,
|
|
"epoch": 0.5800979680696662,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004972977902010357,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.1713629350066185,
|
|
"num_tokens": 13288121.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.772391843795776,
|
|
"epoch": 0.5805515239477503,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004972927882956439,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.15260053873062135,
|
|
"num_tokens": 13298620.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.630117321014405,
|
|
"epoch": 0.5810050798258345,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004972877817931807,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.16051941812038423,
|
|
"num_tokens": 13308413.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.5901875495910645,
|
|
"epoch": 0.5814586357039188,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004972827706937493,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.16214399337768554,
|
|
"num_tokens": 13319387.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.653078556060791,
|
|
"epoch": 0.5819121915820029,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972777549974537,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.16626724004745483,
|
|
"num_tokens": 13330494.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.667278242111206,
|
|
"epoch": 0.5823657474600871,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004972727347043975,
|
|
"loss": 5.5175,
|
|
"mean_token_accuracy": 0.15966289341449738,
|
|
"num_tokens": 13341009.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.6079059600830075,
|
|
"epoch": 0.5828193033381712,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004972677098146845,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16285288631916045,
|
|
"num_tokens": 13351269.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.573035478591919,
|
|
"epoch": 0.5832728592162555,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004972626803284185,
|
|
"loss": 5.5728,
|
|
"mean_token_accuracy": 0.16400626450777053,
|
|
"num_tokens": 13362160.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.701131343841553,
|
|
"epoch": 0.5837264150943396,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004972576462457038,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.16086410582065583,
|
|
"num_tokens": 13372497.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.788417720794678,
|
|
"epoch": 0.5841799709724238,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004972526075666442,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.16689816117286682,
|
|
"num_tokens": 13381665.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.620719575881958,
|
|
"epoch": 0.584633526850508,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004972475642913442,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16386179476976395,
|
|
"num_tokens": 13392507.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.537435913085938,
|
|
"epoch": 0.5850870827285921,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004972425164199078,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.17011575847864152,
|
|
"num_tokens": 13402171.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.713273334503174,
|
|
"epoch": 0.5855406386066764,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004972374639524396,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.15556367337703705,
|
|
"num_tokens": 13412933.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.7077325820922855,
|
|
"epoch": 0.5859941944847605,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497232406889044,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.15624898225069045,
|
|
"num_tokens": 13423563.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.683661603927613,
|
|
"epoch": 0.5864477503628447,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004972273452298255,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.16698916330933572,
|
|
"num_tokens": 13433998.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.607936191558838,
|
|
"epoch": 0.5869013062409288,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004972222789748888,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16828617155551912,
|
|
"num_tokens": 13443878.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.618822765350342,
|
|
"epoch": 0.5873548621190131,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004972172081243389,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.1563350200653076,
|
|
"num_tokens": 13456051.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.6659345626831055,
|
|
"epoch": 0.5878084179970973,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004972121326782806,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.16245667785406112,
|
|
"num_tokens": 13467276.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.6519945621490475,
|
|
"epoch": 0.5882619738751814,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004972070526368186,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.1641760379076004,
|
|
"num_tokens": 13478331.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.698674488067627,
|
|
"epoch": 0.5887155297532656,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004972019680000582,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.16153709441423417,
|
|
"num_tokens": 13489879.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.666459035873413,
|
|
"epoch": 0.5891690856313497,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004971968787681044,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.16374465972185134,
|
|
"num_tokens": 13500879.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.701348543167114,
|
|
"epoch": 0.589622641509434,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004971917849410627,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.1603960059583187,
|
|
"num_tokens": 13511719.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.652278709411621,
|
|
"epoch": 0.5900761973875182,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004971866865190381,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.16301714330911637,
|
|
"num_tokens": 13521850.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.681592130661011,
|
|
"epoch": 0.5905297532656023,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004971815835021362,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.16761482805013656,
|
|
"num_tokens": 13532095.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.670617389678955,
|
|
"epoch": 0.5909833091436865,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004971764758904626,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.1592058703303337,
|
|
"num_tokens": 13543133.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.653409767150879,
|
|
"epoch": 0.5914368650217707,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004971713636841229,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.1548130914568901,
|
|
"num_tokens": 13553771.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.633445310592651,
|
|
"epoch": 0.5918904208998549,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004971662468832228,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.16742569208145142,
|
|
"num_tokens": 13564548.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.644088172912598,
|
|
"epoch": 0.592343976777939,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000497161125487868,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1607619509100914,
|
|
"num_tokens": 13574567.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.584167718887329,
|
|
"epoch": 0.5927975326560232,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004971559994981645,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.15815457254648208,
|
|
"num_tokens": 13585302.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.720269870758057,
|
|
"epoch": 0.5932510885341074,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971508689142184,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.15577241480350495,
|
|
"num_tokens": 13594754.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.678057336807251,
|
|
"epoch": 0.5937046444121916,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004971457337361356,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.16067788600921631,
|
|
"num_tokens": 13604691.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.523071575164795,
|
|
"epoch": 0.5941582002902758,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004971405939640225,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.16877733170986176,
|
|
"num_tokens": 13613911.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.77616057395935,
|
|
"epoch": 0.5946117561683599,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971354495979854,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.1572772741317749,
|
|
"num_tokens": 13624285.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.626784420013427,
|
|
"epoch": 0.5950653120464441,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004971303006381305,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.16492559462785722,
|
|
"num_tokens": 13635434.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.600918865203857,
|
|
"epoch": 0.5955188679245284,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004971251470845643,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.16005088835954667,
|
|
"num_tokens": 13645582.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.643901062011719,
|
|
"epoch": 0.5959724238026125,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004971199889373935,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.16063801646232606,
|
|
"num_tokens": 13655029.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.631298017501831,
|
|
"epoch": 0.5964259796806967,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004971148261967249,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.1626351296901703,
|
|
"num_tokens": 13665204.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.613391780853272,
|
|
"epoch": 0.5968795355587808,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004971096588626649,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.15829678177833556,
|
|
"num_tokens": 13676281.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.623476934432984,
|
|
"epoch": 0.597333091436865,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004971044869353206,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.16425087451934814,
|
|
"num_tokens": 13687144.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.665033578872681,
|
|
"epoch": 0.5977866473149492,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497099310414799,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.1613985627889633,
|
|
"num_tokens": 13696371.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.68272442817688,
|
|
"epoch": 0.5982402031930334,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004970941293012069,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16283626109361649,
|
|
"num_tokens": 13706900.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.613545656204224,
|
|
"epoch": 0.5986937590711175,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004970889435946518,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.1644856095314026,
|
|
"num_tokens": 13717874.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.616415214538574,
|
|
"epoch": 0.5991473149492017,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004970837532952406,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.15892142057418823,
|
|
"num_tokens": 13728020.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.709966087341309,
|
|
"epoch": 0.599600870827286,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004970785584030808,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.16402234882116318,
|
|
"num_tokens": 13738007.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.693265438079834,
|
|
"epoch": 0.6000544267053701,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970733589182799,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.15396313965320588,
|
|
"num_tokens": 13749429.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.636207914352417,
|
|
"epoch": 0.6005079825834543,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004970681548409452,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.17165576219558715,
|
|
"num_tokens": 13760279.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.659836006164551,
|
|
"epoch": 0.6009615384615384,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004970629461711846,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.15390522927045822,
|
|
"num_tokens": 13770575.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.6224652290344235,
|
|
"epoch": 0.6014150943396226,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004970577329091057,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.16576763540506362,
|
|
"num_tokens": 13781068.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.711998653411865,
|
|
"epoch": 0.6018686502177069,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004970525150548162,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.16630152910947799,
|
|
"num_tokens": 13790745.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.654412794113159,
|
|
"epoch": 0.602322206095791,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004970472926084242,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16336238980293274,
|
|
"num_tokens": 13800196.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.580491256713867,
|
|
"epoch": 0.6027757619738752,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004970420655700375,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.17028857320547103,
|
|
"num_tokens": 13809954.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.61370964050293,
|
|
"epoch": 0.6032293178519593,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004970368339397643,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1555069014430046,
|
|
"num_tokens": 13820281.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.714426946640015,
|
|
"epoch": 0.6036828737300436,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004970315977177129,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.16427477449178696,
|
|
"num_tokens": 13830614.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.630530929565429,
|
|
"epoch": 0.6041364296081277,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004970263569039914,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.1645730271935463,
|
|
"num_tokens": 13840551.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.715430402755738,
|
|
"epoch": 0.6045899854862119,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004970211114987083,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.15893951207399368,
|
|
"num_tokens": 13851830.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.650357341766357,
|
|
"epoch": 0.6050435413642961,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004970158615019719,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.16365663409233094,
|
|
"num_tokens": 13862299.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.756088066101074,
|
|
"epoch": 0.6054970972423802,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004970106069138912,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.15317101627588273,
|
|
"num_tokens": 13872852.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.660994815826416,
|
|
"epoch": 0.6059506531204645,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004970053477345743,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.16634648889303208,
|
|
"num_tokens": 13883601.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.639829063415528,
|
|
"epoch": 0.6064042089985486,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004970000839641304,
|
|
"loss": 5.5516,
|
|
"mean_token_accuracy": 0.16657450199127197,
|
|
"num_tokens": 13894246.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.607128047943116,
|
|
"epoch": 0.6068577648766328,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004969948156026681,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.16131135672330857,
|
|
"num_tokens": 13904823.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.694171953201294,
|
|
"epoch": 0.6073113207547169,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004969895426502965,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.16069512516260148,
|
|
"num_tokens": 13915338.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.619790935516358,
|
|
"epoch": 0.6077648766328012,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004969842651071246,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.16402424424886702,
|
|
"num_tokens": 13925838.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.7219775199890135,
|
|
"epoch": 0.6082184325108854,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004969789829732615,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.15887922644615174,
|
|
"num_tokens": 13936341.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.68441743850708,
|
|
"epoch": 0.6086719883889695,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004969736962488164,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.1660606235265732,
|
|
"num_tokens": 13945438.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.621346664428711,
|
|
"epoch": 0.6091255442670537,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004969684049338987,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.16126258224248885,
|
|
"num_tokens": 13956029.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.666759252548218,
|
|
"epoch": 0.6095791001451378,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496963109028618,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.1595468908548355,
|
|
"num_tokens": 13966498.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.627069568634033,
|
|
"epoch": 0.6100326560232221,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004969578085330834,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.16338904947042465,
|
|
"num_tokens": 13976997.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.680052900314331,
|
|
"epoch": 0.6104862119013063,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004969525034474049,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.1636262834072113,
|
|
"num_tokens": 13986664.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.596657180786133,
|
|
"epoch": 0.6109397677793904,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000496947193771692,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1638951927423477,
|
|
"num_tokens": 13997828.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.608260631561279,
|
|
"epoch": 0.6113933236574746,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004969418795060548,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.15902622193098068,
|
|
"num_tokens": 14008293.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.629490756988526,
|
|
"epoch": 0.6118468795355588,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004969365606506027,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.16772356033325195,
|
|
"num_tokens": 14018031.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.596383762359619,
|
|
"epoch": 0.612300435413643,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004969312372054461,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.17152134627103804,
|
|
"num_tokens": 14028013.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.552363443374634,
|
|
"epoch": 0.6127539912917271,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004969259091706948,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.16048205494880677,
|
|
"num_tokens": 14039787.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.588634395599366,
|
|
"epoch": 0.6132075471698113,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004969205765464593,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.1649627611041069,
|
|
"num_tokens": 14049223.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.660885524749756,
|
|
"epoch": 0.6136611030478955,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004969152393328497,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.16500439047813414,
|
|
"num_tokens": 14059004.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.674933958053589,
|
|
"epoch": 0.6141146589259797,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004969098975299764,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.15621163845062255,
|
|
"num_tokens": 14069615.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.6336719512939455,
|
|
"epoch": 0.6145682148040639,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004969045511379499,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.16255359649658202,
|
|
"num_tokens": 14078886.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.673841714859009,
|
|
"epoch": 0.615021770682148,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004968992001568806,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.1564471200108528,
|
|
"num_tokens": 14089021.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.651300048828125,
|
|
"epoch": 0.6154753265602322,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004968938445868795,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.17256750017404557,
|
|
"num_tokens": 14098316.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.591040754318238,
|
|
"epoch": 0.6159288824383164,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004968884844280569,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.1584145352244377,
|
|
"num_tokens": 14108874.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.641624498367309,
|
|
"epoch": 0.6163824383164006,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004968831196805242,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.16046148389577866,
|
|
"num_tokens": 14119613.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.676394128799439,
|
|
"epoch": 0.6168359941944848,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004968777503443918,
|
|
"loss": 5.5095,
|
|
"mean_token_accuracy": 0.16080328971147537,
|
|
"num_tokens": 14129085.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.512157869338989,
|
|
"epoch": 0.6172895500725689,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004968723764197711,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1770444855093956,
|
|
"num_tokens": 14138461.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.594473648071289,
|
|
"epoch": 0.6177431059506531,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000496866997906773,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.16651539504528046,
|
|
"num_tokens": 14149126.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.635282516479492,
|
|
"epoch": 0.6181966618287373,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004968616148055089,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.1690201073884964,
|
|
"num_tokens": 14160068.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.627933597564697,
|
|
"epoch": 0.6186502177068215,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004968562271160901,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.166331148147583,
|
|
"num_tokens": 14170288.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.728124380111694,
|
|
"epoch": 0.6191037735849056,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000496850834838628,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.16276340931653976,
|
|
"num_tokens": 14181231.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.669750642776489,
|
|
"epoch": 0.6195573294629898,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004968454379732342,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.16779735684394836,
|
|
"num_tokens": 14191715.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.602129220962524,
|
|
"epoch": 0.6200108853410741,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00049684003652002,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.1612647980451584,
|
|
"num_tokens": 14203416.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.548123359680176,
|
|
"epoch": 0.6204644412191582,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004968346304790973,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.17077218294143676,
|
|
"num_tokens": 14213658.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.668492031097412,
|
|
"epoch": 0.6209179970972424,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.0004968292198505781,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.15588149279356003,
|
|
"num_tokens": 14223956.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.668875312805175,
|
|
"epoch": 0.6213715529753265,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000496823804634574,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1597575768828392,
|
|
"num_tokens": 14236801.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.602407693862915,
|
|
"epoch": 0.6218251088534107,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004968183848311972,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.17220478355884553,
|
|
"num_tokens": 14247382.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.683701372146606,
|
|
"epoch": 0.622278664731495,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004968129604405596,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.16317506432533263,
|
|
"num_tokens": 14258627.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.559516525268554,
|
|
"epoch": 0.6227322206095791,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004968075314627734,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.16878147274255753,
|
|
"num_tokens": 14269013.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.602084016799926,
|
|
"epoch": 0.6231857764876633,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000496802097897951,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.1642188236117363,
|
|
"num_tokens": 14279620.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.647443389892578,
|
|
"epoch": 0.6236393323657474,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004967966597462046,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.17011392563581468,
|
|
"num_tokens": 14289448.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.62725305557251,
|
|
"epoch": 0.6240928882438317,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004967912170076469,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.16029064506292343,
|
|
"num_tokens": 14299999.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.5908074378967285,
|
|
"epoch": 0.6245464441219158,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004967857696823901,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.1604388862848282,
|
|
"num_tokens": 14310384.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.666422319412232,
|
|
"epoch": 0.625,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004967803177705472,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.15651167333126068,
|
|
"num_tokens": 14320644.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.684583044052124,
|
|
"epoch": 0.6254535558780842,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004967748612722308,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.16236335188150405,
|
|
"num_tokens": 14330077.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.7078063011169435,
|
|
"epoch": 0.6259071117561683,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004967694001875538,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.1552937150001526,
|
|
"num_tokens": 14341549.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.68909273147583,
|
|
"epoch": 0.6263606676342526,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000496763934516629,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1664724200963974,
|
|
"num_tokens": 14352146.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.614871978759766,
|
|
"epoch": 0.6268142235123367,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004967584642595696,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.15754454135894774,
|
|
"num_tokens": 14362521.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.698942518234253,
|
|
"epoch": 0.6272677793904209,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004967529894164887,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.16412983238697051,
|
|
"num_tokens": 14373216.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.63185224533081,
|
|
"epoch": 0.627721335268505,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004967475099874992,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.17082804292440415,
|
|
"num_tokens": 14383104.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.556405639648437,
|
|
"epoch": 0.6281748911465893,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000496742025972715,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.16977826058864592,
|
|
"num_tokens": 14393854.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.622954559326172,
|
|
"epoch": 0.6286284470246735,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000496736537372249,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.17209360599517823,
|
|
"num_tokens": 14403213.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.703037691116333,
|
|
"epoch": 0.6290820029027576,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004967310441862151,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.1583329074084759,
|
|
"num_tokens": 14412792.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.676712512969971,
|
|
"epoch": 0.6295355587808418,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004967255464147265,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.16898928731679916,
|
|
"num_tokens": 14423061.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.653528928756714,
|
|
"epoch": 0.6299891146589259,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004967200440578972,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16783155202865602,
|
|
"num_tokens": 14433338.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.568450927734375,
|
|
"epoch": 0.6304426705370102,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004967145371158408,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.17319378405809402,
|
|
"num_tokens": 14444124.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.613980054855347,
|
|
"epoch": 0.6308962264150944,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004967090255886714,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.16500539034605027,
|
|
"num_tokens": 14453868.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.628482532501221,
|
|
"epoch": 0.6313497822931785,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004967035094765028,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.16420088410377504,
|
|
"num_tokens": 14465015.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.596653985977173,
|
|
"epoch": 0.6318033381712627,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004966979887794491,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.17249543368816375,
|
|
"num_tokens": 14475523.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.6447957992553714,
|
|
"epoch": 0.6322568940493469,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004966924634976245,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1661619022488594,
|
|
"num_tokens": 14485523.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.697253131866455,
|
|
"epoch": 0.6327104499274311,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004966869336311433,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.1666168376803398,
|
|
"num_tokens": 14495237.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.640621852874756,
|
|
"epoch": 0.6331640058055152,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004966813991801197,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.15432378351688386,
|
|
"num_tokens": 14506431.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.727398633956909,
|
|
"epoch": 0.6336175616835994,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004966758601446684,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.15618521571159363,
|
|
"num_tokens": 14517445.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.673369693756103,
|
|
"epoch": 0.6340711175616836,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004966703165249038,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.1577815368771553,
|
|
"num_tokens": 14527818.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.660148620605469,
|
|
"epoch": 0.6345246734397678,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004966647683209406,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.1515124946832657,
|
|
"num_tokens": 14538235.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.7893064498901365,
|
|
"epoch": 0.634978229317852,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004966592155328935,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.15409057587385178,
|
|
"num_tokens": 14549784.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.675354909896851,
|
|
"epoch": 0.6354317851959361,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004966536581608771,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.15651679188013076,
|
|
"num_tokens": 14561057.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.6757800579071045,
|
|
"epoch": 0.6358853410740203,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004966480962050069,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.1694130152463913,
|
|
"num_tokens": 14570859.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.654591512680054,
|
|
"epoch": 0.6363388969521045,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004966425296653974,
|
|
"loss": 5.548,
|
|
"mean_token_accuracy": 0.16952096819877624,
|
|
"num_tokens": 14581066.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.601092910766601,
|
|
"epoch": 0.6367924528301887,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000496636958542164,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.16194411963224412,
|
|
"num_tokens": 14590709.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.6308215141296385,
|
|
"epoch": 0.6372460087082729,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004966313828354218,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1659430295228958,
|
|
"num_tokens": 14600849.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.604932880401611,
|
|
"epoch": 0.637699564586357,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000496625802545286,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.16500746309757233,
|
|
"num_tokens": 14611427.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.651730728149414,
|
|
"epoch": 0.6381531204644412,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004966202176718723,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16733615100383759,
|
|
"num_tokens": 14623860.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.621776580810547,
|
|
"epoch": 0.6386066763425254,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004966146282152959,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.1645897924900055,
|
|
"num_tokens": 14633481.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.639799451828003,
|
|
"epoch": 0.6390602322206096,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004966090341756726,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.173050656914711,
|
|
"num_tokens": 14643519.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.589098262786865,
|
|
"epoch": 0.6395137880986937,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496603435553118,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.16662810295820235,
|
|
"num_tokens": 14654570.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.610861587524414,
|
|
"epoch": 0.6399673439767779,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004965978323477478,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.15878622084856034,
|
|
"num_tokens": 14665596.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.670983934402466,
|
|
"epoch": 0.6404208998548622,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000496592224559678,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.17061298489570617,
|
|
"num_tokens": 14675660.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.668635034561158,
|
|
"epoch": 0.6408744557329463,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004965866121890245,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.161976358294487,
|
|
"num_tokens": 14685229.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.66521725654602,
|
|
"epoch": 0.6413280116110305,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004965809952359034,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.15676263421773912,
|
|
"num_tokens": 14695672.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.630953550338745,
|
|
"epoch": 0.6417815674891146,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004965753737004309,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.17113818228244781,
|
|
"num_tokens": 14705160.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.616978645324707,
|
|
"epoch": 0.6422351233671988,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004965697475827231,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.1638179302215576,
|
|
"num_tokens": 14715487.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.648258352279663,
|
|
"epoch": 0.6426886792452831,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004965641168828965,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.16361365467309952,
|
|
"num_tokens": 14726987.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.580990219116211,
|
|
"epoch": 0.6431422351233672,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004965584816010676,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.16957174092531205,
|
|
"num_tokens": 14737810.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.700578737258911,
|
|
"epoch": 0.6435957910014514,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004965528417373528,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.15920886397361755,
|
|
"num_tokens": 14748997.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.654855442047119,
|
|
"epoch": 0.6440493468795355,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004965471972918688,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.1612129181623459,
|
|
"num_tokens": 14760439.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.593002033233643,
|
|
"epoch": 0.6445029027576198,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004965415482647322,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16583144515752793,
|
|
"num_tokens": 14770828.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.570415592193603,
|
|
"epoch": 0.6449564586357039,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00049653589465606,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.16377214789390565,
|
|
"num_tokens": 14781753.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.717770576477051,
|
|
"epoch": 0.6454100145137881,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000496530236465969,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.159645214676857,
|
|
"num_tokens": 14792241.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.6190179824829105,
|
|
"epoch": 0.6458635703918723,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004965245736945763,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17340738624334334,
|
|
"num_tokens": 14802580.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.597347974777222,
|
|
"epoch": 0.6463171262699564,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004965189063419989,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.16257513761520387,
|
|
"num_tokens": 14813103.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.628874015808106,
|
|
"epoch": 0.6467706821480407,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004965132344083541,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.16554489135742187,
|
|
"num_tokens": 14823334.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.747768974304199,
|
|
"epoch": 0.6472242380261248,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004965075578937593,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.15984877645969392,
|
|
"num_tokens": 14834850.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.638379621505737,
|
|
"epoch": 0.647677793904209,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004965018767983316,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.1638460412621498,
|
|
"num_tokens": 14844276.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.518471670150757,
|
|
"epoch": 0.6481313497822931,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004964961911221886,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.17712354212999343,
|
|
"num_tokens": 14854352.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.6490014553070065,
|
|
"epoch": 0.6485849056603774,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000496490500865448,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.1627000540494919,
|
|
"num_tokens": 14864395.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.6571167469024655,
|
|
"epoch": 0.6490384615384616,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004964848060282275,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.17021121829748154,
|
|
"num_tokens": 14874373.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.620741987228394,
|
|
"epoch": 0.6494920174165457,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004964791066106447,
|
|
"loss": 5.4425,
|
|
"mean_token_accuracy": 0.1613517627120018,
|
|
"num_tokens": 14884932.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.63075442314148,
|
|
"epoch": 0.6499455732946299,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004964734026128175,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.1577137976884842,
|
|
"num_tokens": 14896254.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.713843965530396,
|
|
"epoch": 0.650399129172714,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004964676940348638,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.16059393137693406,
|
|
"num_tokens": 14907392.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.73220853805542,
|
|
"epoch": 0.6508526850507983,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000496461980876902,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.16424211263656616,
|
|
"num_tokens": 14917676.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.627636861801148,
|
|
"epoch": 0.6513062409288825,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004964562631390498,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.16617691963911058,
|
|
"num_tokens": 14928500.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.609093856811524,
|
|
"epoch": 0.6517597968069666,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004964505408214257,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.17101617455482482,
|
|
"num_tokens": 14938970.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.616778039932251,
|
|
"epoch": 0.6522133526850508,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000496444813924148,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.16331736892461776,
|
|
"num_tokens": 14949017.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.654310798645019,
|
|
"epoch": 0.652666908563135,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004964390824473351,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.1724479764699936,
|
|
"num_tokens": 14958529.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.597932052612305,
|
|
"epoch": 0.6531204644412192,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004964333463911056,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.15932074636220933,
|
|
"num_tokens": 14968044.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.65596113204956,
|
|
"epoch": 0.6535740203193033,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004964276057555779,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.16014891862869263,
|
|
"num_tokens": 14977867.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.783083295822143,
|
|
"epoch": 0.6540275761973875,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000496421860540871,
|
|
"loss": 5.5475,
|
|
"mean_token_accuracy": 0.16266472786664962,
|
|
"num_tokens": 14986936.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.61876163482666,
|
|
"epoch": 0.6544811320754716,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004964161107471036,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.1681314930319786,
|
|
"num_tokens": 14996681.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.598669624328613,
|
|
"epoch": 0.6549346879535559,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004964103563743946,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.1631477177143097,
|
|
"num_tokens": 15007100.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.694092845916748,
|
|
"epoch": 0.6553882438316401,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000496404597422863,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.1644970640540123,
|
|
"num_tokens": 15017452.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.620909023284912,
|
|
"epoch": 0.6558417997097242,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000496398833892628,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.16442154794931413,
|
|
"num_tokens": 15028362.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.638983058929443,
|
|
"epoch": 0.6562953555878084,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004963930657838086,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1629357695579529,
|
|
"num_tokens": 15038691.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.651097059249878,
|
|
"epoch": 0.6567489114658926,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004963872930965242,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.16842897832393647,
|
|
"num_tokens": 15050037.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.642683744430542,
|
|
"epoch": 0.6572024673439768,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004963815158308941,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.16414920687675477,
|
|
"num_tokens": 15059793.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.633060359954834,
|
|
"epoch": 0.657656023222061,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004963757339870379,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.1542697638273239,
|
|
"num_tokens": 15070500.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.718131399154663,
|
|
"epoch": 0.6581095791001451,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004963699475650751,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15848404318094253,
|
|
"num_tokens": 15081109.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.629377222061157,
|
|
"epoch": 0.6585631349782293,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004963641565651255,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.16712549030780793,
|
|
"num_tokens": 15092315.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.615194702148438,
|
|
"epoch": 0.6590166908563135,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963583609873084,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.16172214299440385,
|
|
"num_tokens": 15103957.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.7270472049713135,
|
|
"epoch": 0.6594702467343977,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004963525608317443,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.1632919952273369,
|
|
"num_tokens": 15114996.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.7020470142364506,
|
|
"epoch": 0.6599238026124818,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004963467560985527,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.16006214767694474,
|
|
"num_tokens": 15125098.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.632985973358155,
|
|
"epoch": 0.660377358490566,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963409467878538,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.15927427560091018,
|
|
"num_tokens": 15134746.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.706460189819336,
|
|
"epoch": 0.6608309143686503,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963351328997678,
|
|
"loss": 5.5321,
|
|
"mean_token_accuracy": 0.15826075226068498,
|
|
"num_tokens": 15145698.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.623006582260132,
|
|
"epoch": 0.6612844702467344,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004963293144344148,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.15674502849578859,
|
|
"num_tokens": 15156026.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.632738924026489,
|
|
"epoch": 0.6617380261248186,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004963234913919151,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.15496615469455718,
|
|
"num_tokens": 15165900.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.635572147369385,
|
|
"epoch": 0.6621915820029027,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004963176637723893,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.1640890881419182,
|
|
"num_tokens": 15176693.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.696575164794922,
|
|
"epoch": 0.6626451378809869,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004963118315759578,
|
|
"loss": 5.6022,
|
|
"mean_token_accuracy": 0.14927273318171502,
|
|
"num_tokens": 15186535.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.7064004898071286,
|
|
"epoch": 0.6630986937590712,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004963059948027411,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.1611385740339756,
|
|
"num_tokens": 15196019.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.552914619445801,
|
|
"epoch": 0.6635522496371553,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004963001534528601,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.1719992369413376,
|
|
"num_tokens": 15205273.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.627516508102417,
|
|
"epoch": 0.6640058055152395,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004962943075264355,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.16372389495372772,
|
|
"num_tokens": 15216716.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.636356401443481,
|
|
"epoch": 0.6644593613933236,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004962884570235884,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.15782008916139603,
|
|
"num_tokens": 15227306.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.564645528793335,
|
|
"epoch": 0.6649129172714079,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004962826019444394,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.16822835057973862,
|
|
"num_tokens": 15237302.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.635433626174927,
|
|
"epoch": 0.665366473149492,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004962767422891099,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.16430780440568923,
|
|
"num_tokens": 15247064.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.672469520568848,
|
|
"epoch": 0.6658200290275762,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000496270878057721,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.16559139490127564,
|
|
"num_tokens": 15257006.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.680461406707764,
|
|
"epoch": 0.6662735849056604,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004962650092503939,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1673779770731926,
|
|
"num_tokens": 15266720.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.6296360969543455,
|
|
"epoch": 0.6667271407837445,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004962591358672502,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16174665689468384,
|
|
"num_tokens": 15277330.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.600244045257568,
|
|
"epoch": 0.6671806966618288,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496253257908411,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.16490522772073746,
|
|
"num_tokens": 15287401.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.532177495956421,
|
|
"epoch": 0.6676342525399129,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962473753739981,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.16928917169570923,
|
|
"num_tokens": 15297426.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.651616144180298,
|
|
"epoch": 0.6680878084179971,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000496241488264133,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.16742407381534577,
|
|
"num_tokens": 15308412.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.6203423023223875,
|
|
"epoch": 0.6685413642960812,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004962355965789377,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.16204553544521333,
|
|
"num_tokens": 15318821.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.587005376815796,
|
|
"epoch": 0.6689949201741655,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004962297003185338,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.1618948683142662,
|
|
"num_tokens": 15328737.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.670815324783325,
|
|
"epoch": 0.6694484760522497,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004962237994830433,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.1564209431409836,
|
|
"num_tokens": 15339695.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.707769441604614,
|
|
"epoch": 0.6699020319303338,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004962178940725883,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.16244056969881057,
|
|
"num_tokens": 15350270.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.664539051055908,
|
|
"epoch": 0.670355587808418,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004962119840872908,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.1645205706357956,
|
|
"num_tokens": 15360986.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.645076084136963,
|
|
"epoch": 0.6708091436865021,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004962060695272733,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.16415667831897734,
|
|
"num_tokens": 15371786.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.63773102760315,
|
|
"epoch": 0.6712626995645864,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004962001503926577,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16971592009067535,
|
|
"num_tokens": 15382960.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.576283693313599,
|
|
"epoch": 0.6717162554426706,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004961942266835667,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.1673077717423439,
|
|
"num_tokens": 15392807.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.650079441070557,
|
|
"epoch": 0.6721698113207547,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004961882984001227,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.1599237620830536,
|
|
"num_tokens": 15403712.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.676372385025024,
|
|
"epoch": 0.6726233671988389,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004961823655424484,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.16035202890634537,
|
|
"num_tokens": 15414839.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.642154216766357,
|
|
"epoch": 0.6730769230769231,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004961764281106664,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.1691312834620476,
|
|
"num_tokens": 15425320.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.652766180038452,
|
|
"epoch": 0.6735304789550073,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004961704861048995,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.16118890792131424,
|
|
"num_tokens": 15435476.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.64156289100647,
|
|
"epoch": 0.6739840348330914,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004961645395252705,
|
|
"loss": 5.5884,
|
|
"mean_token_accuracy": 0.16087498962879182,
|
|
"num_tokens": 15445786.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.700147104263306,
|
|
"epoch": 0.6744375907111756,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004961585883719025,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1652859181165695,
|
|
"num_tokens": 15455915.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.735110139846801,
|
|
"epoch": 0.6748911465892597,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004961526326449186,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.16309167593717575,
|
|
"num_tokens": 15466523.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.655019807815552,
|
|
"epoch": 0.675344702467344,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004961466723444419,
|
|
"loss": 5.5459,
|
|
"mean_token_accuracy": 0.16104988008737564,
|
|
"num_tokens": 15476821.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.603958559036255,
|
|
"epoch": 0.6757982583454282,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004961407074705955,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16059614568948746,
|
|
"num_tokens": 15487182.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.692904949188232,
|
|
"epoch": 0.6762518142235123,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004961347380235031,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.16992294639348984,
|
|
"num_tokens": 15497600.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.706664991378784,
|
|
"epoch": 0.6767053701015965,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004961287640032879,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15421608984470367,
|
|
"num_tokens": 15508278.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.7377471923828125,
|
|
"epoch": 0.6771589259796807,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004961227854100734,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15761489421129227,
|
|
"num_tokens": 15518458.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.603558444976807,
|
|
"epoch": 0.6776124818577649,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004961168022439835,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.16726915091276168,
|
|
"num_tokens": 15528738.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.601382780075073,
|
|
"epoch": 0.6780660377358491,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004961108145051417,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.16797880381345748,
|
|
"num_tokens": 15538656.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.526081609725952,
|
|
"epoch": 0.6785195936139332,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000496104822193672,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.16627522855997084,
|
|
"num_tokens": 15549285.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.69929609298706,
|
|
"epoch": 0.6789731494920174,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004960988253096982,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.17137698233127593,
|
|
"num_tokens": 15559766.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.658153438568116,
|
|
"epoch": 0.6794267053701016,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004960928238533443,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.1714092329144478,
|
|
"num_tokens": 15570873.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.671041440963745,
|
|
"epoch": 0.6798802612481858,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004960868178247344,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1592846006155014,
|
|
"num_tokens": 15581229.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.626502847671508,
|
|
"epoch": 0.68033381712627,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004960808072239929,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.15719763189554214,
|
|
"num_tokens": 15591686.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.696853733062744,
|
|
"epoch": 0.6807873730043541,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004960747920512439,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1583081491291523,
|
|
"num_tokens": 15601869.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.6992940425872805,
|
|
"epoch": 0.6812409288824384,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000496068772306612,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.1609680771827698,
|
|
"num_tokens": 15612946.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.662940216064453,
|
|
"epoch": 0.6816944847605225,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004960627479902214,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.15721766501665116,
|
|
"num_tokens": 15623761.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.627185249328614,
|
|
"epoch": 0.6821480406386067,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000496056719102197,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.15465673059225082,
|
|
"num_tokens": 15634500.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.67201452255249,
|
|
"epoch": 0.6826015965166908,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004960506856426631,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.16561726480722427,
|
|
"num_tokens": 15644896.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.644251871109009,
|
|
"epoch": 0.683055152394775,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004960446476117448,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.16353006064891815,
|
|
"num_tokens": 15655008.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.605746555328369,
|
|
"epoch": 0.6835087082728593,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004960386050095668,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.16005973517894745,
|
|
"num_tokens": 15665944.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.689500379562378,
|
|
"epoch": 0.6839622641509434,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004960325578362543,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.1629498139023781,
|
|
"num_tokens": 15677099.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.708564949035645,
|
|
"epoch": 0.6844158200290276,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000496026506091932,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.16468921154737473,
|
|
"num_tokens": 15687531.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.658125495910644,
|
|
"epoch": 0.6848693759071117,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004960204497767253,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.16106893569231034,
|
|
"num_tokens": 15697002.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.572294759750366,
|
|
"epoch": 0.685322931785196,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004960143888907594,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.16344174593687058,
|
|
"num_tokens": 15707249.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.641739702224731,
|
|
"epoch": 0.6857764876632801,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004960083234341595,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.16488028764724733,
|
|
"num_tokens": 15718764.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.649561786651612,
|
|
"epoch": 0.6862300435413643,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004960022534070513,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.17171214669942855,
|
|
"num_tokens": 15728854.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.563173294067383,
|
|
"epoch": 0.6866835994194485,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00049599617880956,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.16561209410429,
|
|
"num_tokens": 15739682.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.589160346984864,
|
|
"epoch": 0.6871371552975326,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004959900996418115,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.16965826749801635,
|
|
"num_tokens": 15749628.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.614845037460327,
|
|
"epoch": 0.6875907111756169,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004959840159039315,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.1624355211853981,
|
|
"num_tokens": 15760137.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.6442975997924805,
|
|
"epoch": 0.688044267053701,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004959779275960456,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.1618069216609001,
|
|
"num_tokens": 15769889.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.643933296203613,
|
|
"epoch": 0.6884978229317852,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00049597183471828,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.15737499594688414,
|
|
"num_tokens": 15780912.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.657950305938721,
|
|
"epoch": 0.6889513788098693,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004959657372707604,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.17339664250612258,
|
|
"num_tokens": 15791719.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.65258297920227,
|
|
"epoch": 0.6894049346879536,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004959596352536132,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.16826928555965423,
|
|
"num_tokens": 15802551.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.662902116775513,
|
|
"epoch": 0.6898584905660378,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004959535286669643,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.15824030786752702,
|
|
"num_tokens": 15813551.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.67209939956665,
|
|
"epoch": 0.6903120464441219,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004959474175109402,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.16531185656785966,
|
|
"num_tokens": 15824262.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.7075118064880375,
|
|
"epoch": 0.6907656023222061,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004959413017856672,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16659896671772004,
|
|
"num_tokens": 15835493.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.561695861816406,
|
|
"epoch": 0.6912191582002902,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004959351814912716,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.16452614217996597,
|
|
"num_tokens": 15846224.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.615854978561401,
|
|
"epoch": 0.6916727140783745,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004959290566278803,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.1664932370185852,
|
|
"num_tokens": 15855622.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.7003296375274655,
|
|
"epoch": 0.6921262699564587,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004959229271956199,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.16689909547567366,
|
|
"num_tokens": 15865835.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.669817972183227,
|
|
"epoch": 0.6925798258345428,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004959167931946169,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.16737326830625535,
|
|
"num_tokens": 15875915.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.633016347885132,
|
|
"epoch": 0.693033381712627,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004959106546249984,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.16724033057689666,
|
|
"num_tokens": 15887111.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.636037111282349,
|
|
"epoch": 0.6934869375907112,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959045114868913,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.15588464289903642,
|
|
"num_tokens": 15899528.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.619613742828369,
|
|
"epoch": 0.6939404934687954,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004958983637804225,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.17082595229148864,
|
|
"num_tokens": 15910881.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.7317766666412355,
|
|
"epoch": 0.6943940493468795,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004958922115057194,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16362126916646957,
|
|
"num_tokens": 15921189.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.708053493499756,
|
|
"epoch": 0.6948476052249637,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004958860546629089,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.17005573958158493,
|
|
"num_tokens": 15931276.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.700485134124756,
|
|
"epoch": 0.6953011611030478,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004958798932521186,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.15413284301757812,
|
|
"num_tokens": 15941506.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.591758680343628,
|
|
"epoch": 0.6957547169811321,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004958737272734759,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.16640574038028716,
|
|
"num_tokens": 15951158.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.682381105422974,
|
|
"epoch": 0.6962082728592163,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004958675567271081,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.16660627275705336,
|
|
"num_tokens": 15960852.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.649328660964966,
|
|
"epoch": 0.6966618287373004,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000495861381613143,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.1625627711415291,
|
|
"num_tokens": 15971291.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.6603899002075195,
|
|
"epoch": 0.6971153846153846,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004958552019317082,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.16272665113210677,
|
|
"num_tokens": 15982180.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.628291273117066,
|
|
"epoch": 0.6975689404934688,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004958490176829316,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.16861288696527482,
|
|
"num_tokens": 15992363.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.6698826313018795,
|
|
"epoch": 0.698022496371553,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000495842828866941,
|
|
"loss": 5.5444,
|
|
"mean_token_accuracy": 0.16244934797286986,
|
|
"num_tokens": 16003477.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.652411031723022,
|
|
"epoch": 0.6984760522496372,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004958366354838645,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.16245862245559692,
|
|
"num_tokens": 16013747.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.642243480682373,
|
|
"epoch": 0.6989296081277213,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00049583043753383,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.16651039719581603,
|
|
"num_tokens": 16025662.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.605423450469971,
|
|
"epoch": 0.6993831640058055,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004958242350169658,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.16867056488990784,
|
|
"num_tokens": 16037315.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.584050416946411,
|
|
"epoch": 0.6998367198838897,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004958180279334001,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.16454358100891114,
|
|
"num_tokens": 16047297.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.66097617149353,
|
|
"epoch": 0.7002902757619739,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004958118162832614,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.16869923025369643,
|
|
"num_tokens": 16057573.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.605273962020874,
|
|
"epoch": 0.700743831640058,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004958056000666781,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.15875106006860734,
|
|
"num_tokens": 16067926.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.6579488754272464,
|
|
"epoch": 0.7011973875181422,
|
|
"grad_norm": 4.46875,
|
|
"learning_rate": 0.0004957993792837786,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16394148617982865,
|
|
"num_tokens": 16077938.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.610279369354248,
|
|
"epoch": 0.7016509433962265,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004957931539346917,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1661431223154068,
|
|
"num_tokens": 16088163.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.670271682739258,
|
|
"epoch": 0.7021044992743106,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004957869240195462,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.15643369257450104,
|
|
"num_tokens": 16100640.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.63419885635376,
|
|
"epoch": 0.7025580551523948,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004957806895384707,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.16354862451553345,
|
|
"num_tokens": 16111018.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.5481712341308596,
|
|
"epoch": 0.7030116110304789,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004957744504915944,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.1648949444293976,
|
|
"num_tokens": 16120873.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.671518754959107,
|
|
"epoch": 0.7034651669085631,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004957682068790463,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.1649119570851326,
|
|
"num_tokens": 16131178.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.646680402755737,
|
|
"epoch": 0.7039187227866474,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004957619587009553,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.16286496371030806,
|
|
"num_tokens": 16141156.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.633469486236573,
|
|
"epoch": 0.7043722786647315,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004957557059574507,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.15549362897872926,
|
|
"num_tokens": 16150077.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.645452451705933,
|
|
"epoch": 0.7048258345428157,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004957494486486618,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.16329682469367982,
|
|
"num_tokens": 16160514.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.671679973602295,
|
|
"epoch": 0.7052793904208998,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004957431867747182,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16956402212381363,
|
|
"num_tokens": 16170811.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.577692174911499,
|
|
"epoch": 0.7057329462989841,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004957369203357492,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.16849376410245895,
|
|
"num_tokens": 16181553.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.606373643875122,
|
|
"epoch": 0.7061865021770682,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004957306493318844,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17001904994249345,
|
|
"num_tokens": 16191308.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.617648077011109,
|
|
"epoch": 0.7066400580551524,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004957243737632535,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.17012592554092407,
|
|
"num_tokens": 16201311.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.680548620223999,
|
|
"epoch": 0.7070936139332366,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004957180936299863,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.1714714452624321,
|
|
"num_tokens": 16211105.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.652728271484375,
|
|
"epoch": 0.7075471698113207,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004957118089322127,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.16141459792852403,
|
|
"num_tokens": 16220836.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.632328701019287,
|
|
"epoch": 0.708000725689405,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004957055196700628,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.170921191573143,
|
|
"num_tokens": 16231630.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.648638772964477,
|
|
"epoch": 0.7084542815674891,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004956992258436663,
|
|
"loss": 5.521,
|
|
"mean_token_accuracy": 0.16436462551355363,
|
|
"num_tokens": 16242272.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.563827037811279,
|
|
"epoch": 0.7089078374455733,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004956929274531536,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.16884785741567612,
|
|
"num_tokens": 16252555.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.5962522506713865,
|
|
"epoch": 0.7093613933236574,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000495686624498655,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.16552574336528778,
|
|
"num_tokens": 16261964.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.690983247756958,
|
|
"epoch": 0.7098149492017417,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004956803169803007,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.1607639327645302,
|
|
"num_tokens": 16274543.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.619023227691651,
|
|
"epoch": 0.7102685050798259,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004956740048982212,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.16002560406923294,
|
|
"num_tokens": 16285124.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.624927282333374,
|
|
"epoch": 0.71072206095791,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004956676882525472,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.1634851261973381,
|
|
"num_tokens": 16295727.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.696490097045898,
|
|
"epoch": 0.7111756168359942,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000495661367043409,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.17260087430477142,
|
|
"num_tokens": 16305496.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.607415437698364,
|
|
"epoch": 0.7116291727140783,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004956550412709376,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.16924340277910233,
|
|
"num_tokens": 16315112.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.623329830169678,
|
|
"epoch": 0.7120827285921626,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004956487109352637,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17477993816137313,
|
|
"num_tokens": 16325613.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.665192794799805,
|
|
"epoch": 0.7125362844702468,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004956423760365181,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16873666346073152,
|
|
"num_tokens": 16335317.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.609439182281494,
|
|
"epoch": 0.7129898403483309,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004956360365748321,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.15723467022180557,
|
|
"num_tokens": 16345003.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.658202457427978,
|
|
"epoch": 0.7134433962264151,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004956296925503367,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.1622123345732689,
|
|
"num_tokens": 16356108.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.6005700588226315,
|
|
"epoch": 0.7138969521044993,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004956233439631628,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.16724979281425476,
|
|
"num_tokens": 16364733.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.619435358047485,
|
|
"epoch": 0.7143505079825835,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004956169908134421,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.16559068113565445,
|
|
"num_tokens": 16375229.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.59596996307373,
|
|
"epoch": 0.7148040638606676,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004956106331013057,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.1656107187271118,
|
|
"num_tokens": 16386366.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.6192371368408205,
|
|
"epoch": 0.7152576197387518,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004956042708268853,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.16840773224830627,
|
|
"num_tokens": 16397067.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.605705690383911,
|
|
"epoch": 0.715711175616836,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004955979039903123,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.1653614744544029,
|
|
"num_tokens": 16407256.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.532815551757812,
|
|
"epoch": 0.7161647314949202,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004955915325917183,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.16202937364578246,
|
|
"num_tokens": 16418701.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.560326719284058,
|
|
"epoch": 0.7166182873730044,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004955851566312354,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.1720588907599449,
|
|
"num_tokens": 16428019.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.603496789932251,
|
|
"epoch": 0.7170718432510885,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004955787761089952,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1611000120639801,
|
|
"num_tokens": 16440122.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.698283433914185,
|
|
"epoch": 0.7175253991291727,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004955723910251296,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.1604372724890709,
|
|
"num_tokens": 16449801.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.602445983886719,
|
|
"epoch": 0.717978955007257,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004955660013797709,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.16884026378393174,
|
|
"num_tokens": 16460155.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.65273084640503,
|
|
"epoch": 0.7184325108853411,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000495559607173051,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.15278467386960984,
|
|
"num_tokens": 16470656.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.678693532943726,
|
|
"epoch": 0.7188860667634253,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004955532084051022,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.16545139700174333,
|
|
"num_tokens": 16481449.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.689681911468506,
|
|
"epoch": 0.7193396226415094,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004955468050760568,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.1603458657860756,
|
|
"num_tokens": 16492032.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.605563116073609,
|
|
"epoch": 0.7197931785195936,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004955403971860474,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.16635042279958726,
|
|
"num_tokens": 16502221.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.575072383880615,
|
|
"epoch": 0.7202467343976778,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004955339847352063,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.1656094402074814,
|
|
"num_tokens": 16512021.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.602277755737305,
|
|
"epoch": 0.720700290275762,
|
|
"grad_norm": 7.3125,
|
|
"learning_rate": 0.0004955275677236662,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.16556978672742845,
|
|
"num_tokens": 16522060.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.636832046508789,
|
|
"epoch": 0.7211538461538461,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 0.0004955211461515599,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.16849270910024644,
|
|
"num_tokens": 16532827.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.637872695922852,
|
|
"epoch": 0.7216074020319303,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00049551472001902,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.1674077406525612,
|
|
"num_tokens": 16542838.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.592290878295898,
|
|
"epoch": 0.7220609579100146,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004955082893261796,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.17216830253601073,
|
|
"num_tokens": 16552615.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.716319561004639,
|
|
"epoch": 0.7225145137880987,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004955018540731714,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.15874373018741608,
|
|
"num_tokens": 16561777.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.671530818939209,
|
|
"epoch": 0.7229680696661829,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004954954142601288,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.16330315917730331,
|
|
"num_tokens": 16572111.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.677050161361694,
|
|
"epoch": 0.723421625544267,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004954889698871849,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.16566748470067977,
|
|
"num_tokens": 16581674.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.697398138046265,
|
|
"epoch": 0.7238751814223512,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954825209544728,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17010942101478577,
|
|
"num_tokens": 16591802.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.579377937316894,
|
|
"epoch": 0.7243287373004355,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000495476067462126,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.17563054859638214,
|
|
"num_tokens": 16602772.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.614494657516479,
|
|
"epoch": 0.7247822931785196,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000495469609410278,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.16485417038202285,
|
|
"num_tokens": 16613526.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.538692665100098,
|
|
"epoch": 0.7252358490566038,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004954631467990622,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.16715267151594163,
|
|
"num_tokens": 16623583.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.623130130767822,
|
|
"epoch": 0.7256894049346879,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004954566796286124,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.1612747296690941,
|
|
"num_tokens": 16635068.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.659089231491089,
|
|
"epoch": 0.7261429608127722,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004954502078990623,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.16616036742925644,
|
|
"num_tokens": 16645021.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.618288230895996,
|
|
"epoch": 0.7265965166908563,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954437316105457,
|
|
"loss": 5.5206,
|
|
"mean_token_accuracy": 0.16156897693872452,
|
|
"num_tokens": 16656021.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.596080017089844,
|
|
"epoch": 0.7270500725689405,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004954372507631965,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17329126596450806,
|
|
"num_tokens": 16665236.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.621707201004028,
|
|
"epoch": 0.7275036284470247,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004954307653571489,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.15767206251621246,
|
|
"num_tokens": 16676690.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.598207330703735,
|
|
"epoch": 0.7279571843251088,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004954242753925367,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.16131179332733153,
|
|
"num_tokens": 16687288.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.669662570953369,
|
|
"epoch": 0.7284107402031931,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004954177808694946,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.15983750075101852,
|
|
"num_tokens": 16697873.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.608494615554809,
|
|
"epoch": 0.7288642960812772,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004954112817881565,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.16026637256145476,
|
|
"num_tokens": 16709002.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.5762261867523195,
|
|
"epoch": 0.7293178519593614,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004954047781486568,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16284284740686417,
|
|
"num_tokens": 16718989.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.748119974136353,
|
|
"epoch": 0.7297714078374455,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953982699511303,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16285916417837143,
|
|
"num_tokens": 16730425.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.667424249649048,
|
|
"epoch": 0.7302249637155298,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004953917571957114,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.16531988382339477,
|
|
"num_tokens": 16740216.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.566254091262818,
|
|
"epoch": 0.730678519593614,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004953852398825346,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.16659636050462723,
|
|
"num_tokens": 16752436.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.577506065368652,
|
|
"epoch": 0.7311320754716981,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000495378718011735,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.1658300280570984,
|
|
"num_tokens": 16762631.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.710255908966064,
|
|
"epoch": 0.7315856313497823,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953721915834473,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.16436021476984025,
|
|
"num_tokens": 16772613.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.665786218643189,
|
|
"epoch": 0.7320391872278664,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004953656605978067,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.1608337089419365,
|
|
"num_tokens": 16782963.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.600820016860962,
|
|
"epoch": 0.7324927431059507,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000495359125054948,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.16788298934698104,
|
|
"num_tokens": 16793892.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.526678943634034,
|
|
"epoch": 0.7329462989840348,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004953525849550063,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16043167561292648,
|
|
"num_tokens": 16803388.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.590819931030273,
|
|
"epoch": 0.733399854862119,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004953460402981172,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.17100578546524048,
|
|
"num_tokens": 16813201.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.688029956817627,
|
|
"epoch": 0.7338534107402032,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004953394910844157,
|
|
"loss": 5.6513,
|
|
"mean_token_accuracy": 0.1624013900756836,
|
|
"num_tokens": 16823265.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.64172945022583,
|
|
"epoch": 0.7343069666182874,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004953329373140374,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.16412428468465806,
|
|
"num_tokens": 16833057.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.550912380218506,
|
|
"epoch": 0.7347605224963716,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953263789871179,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.16362497657537461,
|
|
"num_tokens": 16843488.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.552389669418335,
|
|
"epoch": 0.7352140783744557,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004953198161037925,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.17534587383270264,
|
|
"num_tokens": 16852448.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.507678890228272,
|
|
"epoch": 0.7356676342525399,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004953132486641975,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.16817467659711838,
|
|
"num_tokens": 16863944.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.596392822265625,
|
|
"epoch": 0.736121190130624,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000495306676668468,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.1675754576921463,
|
|
"num_tokens": 16873923.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.61533260345459,
|
|
"epoch": 0.7365747460087083,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004953001001167406,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.16641771644353867,
|
|
"num_tokens": 16884373.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.675483465194702,
|
|
"epoch": 0.7370283018867925,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004952935190091508,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.16353694051504136,
|
|
"num_tokens": 16895869.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.536702632904053,
|
|
"epoch": 0.7374818577648766,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004952869333458349,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.16639091521501542,
|
|
"num_tokens": 16906737.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.584896087646484,
|
|
"epoch": 0.7379354136429608,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004952803431269292,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.17622085362672807,
|
|
"num_tokens": 16916083.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.665721368789673,
|
|
"epoch": 0.738388969521045,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952737483525699,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.16562667936086656,
|
|
"num_tokens": 16926419.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.680433750152588,
|
|
"epoch": 0.7388425253991292,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004952671490228932,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.16464401185512542,
|
|
"num_tokens": 16936067.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.651733016967773,
|
|
"epoch": 0.7392960812772134,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004952605451380357,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.1683550000190735,
|
|
"num_tokens": 16946571.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.558815574645996,
|
|
"epoch": 0.7397496371552975,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004952539366981342,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.16246189475059508,
|
|
"num_tokens": 16956764.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.61862416267395,
|
|
"epoch": 0.7402031930333817,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000495247323703325,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.17167850583791733,
|
|
"num_tokens": 16966002.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.65856704711914,
|
|
"epoch": 0.7406567489114659,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000495240706153745,
|
|
"loss": 5.5475,
|
|
"mean_token_accuracy": 0.165491583943367,
|
|
"num_tokens": 16975705.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.617011165618896,
|
|
"epoch": 0.7411103047895501,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004952340840495312,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.16945848613977432,
|
|
"num_tokens": 16985945.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.5943726062774655,
|
|
"epoch": 0.7415638606676342,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004952274573908203,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.16729725301265716,
|
|
"num_tokens": 16995475.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.578772687911988,
|
|
"epoch": 0.7420174165457184,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004952208261777496,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.1648031771183014,
|
|
"num_tokens": 17005028.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.645346689224243,
|
|
"epoch": 0.7424709724238027,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000495214190410456,
|
|
"loss": 5.5031,
|
|
"mean_token_accuracy": 0.16819154769182204,
|
|
"num_tokens": 17014786.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.651758861541748,
|
|
"epoch": 0.7429245283018868,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004952075500890768,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.16572055369615554,
|
|
"num_tokens": 17024431.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.568734359741211,
|
|
"epoch": 0.743378084179971,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004952009052137493,
|
|
"loss": 5.4671,
|
|
"mean_token_accuracy": 0.1714123785495758,
|
|
"num_tokens": 17034368.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.56487398147583,
|
|
"epoch": 0.7438316400580551,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004951942557846112,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.16194852590560913,
|
|
"num_tokens": 17043818.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.666324090957642,
|
|
"epoch": 0.7442851959361393,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004951876018017997,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.16839117258787156,
|
|
"num_tokens": 17054843.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.672155237197876,
|
|
"epoch": 0.7447387518142236,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004951809432654524,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.1668528288602829,
|
|
"num_tokens": 17065539.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.580246162414551,
|
|
"epoch": 0.7451923076923077,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000495174280175707,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.16898000985383987,
|
|
"num_tokens": 17075443.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.681068229675293,
|
|
"epoch": 0.7456458635703919,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004951676125327015,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.16850530058145524,
|
|
"num_tokens": 17085490.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.652074337005615,
|
|
"epoch": 0.746099419448476,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004951609403365737,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.17004851400852203,
|
|
"num_tokens": 17094803.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.583604717254639,
|
|
"epoch": 0.7465529753265603,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004951542635874615,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.16981043070554733,
|
|
"num_tokens": 17104373.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.644840860366822,
|
|
"epoch": 0.7470065312046444,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004951475822855029,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.16572268605232238,
|
|
"num_tokens": 17115469.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.609163236618042,
|
|
"epoch": 0.7474600870827286,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004951408964308364,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16574133783578873,
|
|
"num_tokens": 17125443.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.555290651321411,
|
|
"epoch": 0.7479136429608128,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004951342060236,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.1661999449133873,
|
|
"num_tokens": 17136253.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.700448513031006,
|
|
"epoch": 0.7483671988388969,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004951275110639321,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.16710744500160218,
|
|
"num_tokens": 17145544.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.659205961227417,
|
|
"epoch": 0.7488207547169812,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004951208115519712,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.1646759882569313,
|
|
"num_tokens": 17155043.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.596213150024414,
|
|
"epoch": 0.7492743105950653,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004951141074878558,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.1620617538690567,
|
|
"num_tokens": 17164885.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.673506355285644,
|
|
"epoch": 0.7497278664731495,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004951073988717246,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.16366185396909713,
|
|
"num_tokens": 17175681.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.618485164642334,
|
|
"epoch": 0.7501814223512336,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004951006857037163,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16720621883869172,
|
|
"num_tokens": 17186002.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.59273247718811,
|
|
"epoch": 0.7506349782293179,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004950939679839696,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.17087941765785217,
|
|
"num_tokens": 17195499.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.597292947769165,
|
|
"epoch": 0.7510885341074021,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004950872457126237,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.16754258424043655,
|
|
"num_tokens": 17204684.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.606363010406494,
|
|
"epoch": 0.7515420899854862,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004950805188898175,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.16287693679332732,
|
|
"num_tokens": 17213987.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.635597372055054,
|
|
"epoch": 0.7519956458635704,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00049507378751569,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.1621052622795105,
|
|
"num_tokens": 17224512.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.718463325500489,
|
|
"epoch": 0.7524492017416545,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004950670515903805,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16537761837244033,
|
|
"num_tokens": 17234362.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.61590986251831,
|
|
"epoch": 0.7529027576197388,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950603111140283,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.16930110305547713,
|
|
"num_tokens": 17244241.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.533387899398804,
|
|
"epoch": 0.753356313497823,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004950535660867728,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.17571018189191817,
|
|
"num_tokens": 17254689.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.653801774978637,
|
|
"epoch": 0.7538098693759071,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004950468165087535,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1659944862127304,
|
|
"num_tokens": 17265506.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.675744581222534,
|
|
"epoch": 0.7542634252539913,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004950400623801098,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1633657842874527,
|
|
"num_tokens": 17276376.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.673819494247437,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004950333037009818,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.1547602504491806,
|
|
"num_tokens": 17287005.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.646138334274292,
|
|
"epoch": 0.7551705370101597,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004950265404715089,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.16027978658676148,
|
|
"num_tokens": 17297595.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.5359149932861325,
|
|
"epoch": 0.7556240928882438,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000495019772691831,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.16829735040664673,
|
|
"num_tokens": 17307319.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.618014287948609,
|
|
"epoch": 0.756077648766328,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004950130003620882,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16626063138246536,
|
|
"num_tokens": 17317978.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.620723533630371,
|
|
"epoch": 0.7565312046444121,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004950062234824204,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16590883433818818,
|
|
"num_tokens": 17328339.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.63666729927063,
|
|
"epoch": 0.7569847605224964,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004949994420529679,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.16365355849266053,
|
|
"num_tokens": 17338668.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.61228494644165,
|
|
"epoch": 0.7574383164005806,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004949926560738709,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.16132984161376954,
|
|
"num_tokens": 17348609.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.669183969497681,
|
|
"epoch": 0.7578918722786647,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004949858655452697,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.16427465975284578,
|
|
"num_tokens": 17358014.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.620366477966309,
|
|
"epoch": 0.7583454281567489,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004949790704673048,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16788626164197923,
|
|
"num_tokens": 17367975.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.630387926101685,
|
|
"epoch": 0.7587989840348331,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004949722708401166,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.16372619867324828,
|
|
"num_tokens": 17377960.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.629988765716552,
|
|
"epoch": 0.7592525399129173,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004949654666638457,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16987081617116928,
|
|
"num_tokens": 17387334.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.618249797821045,
|
|
"epoch": 0.7597060957910015,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000494958657938633,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16165588349103927,
|
|
"num_tokens": 17396521.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.584721469879151,
|
|
"epoch": 0.7601596516690856,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004949518446646192,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.16930657476186753,
|
|
"num_tokens": 17407217.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.659988975524902,
|
|
"epoch": 0.7606132075471698,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004949450268419451,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.1590219631791115,
|
|
"num_tokens": 17416982.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.568830490112305,
|
|
"epoch": 0.761066763425254,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000494938204470752,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16622348129749298,
|
|
"num_tokens": 17427636.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.612373018264771,
|
|
"epoch": 0.7615203193033382,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004949313775511806,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.1630595237016678,
|
|
"num_tokens": 17437488.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.589271116256714,
|
|
"epoch": 0.7619738751814223,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004949245460833723,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.17178670167922974,
|
|
"num_tokens": 17447838.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.6152825355529785,
|
|
"epoch": 0.7624274310595065,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004949177100674684,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.16557554602622987,
|
|
"num_tokens": 17457257.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.63554835319519,
|
|
"epoch": 0.7628809869375908,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004949108695036102,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.1702419102191925,
|
|
"num_tokens": 17467729.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.643184089660645,
|
|
"epoch": 0.7633345428156749,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004949040243919392,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.15880836993455888,
|
|
"num_tokens": 17477692.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.608482503890992,
|
|
"epoch": 0.7637880986937591,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004948971747325968,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.16530852615833283,
|
|
"num_tokens": 17488730.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.662958192825317,
|
|
"epoch": 0.7642416545718432,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000494890320525725,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.16616504043340682,
|
|
"num_tokens": 17498374.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.644989442825318,
|
|
"epoch": 0.7646952104499274,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004948834617714652,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.17348451167345047,
|
|
"num_tokens": 17508601.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.626499938964844,
|
|
"epoch": 0.7651487663280117,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004948765984699595,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.1681686297059059,
|
|
"num_tokens": 17518164.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.593100833892822,
|
|
"epoch": 0.7656023222060958,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004948697306213494,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.17205666303634642,
|
|
"num_tokens": 17527244.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.661113691329956,
|
|
"epoch": 0.76605587808418,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004948628582257775,
|
|
"loss": 5.5026,
|
|
"mean_token_accuracy": 0.16697869300842286,
|
|
"num_tokens": 17538045.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.594349479675293,
|
|
"epoch": 0.7665094339622641,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004948559812833857,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.16509982347488403,
|
|
"num_tokens": 17547584.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.607390213012695,
|
|
"epoch": 0.7669629898403484,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004948490997943162,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16601382941007614,
|
|
"num_tokens": 17558925.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.617490577697754,
|
|
"epoch": 0.7674165457184325,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004948422137587111,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.15748300403356552,
|
|
"num_tokens": 17569355.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.650879049301148,
|
|
"epoch": 0.7678701015965167,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004948353231767131,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.16597110778093338,
|
|
"num_tokens": 17579782.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.610150527954102,
|
|
"epoch": 0.7683236574746009,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004948284280484645,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.1709799662232399,
|
|
"num_tokens": 17589772.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.549994325637817,
|
|
"epoch": 0.768777213352685,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004948215283741081,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.16429323256015776,
|
|
"num_tokens": 17599613.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.6233827590942385,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004948146241537866,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.16073604077100753,
|
|
"num_tokens": 17609056.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.569718742370606,
|
|
"epoch": 0.7696843251088534,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004948077153876425,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.16776058673858643,
|
|
"num_tokens": 17618620.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.547171401977539,
|
|
"epoch": 0.7701378809869376,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004948008020758188,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.1737499088048935,
|
|
"num_tokens": 17627630.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.569094276428222,
|
|
"epoch": 0.7705914368650217,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004947938842184585,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.16861821115016937,
|
|
"num_tokens": 17638903.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.597677564620971,
|
|
"epoch": 0.771044992743106,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004947869618157048,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.1655205011367798,
|
|
"num_tokens": 17649257.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.566603136062622,
|
|
"epoch": 0.7714985486211902,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004947800348677006,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.1743499293923378,
|
|
"num_tokens": 17659495.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.5201982975006105,
|
|
"epoch": 0.7719521044992743,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004947731033745893,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.1677752047777176,
|
|
"num_tokens": 17669671.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.661861324310303,
|
|
"epoch": 0.7724056603773585,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004947661673365142,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15949635207653046,
|
|
"num_tokens": 17680927.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.592693090438843,
|
|
"epoch": 0.7728592162554426,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004947592267536188,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.169338421523571,
|
|
"num_tokens": 17691378.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.6139641284942625,
|
|
"epoch": 0.7733127721335269,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004947522816260466,
|
|
"loss": 5.5283,
|
|
"mean_token_accuracy": 0.16320052444934846,
|
|
"num_tokens": 17700942.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.638260126113892,
|
|
"epoch": 0.773766328011611,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004947453319539411,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.1692434623837471,
|
|
"num_tokens": 17710076.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.60617470741272,
|
|
"epoch": 0.7742198838896952,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004947383777374462,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.16550959944725036,
|
|
"num_tokens": 17721009.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.536574983596802,
|
|
"epoch": 0.7746734397677794,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004947314189767058,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.16459177136421205,
|
|
"num_tokens": 17731821.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.5489661693573,
|
|
"epoch": 0.7751269956458636,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004947244556718635,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.17378001660108566,
|
|
"num_tokens": 17741425.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.602510833740235,
|
|
"epoch": 0.7755805515239478,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004947174878230635,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17464102655649186,
|
|
"num_tokens": 17752381.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.51142692565918,
|
|
"epoch": 0.7760341074020319,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004947105154304498,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.16561309546232222,
|
|
"num_tokens": 17762768.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.576867341995239,
|
|
"epoch": 0.7764876632801161,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004947035384941667,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.16490090787410736,
|
|
"num_tokens": 17774032.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.681223964691162,
|
|
"epoch": 0.7769412191582002,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004946965570143584,
|
|
"loss": 5.5794,
|
|
"mean_token_accuracy": 0.1618152603507042,
|
|
"num_tokens": 17785098.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.647640323638916,
|
|
"epoch": 0.7773947750362845,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004946895709911695,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.16696828752756118,
|
|
"num_tokens": 17795487.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.615338945388794,
|
|
"epoch": 0.7778483309143687,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004946825804247442,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.15942772179841996,
|
|
"num_tokens": 17806045.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.659988880157471,
|
|
"epoch": 0.7783018867924528,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000494675585315227,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.1624840170145035,
|
|
"num_tokens": 17816948.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.621607828140259,
|
|
"epoch": 0.778755442670537,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004946685856627628,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16741457730531692,
|
|
"num_tokens": 17826929.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.656989812850952,
|
|
"epoch": 0.7792089985486212,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004946615814674963,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.16943255215883254,
|
|
"num_tokens": 17837780.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.49801287651062,
|
|
"epoch": 0.7796625544267054,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946545727295724,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1726154550909996,
|
|
"num_tokens": 17847835.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.560629606246948,
|
|
"epoch": 0.7801161103047896,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004946475594491359,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.1720295011997223,
|
|
"num_tokens": 17858324.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.627698230743408,
|
|
"epoch": 0.7805696661828737,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004946405416263319,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.16047568321228028,
|
|
"num_tokens": 17868455.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.667699670791626,
|
|
"epoch": 0.7810232220609579,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004946335192613054,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.16973807662725449,
|
|
"num_tokens": 17879038.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.498501920700074,
|
|
"epoch": 0.7814767779390421,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004946264923542019,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.17062352299690248,
|
|
"num_tokens": 17888153.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.567123794555664,
|
|
"epoch": 0.7819303338171263,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004946194609051664,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.17214930728077887,
|
|
"num_tokens": 17898289.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.640062475204468,
|
|
"epoch": 0.7823838896952104,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004946124249143447,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.16954964846372605,
|
|
"num_tokens": 17909192.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.533799076080323,
|
|
"epoch": 0.7828374455732946,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000494605384381882,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.1630323737859726,
|
|
"num_tokens": 17918937.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.554599857330322,
|
|
"epoch": 0.7832910014513788,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004945983393079239,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.17361268699169158,
|
|
"num_tokens": 17929346.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.599385929107666,
|
|
"epoch": 0.783744557329463,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004945912896926163,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.16786740422248841,
|
|
"num_tokens": 17939479.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.6467255592346195,
|
|
"epoch": 0.7841981132075472,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004945842355361049,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.16834045499563216,
|
|
"num_tokens": 17949841.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.562479829788208,
|
|
"epoch": 0.7846516690856313,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004945771768385355,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.168412184715271,
|
|
"num_tokens": 17960334.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.593608140945435,
|
|
"epoch": 0.7851052249637155,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000494570113600054,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.1693262502551079,
|
|
"num_tokens": 17970595.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.642229700088501,
|
|
"epoch": 0.7855587808417998,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004945630458208068,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.15822365134954453,
|
|
"num_tokens": 17981301.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.552031660079956,
|
|
"epoch": 0.7860123367198839,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004945559735009397,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.17165354639291763,
|
|
"num_tokens": 17991262.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.594365787506104,
|
|
"epoch": 0.7864658925979681,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004945488966405993,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.17020548284053802,
|
|
"num_tokens": 18001212.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.615402460098267,
|
|
"epoch": 0.7869194484760522,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004945418152399317,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.17426688373088836,
|
|
"num_tokens": 18010432.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.61946291923523,
|
|
"epoch": 0.7873730043541364,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004945347292990833,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.16698182374238968,
|
|
"num_tokens": 18020902.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.618869018554688,
|
|
"epoch": 0.7878265602322206,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004945276388182008,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.16942863166332245,
|
|
"num_tokens": 18031133.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.64780101776123,
|
|
"epoch": 0.7882801161103048,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004945205437974309,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17045676559209824,
|
|
"num_tokens": 18042050.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.468453788757325,
|
|
"epoch": 0.788733671988389,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004945134442369201,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.17557145655155182,
|
|
"num_tokens": 18051642.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.660046672821045,
|
|
"epoch": 0.7891872278664731,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004945063401368154,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.15648096203804016,
|
|
"num_tokens": 18062180.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.644154119491577,
|
|
"epoch": 0.7896407837445574,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004944992314972637,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.16445865631103515,
|
|
"num_tokens": 18072302.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.597486782073974,
|
|
"epoch": 0.7900943396226415,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004944921183184118,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.1722353458404541,
|
|
"num_tokens": 18081824.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.574193096160888,
|
|
"epoch": 0.7905478955007257,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000494485000600407,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.17043693363666534,
|
|
"num_tokens": 18092696.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.570696210861206,
|
|
"epoch": 0.7910014513788098,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004944778783433965,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.17257224768400192,
|
|
"num_tokens": 18101790.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.677782106399536,
|
|
"epoch": 0.791455007256894,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004944707515475276,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.16561739444732665,
|
|
"num_tokens": 18111572.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.673485660552979,
|
|
"epoch": 0.7919085631349783,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004944636202129475,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.17471941858530043,
|
|
"num_tokens": 18120650.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.583009815216064,
|
|
"epoch": 0.7923621190130624,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004944564843398039,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.1823519989848137,
|
|
"num_tokens": 18131055.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.659669351577759,
|
|
"epoch": 0.7928156748911466,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004944493439282443,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.1695306792855263,
|
|
"num_tokens": 18141423.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.525578498840332,
|
|
"epoch": 0.7932692307692307,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004944421989784162,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17386405616998674,
|
|
"num_tokens": 18152015.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.573276948928833,
|
|
"epoch": 0.793722786647315,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004944350494904676,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.16456999033689498,
|
|
"num_tokens": 18161934.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.623917818069458,
|
|
"epoch": 0.7941763425253991,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004944278954645463,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.17385263442993165,
|
|
"num_tokens": 18172287.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.685469770431519,
|
|
"epoch": 0.7946298984034833,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004944207369008002,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.17678707838058472,
|
|
"num_tokens": 18181015.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.643927192687988,
|
|
"epoch": 0.7950834542815675,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004944135737993773,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.1640169993042946,
|
|
"num_tokens": 18192382.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.567079830169678,
|
|
"epoch": 0.7955370101596516,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004944064061604258,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.17833883166313172,
|
|
"num_tokens": 18202597.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.666832399368286,
|
|
"epoch": 0.7959905660377359,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004943992339840939,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.16130754947662354,
|
|
"num_tokens": 18213756.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.580977487564087,
|
|
"epoch": 0.79644412191582,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00049439205727053,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.1659858763217926,
|
|
"num_tokens": 18223669.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.619691276550293,
|
|
"epoch": 0.7968976777939042,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004943848760198823,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.1736903518438339,
|
|
"num_tokens": 18234884.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.579283094406128,
|
|
"epoch": 0.7973512336719883,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004943776902322995,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.16901502311229705,
|
|
"num_tokens": 18245155.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.499757480621338,
|
|
"epoch": 0.7978047895500726,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004943704999079302,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.17517054378986358,
|
|
"num_tokens": 18254686.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.565064907073975,
|
|
"epoch": 0.7982583454281568,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004943633050469231,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.17353624999523162,
|
|
"num_tokens": 18265473.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.671705102920532,
|
|
"epoch": 0.7987119013062409,
|
|
"grad_norm": 7.375,
|
|
"learning_rate": 0.0004943561056494269,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.16333960890769958,
|
|
"num_tokens": 18276024.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.6350846767425535,
|
|
"epoch": 0.7991654571843251,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004943489017155906,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.15510011464357376,
|
|
"num_tokens": 18287261.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.618888854980469,
|
|
"epoch": 0.7996190130624092,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004943416932455631,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.16325552016496658,
|
|
"num_tokens": 18299374.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.56708722114563,
|
|
"epoch": 0.8000725689404935,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004943344802394935,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.16325221210718155,
|
|
"num_tokens": 18309344.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.679027700424195,
|
|
"epoch": 0.8005261248185777,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004943272626975309,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.16476835906505585,
|
|
"num_tokens": 18319778.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.721097755432129,
|
|
"epoch": 0.8009796806966618,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004943200406198246,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.1666264146566391,
|
|
"num_tokens": 18329787.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.5708975315094,
|
|
"epoch": 0.801433236574746,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000494312814006524,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.17473117858171464,
|
|
"num_tokens": 18340670.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.561055850982666,
|
|
"epoch": 0.8018867924528302,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004943055828577784,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.16693542152643204,
|
|
"num_tokens": 18352484.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.611057615280151,
|
|
"epoch": 0.8023403483309144,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004942983471737376,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.1695320188999176,
|
|
"num_tokens": 18363103.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.557615613937378,
|
|
"epoch": 0.8027939042089985,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942911069545511,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.17061060220003127,
|
|
"num_tokens": 18373925.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.607903099060058,
|
|
"epoch": 0.8032474600870827,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004942838622003686,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.16096073687076567,
|
|
"num_tokens": 18384081.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.642839336395264,
|
|
"epoch": 0.8037010159651669,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004942766129113399,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.16844492107629777,
|
|
"num_tokens": 18392510.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.689938163757324,
|
|
"epoch": 0.8041545718432511,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004942693590876151,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.16685045510530472,
|
|
"num_tokens": 18402809.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.6905910015106205,
|
|
"epoch": 0.8046081277213353,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000494262100729344,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.16762113571166992,
|
|
"num_tokens": 18413342.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.62622389793396,
|
|
"epoch": 0.8050616835994194,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004942548378366768,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.16534917205572128,
|
|
"num_tokens": 18424735.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.619510841369629,
|
|
"epoch": 0.8055152394775036,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004942475704097635,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.1706240862607956,
|
|
"num_tokens": 18434797.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.576655149459839,
|
|
"epoch": 0.8059687953555879,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004942402984487548,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.16197436153888703,
|
|
"num_tokens": 18445456.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.545839595794678,
|
|
"epoch": 0.806422351233672,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004942330219538008,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.163727068901062,
|
|
"num_tokens": 18456728.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.749781274795533,
|
|
"epoch": 0.8068759071117562,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000494225740925052,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.16090889275074005,
|
|
"num_tokens": 18468813.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.674880886077881,
|
|
"epoch": 0.8073294629898403,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004942184553626591,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.1678992658853531,
|
|
"num_tokens": 18477912.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.607471370697022,
|
|
"epoch": 0.8077830188679245,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004942111652667726,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.17500946670770645,
|
|
"num_tokens": 18488115.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.58686318397522,
|
|
"epoch": 0.8082365747460087,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004942038706375433,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.16537439674139023,
|
|
"num_tokens": 18498853.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.577048015594483,
|
|
"epoch": 0.8086901306240929,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941965714751222,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.16133568957448005,
|
|
"num_tokens": 18510047.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.638028335571289,
|
|
"epoch": 0.809143686502177,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004941892677796601,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.17180612534284592,
|
|
"num_tokens": 18519673.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.619547414779663,
|
|
"epoch": 0.8095972423802612,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004941819595513081,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16819463521242142,
|
|
"num_tokens": 18530090.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.719571781158447,
|
|
"epoch": 0.8100507982583455,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004941746467902173,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.15966865420341492,
|
|
"num_tokens": 18541862.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.710291719436645,
|
|
"epoch": 0.8105043541364296,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000494167329496539,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.15767375528812408,
|
|
"num_tokens": 18551624.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.617796134948731,
|
|
"epoch": 0.8109579100145138,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004941600076704244,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.1689252883195877,
|
|
"num_tokens": 18561784.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.647332811355591,
|
|
"epoch": 0.8114114658925979,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004941526813120251,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.1632409393787384,
|
|
"num_tokens": 18572110.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.661430311203003,
|
|
"epoch": 0.8118650217706821,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004941453504214924,
|
|
"loss": 5.4947,
|
|
"mean_token_accuracy": 0.16330064535140992,
|
|
"num_tokens": 18582012.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.565213871002197,
|
|
"epoch": 0.8123185776487664,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004941380149989781,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.17561429738998413,
|
|
"num_tokens": 18592850.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.594003438949585,
|
|
"epoch": 0.8127721335268505,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004941306750446336,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.16701007038354873,
|
|
"num_tokens": 18602590.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.596885013580322,
|
|
"epoch": 0.8132256894049347,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000494123330558611,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.16790961176157,
|
|
"num_tokens": 18612607.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.572688865661621,
|
|
"epoch": 0.8136792452830188,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004941159815410622,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.17194055318832396,
|
|
"num_tokens": 18622936.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.582172870635986,
|
|
"epoch": 0.8141328011611031,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000494108627992139,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.15717708468437194,
|
|
"num_tokens": 18633997.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.608917236328125,
|
|
"epoch": 0.8145863570391872,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004941012699119936,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17790337949991225,
|
|
"num_tokens": 18644347.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.617583227157593,
|
|
"epoch": 0.8150399129172714,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004940939073007779,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.16982878595590592,
|
|
"num_tokens": 18654989.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.628685855865479,
|
|
"epoch": 0.8154934687953556,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004940865401586446,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.16858104318380357,
|
|
"num_tokens": 18665526.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.599122714996338,
|
|
"epoch": 0.8159470246734397,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004940791684857458,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.1744929790496826,
|
|
"num_tokens": 18676226.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.596544647216797,
|
|
"epoch": 0.816400580551524,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004940717922822339,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1740715578198433,
|
|
"num_tokens": 18686499.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.816400580551524,
|
|
"eval_entropy": 5.499293960273535,
|
|
"eval_loss": 5.492147922515869,
|
|
"eval_mean_token_accuracy": 0.17267374004494415,
|
|
"eval_num_tokens": 18686499.0,
|
|
"eval_runtime": 26.5091,
|
|
"eval_samples_per_second": 1333.882,
|
|
"eval_steps_per_second": 166.735,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.648325109481812,
|
|
"epoch": 0.8168541364296081,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004940644115482615,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.16429938971996308,
|
|
"num_tokens": 18696543.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.581717205047608,
|
|
"epoch": 0.8173076923076923,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004940570262839812,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.1612074851989746,
|
|
"num_tokens": 18707029.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.606132745742798,
|
|
"epoch": 0.8177612481857764,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004940496364895457,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.16660574823617935,
|
|
"num_tokens": 18716937.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.674174022674561,
|
|
"epoch": 0.8182148040638607,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004940422421651082,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.16896364241838455,
|
|
"num_tokens": 18727478.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.573435878753662,
|
|
"epoch": 0.8186683599419449,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004940348433108211,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.16320528239011764,
|
|
"num_tokens": 18737339.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.609128522872925,
|
|
"epoch": 0.819121915820029,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004940274399268377,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.16753003001213074,
|
|
"num_tokens": 18747810.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.60022087097168,
|
|
"epoch": 0.8195754716981132,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004940200320133109,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.16738731861114503,
|
|
"num_tokens": 18757564.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.6804650783538815,
|
|
"epoch": 0.8200290275761973,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004940126195703941,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.16182428747415542,
|
|
"num_tokens": 18768196.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.6730348587036135,
|
|
"epoch": 0.8204825834542816,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004940052025982405,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.17686939835548401,
|
|
"num_tokens": 18778350.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.607815074920654,
|
|
"epoch": 0.8209361393323658,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004939977810970035,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.16083383411169053,
|
|
"num_tokens": 18789825.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.555605840682984,
|
|
"epoch": 0.8213896952104499,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004939903550668366,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16935580968856812,
|
|
"num_tokens": 18799793.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.564256954193115,
|
|
"epoch": 0.8218432510885341,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004939829245078934,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.16753165423870087,
|
|
"num_tokens": 18809771.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.619735240936279,
|
|
"epoch": 0.8222968069666183,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004939754894203275,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.16463650315999984,
|
|
"num_tokens": 18820529.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.5516197204589846,
|
|
"epoch": 0.8227503628447025,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004939680498042926,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.17473565191030502,
|
|
"num_tokens": 18830797.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.579305028915405,
|
|
"epoch": 0.8232039187227866,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004939606056599428,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.16576789766550065,
|
|
"num_tokens": 18840526.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.575499153137207,
|
|
"epoch": 0.8236574746008708,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004939531569874316,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.16471141427755356,
|
|
"num_tokens": 18851201.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.503150367736817,
|
|
"epoch": 0.824111030478955,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004939457037869135,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.18129919618368148,
|
|
"num_tokens": 18861676.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.5292870044708256,
|
|
"epoch": 0.8245645863570392,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004939382460585424,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.1645190566778183,
|
|
"num_tokens": 18872669.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.5579780578613285,
|
|
"epoch": 0.8250181422351234,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004939307838024726,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16422475427389144,
|
|
"num_tokens": 18882130.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.5297197818756105,
|
|
"epoch": 0.8254716981132075,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004939233170188585,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16917428374290466,
|
|
"num_tokens": 18892457.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.6344566822052,
|
|
"epoch": 0.8259252539912917,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004939158457078543,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.16588743925094604,
|
|
"num_tokens": 18903152.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.5791308879852295,
|
|
"epoch": 0.826378809869376,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004939083698696146,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.16439961045980453,
|
|
"num_tokens": 18913740.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.640698719024658,
|
|
"epoch": 0.8268323657474601,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.000493900889504294,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.17006396055221557,
|
|
"num_tokens": 18923501.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.62080750465393,
|
|
"epoch": 0.8272859216255443,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004938934046120473,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.16710171848535538,
|
|
"num_tokens": 18933255.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.551970100402832,
|
|
"epoch": 0.8277394775036284,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004938859151930293,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.1690342456102371,
|
|
"num_tokens": 18943649.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.584992265701294,
|
|
"epoch": 0.8281930333817126,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004938784212473947,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.17703648358583451,
|
|
"num_tokens": 18953187.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.631279706954956,
|
|
"epoch": 0.8286465892597968,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004938709227752985,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.16520616114139558,
|
|
"num_tokens": 18963015.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.565444612503052,
|
|
"epoch": 0.829100145137881,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000493863419776896,
|
|
"loss": 5.4996,
|
|
"mean_token_accuracy": 0.16376311779022218,
|
|
"num_tokens": 18974184.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.549704885482788,
|
|
"epoch": 0.8295537010159652,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004938559122523421,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.16940660178661346,
|
|
"num_tokens": 18985036.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.625360918045044,
|
|
"epoch": 0.8300072568940493,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004938484002017921,
|
|
"loss": 5.5363,
|
|
"mean_token_accuracy": 0.16343602538108826,
|
|
"num_tokens": 18995237.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.653959465026856,
|
|
"epoch": 0.8304608127721336,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004938408836254015,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.16166142523288726,
|
|
"num_tokens": 19006272.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.618923091888428,
|
|
"epoch": 0.8309143686502177,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004938333625233258,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.16922508031129838,
|
|
"num_tokens": 19016728.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.653804159164428,
|
|
"epoch": 0.8313679245283019,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004938258368957202,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.16299268156290053,
|
|
"num_tokens": 19028024.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.588284826278686,
|
|
"epoch": 0.831821480406386,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004938183067427406,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.17027496546506882,
|
|
"num_tokens": 19038218.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.565521621704102,
|
|
"epoch": 0.8322750362844702,
|
|
"grad_norm": 7.5625,
|
|
"learning_rate": 0.0004938107720645426,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.16394347697496414,
|
|
"num_tokens": 19048574.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.626050996780395,
|
|
"epoch": 0.8327285921625545,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004938032328612821,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.16529956907033921,
|
|
"num_tokens": 19057721.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.588996124267578,
|
|
"epoch": 0.8331821480406386,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000493795689133115,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.1627140760421753,
|
|
"num_tokens": 19067582.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.563428068161011,
|
|
"epoch": 0.8336357039187228,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004937881408801974,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.1715189129114151,
|
|
"num_tokens": 19077896.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.598232936859131,
|
|
"epoch": 0.8340892597968069,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000493780588102685,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.1720636621117592,
|
|
"num_tokens": 19088082.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.667886781692505,
|
|
"epoch": 0.8345428156748912,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004937730308007346,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.16846424341201782,
|
|
"num_tokens": 19097176.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.573349237442017,
|
|
"epoch": 0.8349963715529753,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004937654689745021,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.1709039628505707,
|
|
"num_tokens": 19107835.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.536523103713989,
|
|
"epoch": 0.8354499274310595,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004937579026241439,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.17664874494075775,
|
|
"num_tokens": 19118028.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.637387037277222,
|
|
"epoch": 0.8359034833091437,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004937503317498165,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1704498365521431,
|
|
"num_tokens": 19129223.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.603167486190796,
|
|
"epoch": 0.8363570391872278,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004937427563516765,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.16333572715520858,
|
|
"num_tokens": 19140048.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.6831597805023195,
|
|
"epoch": 0.8368105950653121,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004937351764298805,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.16168099492788315,
|
|
"num_tokens": 19150853.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.675702953338623,
|
|
"epoch": 0.8372641509433962,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004937275919845855,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.16548409759998323,
|
|
"num_tokens": 19161645.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.678725910186768,
|
|
"epoch": 0.8377177068214804,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004937200030159481,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.16480537950992585,
|
|
"num_tokens": 19173276.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.632607173919678,
|
|
"epoch": 0.8381712626995645,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004937124095241252,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.17256869822740556,
|
|
"num_tokens": 19182949.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.630819845199585,
|
|
"epoch": 0.8386248185776488,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004937048115092739,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16706619113683702,
|
|
"num_tokens": 19193504.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.610013198852539,
|
|
"epoch": 0.839078374455733,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004936972089715515,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.15942700803279877,
|
|
"num_tokens": 19203406.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.647968816757202,
|
|
"epoch": 0.8395319303338171,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000493689601911115,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16736481189727784,
|
|
"num_tokens": 19214325.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.619275045394898,
|
|
"epoch": 0.8399854862119013,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004936819903281219,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.15449996888637543,
|
|
"num_tokens": 19226466.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.677626037597657,
|
|
"epoch": 0.8404390420899854,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004936743742227295,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.16590409278869628,
|
|
"num_tokens": 19237032.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.7064573764801025,
|
|
"epoch": 0.8408925979680697,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004936667535950952,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.16213936507701873,
|
|
"num_tokens": 19248009.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.655757761001587,
|
|
"epoch": 0.8413461538461539,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004936591284453768,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.16394732594490052,
|
|
"num_tokens": 19259363.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.610392808914185,
|
|
"epoch": 0.841799709724238,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004936514987737319,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.16612009406089784,
|
|
"num_tokens": 19269191.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.631801128387451,
|
|
"epoch": 0.8422532656023222,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004936438645803182,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.16355190873146058,
|
|
"num_tokens": 19280278.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.6273674964904785,
|
|
"epoch": 0.8427068214804064,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004936362258652938,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.16636256724596024,
|
|
"num_tokens": 19290130.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.745988178253174,
|
|
"epoch": 0.8431603773584906,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936285826288165,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16738905161619186,
|
|
"num_tokens": 19301669.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.549793291091919,
|
|
"epoch": 0.8436139332365747,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004936209348710444,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.1677660569548607,
|
|
"num_tokens": 19312490.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.5131879329681395,
|
|
"epoch": 0.8440674891146589,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004936132825921355,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.1659799888730049,
|
|
"num_tokens": 19321743.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.606175374984741,
|
|
"epoch": 0.844521044992743,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004936056257922484,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.1735738232731819,
|
|
"num_tokens": 19332149.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.589995050430298,
|
|
"epoch": 0.8449746008708273,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004935979644715412,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.16639793962240218,
|
|
"num_tokens": 19341655.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.573223495483399,
|
|
"epoch": 0.8454281567489115,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004935902986301724,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.16116373836994172,
|
|
"num_tokens": 19351404.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.657394313812256,
|
|
"epoch": 0.8458817126269956,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935826282683005,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.16180313229560853,
|
|
"num_tokens": 19361788.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.650906705856324,
|
|
"epoch": 0.8463352685050798,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004935749533860842,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.16616404056549072,
|
|
"num_tokens": 19372902.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.5491042137146,
|
|
"epoch": 0.846788824383164,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000493567273983682,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.16852847784757613,
|
|
"num_tokens": 19382181.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.611289405822754,
|
|
"epoch": 0.8472423802612482,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000493559590061253,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.16242333501577377,
|
|
"num_tokens": 19393692.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.629254102706909,
|
|
"epoch": 0.8476959361393324,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004935519016189559,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.17058742940425872,
|
|
"num_tokens": 19404587.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.630183506011963,
|
|
"epoch": 0.8481494920174165,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004935442086569498,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.16475782990455629,
|
|
"num_tokens": 19415296.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.683138704299926,
|
|
"epoch": 0.8486030478955007,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935365111753939,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.1648883879184723,
|
|
"num_tokens": 19426119.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.616968631744385,
|
|
"epoch": 0.8490566037735849,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004935288091744472,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.16678015291690826,
|
|
"num_tokens": 19436828.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.645136785507202,
|
|
"epoch": 0.8495101596516691,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000493521102654269,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.16086220145225524,
|
|
"num_tokens": 19446583.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.590010356903076,
|
|
"epoch": 0.8499637155297532,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004935133916150187,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.1739301025867462,
|
|
"num_tokens": 19456757.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.503833961486817,
|
|
"epoch": 0.8504172714078374,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004935056760568558,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.16398343741893767,
|
|
"num_tokens": 19467624.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.5467448234558105,
|
|
"epoch": 0.8508708272859217,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004934979559799399,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.16686284244060517,
|
|
"num_tokens": 19477759.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.6368509292602536,
|
|
"epoch": 0.8513243831640058,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004934902313844306,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.16647852212190628,
|
|
"num_tokens": 19488877.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.565980243682861,
|
|
"epoch": 0.85177793904209,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004934825022704875,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16903312206268312,
|
|
"num_tokens": 19499170.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.551848745346069,
|
|
"epoch": 0.8522314949201741,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004934747686382707,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.15809385925531388,
|
|
"num_tokens": 19509944.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.6449051856994625,
|
|
"epoch": 0.8526850507982583,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004934670304879398,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.16593187153339387,
|
|
"num_tokens": 19519014.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.57209005355835,
|
|
"epoch": 0.8531386066763426,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004934592878196553,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.16572651267051697,
|
|
"num_tokens": 19528586.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.6237119197845455,
|
|
"epoch": 0.8535921625544267,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000493451540633577,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.16077084690332413,
|
|
"num_tokens": 19539912.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.611822319030762,
|
|
"epoch": 0.8540457184325109,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004934437889298651,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.15974553525447846,
|
|
"num_tokens": 19549860.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.672833824157715,
|
|
"epoch": 0.854499274310595,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004934360327086799,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.16649190634489058,
|
|
"num_tokens": 19559446.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.714667272567749,
|
|
"epoch": 0.8549528301886793,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000493428271970182,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.17092570215463637,
|
|
"num_tokens": 19570282.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.611190223693848,
|
|
"epoch": 0.8554063860667634,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004934205067145318,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.16731165051460267,
|
|
"num_tokens": 19581087.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.564599466323853,
|
|
"epoch": 0.8558599419448476,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004934127369418898,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.16411774158477782,
|
|
"num_tokens": 19592100.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.570101594924926,
|
|
"epoch": 0.8563134978229318,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004934049626524168,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.16585781723260878,
|
|
"num_tokens": 19602557.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.676563405990601,
|
|
"epoch": 0.8567670537010159,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004933971838462734,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1598167359828949,
|
|
"num_tokens": 19613643.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.647255325317383,
|
|
"epoch": 0.8572206095791002,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004933894005236207,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.16713989078998565,
|
|
"num_tokens": 19624180.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.606472158432007,
|
|
"epoch": 0.8576741654571843,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004933816126846195,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16742375642061233,
|
|
"num_tokens": 19634799.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.561668920516968,
|
|
"epoch": 0.8581277213352685,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004933738203294309,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.1714523419737816,
|
|
"num_tokens": 19644618.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.56659164428711,
|
|
"epoch": 0.8585812772133526,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000493366023458216,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.1622690811753273,
|
|
"num_tokens": 19655550.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.621352195739746,
|
|
"epoch": 0.8590348330914369,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004933582220711362,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.17273536175489426,
|
|
"num_tokens": 19665734.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.668038558959961,
|
|
"epoch": 0.8594883889695211,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004933504161683526,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16332752257585526,
|
|
"num_tokens": 19677130.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.57708215713501,
|
|
"epoch": 0.8599419448476052,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004933426057500269,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.17379804104566574,
|
|
"num_tokens": 19687374.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.641341924667358,
|
|
"epoch": 0.8603955007256894,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004933347908163203,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.16353899091482163,
|
|
"num_tokens": 19698182.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.643030023574829,
|
|
"epoch": 0.8608490566037735,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004933269713673947,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.16726512908935548,
|
|
"num_tokens": 19707664.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.599136781692505,
|
|
"epoch": 0.8613026124818578,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004933191474034116,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.1638665184378624,
|
|
"num_tokens": 19717647.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.622937393188477,
|
|
"epoch": 0.861756168359942,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000493311318924533,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.1666355237364769,
|
|
"num_tokens": 19727444.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.624603986740112,
|
|
"epoch": 0.8622097242380261,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004933034859309208,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.15709710568189622,
|
|
"num_tokens": 19738719.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.7038360118865965,
|
|
"epoch": 0.8626632801161103,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004932956484227367,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16988746225833892,
|
|
"num_tokens": 19749786.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.607921314239502,
|
|
"epoch": 0.8631168359941945,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.000493287806400143,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.17672932147979736,
|
|
"num_tokens": 19759623.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.638581037521362,
|
|
"epoch": 0.8635703918722787,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004932799598633018,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.16770731210708617,
|
|
"num_tokens": 19770117.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.627360916137695,
|
|
"epoch": 0.8640239477503628,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004932721088123753,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.1628728300333023,
|
|
"num_tokens": 19780748.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.646074390411377,
|
|
"epoch": 0.864477503628447,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004932642532475262,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.16957747638225557,
|
|
"num_tokens": 19791816.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.695994901657104,
|
|
"epoch": 0.8649310595065312,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004932563931689168,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.16334045678377151,
|
|
"num_tokens": 19801096.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.635082721710205,
|
|
"epoch": 0.8653846153846154,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004932485285767093,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16868644654750825,
|
|
"num_tokens": 19811258.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.658902931213379,
|
|
"epoch": 0.8658381712626996,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004932406594710667,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.1752654105424881,
|
|
"num_tokens": 19821765.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.6280457973480225,
|
|
"epoch": 0.8662917271407837,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004932327858521517,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.17672177404165268,
|
|
"num_tokens": 19831537.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.535717916488648,
|
|
"epoch": 0.8667452830188679,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000493224907720127,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.16636214405298233,
|
|
"num_tokens": 19841830.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.635063886642456,
|
|
"epoch": 0.8671988388969522,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004932170250751556,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.15869371294975282,
|
|
"num_tokens": 19851896.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.665247392654419,
|
|
"epoch": 0.8676523947750363,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004932091379174006,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.15944714993238449,
|
|
"num_tokens": 19861735.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.637991523742675,
|
|
"epoch": 0.8681059506531205,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000493201246247025,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.17442315816879272,
|
|
"num_tokens": 19872333.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.607363271713257,
|
|
"epoch": 0.8685595065312046,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000493193350064192,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.16355780214071275,
|
|
"num_tokens": 19882896.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.6081709384918215,
|
|
"epoch": 0.8690130624092888,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004931854493690649,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.16593107730150222,
|
|
"num_tokens": 19893767.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.592438220977783,
|
|
"epoch": 0.869466618287373,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004931775441618071,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.17099117934703828,
|
|
"num_tokens": 19904242.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.536753511428833,
|
|
"epoch": 0.8699201741654572,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004931696344425821,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16561063528060913,
|
|
"num_tokens": 19913898.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.674816989898682,
|
|
"epoch": 0.8703737300435413,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004931617202115535,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.1691025123000145,
|
|
"num_tokens": 19923756.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.6317566394805905,
|
|
"epoch": 0.8708272859216255,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004931538014688849,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.17173125892877578,
|
|
"num_tokens": 19932720.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.670051956176758,
|
|
"epoch": 0.8712808417997098,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004931458782147401,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15633623227477073,
|
|
"num_tokens": 19942962.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.6734381198883055,
|
|
"epoch": 0.8717343976777939,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.000493137950449283,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.16917594224214555,
|
|
"num_tokens": 19953735.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.670583915710449,
|
|
"epoch": 0.8721879535558781,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004931300181726775,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1696719706058502,
|
|
"num_tokens": 19964416.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.657572889328003,
|
|
"epoch": 0.8726415094339622,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004931220813850875,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.16641833484172822,
|
|
"num_tokens": 19974531.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.650475597381591,
|
|
"epoch": 0.8730950653120464,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004931141400866773,
|
|
"loss": 5.4961,
|
|
"mean_token_accuracy": 0.17093998789787293,
|
|
"num_tokens": 19984964.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.606709909439087,
|
|
"epoch": 0.8735486211901307,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004931061942776112,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.1740843877196312,
|
|
"num_tokens": 19995568.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.735747480392456,
|
|
"epoch": 0.8740021770682148,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004930982439580534,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.15779380351305008,
|
|
"num_tokens": 20005856.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.714074563980103,
|
|
"epoch": 0.874455732946299,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004930902891281683,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.16212179958820344,
|
|
"num_tokens": 20015683.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.566607093811035,
|
|
"epoch": 0.8749092888243831,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004930823297881205,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.17044655978679657,
|
|
"num_tokens": 20025998.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.638138914108277,
|
|
"epoch": 0.8753628447024674,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004930743659380745,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.1626819744706154,
|
|
"num_tokens": 20036486.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.618236541748047,
|
|
"epoch": 0.8758164005805515,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000493066397578195,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.17181899398565292,
|
|
"num_tokens": 20046784.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.622888803482056,
|
|
"epoch": 0.8762699564586357,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004930584247086468,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.1695317029953003,
|
|
"num_tokens": 20056999.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.560177183151245,
|
|
"epoch": 0.8767235123367199,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000493050447329595,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.1711304858326912,
|
|
"num_tokens": 20067612.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.6600298404693605,
|
|
"epoch": 0.877177068214804,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004930424654412043,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.1657562106847763,
|
|
"num_tokens": 20077330.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.663735485076904,
|
|
"epoch": 0.8776306240928883,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004930344790436398,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.1622760236263275,
|
|
"num_tokens": 20086801.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.621307373046875,
|
|
"epoch": 0.8780841799709724,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004930264881370666,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.16382185965776444,
|
|
"num_tokens": 20097047.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.62794976234436,
|
|
"epoch": 0.8785377358490566,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004930184927216504,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1664504364132881,
|
|
"num_tokens": 20107185.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.686764240264893,
|
|
"epoch": 0.8789912917271407,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004930104927975559,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.16731444001197815,
|
|
"num_tokens": 20118493.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.630422067642212,
|
|
"epoch": 0.879444847605225,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004930024883649489,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.1667337730526924,
|
|
"num_tokens": 20129294.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.5502057552337645,
|
|
"epoch": 0.8798984034833092,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000492994479423995,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.17128972113132476,
|
|
"num_tokens": 20139194.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.601175928115845,
|
|
"epoch": 0.8803519593613933,
|
|
"grad_norm": 3.96875,
|
|
"learning_rate": 0.0004929864659748597,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.1654967784881592,
|
|
"num_tokens": 20149681.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.680785179138184,
|
|
"epoch": 0.8808055152394775,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004929784480177087,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1593937858939171,
|
|
"num_tokens": 20160557.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.672782897949219,
|
|
"epoch": 0.8812590711175616,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004929704255527078,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.16927874982357025,
|
|
"num_tokens": 20171047.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.688721179962158,
|
|
"epoch": 0.8817126269956459,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000492962398580023,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.1585509419441223,
|
|
"num_tokens": 20182148.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.5953943729400635,
|
|
"epoch": 0.88216618287373,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004929543670998203,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.1713259622454643,
|
|
"num_tokens": 20192131.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.6180421829223635,
|
|
"epoch": 0.8826197387518142,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004929463311122657,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.16329212933778764,
|
|
"num_tokens": 20202805.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.596766090393066,
|
|
"epoch": 0.8830732946298984,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004929382906175253,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.17018195986747742,
|
|
"num_tokens": 20212702.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.612695646286011,
|
|
"epoch": 0.8835268505079826,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004929302456157657,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.16651211231946944,
|
|
"num_tokens": 20222661.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.642892456054687,
|
|
"epoch": 0.8839804063860668,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004929221961071531,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16402020901441575,
|
|
"num_tokens": 20233012.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.647194147109985,
|
|
"epoch": 0.8844339622641509,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004929141420918538,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.16944866329431535,
|
|
"num_tokens": 20242918.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.610573482513428,
|
|
"epoch": 0.8848875181422351,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004929060835700347,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17089887857437133,
|
|
"num_tokens": 20253254.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.621883535385132,
|
|
"epoch": 0.8853410740203193,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000492898020541862,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.16487018764019012,
|
|
"num_tokens": 20263355.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.606476926803589,
|
|
"epoch": 0.8857946298984035,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004928899530075029,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.16572795957326888,
|
|
"num_tokens": 20274716.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.545453405380249,
|
|
"epoch": 0.8862481857764877,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004928818809671241,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.16600928008556365,
|
|
"num_tokens": 20285631.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.629395246505737,
|
|
"epoch": 0.8867017416545718,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004928738044208923,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.1744563788175583,
|
|
"num_tokens": 20295717.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.5827960014343265,
|
|
"epoch": 0.887155297532656,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004928657233689748,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1701323866844177,
|
|
"num_tokens": 20306637.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.611489343643188,
|
|
"epoch": 0.8876088534107403,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004928576378115387,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.17060102224349977,
|
|
"num_tokens": 20316629.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.7080353736877445,
|
|
"epoch": 0.8880624092888244,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004928495477487509,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.1562129482626915,
|
|
"num_tokens": 20327935.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.635652685165406,
|
|
"epoch": 0.8885159651669086,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004928414531807792,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.16605042219161986,
|
|
"num_tokens": 20339142.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.605915451049805,
|
|
"epoch": 0.8889695210449927,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004928333541077906,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.17367625385522842,
|
|
"num_tokens": 20348474.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.644237422943116,
|
|
"epoch": 0.8894230769230769,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004928252505299527,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.1646744877099991,
|
|
"num_tokens": 20359440.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.6727293014526365,
|
|
"epoch": 0.8898766328011611,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004928171424474332,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.16782969534397124,
|
|
"num_tokens": 20370355.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.615191698074341,
|
|
"epoch": 0.8903301886792453,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004928090298603996,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.17068232148885726,
|
|
"num_tokens": 20380214.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.6379311084747314,
|
|
"epoch": 0.8907837445573294,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004928009127690199,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.168188439309597,
|
|
"num_tokens": 20389190.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.605611085891724,
|
|
"epoch": 0.8912373004354136,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004927927911734617,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.16537884026765823,
|
|
"num_tokens": 20399531.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.658443212509155,
|
|
"epoch": 0.8916908563134979,
|
|
"grad_norm": 3.984375,
|
|
"learning_rate": 0.0004927846650738931,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.1641345277428627,
|
|
"num_tokens": 20410201.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.617740869522095,
|
|
"epoch": 0.892144412191582,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004927765344704821,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.17194532752037048,
|
|
"num_tokens": 20421579.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.618694734573364,
|
|
"epoch": 0.8925979680696662,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004927683993633969,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.1712222546339035,
|
|
"num_tokens": 20432048.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.697521066665649,
|
|
"epoch": 0.8930515239477503,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004927602597528057,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.16094869524240493,
|
|
"num_tokens": 20441752.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.665847206115723,
|
|
"epoch": 0.8935050798258345,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004927521156388769,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1692692369222641,
|
|
"num_tokens": 20451693.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.636432886123657,
|
|
"epoch": 0.8939586357039188,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004927439670217788,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.15978458672761917,
|
|
"num_tokens": 20462312.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.613775014877319,
|
|
"epoch": 0.8944121915820029,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00049273581390168,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.1645998850464821,
|
|
"num_tokens": 20472546.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.650700902938842,
|
|
"epoch": 0.8948657474600871,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000492727656278749,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.16577322036027908,
|
|
"num_tokens": 20483266.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.587610387802124,
|
|
"epoch": 0.8953193033381712,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004927194941531547,
|
|
"loss": 5.4024,
|
|
"mean_token_accuracy": 0.168634133040905,
|
|
"num_tokens": 20492490.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.582613468170166,
|
|
"epoch": 0.8957728592162555,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004927113275250657,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.17028550952672958,
|
|
"num_tokens": 20503077.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.590944814682007,
|
|
"epoch": 0.8962264150943396,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004927031563946511,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16236511170864104,
|
|
"num_tokens": 20513771.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.610186958312989,
|
|
"epoch": 0.8966799709724238,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004926949807620796,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.16225252002477647,
|
|
"num_tokens": 20523616.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.625984811782837,
|
|
"epoch": 0.897133526850508,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004926868006275204,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.1741590067744255,
|
|
"num_tokens": 20533613.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.634837245941162,
|
|
"epoch": 0.8975870827285921,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004926786159911427,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.16801166236400605,
|
|
"num_tokens": 20543812.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.569585657119751,
|
|
"epoch": 0.8980406386066764,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000492670426853116,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.16847120970487595,
|
|
"num_tokens": 20553785.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.655517578125,
|
|
"epoch": 0.8984941944847605,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004926622332136092,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.1724136456847191,
|
|
"num_tokens": 20563326.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.577728033065796,
|
|
"epoch": 0.8989477503628447,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004926540350727918,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.173677958548069,
|
|
"num_tokens": 20573643.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.55289888381958,
|
|
"epoch": 0.8994013062409288,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004926458324308337,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.17063824236392974,
|
|
"num_tokens": 20583916.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.659201669692993,
|
|
"epoch": 0.8998548621190131,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004926376252879043,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.16558234691619872,
|
|
"num_tokens": 20593984.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.634729337692261,
|
|
"epoch": 0.9003084179970973,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004926294136441733,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.17320367842912673,
|
|
"num_tokens": 20603927.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.62198920249939,
|
|
"epoch": 0.9007619738751814,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004926211974998106,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.170858134329319,
|
|
"num_tokens": 20614147.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.669112634658814,
|
|
"epoch": 0.9012155297532656,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000492612976854986,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.16913086771965027,
|
|
"num_tokens": 20623631.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.569746732711792,
|
|
"epoch": 0.9016690856313497,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004926047517098697,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.17397348433732987,
|
|
"num_tokens": 20632566.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.617513370513916,
|
|
"epoch": 0.902122641509434,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004925965220646315,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.16440732777118683,
|
|
"num_tokens": 20643246.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.643515872955322,
|
|
"epoch": 0.9025761973875182,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004925882879194419,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.16406310051679612,
|
|
"num_tokens": 20653372.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.657034015655517,
|
|
"epoch": 0.9030297532656023,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004925800492744712,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.16646226197481157,
|
|
"num_tokens": 20662687.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.6161580085754395,
|
|
"epoch": 0.9034833091436865,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004925718061298895,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.17280880659818648,
|
|
"num_tokens": 20673168.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.7037781238555905,
|
|
"epoch": 0.9039368650217707,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004925635584858675,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.16221273839473724,
|
|
"num_tokens": 20683100.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.718763256072998,
|
|
"epoch": 0.9043904208998549,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004925553063425755,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.16453297883272172,
|
|
"num_tokens": 20694097.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.639046764373779,
|
|
"epoch": 0.904843976777939,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004925470497001844,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.16766450703144073,
|
|
"num_tokens": 20704640.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.629187488555909,
|
|
"epoch": 0.9052975326560232,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004925387885588648,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16981081664562225,
|
|
"num_tokens": 20714419.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.687669944763184,
|
|
"epoch": 0.9057510885341074,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004925305229187877,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.1662205457687378,
|
|
"num_tokens": 20724705.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.703696823120117,
|
|
"epoch": 0.9062046444121916,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000492522252780124,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.16465610563755034,
|
|
"num_tokens": 20734753.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.616272354125977,
|
|
"epoch": 0.9066582002902758,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004925139781430446,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.1729523003101349,
|
|
"num_tokens": 20745389.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.631888151168823,
|
|
"epoch": 0.9071117561683599,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004925056990077207,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.1671442434191704,
|
|
"num_tokens": 20755702.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.613785123825073,
|
|
"epoch": 0.9075653120464441,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004924974153743235,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.174472938477993,
|
|
"num_tokens": 20766046.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.628176593780518,
|
|
"epoch": 0.9080188679245284,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004924891272430244,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.16712419539690018,
|
|
"num_tokens": 20776654.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.670589637756348,
|
|
"epoch": 0.9084724238026125,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004924808346139948,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.17070617973804475,
|
|
"num_tokens": 20787066.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.666522789001465,
|
|
"epoch": 0.9089259796806967,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004924725374874059,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.1702822580933571,
|
|
"num_tokens": 20796822.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.683545827865601,
|
|
"epoch": 0.9093795355587808,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004924642358634297,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.16714202910661696,
|
|
"num_tokens": 20807602.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.644869184494018,
|
|
"epoch": 0.909833091436865,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004924559297422376,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.16788566261529922,
|
|
"num_tokens": 20819046.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.640174627304077,
|
|
"epoch": 0.9102866473149492,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004924476191240014,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.164874167740345,
|
|
"num_tokens": 20828989.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.627811527252197,
|
|
"epoch": 0.9107402031930334,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000492439304008893,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.16124556064605713,
|
|
"num_tokens": 20839366.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.675979280471802,
|
|
"epoch": 0.9111937590711175,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004924309843970847,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.1698861002922058,
|
|
"num_tokens": 20849513.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.709691905975342,
|
|
"epoch": 0.9116473149492017,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004924226602887479,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.16104661524295807,
|
|
"num_tokens": 20861406.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.598871183395386,
|
|
"epoch": 0.912100870827286,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004924143316840552,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1793083667755127,
|
|
"num_tokens": 20871190.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.660051965713501,
|
|
"epoch": 0.9125544267053701,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004924059985831787,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.16229840219020844,
|
|
"num_tokens": 20881589.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.66608419418335,
|
|
"epoch": 0.9130079825834543,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004923976609862908,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.1605662927031517,
|
|
"num_tokens": 20892072.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.685091018676758,
|
|
"epoch": 0.9134615384615384,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004923893188935638,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.16243244409561158,
|
|
"num_tokens": 20902616.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.653387975692749,
|
|
"epoch": 0.9139150943396226,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004923809723051702,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.16339652985334396,
|
|
"num_tokens": 20913832.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.518843936920166,
|
|
"epoch": 0.9143686502177069,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004923726212212829,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.16908359676599502,
|
|
"num_tokens": 20923322.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.597713804244995,
|
|
"epoch": 0.914822206095791,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004923642656420742,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.16452524811029434,
|
|
"num_tokens": 20933334.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.64165244102478,
|
|
"epoch": 0.9152757619738752,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004923559055677173,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1654943734407425,
|
|
"num_tokens": 20944171.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.658243036270141,
|
|
"epoch": 0.9157293178519593,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004923475409983848,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.16481802463531495,
|
|
"num_tokens": 20954200.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.592943096160889,
|
|
"epoch": 0.9161828737300436,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004923391719342497,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.16222574710845947,
|
|
"num_tokens": 20964935.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.679191446304321,
|
|
"epoch": 0.9166364296081277,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004923307983754852,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.16879493445158006,
|
|
"num_tokens": 20975499.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.59067120552063,
|
|
"epoch": 0.9170899854862119,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004923224203222645,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.16911139339208603,
|
|
"num_tokens": 20986199.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.612363624572754,
|
|
"epoch": 0.9175435413642961,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004923140377747606,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.16479670703411103,
|
|
"num_tokens": 20996313.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.621811199188232,
|
|
"epoch": 0.9179970972423802,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004923056507331471,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.16965973675251006,
|
|
"num_tokens": 21006133.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.699572801589966,
|
|
"epoch": 0.9184506531204645,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004922972591975974,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.16748667806386947,
|
|
"num_tokens": 21016448.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.622897386550903,
|
|
"epoch": 0.9189042089985486,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004922888631682849,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.16948991268873215,
|
|
"num_tokens": 21026458.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.5447803974151615,
|
|
"epoch": 0.9193577648766328,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004922804626453834,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.1717316135764122,
|
|
"num_tokens": 21037111.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.529819822311401,
|
|
"epoch": 0.9198113207547169,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004922720576290665,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1738602638244629,
|
|
"num_tokens": 21048041.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.581639623641967,
|
|
"epoch": 0.9202648766328012,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004922636481195082,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.18189457952976226,
|
|
"num_tokens": 21058099.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.649187707901001,
|
|
"epoch": 0.9207184325108854,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004922552341168823,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.1608864963054657,
|
|
"num_tokens": 21068137.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.555316972732544,
|
|
"epoch": 0.9211719883889695,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004922468156213627,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17540239095687865,
|
|
"num_tokens": 21077556.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.5683581829071045,
|
|
"epoch": 0.9216255442670537,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004922383926331236,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.17052381485700607,
|
|
"num_tokens": 21087524.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.541804695129395,
|
|
"epoch": 0.9220791001451378,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004922299651523392,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.16598909497261047,
|
|
"num_tokens": 21098446.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.590465116500854,
|
|
"epoch": 0.9225326560232221,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004922215331791837,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.16691119074821473,
|
|
"num_tokens": 21109291.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.647093009948731,
|
|
"epoch": 0.9229862119013063,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004922130967138316,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.17282696664333344,
|
|
"num_tokens": 21120043.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.6608076095581055,
|
|
"epoch": 0.9234397677793904,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004922046557564574,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.16004344522953035,
|
|
"num_tokens": 21130339.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.618777227401734,
|
|
"epoch": 0.9238933236574746,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004921962103072355,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.16347383558750153,
|
|
"num_tokens": 21142307.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.5993763446807865,
|
|
"epoch": 0.9243468795355588,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004921877603663406,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.1706625923514366,
|
|
"num_tokens": 21151843.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.5873476505279545,
|
|
"epoch": 0.924800435413643,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004921793059339474,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.16952639818191528,
|
|
"num_tokens": 21162574.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.616939735412598,
|
|
"epoch": 0.9252539912917271,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004921708470102309,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.171491040289402,
|
|
"num_tokens": 21172637.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.596718406677246,
|
|
"epoch": 0.9257075471698113,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000492162383595366,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.17129719704389573,
|
|
"num_tokens": 21182272.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.637783479690552,
|
|
"epoch": 0.9261611030478955,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004921539156895275,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.16203432977199556,
|
|
"num_tokens": 21193712.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.6768382549285885,
|
|
"epoch": 0.9266146589259797,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004921454432928908,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16012393087148666,
|
|
"num_tokens": 21205104.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.695552110671997,
|
|
"epoch": 0.9270682148040639,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000492136966405631,
|
|
"loss": 5.4251,
|
|
"mean_token_accuracy": 0.16568379253149032,
|
|
"num_tokens": 21215495.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.629831695556641,
|
|
"epoch": 0.927521770682148,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004921284850279233,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.17006988748908042,
|
|
"num_tokens": 21226047.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.6132285594940186,
|
|
"epoch": 0.9279753265602322,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004921199991599433,
|
|
"loss": 5.4882,
|
|
"mean_token_accuracy": 0.164862522482872,
|
|
"num_tokens": 21235784.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.594307994842529,
|
|
"epoch": 0.9284288824383164,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004921115088018665,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.16549347192049027,
|
|
"num_tokens": 21245493.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.748114490509034,
|
|
"epoch": 0.9288824383164006,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000492103013953868,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.16245089769363402,
|
|
"num_tokens": 21255541.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.609032535552979,
|
|
"epoch": 0.9293359941944848,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004920945146161242,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.17053214609622955,
|
|
"num_tokens": 21265427.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.5645238876342775,
|
|
"epoch": 0.9297895500725689,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004920860107888105,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.17055170685052873,
|
|
"num_tokens": 21276597.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.585609579086304,
|
|
"epoch": 0.9302431059506531,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004920775024721026,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.16735020279884338,
|
|
"num_tokens": 21286416.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.60588436126709,
|
|
"epoch": 0.9306966618287373,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004920689896661767,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.1755400061607361,
|
|
"num_tokens": 21296064.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.556747627258301,
|
|
"epoch": 0.9311502177068215,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004920604723712088,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.16989123821258545,
|
|
"num_tokens": 21306836.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.569533777236939,
|
|
"epoch": 0.9316037735849056,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004920519505873751,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17076023817062377,
|
|
"num_tokens": 21316936.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.570468902587891,
|
|
"epoch": 0.9320573294629898,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004920434243148515,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.17534030824899674,
|
|
"num_tokens": 21326892.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.61998815536499,
|
|
"epoch": 0.9325108853410741,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004920348935538147,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.16621700972318648,
|
|
"num_tokens": 21337270.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.621613168716431,
|
|
"epoch": 0.9329644412191582,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000492026358304441,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.16533970683813096,
|
|
"num_tokens": 21347968.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.577658987045288,
|
|
"epoch": 0.9334179970972424,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000492017818566907,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.1734221026301384,
|
|
"num_tokens": 21358312.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.544279146194458,
|
|
"epoch": 0.9338715529753265,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004920092743413892,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.1729722023010254,
|
|
"num_tokens": 21368794.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.659960556030273,
|
|
"epoch": 0.9343251088534107,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004920007256280642,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.16844243556261063,
|
|
"num_tokens": 21380080.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.648020219802857,
|
|
"epoch": 0.934778664731495,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000491992172427109,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.1703952133655548,
|
|
"num_tokens": 21389961.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.596118021011352,
|
|
"epoch": 0.9352322206095791,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004919836147387002,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.1696673095226288,
|
|
"num_tokens": 21399869.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.640964031219482,
|
|
"epoch": 0.9356857764876633,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919750525630151,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.1662815734744072,
|
|
"num_tokens": 21410343.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.635088062286377,
|
|
"epoch": 0.9361393323657474,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004919664859002306,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.16929827481508256,
|
|
"num_tokens": 21420915.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.637465095520019,
|
|
"epoch": 0.9365928882438317,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004919579147505239,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.1708474949002266,
|
|
"num_tokens": 21430879.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.602361822128296,
|
|
"epoch": 0.9370464441219158,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004919493391140721,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.16649596393108368,
|
|
"num_tokens": 21440843.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.674230480194092,
|
|
"epoch": 0.9375,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004919407589910529,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.15944903194904328,
|
|
"num_tokens": 21452132.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.667742013931274,
|
|
"epoch": 0.9379535558780842,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004919321743816434,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.16516388356685638,
|
|
"num_tokens": 21461861.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.591098022460938,
|
|
"epoch": 0.9384071117561683,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004919235852860213,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.1637754425406456,
|
|
"num_tokens": 21472244.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.635477733612061,
|
|
"epoch": 0.9388606676342526,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004919149917043641,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.1652377024292946,
|
|
"num_tokens": 21482394.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.654922580718994,
|
|
"epoch": 0.9393142235123367,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004919063936368496,
|
|
"loss": 5.5379,
|
|
"mean_token_accuracy": 0.16441430747509003,
|
|
"num_tokens": 21493334.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.699097156524658,
|
|
"epoch": 0.9397677793904209,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004918977910836557,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.1640081062912941,
|
|
"num_tokens": 21504443.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.647023248672485,
|
|
"epoch": 0.940221335268505,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004918891840449601,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.165273255109787,
|
|
"num_tokens": 21513908.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.655364942550659,
|
|
"epoch": 0.9406748911465893,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000491880572520941,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.15919932425022126,
|
|
"num_tokens": 21524349.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.7412327289581295,
|
|
"epoch": 0.9411284470246735,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004918719565117763,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.16886789351701736,
|
|
"num_tokens": 21535003.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.734970474243164,
|
|
"epoch": 0.9415820029027576,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004918633360176444,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.15955100655555726,
|
|
"num_tokens": 21545045.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.5925661563873295,
|
|
"epoch": 0.9420355587808418,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004918547110387234,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.16955724358558655,
|
|
"num_tokens": 21554830.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.615862941741943,
|
|
"epoch": 0.9424891146589259,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004918460815751916,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.16941992640495301,
|
|
"num_tokens": 21564693.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.583719253540039,
|
|
"epoch": 0.9429426705370102,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004918374476272277,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.16966528594493865,
|
|
"num_tokens": 21575475.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.5933574676513675,
|
|
"epoch": 0.9433962264150944,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004918288091950101,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.16622391939163209,
|
|
"num_tokens": 21586944.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.691214942932129,
|
|
"epoch": 0.9438497822931785,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004918201662787174,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.16582643538713454,
|
|
"num_tokens": 21598170.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.575848245620728,
|
|
"epoch": 0.9443033381712627,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004918115188785285,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.1633247345685959,
|
|
"num_tokens": 21609170.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.630935955047607,
|
|
"epoch": 0.9447568940493469,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004918028669946221,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.16391694992780687,
|
|
"num_tokens": 21620171.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.694646644592285,
|
|
"epoch": 0.9452104499274311,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004917942106271771,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.17085294872522355,
|
|
"num_tokens": 21631072.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.559463977813721,
|
|
"epoch": 0.9456640058055152,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004917855497763727,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.17428645938634874,
|
|
"num_tokens": 21641543.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.57183518409729,
|
|
"epoch": 0.9461175616835994,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004917768844423878,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.16970002353191377,
|
|
"num_tokens": 21651342.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.677303838729858,
|
|
"epoch": 0.9465711175616836,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004917682146254017,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.1728857398033142,
|
|
"num_tokens": 21661043.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.538600015640259,
|
|
"epoch": 0.9470246734397678,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004917595403255938,
|
|
"loss": 5.3096,
|
|
"mean_token_accuracy": 0.17871788889169693,
|
|
"num_tokens": 21671197.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.501651239395142,
|
|
"epoch": 0.947478229317852,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004917508615431431,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17176435738801957,
|
|
"num_tokens": 21682066.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.654246997833252,
|
|
"epoch": 0.9479317851959361,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004917421782782296,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1663619577884674,
|
|
"num_tokens": 21692117.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.694399499893189,
|
|
"epoch": 0.9483853410740203,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004917334905310325,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.15789986699819564,
|
|
"num_tokens": 21703544.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.5399058818817135,
|
|
"epoch": 0.9488388969521045,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004917247983017317,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.17476127594709395,
|
|
"num_tokens": 21712850.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.614771795272827,
|
|
"epoch": 0.9492924528301887,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004917161015905067,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.16575202494859695,
|
|
"num_tokens": 21723015.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.598294687271118,
|
|
"epoch": 0.9497460087082729,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004917074003975376,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.16261564195156097,
|
|
"num_tokens": 21732453.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.646253156661987,
|
|
"epoch": 0.950199564586357,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004916986947230042,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.1652168944478035,
|
|
"num_tokens": 21743251.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.618532323837281,
|
|
"epoch": 0.9506531204644412,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004916899845670866,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.1703191101551056,
|
|
"num_tokens": 21752891.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.6609643459320065,
|
|
"epoch": 0.9511066763425254,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004916812699299649,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.16858232170343398,
|
|
"num_tokens": 21763230.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.6318341255187985,
|
|
"epoch": 0.9515602322206096,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004916725508118193,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.16566513776779174,
|
|
"num_tokens": 21773663.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.627205228805542,
|
|
"epoch": 0.9520137880986937,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004916638272128301,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.16785551458597184,
|
|
"num_tokens": 21784265.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.554153251647949,
|
|
"epoch": 0.9524673439767779,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004916550991331777,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.17339823246002198,
|
|
"num_tokens": 21795056.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.578380060195923,
|
|
"epoch": 0.9529208998548622,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004916463665730427,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.16940593868494033,
|
|
"num_tokens": 21806204.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.603130865097046,
|
|
"epoch": 0.9533744557329463,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004916376295326057,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.16669130325317383,
|
|
"num_tokens": 21816993.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.5685646533966064,
|
|
"epoch": 0.9538280116110305,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004916288880120472,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.17768334001302719,
|
|
"num_tokens": 21827457.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.594205617904663,
|
|
"epoch": 0.9542815674891146,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004916201420115482,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.16775002628564833,
|
|
"num_tokens": 21837555.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.697423982620239,
|
|
"epoch": 0.9547351233671988,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004916113915312895,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.17421349436044692,
|
|
"num_tokens": 21847074.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.668843555450439,
|
|
"epoch": 0.9551886792452831,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004916026365714519,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.16593135595321656,
|
|
"num_tokens": 21858333.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.541938638687133,
|
|
"epoch": 0.9556422351233672,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004915938771322165,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.16816020756959915,
|
|
"num_tokens": 21869132.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.560562515258789,
|
|
"epoch": 0.9560957910014514,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004915851132137646,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.16549153625965118,
|
|
"num_tokens": 21879153.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.666241884231567,
|
|
"epoch": 0.9565493468795355,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004915763448162774,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.17085392624139786,
|
|
"num_tokens": 21889063.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.685885953903198,
|
|
"epoch": 0.9570029027576198,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004915675719399362,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.16560063809156417,
|
|
"num_tokens": 21899005.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.639123916625977,
|
|
"epoch": 0.9574564586357039,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004915587945849225,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.17045865058898926,
|
|
"num_tokens": 21908391.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.613085746765137,
|
|
"epoch": 0.9579100145137881,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004915500127514176,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1698034629225731,
|
|
"num_tokens": 21917655.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.7150092124938965,
|
|
"epoch": 0.9583635703918723,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004915412264396034,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.1664179176092148,
|
|
"num_tokens": 21928038.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.629287338256836,
|
|
"epoch": 0.9588171262699564,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004915324356496613,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.1750314638018608,
|
|
"num_tokens": 21938106.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.575638914108277,
|
|
"epoch": 0.9592706821480407,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.0004915236403817733,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.17556844651699066,
|
|
"num_tokens": 21947484.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.603404188156128,
|
|
"epoch": 0.9597242380261248,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004915148406361213,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.1709429606795311,
|
|
"num_tokens": 21957139.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.618351602554322,
|
|
"epoch": 0.960177793904209,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004915060364128872,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.16406761407852172,
|
|
"num_tokens": 21967030.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.593357563018799,
|
|
"epoch": 0.9606313497822931,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004914972277122532,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1659909650683403,
|
|
"num_tokens": 21976418.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.595254135131836,
|
|
"epoch": 0.9610849056603774,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004914884145344012,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17377042919397354,
|
|
"num_tokens": 21987284.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.500611209869385,
|
|
"epoch": 0.9615384615384616,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004914795968795137,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.17092138677835464,
|
|
"num_tokens": 21997106.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.594227981567383,
|
|
"epoch": 0.9619920174165457,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004914707747477728,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.17086504995822907,
|
|
"num_tokens": 22007589.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.621239805221558,
|
|
"epoch": 0.9624455732946299,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914619481393613,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.16725393682718276,
|
|
"num_tokens": 22017669.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.732152843475342,
|
|
"epoch": 0.962899129172714,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004914531170544615,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.16082653999328614,
|
|
"num_tokens": 22029330.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.58074631690979,
|
|
"epoch": 0.9633526850507983,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004914442814932561,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.16925872266292571,
|
|
"num_tokens": 22039877.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.604477071762085,
|
|
"epoch": 0.9638062409288825,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004914354414559278,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.17077770978212356,
|
|
"num_tokens": 22049579.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.504826402664184,
|
|
"epoch": 0.9642597968069666,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004914265969426594,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.1832723319530487,
|
|
"num_tokens": 22059608.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.55698938369751,
|
|
"epoch": 0.9647133526850508,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004914177479536338,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.16628993898630143,
|
|
"num_tokens": 22070036.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.5715710639953615,
|
|
"epoch": 0.965166908563135,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000491408894489034,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.16512693017721175,
|
|
"num_tokens": 22080679.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.610262632369995,
|
|
"epoch": 0.9656204644412192,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004914000365490432,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.1728259280323982,
|
|
"num_tokens": 22092192.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.620035028457641,
|
|
"epoch": 0.9660740203193033,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004913911741338445,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.1626466490328312,
|
|
"num_tokens": 22102722.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.625868129730224,
|
|
"epoch": 0.9665275761973875,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004913823072436211,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17529655545949935,
|
|
"num_tokens": 22113521.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.64664397239685,
|
|
"epoch": 0.9669811320754716,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004913734358785565,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.16819260120391846,
|
|
"num_tokens": 22124891.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.53647198677063,
|
|
"epoch": 0.9674346879535559,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004913645600388341,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.1639208272099495,
|
|
"num_tokens": 22135972.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.657358455657959,
|
|
"epoch": 0.9678882438316401,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004913556797246374,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.15633328408002853,
|
|
"num_tokens": 22146623.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.737673711776734,
|
|
"epoch": 0.9683417997097242,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004913467949361503,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.1660117581486702,
|
|
"num_tokens": 22157619.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.6835862159729,
|
|
"epoch": 0.9687953555878084,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004913379056735561,
|
|
"loss": 5.4414,
|
|
"mean_token_accuracy": 0.16401823461055756,
|
|
"num_tokens": 22168655.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.6037169933319095,
|
|
"epoch": 0.9692489114658926,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000491329011937039,
|
|
"loss": 5.4783,
|
|
"mean_token_accuracy": 0.16528795212507247,
|
|
"num_tokens": 22178500.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.677508354187012,
|
|
"epoch": 0.9697024673439768,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004913201137267828,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.16165651381015778,
|
|
"num_tokens": 22188873.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.586783695220947,
|
|
"epoch": 0.970156023222061,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004913112110429715,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.1676276743412018,
|
|
"num_tokens": 22199743.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.557729578018188,
|
|
"epoch": 0.9706095791001451,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004913023038857892,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.17372817248106004,
|
|
"num_tokens": 22210301.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.558896493911743,
|
|
"epoch": 0.9710631349782293,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004912933922554203,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.17335860878229142,
|
|
"num_tokens": 22220771.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.609603786468506,
|
|
"epoch": 0.9715166908563135,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004912844761520487,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.16578324362635613,
|
|
"num_tokens": 22231100.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.63015341758728,
|
|
"epoch": 0.9719702467343977,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004912755555758592,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.16642088890075685,
|
|
"num_tokens": 22240997.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.607190656661987,
|
|
"epoch": 0.9724238026124818,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000491266630527036,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.16432343423366547,
|
|
"num_tokens": 22251795.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.6826615810394285,
|
|
"epoch": 0.972877358490566,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004912577010057638,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.16548267304897307,
|
|
"num_tokens": 22262465.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.744708251953125,
|
|
"epoch": 0.9733309143686503,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004912487670122273,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.16162458509206773,
|
|
"num_tokens": 22272399.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.687432813644409,
|
|
"epoch": 0.9737844702467344,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004912398285466111,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.16217903792858124,
|
|
"num_tokens": 22282545.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.626268434524536,
|
|
"epoch": 0.9742380261248186,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004912308856091002,
|
|
"loss": 5.4557,
|
|
"mean_token_accuracy": 0.16961072236299515,
|
|
"num_tokens": 22293154.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.633498001098633,
|
|
"epoch": 0.9746915820029027,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004912219381998795,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.17631157487630844,
|
|
"num_tokens": 22302309.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.608208513259887,
|
|
"epoch": 0.9751451378809869,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004912129863191339,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.15686720460653306,
|
|
"num_tokens": 22312316.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.652306604385376,
|
|
"epoch": 0.9755986937590712,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004912040299670487,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.16555508375167846,
|
|
"num_tokens": 22322387.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.691938161849976,
|
|
"epoch": 0.9760522496371553,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004911950691438091,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.1755552962422371,
|
|
"num_tokens": 22332759.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.665207719802856,
|
|
"epoch": 0.9765058055152395,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004911861038496004,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.16096826121211052,
|
|
"num_tokens": 22344056.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.541015195846557,
|
|
"epoch": 0.9769593613933236,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004911771340846079,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.16349495202302933,
|
|
"num_tokens": 22353877.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.6556745052337645,
|
|
"epoch": 0.9774129172714079,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004911681598490172,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.1672011524438858,
|
|
"num_tokens": 22363549.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.737138319015503,
|
|
"epoch": 0.977866473149492,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004911591811430139,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.1661311835050583,
|
|
"num_tokens": 22374040.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.660326099395752,
|
|
"epoch": 0.9783200290275762,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004911501979667836,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.16359687969088554,
|
|
"num_tokens": 22384819.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.646378850936889,
|
|
"epoch": 0.9787735849056604,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004911412103205122,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.1688998430967331,
|
|
"num_tokens": 22395130.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.616553831100464,
|
|
"epoch": 0.9792271407837445,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004911322182043855,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.1648877426981926,
|
|
"num_tokens": 22405093.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.657214879989624,
|
|
"epoch": 0.9796806966618288,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004911232216185893,
|
|
"loss": 5.4734,
|
|
"mean_token_accuracy": 0.16335293501615525,
|
|
"num_tokens": 22415008.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.672890996932983,
|
|
"epoch": 0.9801342525399129,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004911142205633099,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.16531921476125716,
|
|
"num_tokens": 22426486.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.619123888015747,
|
|
"epoch": 0.9805878084179971,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004911052150387334,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.16570301055908204,
|
|
"num_tokens": 22436844.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.696360635757446,
|
|
"epoch": 0.9810413642960812,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004910962050450458,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.1659548982977867,
|
|
"num_tokens": 22446630.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.66130223274231,
|
|
"epoch": 0.9814949201741655,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004910871905824338,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.17135941237211227,
|
|
"num_tokens": 22456406.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.541624641418457,
|
|
"epoch": 0.9819484760522497,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004910781716510837,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.1720363527536392,
|
|
"num_tokens": 22466210.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.620612621307373,
|
|
"epoch": 0.9824020319303338,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004910691482511817,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16932221949100495,
|
|
"num_tokens": 22476978.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.7275959014892575,
|
|
"epoch": 0.982855587808418,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004910601203829148,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.1642207011580467,
|
|
"num_tokens": 22488613.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.5737100601196286,
|
|
"epoch": 0.9833091436865021,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004910510880464696,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.17655791491270065,
|
|
"num_tokens": 22498312.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.546988391876221,
|
|
"epoch": 0.9837626995645864,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004910420512420327,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.16846197545528413,
|
|
"num_tokens": 22508131.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.67532377243042,
|
|
"epoch": 0.9842162554426706,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004910330099697913,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.17251691222190857,
|
|
"num_tokens": 22517842.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.655220031738281,
|
|
"epoch": 0.9846698113207547,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004910239642299321,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.1687016546726227,
|
|
"num_tokens": 22528239.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.625150299072265,
|
|
"epoch": 0.9851233671988389,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004910149140226422,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.16798526495695115,
|
|
"num_tokens": 22539734.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.620212841033935,
|
|
"epoch": 0.9855769230769231,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004910058593481089,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.17239609360694885,
|
|
"num_tokens": 22549796.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.554531002044678,
|
|
"epoch": 0.9860304789550073,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004909968002065195,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.17158298045396805,
|
|
"num_tokens": 22559934.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.662750625610352,
|
|
"epoch": 0.9864840348330914,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000490987736598061,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.15988094210624695,
|
|
"num_tokens": 22569864.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.611508750915528,
|
|
"epoch": 0.9869375907111756,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004909786685229211,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.17335709184408188,
|
|
"num_tokens": 22580687.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.648767518997192,
|
|
"epoch": 0.9873911465892597,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004909695959812875,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.16742359101772308,
|
|
"num_tokens": 22590507.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.681576299667358,
|
|
"epoch": 0.987844702467344,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004909605189733474,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.16965399086475372,
|
|
"num_tokens": 22601901.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.578258848190307,
|
|
"epoch": 0.9882982583454282,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004909514374992889,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.1665840521454811,
|
|
"num_tokens": 22613003.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.582123470306397,
|
|
"epoch": 0.9887518142235123,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004909423515592996,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.17244535386562349,
|
|
"num_tokens": 22623401.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.639914417266846,
|
|
"epoch": 0.9892053701015965,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004909332611535675,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.1673109322786331,
|
|
"num_tokens": 22633147.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.634562587738037,
|
|
"epoch": 0.9896589259796807,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004909241662822804,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.18473917990922928,
|
|
"num_tokens": 22642990.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.662867212295533,
|
|
"epoch": 0.9901124818577649,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004909150669456265,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.16324340552091599,
|
|
"num_tokens": 22652734.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.61931586265564,
|
|
"epoch": 0.9905660377358491,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000490905963143794,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1586074098944664,
|
|
"num_tokens": 22662968.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.570623779296875,
|
|
"epoch": 0.9910195936139332,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004908968548769713,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.17906321883201598,
|
|
"num_tokens": 22673157.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.661365270614624,
|
|
"epoch": 0.9914731494920174,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004908877421453466,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.16541301161050798,
|
|
"num_tokens": 22683105.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.677806234359741,
|
|
"epoch": 0.9919267053701016,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004908786249491082,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.1736716389656067,
|
|
"num_tokens": 22693793.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.736819887161255,
|
|
"epoch": 0.9923802612481858,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000490869503288445,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.16935908496379853,
|
|
"num_tokens": 22703884.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.64982419013977,
|
|
"epoch": 0.99283381712627,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004908603771635454,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.1698847383260727,
|
|
"num_tokens": 22713699.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.6703019618988035,
|
|
"epoch": 0.9932873730043541,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004908512465745982,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1739519238471985,
|
|
"num_tokens": 22722871.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.618347883224487,
|
|
"epoch": 0.9937409288824384,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004908421115217922,
|
|
"loss": 5.3935,
|
|
"mean_token_accuracy": 0.1663510337471962,
|
|
"num_tokens": 22733314.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.541477346420288,
|
|
"epoch": 0.9941944847605225,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004908329720053164,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.1778403714299202,
|
|
"num_tokens": 22743255.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.504152488708496,
|
|
"epoch": 0.9946480406386067,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004908238280253597,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.17440174520015717,
|
|
"num_tokens": 22753857.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.617768621444702,
|
|
"epoch": 0.9951015965166908,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004908146795821112,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.166821451485157,
|
|
"num_tokens": 22764326.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.653025674819946,
|
|
"epoch": 0.995555152394775,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004908055266757602,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.1688439816236496,
|
|
"num_tokens": 22774958.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.584131574630737,
|
|
"epoch": 0.9960087082728593,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004907963693064958,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.16801189184188842,
|
|
"num_tokens": 22785616.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.6416544914245605,
|
|
"epoch": 0.9964622641509434,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004907872074745075,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.1628538802266121,
|
|
"num_tokens": 22795967.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.594269466400147,
|
|
"epoch": 0.9969158200290276,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004907780411799849,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.16120059192180633,
|
|
"num_tokens": 22806335.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.702027273178101,
|
|
"epoch": 0.9973693759071117,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004907688704231173,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.1731191873550415,
|
|
"num_tokens": 22816390.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.7088724136352536,
|
|
"epoch": 0.997822931785196,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004907596952040945,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.1675207257270813,
|
|
"num_tokens": 22826395.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.679268312454224,
|
|
"epoch": 0.9982764876632801,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004907505155231063,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.16937604695558547,
|
|
"num_tokens": 22836790.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.599216890335083,
|
|
"epoch": 0.9987300435413643,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004907413313803424,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.16755914837121963,
|
|
"num_tokens": 22846687.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.633000278472901,
|
|
"epoch": 0.9991835994194485,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004907321427759928,
|
|
"loss": 5.4314,
|
|
"mean_token_accuracy": 0.17038674354553224,
|
|
"num_tokens": 22857208.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.656092023849487,
|
|
"epoch": 0.9996371552975326,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004907229497102475,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.16008800864219666,
|
|
"num_tokens": 22868556.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.639604282379151,
|
|
"epoch": 1.0000907111756168,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004907137521832966,
|
|
"loss": 5.505,
|
|
"mean_token_accuracy": 0.16944388896226883,
|
|
"num_tokens": 22880081.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.6398672580719,
|
|
"epoch": 1.000544267053701,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004907045501953304,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.1732504278421402,
|
|
"num_tokens": 22892141.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.637064456939697,
|
|
"epoch": 1.0009978229317853,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000490695343746539,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.1710570126771927,
|
|
"num_tokens": 22902688.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.497150611877442,
|
|
"epoch": 1.0014513788098693,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004906861328371131,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.17424043715000154,
|
|
"num_tokens": 22912453.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.631495571136474,
|
|
"epoch": 1.0019049346879536,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004906769174672429,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.16529137939214705,
|
|
"num_tokens": 22923167.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.729016590118408,
|
|
"epoch": 1.0023584905660377,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000490667697637119,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.16472474336624146,
|
|
"num_tokens": 22934753.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.587201690673828,
|
|
"epoch": 1.002812046444122,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004906584733469324,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17595323026180268,
|
|
"num_tokens": 22945277.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.613748550415039,
|
|
"epoch": 1.0032656023222062,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004906492445968735,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.16204020231962205,
|
|
"num_tokens": 22955797.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.683445882797241,
|
|
"epoch": 1.0037191582002902,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004906400113871332,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.16932731568813325,
|
|
"num_tokens": 22965969.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.689712619781494,
|
|
"epoch": 1.0041727140783745,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004906307737179026,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.17712394148111343,
|
|
"num_tokens": 22975323.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.61050066947937,
|
|
"epoch": 1.0046262699564585,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004906215315893726,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.17275502830743789,
|
|
"num_tokens": 22985063.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.614771890640259,
|
|
"epoch": 1.0050798258345428,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004906122850017344,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.1602733001112938,
|
|
"num_tokens": 22996001.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.636023378372192,
|
|
"epoch": 1.005533381712627,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004906030339551792,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.1702730357646942,
|
|
"num_tokens": 23006896.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.630139017105103,
|
|
"epoch": 1.0059869375907111,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004905937784498983,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.17295269072055816,
|
|
"num_tokens": 23017080.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.649996185302735,
|
|
"epoch": 1.0064404934687954,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 0.0004905845184860831,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.1737719804048538,
|
|
"num_tokens": 23027168.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.61572232246399,
|
|
"epoch": 1.0068940493468794,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004905752540639252,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.16635738760232927,
|
|
"num_tokens": 23037364.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.531828784942627,
|
|
"epoch": 1.0073476052249637,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004905659851836161,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17861230075359344,
|
|
"num_tokens": 23047609.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.608002805709839,
|
|
"epoch": 1.007801161103048,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004905567118453475,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.17069784104824065,
|
|
"num_tokens": 23057942.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.608658170700073,
|
|
"epoch": 1.008254716981132,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004905474340493111,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.17128928005695343,
|
|
"num_tokens": 23069119.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.557733488082886,
|
|
"epoch": 1.0087082728592163,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004905381517956988,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.1733451947569847,
|
|
"num_tokens": 23080060.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.568910789489746,
|
|
"epoch": 1.0091618287373005,
|
|
"grad_norm": 6.4375,
|
|
"learning_rate": 0.0004905288650847027,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.16494861245155334,
|
|
"num_tokens": 23090645.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.657036018371582,
|
|
"epoch": 1.0096153846153846,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004905195739165146,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.16976771950721742,
|
|
"num_tokens": 23100449.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.637253189086914,
|
|
"epoch": 1.0100689404934688,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000490510278291327,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.1682575449347496,
|
|
"num_tokens": 23110415.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.54347448348999,
|
|
"epoch": 1.010522496371553,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004905009782093318,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.1727476641535759,
|
|
"num_tokens": 23120336.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.569380283355713,
|
|
"epoch": 1.0109760522496372,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004904916736707214,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.1605848491191864,
|
|
"num_tokens": 23130568.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.645925760269165,
|
|
"epoch": 1.0114296081277214,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004904823646756885,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.16973509043455123,
|
|
"num_tokens": 23140080.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.605403327941895,
|
|
"epoch": 1.0118831640058055,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004904730512244252,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.17408903390169145,
|
|
"num_tokens": 23150360.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.547512102127075,
|
|
"epoch": 1.0123367198838897,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004904637333171243,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.16765036731958388,
|
|
"num_tokens": 23160620.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.625001668930054,
|
|
"epoch": 1.0127902757619738,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004904544109539785,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.17393511682748794,
|
|
"num_tokens": 23171920.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.6038806438446045,
|
|
"epoch": 1.013243831640058,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004904450841351805,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.17274330407381058,
|
|
"num_tokens": 23182929.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.6337761878967285,
|
|
"epoch": 1.0136973875181423,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004904357528609236,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.1682947263121605,
|
|
"num_tokens": 23193020.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.560843801498413,
|
|
"epoch": 1.0141509433962264,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004904264171314,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17510967701673508,
|
|
"num_tokens": 23204073.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.544686508178711,
|
|
"epoch": 1.0146044992743106,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004904170769468035,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.16796393543481827,
|
|
"num_tokens": 23214376.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.650951957702636,
|
|
"epoch": 1.0150580551523947,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004904077323073268,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.16763273030519485,
|
|
"num_tokens": 23224304.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.610902404785156,
|
|
"epoch": 1.015511611030479,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004903983832131633,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.16713034361600876,
|
|
"num_tokens": 23235324.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.605709981918335,
|
|
"epoch": 1.0159651669085632,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004903890296645063,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.1695600464940071,
|
|
"num_tokens": 23245774.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.634368467330932,
|
|
"epoch": 1.0164187227866472,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004903796716615495,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.16800456941127778,
|
|
"num_tokens": 23256274.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.590472078323364,
|
|
"epoch": 1.0168722786647315,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004903703092044861,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.16843401342630387,
|
|
"num_tokens": 23266304.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.500264310836792,
|
|
"epoch": 1.0173258345428158,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004903609422935097,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.17742429822683334,
|
|
"num_tokens": 23276552.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.577713441848755,
|
|
"epoch": 1.0177793904208998,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004903515709288143,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.16179130971431732,
|
|
"num_tokens": 23287799.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.572709417343139,
|
|
"epoch": 1.018232946298984,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004903421951105933,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.17750613689422606,
|
|
"num_tokens": 23297958.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.593379259109497,
|
|
"epoch": 1.0186865021770681,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004903328148390411,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16655783653259276,
|
|
"num_tokens": 23307523.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.576770782470703,
|
|
"epoch": 1.0191400580551524,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004903234301143513,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.17188440263271332,
|
|
"num_tokens": 23317970.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.5847412109375,
|
|
"epoch": 1.0195936139332367,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004903140409367181,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17394014745950698,
|
|
"num_tokens": 23328612.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.572464323043823,
|
|
"epoch": 1.0200471698113207,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004903046473063357,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.17184139490127565,
|
|
"num_tokens": 23338104.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.6089866161346436,
|
|
"epoch": 1.020500725689405,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004902952492233983,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.18489170372486113,
|
|
"num_tokens": 23348105.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.556183958053589,
|
|
"epoch": 1.020954281567489,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004902858466881002,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.17444435209035875,
|
|
"num_tokens": 23357150.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.600876045227051,
|
|
"epoch": 1.0214078374455733,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000490276439700636,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.17182350754737855,
|
|
"num_tokens": 23367223.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.600956726074219,
|
|
"epoch": 1.0218613933236576,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004902670282612002,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.1688934974372387,
|
|
"num_tokens": 23377664.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.52209243774414,
|
|
"epoch": 1.0223149492017416,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004902576123699873,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.1766052410006523,
|
|
"num_tokens": 23388057.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.466941595077515,
|
|
"epoch": 1.0227685050798259,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004902481920271922,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.17293768748641014,
|
|
"num_tokens": 23397808.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.534582138061523,
|
|
"epoch": 1.02322206095791,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004902387672330097,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.17146763652563096,
|
|
"num_tokens": 23406979.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.599915313720703,
|
|
"epoch": 1.0236756168359942,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004902293379876345,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.1721256121993065,
|
|
"num_tokens": 23416545.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.600649118423462,
|
|
"epoch": 1.0241291727140784,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004902199042912618,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.16481490582227706,
|
|
"num_tokens": 23427464.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.6426581859588625,
|
|
"epoch": 1.0245827285921625,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004902104661440868,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.1715350404381752,
|
|
"num_tokens": 23436690.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.587870264053345,
|
|
"epoch": 1.0250362844702468,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004902010235463042,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.17325413078069687,
|
|
"num_tokens": 23446701.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.644993925094605,
|
|
"epoch": 1.025489840348331,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004901915764981098,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.16523970365524293,
|
|
"num_tokens": 23456966.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.623632907867432,
|
|
"epoch": 1.025943396226415,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004901821249996988,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.17261502742767335,
|
|
"num_tokens": 23467300.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.639683961868286,
|
|
"epoch": 1.0263969521044993,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004901726690512665,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.1675952449440956,
|
|
"num_tokens": 23478457.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.6091742515563965,
|
|
"epoch": 1.0268505079825834,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004901632086530087,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.1715937301516533,
|
|
"num_tokens": 23488066.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.596414279937744,
|
|
"epoch": 1.0273040638606676,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004901537438051207,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.1635369509458542,
|
|
"num_tokens": 23498856.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.591539669036865,
|
|
"epoch": 1.027757619738752,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004901442745077986,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.1709854334592819,
|
|
"num_tokens": 23509845.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.6809183120727536,
|
|
"epoch": 1.028211175616836,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004901348007612381,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.16896604150533676,
|
|
"num_tokens": 23520322.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.678867530822754,
|
|
"epoch": 1.0286647314949202,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004901253225656351,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.17234744727611542,
|
|
"num_tokens": 23530030.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.676992511749267,
|
|
"epoch": 1.0291182873730043,
|
|
"grad_norm": 16.125,
|
|
"learning_rate": 0.0004901158399211855,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.17008337378501892,
|
|
"num_tokens": 23541063.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.572519445419312,
|
|
"epoch": 1.0295718432510885,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004901063528280856,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.16454305946826936,
|
|
"num_tokens": 23551693.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.64924726486206,
|
|
"epoch": 1.0300253991291728,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004900968612865314,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.17524353563785552,
|
|
"num_tokens": 23561758.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.573123121261597,
|
|
"epoch": 1.0304789550072568,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004900873652967195,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.16829973012208937,
|
|
"num_tokens": 23571912.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.592647314071655,
|
|
"epoch": 1.030932510885341,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004900778648588459,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1677442193031311,
|
|
"num_tokens": 23582600.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.618772172927857,
|
|
"epoch": 1.0313860667634251,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004900683599731073,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.17848899364471435,
|
|
"num_tokens": 23592761.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.710945415496826,
|
|
"epoch": 1.0318396226415094,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004900588506397002,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.17176624089479448,
|
|
"num_tokens": 23603119.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.533707857131958,
|
|
"epoch": 1.0322931785195937,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004900493368588213,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.1732027918100357,
|
|
"num_tokens": 23613916.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.600461626052857,
|
|
"epoch": 1.0327467343976777,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004900398186306672,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.16654439717531205,
|
|
"num_tokens": 23623956.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.6156196117401125,
|
|
"epoch": 1.033200290275762,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000490030295955435,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.16991166919469833,
|
|
"num_tokens": 23634666.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.598365688323975,
|
|
"epoch": 1.0336538461538463,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004900207688333215,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.16624072343111038,
|
|
"num_tokens": 23645601.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.633153963088989,
|
|
"epoch": 1.0341074020319303,
|
|
"grad_norm": 5.84375,
|
|
"learning_rate": 0.0004900112372645236,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.17123257666826247,
|
|
"num_tokens": 23656339.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.604528951644897,
|
|
"epoch": 1.0345609579100146,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004900017012492386,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.17367076873779297,
|
|
"num_tokens": 23667433.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.644150257110596,
|
|
"epoch": 1.0350145137880986,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004899921607876634,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16625724285840987,
|
|
"num_tokens": 23678186.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.614169263839722,
|
|
"epoch": 1.0354680696661829,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004899826158799958,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.1678687408566475,
|
|
"num_tokens": 23688317.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.572248554229736,
|
|
"epoch": 1.0359216255442671,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004899730665264328,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.1699757918715477,
|
|
"num_tokens": 23697752.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.4876162052154545,
|
|
"epoch": 1.0363751814223512,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004899635127271721,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.1753618225455284,
|
|
"num_tokens": 23707803.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.552979755401611,
|
|
"epoch": 1.0368287373004355,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004899539544824111,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.17673207223415374,
|
|
"num_tokens": 23717630.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.65933198928833,
|
|
"epoch": 1.0372822931785195,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004899443917923476,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.16775544807314874,
|
|
"num_tokens": 23728836.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.553336429595947,
|
|
"epoch": 1.0377358490566038,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004899348246571792,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.16835874766111375,
|
|
"num_tokens": 23740145.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.576502132415771,
|
|
"epoch": 1.038189404934688,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000489925253077104,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.1710005670785904,
|
|
"num_tokens": 23751162.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.638379001617432,
|
|
"epoch": 1.038642960812772,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004899156770523196,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.16817111074924468,
|
|
"num_tokens": 23761634.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.633851337432861,
|
|
"epoch": 1.0390965166908563,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004899060965830244,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.17330029457807541,
|
|
"num_tokens": 23772483.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.59468264579773,
|
|
"epoch": 1.0395500725689404,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004898965116694162,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.1680698201060295,
|
|
"num_tokens": 23782298.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.569092273712158,
|
|
"epoch": 1.0400036284470247,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004898869223116935,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.16889462172985076,
|
|
"num_tokens": 23792492.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.699532079696655,
|
|
"epoch": 1.040457184325109,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004898773285100546,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.1637313649058342,
|
|
"num_tokens": 23802999.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.603556537628174,
|
|
"epoch": 1.040910740203193,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004898677302646975,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.1761540174484253,
|
|
"num_tokens": 23812541.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.5463886737823485,
|
|
"epoch": 1.0413642960812772,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004898581275758211,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.16390567123889924,
|
|
"num_tokens": 23823244.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.54480562210083,
|
|
"epoch": 1.0418178519593615,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004898485204436239,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.17889072000980377,
|
|
"num_tokens": 23832346.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.650099802017212,
|
|
"epoch": 1.0422714078374455,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004898389088683047,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.17537481784820558,
|
|
"num_tokens": 23842554.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.580894851684571,
|
|
"epoch": 1.0427249637155298,
|
|
"grad_norm": 3.890625,
|
|
"learning_rate": 0.0004898292928500619,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.17736405432224273,
|
|
"num_tokens": 23852938.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.598966026306153,
|
|
"epoch": 1.0431785195936139,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004898196723890947,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.17443305552005767,
|
|
"num_tokens": 23862367.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.558216524124146,
|
|
"epoch": 1.0436320754716981,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004898100474856019,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.17014889568090438,
|
|
"num_tokens": 23873249.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.5902259349823,
|
|
"epoch": 1.0440856313497824,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004898004181397824,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.16259795129299165,
|
|
"num_tokens": 23883830.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.622036981582641,
|
|
"epoch": 1.0445391872278664,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004897907843518358,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.17028684467077254,
|
|
"num_tokens": 23894359.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.569010543823242,
|
|
"epoch": 1.0449927431059507,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004897811461219609,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.17068181782960892,
|
|
"num_tokens": 23903779.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.6016926765441895,
|
|
"epoch": 1.0454462989840347,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004897715034503571,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.16589456498622895,
|
|
"num_tokens": 23914523.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.55782413482666,
|
|
"epoch": 1.045899854862119,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000489761856337224,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.17274439632892608,
|
|
"num_tokens": 23924996.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.594377183914185,
|
|
"epoch": 1.0463534107402033,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004897522047827609,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.1750901833176613,
|
|
"num_tokens": 23935843.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.613669109344483,
|
|
"epoch": 1.0468069666182873,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004897425487871676,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.1711737558245659,
|
|
"num_tokens": 23945044.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.5151208400726315,
|
|
"epoch": 1.0472605224963716,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004897328883506436,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.16891540288925172,
|
|
"num_tokens": 23955933.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.636126756668091,
|
|
"epoch": 1.0477140783744556,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004897232234733887,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.16608502417802812,
|
|
"num_tokens": 23966320.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.627421760559082,
|
|
"epoch": 1.04816763425254,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004897135541556028,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.17145986109972,
|
|
"num_tokens": 23976233.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.628482675552368,
|
|
"epoch": 1.0486211901306242,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.000489703880397486,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.17113422602415085,
|
|
"num_tokens": 23987854.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.56703929901123,
|
|
"epoch": 1.0490747460087082,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004896942021992382,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1662612795829773,
|
|
"num_tokens": 23997973.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.584162759780884,
|
|
"epoch": 1.0495283018867925,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004896845195610595,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.1711257964372635,
|
|
"num_tokens": 24007313.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.626845645904541,
|
|
"epoch": 1.0499818577648767,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004896748324831504,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.1633000910282135,
|
|
"num_tokens": 24018254.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.651694965362549,
|
|
"epoch": 1.0504354136429608,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004896651409657109,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.16983163505792617,
|
|
"num_tokens": 24029799.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.550058126449585,
|
|
"epoch": 1.050888969521045,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004896554450089417,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.17730078995227813,
|
|
"num_tokens": 24040972.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.540880584716797,
|
|
"epoch": 1.051342525399129,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004896457446130431,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.17580059617757798,
|
|
"num_tokens": 24050781.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.529133701324463,
|
|
"epoch": 1.0517960812772134,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004896360397782159,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.16468161195516587,
|
|
"num_tokens": 24060184.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.647056913375854,
|
|
"epoch": 1.0522496371552976,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004896263305046607,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.1736113965511322,
|
|
"num_tokens": 24070777.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.654244089126587,
|
|
"epoch": 1.0527031930333817,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004896166167925782,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.16724486500024796,
|
|
"num_tokens": 24080878.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.6524169921875,
|
|
"epoch": 1.053156748911466,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004896068986421693,
|
|
"loss": 5.3879,
|
|
"mean_token_accuracy": 0.17224199324846268,
|
|
"num_tokens": 24090038.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.6196681499481205,
|
|
"epoch": 1.05361030478955,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004895971760536351,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.17333686649799346,
|
|
"num_tokens": 24100425.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.627913570404052,
|
|
"epoch": 1.0540638606676342,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004895874490271768,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.16355858445167543,
|
|
"num_tokens": 24112182.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.603630542755127,
|
|
"epoch": 1.0545174165457185,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004895777175629952,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.17166843712329866,
|
|
"num_tokens": 24122182.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.614436769485474,
|
|
"epoch": 1.0549709724238026,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004895679816612917,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17125269323587416,
|
|
"num_tokens": 24131930.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.65815486907959,
|
|
"epoch": 1.0554245283018868,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004895582413222678,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.18034985512495041,
|
|
"num_tokens": 24141575.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.679404544830322,
|
|
"epoch": 1.0558780841799709,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004895484965461247,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.16713959127664565,
|
|
"num_tokens": 24151720.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.5869152545928955,
|
|
"epoch": 1.0563316400580551,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000489538747333064,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.17306092977523804,
|
|
"num_tokens": 24161881.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.538717746734619,
|
|
"epoch": 1.0567851959361394,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004895289936832874,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.17443083673715593,
|
|
"num_tokens": 24171474.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.6506819248199465,
|
|
"epoch": 1.0572387518142234,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004895192355969966,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1692167952656746,
|
|
"num_tokens": 24182186.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.636696863174438,
|
|
"epoch": 1.0576923076923077,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004895094730743932,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.17387636750936508,
|
|
"num_tokens": 24192318.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.633651304244995,
|
|
"epoch": 1.058145863570392,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004894997061156793,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.1694432780146599,
|
|
"num_tokens": 24202918.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.5955101490020756,
|
|
"epoch": 1.058599419448476,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004894899347210567,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.17389714866876602,
|
|
"num_tokens": 24213218.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.598051071166992,
|
|
"epoch": 1.0590529753265603,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004894801588907278,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.17599815875291824,
|
|
"num_tokens": 24223229.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.652417850494385,
|
|
"epoch": 1.0595065312046443,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004894703786248944,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.1630527600646019,
|
|
"num_tokens": 24233637.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.634524631500244,
|
|
"epoch": 1.0599600870827286,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000489460593923759,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.17403268963098525,
|
|
"num_tokens": 24244251.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.592057085037231,
|
|
"epoch": 1.0604136429608129,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004894508047875237,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.1699887201189995,
|
|
"num_tokens": 24254380.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.460594224929809,
|
|
"epoch": 1.060867198838897,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004894410112163913,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.1714046984910965,
|
|
"num_tokens": 24264841.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.500969696044922,
|
|
"epoch": 1.0613207547169812,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004894312132105641,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17383984178304673,
|
|
"num_tokens": 24274383.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.636331558227539,
|
|
"epoch": 1.0617743105950652,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004894214107702447,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.16789450645446777,
|
|
"num_tokens": 24284140.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.7018595218658445,
|
|
"epoch": 1.0622278664731495,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000489411603895636,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.1698828309774399,
|
|
"num_tokens": 24295044.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.641237354278564,
|
|
"epoch": 1.0626814223512338,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004894017925869406,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.17169802039861679,
|
|
"num_tokens": 24305080.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.598285913467407,
|
|
"epoch": 1.0631349782293178,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004893919768443615,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.17039976567029952,
|
|
"num_tokens": 24316306.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.482102537155152,
|
|
"epoch": 1.063588534107402,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004893821566681017,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.17302751988172532,
|
|
"num_tokens": 24326740.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.577399110794067,
|
|
"epoch": 1.0640420899854863,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004893723320583644,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.1635014906525612,
|
|
"num_tokens": 24337621.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.549607038497925,
|
|
"epoch": 1.0644956458635704,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004893625030153525,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.17473862320184708,
|
|
"num_tokens": 24347732.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.5875303745269775,
|
|
"epoch": 1.0649492017416546,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004893526695392694,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.18272399604320527,
|
|
"num_tokens": 24359173.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.5956933975219725,
|
|
"epoch": 1.0654027576197387,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004893428316303185,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.17074852734804152,
|
|
"num_tokens": 24369465.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.559246158599853,
|
|
"epoch": 1.065856313497823,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004893329892887031,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.17232367992401124,
|
|
"num_tokens": 24378899.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.540904426574707,
|
|
"epoch": 1.0663098693759072,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004893231425146271,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.165650475025177,
|
|
"num_tokens": 24388919.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.540589141845703,
|
|
"epoch": 1.0667634252539913,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004893132913082937,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.1708405449986458,
|
|
"num_tokens": 24399632.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.621877193450928,
|
|
"epoch": 1.0672169811320755,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004893034356699069,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.17433714866638184,
|
|
"num_tokens": 24410817.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.619347333908081,
|
|
"epoch": 1.0676705370101596,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004892935755996705,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.17336190938949586,
|
|
"num_tokens": 24421058.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.566294860839844,
|
|
"epoch": 1.0681240928882438,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004892837110977883,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.17225192338228226,
|
|
"num_tokens": 24431522.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.544850015640259,
|
|
"epoch": 1.068577648766328,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004892738421644644,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.1740766227245331,
|
|
"num_tokens": 24441746.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.505834913253784,
|
|
"epoch": 1.0690312046444121,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004892639687999027,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.17782359719276428,
|
|
"num_tokens": 24451916.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.546728324890137,
|
|
"epoch": 1.0694847605224964,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004892540910043076,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.1773233100771904,
|
|
"num_tokens": 24461935.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.585660028457641,
|
|
"epoch": 1.0699383164005805,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004892442087778833,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.17202629297971725,
|
|
"num_tokens": 24472437.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.589559173583984,
|
|
"epoch": 1.0703918722786647,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004892343221208342,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1752584308385849,
|
|
"num_tokens": 24481726.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.60119514465332,
|
|
"epoch": 1.070845428156749,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004892244310333646,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.1676913768053055,
|
|
"num_tokens": 24492340.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.546935272216797,
|
|
"epoch": 1.071298984034833,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004892145355156793,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1705259934067726,
|
|
"num_tokens": 24502138.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.560450696945191,
|
|
"epoch": 1.0717525399129173,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004892046355679829,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.1682853877544403,
|
|
"num_tokens": 24512723.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.604918575286865,
|
|
"epoch": 1.0722060957910013,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004891947311904799,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.16189062148332595,
|
|
"num_tokens": 24523766.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.623622941970825,
|
|
"epoch": 1.0726596516690856,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004891848223833753,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.17246003299951554,
|
|
"num_tokens": 24534571.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.653265762329101,
|
|
"epoch": 1.0731132075471699,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000489174909146874,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.17910315543413163,
|
|
"num_tokens": 24545265.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.6582252979278564,
|
|
"epoch": 1.073566763425254,
|
|
"grad_norm": 5.90625,
|
|
"learning_rate": 0.0004891649914811811,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.16662697345018387,
|
|
"num_tokens": 24555524.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.51617956161499,
|
|
"epoch": 1.0740203193033382,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004891550693865014,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.17839529514312744,
|
|
"num_tokens": 24565420.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.609707641601562,
|
|
"epoch": 1.0744738751814222,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004891451428630405,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1649378016591072,
|
|
"num_tokens": 24576794.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.624512720108032,
|
|
"epoch": 1.0749274310595065,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004891352119110033,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.17520020753145218,
|
|
"num_tokens": 24586320.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.593661451339722,
|
|
"epoch": 1.0753809869375908,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004891252765305954,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.17566470056772232,
|
|
"num_tokens": 24596524.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.621684932708741,
|
|
"epoch": 1.0758345428156748,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004891153367220222,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.17703112959861755,
|
|
"num_tokens": 24605877.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.645792245864868,
|
|
"epoch": 1.076288098693759,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004891053924854894,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.1607166647911072,
|
|
"num_tokens": 24616719.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.580338191986084,
|
|
"epoch": 1.0767416545718433,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004890954438212024,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.17941452264785768,
|
|
"num_tokens": 24626882.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.61026782989502,
|
|
"epoch": 1.0771952104499274,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004890854907293671,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.16531697511672974,
|
|
"num_tokens": 24637884.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.553039932250977,
|
|
"epoch": 1.0776487663280117,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004890755332101893,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.16965146064758302,
|
|
"num_tokens": 24647389.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.574040079116822,
|
|
"epoch": 1.0781023222060957,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004890655712638749,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.16506000161170958,
|
|
"num_tokens": 24657595.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.613958406448364,
|
|
"epoch": 1.07855587808418,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048905560489063,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.17296027392148972,
|
|
"num_tokens": 24667683.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.658120727539062,
|
|
"epoch": 1.0790094339622642,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004890456340906605,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.16448845267295836,
|
|
"num_tokens": 24678041.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.5773170471191404,
|
|
"epoch": 1.0794629898403483,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004890356588641729,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.17782746106386185,
|
|
"num_tokens": 24688569.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.594895219802856,
|
|
"epoch": 1.0799165457184325,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004890256792113733,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.1775667577981949,
|
|
"num_tokens": 24699913.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.661224460601806,
|
|
"epoch": 1.0803701015965168,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004890156951324681,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.17179592847824096,
|
|
"num_tokens": 24710682.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.72910704612732,
|
|
"epoch": 1.0808236574746009,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004890057066276636,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.1660769134759903,
|
|
"num_tokens": 24721087.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.5810271263122555,
|
|
"epoch": 1.0812772133526851,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004889957136971668,
|
|
"loss": 5.3203,
|
|
"mean_token_accuracy": 0.17739502489566802,
|
|
"num_tokens": 24731323.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.583218431472778,
|
|
"epoch": 1.0817307692307692,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000488985716341184,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.16614993065595626,
|
|
"num_tokens": 24742559.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.639229249954224,
|
|
"epoch": 1.0821843251088534,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004889757145599222,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.17185461968183519,
|
|
"num_tokens": 24752307.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.526152944564819,
|
|
"epoch": 1.0826378809869377,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000488965708353588,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.16761810183525086,
|
|
"num_tokens": 24762792.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.657108974456787,
|
|
"epoch": 1.0830914368650217,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004889556977223883,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.16339073926210404,
|
|
"num_tokens": 24774377.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.6454047679901125,
|
|
"epoch": 1.083544992743106,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004889456826665304,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.17016541510820388,
|
|
"num_tokens": 24785919.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.626445770263672,
|
|
"epoch": 1.08399854862119,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004889356631862211,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.1718483343720436,
|
|
"num_tokens": 24796594.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.576580619812011,
|
|
"epoch": 1.0844521044992743,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.000488925639281668,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.17252150028944016,
|
|
"num_tokens": 24807322.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.555296468734741,
|
|
"epoch": 1.0849056603773586,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004889156109530781,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.1731458216905594,
|
|
"num_tokens": 24817593.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.590374898910523,
|
|
"epoch": 1.0853592162554426,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004889055782006588,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.17565004229545594,
|
|
"num_tokens": 24827577.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.574050760269165,
|
|
"epoch": 1.085812772133527,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004888955410246176,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.17546096444129944,
|
|
"num_tokens": 24838148.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.567724370956421,
|
|
"epoch": 1.086266328011611,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004888854994251621,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.17895624935626983,
|
|
"num_tokens": 24848451.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.546176195144653,
|
|
"epoch": 1.0867198838896952,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004888754534025,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.1617180287837982,
|
|
"num_tokens": 24859619.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.605387496948242,
|
|
"epoch": 1.0871734397677795,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004888654029568391,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.1611100822687149,
|
|
"num_tokens": 24869863.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.651314067840576,
|
|
"epoch": 1.0876269956458635,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004888553480883871,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.16844964623451233,
|
|
"num_tokens": 24880524.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.573370265960693,
|
|
"epoch": 1.0880805515239478,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.000488845288797352,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.17795932441949844,
|
|
"num_tokens": 24891514.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.537796258926392,
|
|
"epoch": 1.0885341074020318,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004888352250839418,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.18009179681539536,
|
|
"num_tokens": 24900842.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0885341074020318,
|
|
"eval_entropy": 5.3571358324715455,
|
|
"eval_loss": 5.452709674835205,
|
|
"eval_mean_token_accuracy": 0.17524898895715696,
|
|
"eval_num_tokens": 24900842.0,
|
|
"eval_runtime": 26.4984,
|
|
"eval_samples_per_second": 1334.418,
|
|
"eval_steps_per_second": 166.802,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.507623529434204,
|
|
"epoch": 1.088987663280116,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004888251569483647,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.1762351632118225,
|
|
"num_tokens": 24911845.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.526329374313354,
|
|
"epoch": 1.0894412191582004,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004888150843908288,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.1737929806113243,
|
|
"num_tokens": 24922211.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.6169493198394775,
|
|
"epoch": 1.0898947750362844,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004888050074115426,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.16657098829746247,
|
|
"num_tokens": 24932129.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.646394968032837,
|
|
"epoch": 1.0903483309143687,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004887949260107143,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.16553286761045455,
|
|
"num_tokens": 24942869.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.553748750686646,
|
|
"epoch": 1.0908018867924527,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004887848401885524,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1705244481563568,
|
|
"num_tokens": 24952621.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.690526676177979,
|
|
"epoch": 1.091255442670537,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004887747499452656,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.15994815826416015,
|
|
"num_tokens": 24963587.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.621628618240356,
|
|
"epoch": 1.0917089985486212,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004887646552810624,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.17487196773290634,
|
|
"num_tokens": 24974122.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.610294485092163,
|
|
"epoch": 1.0921625544267053,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004887545561961517,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.175234654545784,
|
|
"num_tokens": 24985145.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.546441316604614,
|
|
"epoch": 1.0926161103047896,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004887444526907424,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.17132711559534072,
|
|
"num_tokens": 24995511.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.580210113525391,
|
|
"epoch": 1.0930696661828738,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004887343447650432,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.16668287366628648,
|
|
"num_tokens": 25006193.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.643644237518311,
|
|
"epoch": 1.0935232220609579,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004887242324192634,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.17420458793640137,
|
|
"num_tokens": 25016444.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.66413426399231,
|
|
"epoch": 1.0939767779390421,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004887141156536119,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.16439399123191833,
|
|
"num_tokens": 25027898.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.569183969497681,
|
|
"epoch": 1.0944303338171262,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004887039944682981,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.17389585971832275,
|
|
"num_tokens": 25038201.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.657640790939331,
|
|
"epoch": 1.0948838896952104,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004886938688635313,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.16164977103471756,
|
|
"num_tokens": 25048466.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.706678771972657,
|
|
"epoch": 1.0953374455732947,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004886837388395207,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.1703506514430046,
|
|
"num_tokens": 25059064.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.64215497970581,
|
|
"epoch": 1.0957910014513788,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000488673604396476,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.1606872409582138,
|
|
"num_tokens": 25068834.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.586708450317383,
|
|
"epoch": 1.096244557329463,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004886634655346067,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.162100912630558,
|
|
"num_tokens": 25080058.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.591971731185913,
|
|
"epoch": 1.0966981132075473,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004886533222541225,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.17501784563064576,
|
|
"num_tokens": 25089751.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.6128082275390625,
|
|
"epoch": 1.0971516690856313,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004886431745552331,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.17031979709863662,
|
|
"num_tokens": 25099055.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.634336948394775,
|
|
"epoch": 1.0976052249637156,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004886330224381485,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.16404568701982497,
|
|
"num_tokens": 25109793.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.648942136764527,
|
|
"epoch": 1.0980587808417996,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004886228659030785,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.170868156850338,
|
|
"num_tokens": 25119814.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.655860137939453,
|
|
"epoch": 1.098512336719884,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004886127049502331,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.16878984421491622,
|
|
"num_tokens": 25130747.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.593351268768311,
|
|
"epoch": 1.0989658925979682,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004886025395798228,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.16716485768556594,
|
|
"num_tokens": 25142235.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.505036449432373,
|
|
"epoch": 1.0994194484760522,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004885923697920573,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.17605393528938293,
|
|
"num_tokens": 25152047.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.526382112503052,
|
|
"epoch": 1.0998730043541365,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004885821955871472,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.17646963745355607,
|
|
"num_tokens": 25162678.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.637505960464478,
|
|
"epoch": 1.1003265602322205,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004885720169653028,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.17307656705379487,
|
|
"num_tokens": 25172973.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.677087020874024,
|
|
"epoch": 1.1007801161103048,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004885618339267348,
|
|
"loss": 5.4393,
|
|
"mean_token_accuracy": 0.163906592130661,
|
|
"num_tokens": 25183458.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.552436780929566,
|
|
"epoch": 1.101233671988389,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004885516464716537,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.17302643954753877,
|
|
"num_tokens": 25193827.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.6194024085998535,
|
|
"epoch": 1.101687227866473,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048854145460027,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.1634839802980423,
|
|
"num_tokens": 25204448.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.667161560058593,
|
|
"epoch": 1.1021407837445574,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004885312583127946,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.1770660623908043,
|
|
"num_tokens": 25215041.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.618182945251465,
|
|
"epoch": 1.1025943396226414,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004885210576094385,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.16552863866090775,
|
|
"num_tokens": 25225937.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.5022780418396,
|
|
"epoch": 1.1030478955007257,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004885108524904124,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.17433019280433654,
|
|
"num_tokens": 25235270.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.5538805484771725,
|
|
"epoch": 1.10350145137881,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004885006429559275,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.16601527482271194,
|
|
"num_tokens": 25247080.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.626804065704346,
|
|
"epoch": 1.103955007256894,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004884904290061949,
|
|
"loss": 5.3279,
|
|
"mean_token_accuracy": 0.16205299496650696,
|
|
"num_tokens": 25256718.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.646880435943603,
|
|
"epoch": 1.1044085631349783,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004884802106414258,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.16500043272972106,
|
|
"num_tokens": 25266632.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.603062582015991,
|
|
"epoch": 1.1048621190130623,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004884699878618316,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.17417868971824646,
|
|
"num_tokens": 25275598.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.654306173324585,
|
|
"epoch": 1.1053156748911466,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004884597606676236,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.16754518151283265,
|
|
"num_tokens": 25286598.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.577902507781983,
|
|
"epoch": 1.1057692307692308,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004884495290590134,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.1773931473493576,
|
|
"num_tokens": 25296730.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.557775259017944,
|
|
"epoch": 1.1062227866473149,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004884392930362124,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.18149112164974213,
|
|
"num_tokens": 25306326.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.612017250061035,
|
|
"epoch": 1.1066763425253991,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004884290525994326,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17338535636663438,
|
|
"num_tokens": 25316342.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.66097674369812,
|
|
"epoch": 1.1071298984034832,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004884188077488855,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.16372329443693162,
|
|
"num_tokens": 25326129.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.616948175430298,
|
|
"epoch": 1.1075834542815675,
|
|
"grad_norm": 4.375,
|
|
"learning_rate": 0.0004884085584847831,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.16632895767688752,
|
|
"num_tokens": 25337156.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.704233694076538,
|
|
"epoch": 1.1080370101596517,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004883983048073375,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.1600780501961708,
|
|
"num_tokens": 25347632.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.585485649108887,
|
|
"epoch": 1.1084905660377358,
|
|
"grad_norm": 8.5625,
|
|
"learning_rate": 0.0004883880467167603,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.17368678599596024,
|
|
"num_tokens": 25359186.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.620640993118286,
|
|
"epoch": 1.10894412191582,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.000488377784213264,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.16820335239171982,
|
|
"num_tokens": 25368993.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.585221481323242,
|
|
"epoch": 1.1093976777939043,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004883675172970608,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.16990748345851897,
|
|
"num_tokens": 25379880.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.603193998336792,
|
|
"epoch": 1.1098512336719883,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000488357245968363,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.15841159969568253,
|
|
"num_tokens": 25389942.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.587256574630738,
|
|
"epoch": 1.1103047895500726,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004883469702273829,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.17499275505542755,
|
|
"num_tokens": 25400836.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.609990501403809,
|
|
"epoch": 1.1107583454281567,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004883366900743331,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17449965476989746,
|
|
"num_tokens": 25410502.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.545148801803589,
|
|
"epoch": 1.111211901306241,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004883264055094262,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.18040893524885177,
|
|
"num_tokens": 25420301.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.57139105796814,
|
|
"epoch": 1.1116654571843252,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004883161165328749,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.16551127135753632,
|
|
"num_tokens": 25431107.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.595264530181884,
|
|
"epoch": 1.1121190130624092,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.000488305823144892,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.16993945240974426,
|
|
"num_tokens": 25441256.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.624409151077271,
|
|
"epoch": 1.1125725689404935,
|
|
"grad_norm": 5.8125,
|
|
"learning_rate": 0.0004882955253456902,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.17479237616062165,
|
|
"num_tokens": 25451627.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.656954574584961,
|
|
"epoch": 1.1130261248185778,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004882852231354826,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16552453935146333,
|
|
"num_tokens": 25461273.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.587964868545532,
|
|
"epoch": 1.1134796806966618,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004882749165144822,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.17116914242506026,
|
|
"num_tokens": 25471949.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.645139741897583,
|
|
"epoch": 1.113933236574746,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004882646054829023,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17258032262325287,
|
|
"num_tokens": 25482175.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.604651880264282,
|
|
"epoch": 1.1143867924528301,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048825429004095597,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.1717308834195137,
|
|
"num_tokens": 25491786.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.566480207443237,
|
|
"epoch": 1.1148403483309144,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004882439701888566,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17830322086811065,
|
|
"num_tokens": 25502103.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.580591869354248,
|
|
"epoch": 1.1152939042089987,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048823364592681754,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.1707880452275276,
|
|
"num_tokens": 25512530.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.5863017559051515,
|
|
"epoch": 1.1157474600870827,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048822331725505234,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17238383442163469,
|
|
"num_tokens": 25522905.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.592488145828247,
|
|
"epoch": 1.116201015965167,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048821298417377456,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.17962971776723863,
|
|
"num_tokens": 25532963.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.485294008255005,
|
|
"epoch": 1.116654571843251,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.000488202646683198,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.16723102033138276,
|
|
"num_tokens": 25542583.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.586943578720093,
|
|
"epoch": 1.1171081277213353,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004881923047835364,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17322114557027818,
|
|
"num_tokens": 25553367.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.731902122497559,
|
|
"epoch": 1.1175616835994195,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004881819584750036,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.1654035449028015,
|
|
"num_tokens": 25564823.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.634766054153443,
|
|
"epoch": 1.1180152394775036,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048817160775781356,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.16874194741249085,
|
|
"num_tokens": 25574946.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.64937686920166,
|
|
"epoch": 1.1184687953555879,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048816125263218023,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.16683305501937867,
|
|
"num_tokens": 25584779.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.7065942764282225,
|
|
"epoch": 1.118922351233672,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048815089309831803,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.16809054017066954,
|
|
"num_tokens": 25594725.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.621603631973267,
|
|
"epoch": 1.1193759071117562,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000488140529156441,
|
|
"loss": 5.4307,
|
|
"mean_token_accuracy": 0.16446011364459992,
|
|
"num_tokens": 25605499.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.562032842636109,
|
|
"epoch": 1.1198294629898404,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004881301608067635,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.17318881750106813,
|
|
"num_tokens": 25616443.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.619059038162232,
|
|
"epoch": 1.1202830188679245,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048811978804949997,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.17076736688613892,
|
|
"num_tokens": 25627762.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.66572413444519,
|
|
"epoch": 1.1207365747460087,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.000488109410884865,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.16833171248435974,
|
|
"num_tokens": 25637904.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.605768728256225,
|
|
"epoch": 1.1211901306240928,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048809902931307294,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.1745767042040825,
|
|
"num_tokens": 25649058.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.570656871795654,
|
|
"epoch": 1.121643686502177,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004880886433343388,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.17595502585172654,
|
|
"num_tokens": 25659161.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.612319993972778,
|
|
"epoch": 1.1220972423802613,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004880782529488771,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.17882423251867294,
|
|
"num_tokens": 25669336.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.6442542552948,
|
|
"epoch": 1.1225507982583454,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004880678581569029,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1716239035129547,
|
|
"num_tokens": 25680443.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.590997934341431,
|
|
"epoch": 1.1230043541364296,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048805745895863105,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1769050568342209,
|
|
"num_tokens": 25690202.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.585967111587524,
|
|
"epoch": 1.1234579100145137,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004880470553542767,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.17231284379959105,
|
|
"num_tokens": 25699255.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.604588222503662,
|
|
"epoch": 1.123911465892598,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00048803664734405495,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.1651730254292488,
|
|
"num_tokens": 25710714.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.6293251514434814,
|
|
"epoch": 1.1243650217706822,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000488026234928181,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.17343648225069047,
|
|
"num_tokens": 25721722.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.607216262817383,
|
|
"epoch": 1.1248185776487662,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004880158181068703,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.17717739641666413,
|
|
"num_tokens": 25732096.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.627986001968384,
|
|
"epoch": 1.1252721335268505,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048800539688033807,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.17440272569656373,
|
|
"num_tokens": 25741499.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.606373643875122,
|
|
"epoch": 1.1257256894049348,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004879949712488001,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.17155432403087617,
|
|
"num_tokens": 25751913.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.6275887966156,
|
|
"epoch": 1.1261792452830188,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048798454121247177,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.16975918412208557,
|
|
"num_tokens": 25762602.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.5750587463378904,
|
|
"epoch": 1.126632801161103,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004879741067715688,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.1725024700164795,
|
|
"num_tokens": 25773872.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.6519242286682125,
|
|
"epoch": 1.1270863570391871,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048796366792630715,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.1695870876312256,
|
|
"num_tokens": 25784723.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.5859214782714846,
|
|
"epoch": 1.1275399129172714,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004879532246769025,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.17278240323066713,
|
|
"num_tokens": 25794897.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.559264755249023,
|
|
"epoch": 1.1279934687953557,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004879427770235709,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.1784004509449005,
|
|
"num_tokens": 25804445.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.629906272888183,
|
|
"epoch": 1.1284470246734397,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048793232496652846,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.16687726825475693,
|
|
"num_tokens": 25815495.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.6425799369812015,
|
|
"epoch": 1.128900580551524,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00048792186850599124,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17704028636217117,
|
|
"num_tokens": 25826120.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.57022442817688,
|
|
"epoch": 1.1293541364296082,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004879114076421755,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.1738788291811943,
|
|
"num_tokens": 25835926.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.601430511474609,
|
|
"epoch": 1.1298076923076923,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048790094237529763,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.16673785895109178,
|
|
"num_tokens": 25846095.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.64870138168335,
|
|
"epoch": 1.1302612481857766,
|
|
"grad_norm": 7.21875,
|
|
"learning_rate": 0.000487890472705574,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.16596953570842743,
|
|
"num_tokens": 25858541.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.645746803283691,
|
|
"epoch": 1.1307148040638606,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048787999863322113,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.17562833726406096,
|
|
"num_tokens": 25867664.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.601834630966186,
|
|
"epoch": 1.1311683599419449,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004878695201584557,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.1729818180203438,
|
|
"num_tokens": 25877300.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.557867574691772,
|
|
"epoch": 1.1316219158200291,
|
|
"grad_norm": 5.78125,
|
|
"learning_rate": 0.0004878590372814943,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1747228294610977,
|
|
"num_tokens": 25888009.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.63745608329773,
|
|
"epoch": 1.1320754716981132,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048784855000255374,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.1693594604730606,
|
|
"num_tokens": 25897285.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.55023045539856,
|
|
"epoch": 1.1325290275761974,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.00048783805832185097,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17955439239740373,
|
|
"num_tokens": 25907355.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.582215213775635,
|
|
"epoch": 1.1329825834542815,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004878275622396029,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.17706575989723206,
|
|
"num_tokens": 25918566.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.625691747665405,
|
|
"epoch": 1.1334361393323658,
|
|
"grad_norm": 4.84375,
|
|
"learning_rate": 0.00048781706175602665,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.16875527054071426,
|
|
"num_tokens": 25929145.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.602830982208252,
|
|
"epoch": 1.13388969521045,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048780655687133927,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.1770707294344902,
|
|
"num_tokens": 25938163.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.572844696044922,
|
|
"epoch": 1.134343251088534,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048779604758575806,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.168691024184227,
|
|
"num_tokens": 25948962.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.530844593048096,
|
|
"epoch": 1.1347968069666183,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004877855338995004,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.16639216989278793,
|
|
"num_tokens": 25959653.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.650057125091553,
|
|
"epoch": 1.1352503628447024,
|
|
"grad_norm": 4.75,
|
|
"learning_rate": 0.00048777501581278367,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.16966882944107056,
|
|
"num_tokens": 25970268.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.64359221458435,
|
|
"epoch": 1.1357039187227866,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004877644933258254,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.16738999187946318,
|
|
"num_tokens": 25980321.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.593331241607666,
|
|
"epoch": 1.136157474600871,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004877539664388432,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.1679622158408165,
|
|
"num_tokens": 25992466.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.567163467407227,
|
|
"epoch": 1.136611030478955,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048774343515205464,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1757104605436325,
|
|
"num_tokens": 26003553.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.583215379714966,
|
|
"epoch": 1.1370645863570392,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004877328994656778,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17268076688051223,
|
|
"num_tokens": 26013299.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.577181673049926,
|
|
"epoch": 1.1375181422351233,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004877223593799303,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.17435978204011918,
|
|
"num_tokens": 26022913.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.560851335525513,
|
|
"epoch": 1.1379716981132075,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004877118148950302,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.17192198634147643,
|
|
"num_tokens": 26033191.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.666209173202515,
|
|
"epoch": 1.1384252539912918,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048770126601119555,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.1612833708524704,
|
|
"num_tokens": 26043517.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.682900476455688,
|
|
"epoch": 1.1388788098693758,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048769071272864454,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.16507856845855712,
|
|
"num_tokens": 26054173.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.73878493309021,
|
|
"epoch": 1.13933236574746,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00048768015504759536,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.16610510051250457,
|
|
"num_tokens": 26064929.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.569660615921021,
|
|
"epoch": 1.1397859216255442,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004876695929682665,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.17363446354866027,
|
|
"num_tokens": 26074872.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.557733154296875,
|
|
"epoch": 1.1402394775036284,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048765902649087605,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.1786336600780487,
|
|
"num_tokens": 26086328.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.626145648956299,
|
|
"epoch": 1.1406930333817127,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048764845561564285,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.1702533707022667,
|
|
"num_tokens": 26096477.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.601234483718872,
|
|
"epoch": 1.1411465892597967,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048763788034278545,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.17736123502254486,
|
|
"num_tokens": 26106183.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.620738458633423,
|
|
"epoch": 1.141600145137881,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004876273006725225,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.17188373506069182,
|
|
"num_tokens": 26117932.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.573065900802613,
|
|
"epoch": 1.1420537010159653,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.00048761671660507266,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.17553336024284363,
|
|
"num_tokens": 26128616.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.598615646362305,
|
|
"epoch": 1.1425072568940493,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000487606128140655,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.17197948098182678,
|
|
"num_tokens": 26138758.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.534066200256348,
|
|
"epoch": 1.1429608127721336,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004875955352794885,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.17095252275466918,
|
|
"num_tokens": 26149199.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.591140508651733,
|
|
"epoch": 1.1434143686502176,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004875849380217921,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.17149858623743058,
|
|
"num_tokens": 26160276.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.6406333446502686,
|
|
"epoch": 1.1438679245283019,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000487574336367785,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.1732035234570503,
|
|
"num_tokens": 26169564.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.576666784286499,
|
|
"epoch": 1.1443214804063861,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004875637303176865,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.17607302516698836,
|
|
"num_tokens": 26179135.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.617819881439209,
|
|
"epoch": 1.1447750362844702,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00048755311987171585,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.17113402783870696,
|
|
"num_tokens": 26190116.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.6403364658355715,
|
|
"epoch": 1.1452285921625545,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048754250503009244,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.16499626636505127,
|
|
"num_tokens": 26200847.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.711669445037842,
|
|
"epoch": 1.1456821480406387,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048753188579303596,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.16778092607855796,
|
|
"num_tokens": 26211151.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.638349628448486,
|
|
"epoch": 1.1461357039187228,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004875212621607659,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.18072609156370162,
|
|
"num_tokens": 26221273.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.598391008377075,
|
|
"epoch": 1.146589259796807,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048751063413350203,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.1663660630583763,
|
|
"num_tokens": 26231770.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.6362285137176515,
|
|
"epoch": 1.147042815674891,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000487500001711464,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.16883457452058792,
|
|
"num_tokens": 26241386.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.752071523666382,
|
|
"epoch": 1.1474963715529753,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004874893648948719,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.16835420429706574,
|
|
"num_tokens": 26251991.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.724516439437866,
|
|
"epoch": 1.1479499274310596,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048747872368394546,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.16761526167392732,
|
|
"num_tokens": 26262331.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.678382444381714,
|
|
"epoch": 1.1484034833091437,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048746807807890496,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.16898454427719117,
|
|
"num_tokens": 26272939.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.591447019577027,
|
|
"epoch": 1.148857039187228,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048745742807997046,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.17616231739521027,
|
|
"num_tokens": 26282849.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.560210514068603,
|
|
"epoch": 1.149310595065312,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048744677368736216,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.17931461036205293,
|
|
"num_tokens": 26292449.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.534169292449951,
|
|
"epoch": 1.1497641509433962,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048743611490130044,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.17279691994190216,
|
|
"num_tokens": 26302506.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.6572449684143065,
|
|
"epoch": 1.1502177068214805,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048742545172200576,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17448493242263793,
|
|
"num_tokens": 26312346.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.699370336532593,
|
|
"epoch": 1.1506712626995645,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004874147841496986,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.17356102615594865,
|
|
"num_tokens": 26323173.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.6548998832702635,
|
|
"epoch": 1.1511248185776488,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004874041121845996,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.16051401942968369,
|
|
"num_tokens": 26334371.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.611789703369141,
|
|
"epoch": 1.1515783744557329,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004873934358269294,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.17125811725854873,
|
|
"num_tokens": 26344506.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.668434953689575,
|
|
"epoch": 1.1520319303338171,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004873827550769088,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.16571766287088394,
|
|
"num_tokens": 26354534.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.651076793670654,
|
|
"epoch": 1.1524854862119014,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004873720699347587,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.169284388422966,
|
|
"num_tokens": 26365682.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.684403753280639,
|
|
"epoch": 1.1529390420899854,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004873613804007001,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.17238470315933227,
|
|
"num_tokens": 26376702.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.590936088562012,
|
|
"epoch": 1.1533925979680697,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004873506864749541,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.17693755626678467,
|
|
"num_tokens": 26387154.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.658411073684692,
|
|
"epoch": 1.1538461538461537,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004873399881577417,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.16750529110431672,
|
|
"num_tokens": 26397883.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.500313663482666,
|
|
"epoch": 1.154299709724238,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004873292854492842,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.1807516932487488,
|
|
"num_tokens": 26407613.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.5440812587738035,
|
|
"epoch": 1.1547532656023223,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004873185783498031,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.17283984422683715,
|
|
"num_tokens": 26417221.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.603883457183838,
|
|
"epoch": 1.1552068214804063,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004873078668595197,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17053250819444657,
|
|
"num_tokens": 26427976.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.618934535980225,
|
|
"epoch": 1.1556603773584906,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048729715097865534,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.16815861016511918,
|
|
"num_tokens": 26439213.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.586228656768799,
|
|
"epoch": 1.1561139332365746,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004872864307074319,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.17429283857345582,
|
|
"num_tokens": 26449763.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.653108072280884,
|
|
"epoch": 1.156567489114659,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048727570604607096,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.1733284428715706,
|
|
"num_tokens": 26460133.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.630918216705322,
|
|
"epoch": 1.1570210449927432,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048726497699479437,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.17489899545907975,
|
|
"num_tokens": 26470164.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.633225536346435,
|
|
"epoch": 1.1574746008708272,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000487254243553824,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.1685292363166809,
|
|
"num_tokens": 26480314.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.556787967681885,
|
|
"epoch": 1.1579281567489115,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004872435057233817,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.1793245404958725,
|
|
"num_tokens": 26491184.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.519004535675049,
|
|
"epoch": 1.1583817126269957,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048723276350368957,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.17802902013063432,
|
|
"num_tokens": 26501432.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.612009906768799,
|
|
"epoch": 1.1588352685050798,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048722201689496984,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.1688969388604164,
|
|
"num_tokens": 26510379.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.59565372467041,
|
|
"epoch": 1.159288824383164,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004872112658974447,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17860374599695206,
|
|
"num_tokens": 26519454.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.543451499938965,
|
|
"epoch": 1.159742380261248,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048720051051133657,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.17807969748973845,
|
|
"num_tokens": 26531325.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.564303970336914,
|
|
"epoch": 1.1601959361393324,
|
|
"grad_norm": 7.5625,
|
|
"learning_rate": 0.0004871897507368678,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.17585408091545104,
|
|
"num_tokens": 26541510.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.657733917236328,
|
|
"epoch": 1.1606494920174166,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048717898657426093,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16009921431541443,
|
|
"num_tokens": 26553400.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.641717624664307,
|
|
"epoch": 1.1611030478955007,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048716821802373856,
|
|
"loss": 5.3703,
|
|
"mean_token_accuracy": 0.16997628957033156,
|
|
"num_tokens": 26564340.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.6257671356201175,
|
|
"epoch": 1.161556603773585,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048715744508552334,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.1764123722910881,
|
|
"num_tokens": 26573615.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.6515766143798825,
|
|
"epoch": 1.1620101596516692,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004871466677598381,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1637832596898079,
|
|
"num_tokens": 26584149.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.609748268127442,
|
|
"epoch": 1.1624637155297532,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004871358860469057,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.16375558823347092,
|
|
"num_tokens": 26595064.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.586152744293213,
|
|
"epoch": 1.1629172714078375,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048712509994694903,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.16831739246845245,
|
|
"num_tokens": 26605636.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.642949008941651,
|
|
"epoch": 1.1633708272859216,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004871143094601914,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.16458763927221298,
|
|
"num_tokens": 26616065.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.6962902545928955,
|
|
"epoch": 1.1638243831640058,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004871035145868557,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.1654929742217064,
|
|
"num_tokens": 26627246.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.566495084762574,
|
|
"epoch": 1.16427793904209,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048709271532716524,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.16515607237815857,
|
|
"num_tokens": 26637630.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.634595155715942,
|
|
"epoch": 1.1647314949201741,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004870819116813434,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.17313675433397294,
|
|
"num_tokens": 26648683.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.702267360687256,
|
|
"epoch": 1.1651850507982584,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048707110364961363,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.167598594725132,
|
|
"num_tokens": 26659573.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.5648540496826175,
|
|
"epoch": 1.1656386066763424,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048706029123219937,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.17497960329055787,
|
|
"num_tokens": 26669384.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.638215684890747,
|
|
"epoch": 1.1660921625544267,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048704947442932426,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.16881868094205857,
|
|
"num_tokens": 26679721.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.654860210418701,
|
|
"epoch": 1.166545718432511,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048703865324121196,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.179543574154377,
|
|
"num_tokens": 26689923.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.519535636901855,
|
|
"epoch": 1.166999274310595,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048702782766808637,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.1707490310072899,
|
|
"num_tokens": 26699953.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.60990538597107,
|
|
"epoch": 1.1674528301886793,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004870169977101711,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.16255164593458177,
|
|
"num_tokens": 26712099.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.675438261032104,
|
|
"epoch": 1.1679063860667633,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048700616336769037,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.17527406960725783,
|
|
"num_tokens": 26722334.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.627234649658203,
|
|
"epoch": 1.1683599419448476,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048699532464086817,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.1743389457464218,
|
|
"num_tokens": 26732470.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.580811023712158,
|
|
"epoch": 1.1688134978229319,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048698448152992865,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17156845331192017,
|
|
"num_tokens": 26742015.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.554739141464234,
|
|
"epoch": 1.169267053701016,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048697363403509605,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.1754850775003433,
|
|
"num_tokens": 26753231.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.592912435531616,
|
|
"epoch": 1.1697206095791002,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004869627821565946,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.17159301191568374,
|
|
"num_tokens": 26763895.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.644183826446533,
|
|
"epoch": 1.1701741654571842,
|
|
"grad_norm": 3.9375,
|
|
"learning_rate": 0.0004869519258946489,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.16817592978477477,
|
|
"num_tokens": 26774208.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.620671081542969,
|
|
"epoch": 1.1706277213352685,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048694106524948324,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1723668321967125,
|
|
"num_tokens": 26785554.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.626670503616333,
|
|
"epoch": 1.1710812772133528,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048693020022132243,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.17295462340116502,
|
|
"num_tokens": 26795488.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.5940498352050785,
|
|
"epoch": 1.1715348330914368,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000486919330810391,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.16420766115188598,
|
|
"num_tokens": 26806801.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.669963407516479,
|
|
"epoch": 1.171988388969521,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004869084570169139,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.17365534603595734,
|
|
"num_tokens": 26816869.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.6147373676300045,
|
|
"epoch": 1.172441944847605,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048689757884111585,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.1720971494913101,
|
|
"num_tokens": 26827003.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.533352851867676,
|
|
"epoch": 1.1728955007256894,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00048688669628322185,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17673178762197495,
|
|
"num_tokens": 26837065.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.516833209991455,
|
|
"epoch": 1.1733490566037736,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000486875809343457,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.17590547055006028,
|
|
"num_tokens": 26847487.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.595408296585083,
|
|
"epoch": 1.1738026124818577,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048686491802204645,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.18359509110450745,
|
|
"num_tokens": 26858407.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.6458361625671385,
|
|
"epoch": 1.174256168359942,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004868540223192154,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.17196135371923446,
|
|
"num_tokens": 26868469.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.61460919380188,
|
|
"epoch": 1.1747097242380262,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004868431222351892,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.17240348756313323,
|
|
"num_tokens": 26879580.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.578996324539185,
|
|
"epoch": 1.1751632801161103,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048683221777019313,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.17557137757539748,
|
|
"num_tokens": 26889513.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.623287105560303,
|
|
"epoch": 1.1756168359941945,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048682130892445293,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.1664819225668907,
|
|
"num_tokens": 26900792.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.594268465042115,
|
|
"epoch": 1.1760703918722786,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000486810395698194,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.17498817890882493,
|
|
"num_tokens": 26911298.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.617185020446778,
|
|
"epoch": 1.1765239477503628,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048679947809164223,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.1651250973343849,
|
|
"num_tokens": 26921545.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.6643743991851805,
|
|
"epoch": 1.176977503628447,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004867885561050232,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.18152386844158172,
|
|
"num_tokens": 26932140.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.673213815689087,
|
|
"epoch": 1.1774310595065312,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004867776297385629,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16779907494783403,
|
|
"num_tokens": 26942634.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.594217157363891,
|
|
"epoch": 1.1778846153846154,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048676669899248723,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.17593518346548082,
|
|
"num_tokens": 26952758.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.538848495483398,
|
|
"epoch": 1.1783381712626997,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004867557638670222,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.17142992168664933,
|
|
"num_tokens": 26963439.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.598716974258423,
|
|
"epoch": 1.1787917271407837,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004867448243623941,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.16914114207029343,
|
|
"num_tokens": 26974331.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.58670334815979,
|
|
"epoch": 1.179245283018868,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.000486733880478829,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.17722886502742768,
|
|
"num_tokens": 26983416.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.567386436462402,
|
|
"epoch": 1.179698838896952,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048672293221655333,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17718790024518966,
|
|
"num_tokens": 26994176.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.563203144073486,
|
|
"epoch": 1.1801523947750363,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004867119795757935,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.16978540718555452,
|
|
"num_tokens": 27003295.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.594437217712402,
|
|
"epoch": 1.1806059506531206,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000486701022556776,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.17459460943937302,
|
|
"num_tokens": 27014018.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.588791704177856,
|
|
"epoch": 1.1810595065312046,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004866900611597273,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.17550429105758666,
|
|
"num_tokens": 27024706.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.626877975463867,
|
|
"epoch": 1.1815130624092889,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048667909538487427,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.17770835310220717,
|
|
"num_tokens": 27035801.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.519720411300659,
|
|
"epoch": 1.181966618287373,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004866681252324436,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.1783450052142143,
|
|
"num_tokens": 27046596.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.595010089874267,
|
|
"epoch": 1.1824201741654572,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048665715070266214,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.16773384809494019,
|
|
"num_tokens": 27057057.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.4910078048706055,
|
|
"epoch": 1.1828737300435415,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048664617179575685,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.17854873538017274,
|
|
"num_tokens": 27067947.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.592524147033691,
|
|
"epoch": 1.1833272859216255,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004866351885119548,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.17544471025466918,
|
|
"num_tokens": 27077503.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.6903480052947994,
|
|
"epoch": 1.1837808417997098,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004866242008514832,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16892702728509904,
|
|
"num_tokens": 27088298.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.549736833572387,
|
|
"epoch": 1.1842343976777938,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048661320881456904,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.16736720353364945,
|
|
"num_tokens": 27097841.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.486719179153442,
|
|
"epoch": 1.184687953555878,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004866022124014399,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.17707863748073577,
|
|
"num_tokens": 27108263.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.576300191879272,
|
|
"epoch": 1.1851415094339623,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048659121161232313,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.17358799129724503,
|
|
"num_tokens": 27119339.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.637163829803467,
|
|
"epoch": 1.1855950653120464,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004865802064474461,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.16541709303855895,
|
|
"num_tokens": 27130393.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.6292026996612545,
|
|
"epoch": 1.1860486211901307,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048656919690703653,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.16610905081033706,
|
|
"num_tokens": 27141156.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.6156259059906,
|
|
"epoch": 1.1865021770682147,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000486558182991322,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.17152254432439804,
|
|
"num_tokens": 27151630.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.613323926925659,
|
|
"epoch": 1.186955732946299,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004865471647005304,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.17786764204502106,
|
|
"num_tokens": 27160734.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.577333402633667,
|
|
"epoch": 1.1874092888243832,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048653614203488947,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17039074152708053,
|
|
"num_tokens": 27171584.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.536734628677368,
|
|
"epoch": 1.1878628447024673,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004865251149946273,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.1836892694234848,
|
|
"num_tokens": 27180817.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.608707857131958,
|
|
"epoch": 1.1883164005805515,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048651408357997173,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.16944698989391327,
|
|
"num_tokens": 27190363.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.6198090553283695,
|
|
"epoch": 1.1887699564586356,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048650304779115114,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.17619554400444032,
|
|
"num_tokens": 27202181.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.55724778175354,
|
|
"epoch": 1.1892235123367199,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004864920076283935,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.16659168899059296,
|
|
"num_tokens": 27212514.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.585368537902832,
|
|
"epoch": 1.1896770682148041,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004864809630919273,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.17874616682529448,
|
|
"num_tokens": 27223352.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.586872148513794,
|
|
"epoch": 1.1901306240928882,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004864699141819809,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.17861711233854294,
|
|
"num_tokens": 27232643.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.561257791519165,
|
|
"epoch": 1.1905841799709724,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048645886089878276,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.17624130398035048,
|
|
"num_tokens": 27243793.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.592378807067871,
|
|
"epoch": 1.1910377358490567,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048644780324256153,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.17617304623126984,
|
|
"num_tokens": 27254554.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.608823251724243,
|
|
"epoch": 1.1914912917271407,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004864367412135458,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.17065580040216446,
|
|
"num_tokens": 27265842.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.6333879947662355,
|
|
"epoch": 1.191944847605225,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048642567481196446,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.16704277396202089,
|
|
"num_tokens": 27277617.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.576776742935181,
|
|
"epoch": 1.192398403483309,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004864146040380462,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.17662875801324845,
|
|
"num_tokens": 27287450.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.597208642959595,
|
|
"epoch": 1.1928519593613933,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004864035288920202,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.17345335930585862,
|
|
"num_tokens": 27297010.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.553128576278686,
|
|
"epoch": 1.1933055152394776,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.00048639244937411516,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.17080822885036467,
|
|
"num_tokens": 27306874.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.692587232589721,
|
|
"epoch": 1.1937590711175616,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048638136548456045,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.1690503478050232,
|
|
"num_tokens": 27318762.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.568741178512573,
|
|
"epoch": 1.194212626995646,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048637027722358536,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.18417855054140092,
|
|
"num_tokens": 27327231.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.503830003738403,
|
|
"epoch": 1.1946661828737302,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048635918459141893,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.17428579032421113,
|
|
"num_tokens": 27338517.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.6223094940185545,
|
|
"epoch": 1.1951197387518142,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048634808758829073,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.16856776028871537,
|
|
"num_tokens": 27348861.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.590210628509522,
|
|
"epoch": 1.1955732946298985,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.00048633698621443024,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.18056849539279937,
|
|
"num_tokens": 27358610.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.535129499435425,
|
|
"epoch": 1.1960268505079825,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000486325880470067,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.16984545737504958,
|
|
"num_tokens": 27369707.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.574238729476929,
|
|
"epoch": 1.1964804063860668,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004863147703554307,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.1724462628364563,
|
|
"num_tokens": 27381030.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.636377620697021,
|
|
"epoch": 1.196933962264151,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048630365587075115,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.17001646161079406,
|
|
"num_tokens": 27390866.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.607774686813355,
|
|
"epoch": 1.197387518142235,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048629253701625816,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.17824333310127258,
|
|
"num_tokens": 27400724.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.584063959121704,
|
|
"epoch": 1.1978410740203194,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004862814137921816,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17415580600500108,
|
|
"num_tokens": 27411212.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.567069482803345,
|
|
"epoch": 1.1982946298984034,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048627028619875157,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.16939998269081116,
|
|
"num_tokens": 27421279.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.595053100585938,
|
|
"epoch": 1.1987481857764877,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004862591542361982,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17195852249860763,
|
|
"num_tokens": 27432520.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.583989191055298,
|
|
"epoch": 1.199201741654572,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004862480179047516,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.17873045057058334,
|
|
"num_tokens": 27442246.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.600679969787597,
|
|
"epoch": 1.199655297532656,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004862368772046423,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.17643520534038543,
|
|
"num_tokens": 27452134.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.548134994506836,
|
|
"epoch": 1.2001088534107403,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048622573213610057,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.16806789636611938,
|
|
"num_tokens": 27462253.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.59502592086792,
|
|
"epoch": 1.2005624092888243,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048621458269935676,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.17468537986278534,
|
|
"num_tokens": 27473131.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.609209251403809,
|
|
"epoch": 1.2010159651669086,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048620342889464153,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.17891620099544525,
|
|
"num_tokens": 27483683.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.522462654113769,
|
|
"epoch": 1.2014695210449928,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048619227072218565,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.17087059319019318,
|
|
"num_tokens": 27493679.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.583718633651733,
|
|
"epoch": 1.2019230769230769,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004861811081822198,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.18382486552000046,
|
|
"num_tokens": 27503897.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.600480222702027,
|
|
"epoch": 1.2023766328011611,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004861699412749748,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1658663794398308,
|
|
"num_tokens": 27514560.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.528561019897461,
|
|
"epoch": 1.2028301886792452,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004861587700006816,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.17578955888748168,
|
|
"num_tokens": 27525594.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.517774438858032,
|
|
"epoch": 1.2032837445573294,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048614759435957114,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.18220822513103485,
|
|
"num_tokens": 27535676.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.53112564086914,
|
|
"epoch": 1.2037373004354137,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004861364143518747,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.16874281764030458,
|
|
"num_tokens": 27545520.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.659768342971802,
|
|
"epoch": 1.2041908563134978,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004861252299778234,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.16583643853664398,
|
|
"num_tokens": 27556866.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.575717735290527,
|
|
"epoch": 1.204644412191582,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048611404123764855,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.17845721989870073,
|
|
"num_tokens": 27566951.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.564585971832275,
|
|
"epoch": 1.205097968069666,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048610284813158154,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.17460761070251465,
|
|
"num_tokens": 27576796.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.496961212158203,
|
|
"epoch": 1.2055515239477503,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004860916506598538,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.17227614670991898,
|
|
"num_tokens": 27586902.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.658858919143677,
|
|
"epoch": 1.2060050798258346,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048608044882269695,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.16562795490026475,
|
|
"num_tokens": 27599232.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.589589643478393,
|
|
"epoch": 1.2064586357039186,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004860692426203427,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.17265625596046447,
|
|
"num_tokens": 27609022.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.64921293258667,
|
|
"epoch": 1.206912191582003,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004860580320530226,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.17320955991744996,
|
|
"num_tokens": 27619829.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.578033590316773,
|
|
"epoch": 1.2073657474600872,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004860468171209687,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.1777842402458191,
|
|
"num_tokens": 27629337.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.591690254211426,
|
|
"epoch": 1.2078193033381712,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004860355978244128,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.17662533670663833,
|
|
"num_tokens": 27639377.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.6097251892089846,
|
|
"epoch": 1.2082728592162555,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000486024374163587,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.17844983637332917,
|
|
"num_tokens": 27649989.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.612568140029907,
|
|
"epoch": 1.2087264150943395,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048601314613872334,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.16680487841367722,
|
|
"num_tokens": 27659967.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.595348501205445,
|
|
"epoch": 1.2091799709724238,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.000486001913750054,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.1766873061656952,
|
|
"num_tokens": 27670099.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.535204839706421,
|
|
"epoch": 1.209633526850508,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004859906769978113,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.16544295102357864,
|
|
"num_tokens": 27681497.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.67044677734375,
|
|
"epoch": 1.2100870827285921,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048597943588222776,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.16721213459968567,
|
|
"num_tokens": 27691828.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.623655319213867,
|
|
"epoch": 1.2105406386066764,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048596819040353564,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.17424602806568146,
|
|
"num_tokens": 27701426.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.616913557052612,
|
|
"epoch": 1.2109941944847606,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004859569405619676,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.176700422167778,
|
|
"num_tokens": 27711112.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.588740968704224,
|
|
"epoch": 1.2114477503628447,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004859456863577562,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.16844981163740158,
|
|
"num_tokens": 27723160.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.626598691940307,
|
|
"epoch": 1.211901306240929,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048593442779113437,
|
|
"loss": 5.376,
|
|
"mean_token_accuracy": 0.16700208634138108,
|
|
"num_tokens": 27733143.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.588902187347412,
|
|
"epoch": 1.212354862119013,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004859231648623348,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.17078619003295897,
|
|
"num_tokens": 27743956.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.615359687805176,
|
|
"epoch": 1.2128084179970973,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048591189757159035,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.18196104913949968,
|
|
"num_tokens": 27754192.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.623263359069824,
|
|
"epoch": 1.2132619738751815,
|
|
"grad_norm": 6.09375,
|
|
"learning_rate": 0.0004859006259191342,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.16230515986680985,
|
|
"num_tokens": 27763939.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.609740257263184,
|
|
"epoch": 1.2137155297532656,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004858893499051993,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.17944246083498,
|
|
"num_tokens": 27774743.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.629550981521606,
|
|
"epoch": 1.2141690856313498,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004858780695300189,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.17732920199632646,
|
|
"num_tokens": 27785344.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.607261800765992,
|
|
"epoch": 1.2146226415094339,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.0004858667847938263,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16874755024909974,
|
|
"num_tokens": 27797101.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.522930717468261,
|
|
"epoch": 1.2150761973875182,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048585549569685486,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.18136875480413436,
|
|
"num_tokens": 27807581.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.539710998535156,
|
|
"epoch": 1.2155297532656024,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048584420223933805,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.17657115757465364,
|
|
"num_tokens": 27818170.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.550384378433227,
|
|
"epoch": 1.2159833091436865,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004858329044215094,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1752548485994339,
|
|
"num_tokens": 27828153.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.57208662033081,
|
|
"epoch": 1.2164368650217707,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048582160224360253,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.18096850961446762,
|
|
"num_tokens": 27837681.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.543278360366822,
|
|
"epoch": 1.2168904208998548,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004858102957058513,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.17566452026367188,
|
|
"num_tokens": 27847447.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.492272233963012,
|
|
"epoch": 1.217343976777939,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048579898480848933,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.17472253888845443,
|
|
"num_tokens": 27858586.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.552965974807739,
|
|
"epoch": 1.2177975326560233,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004857876695517507,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.17455514818429946,
|
|
"num_tokens": 27868832.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.57877631187439,
|
|
"epoch": 1.2182510885341074,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048577634993586923,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.17423500567674638,
|
|
"num_tokens": 27879339.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.622534132003784,
|
|
"epoch": 1.2187046444121916,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048576502596107924,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.17551299035549164,
|
|
"num_tokens": 27889964.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.6464944839477536,
|
|
"epoch": 1.2191582002902757,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004857536976276148,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.16876127123832702,
|
|
"num_tokens": 27901004.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.556020641326905,
|
|
"epoch": 1.21961175616836,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004857423649357102,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.17484554201364516,
|
|
"num_tokens": 27910788.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.619220113754272,
|
|
"epoch": 1.2200653120464442,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048573102788559974,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.17394628673791884,
|
|
"num_tokens": 27921360.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.560455989837647,
|
|
"epoch": 1.2205188679245282,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004857196864775179,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.1805930107831955,
|
|
"num_tokens": 27931889.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.541463375091553,
|
|
"epoch": 1.2209724238026125,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048570834071169926,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.17708689570426941,
|
|
"num_tokens": 27942049.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.594935178756714,
|
|
"epoch": 1.2214259796806965,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048569699058837856,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.17203628569841384,
|
|
"num_tokens": 27952416.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.566387414932251,
|
|
"epoch": 1.2218795355587808,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004856856361077903,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17856546491384506,
|
|
"num_tokens": 27962009.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.639000082015992,
|
|
"epoch": 1.222333091436865,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004856742772701694,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.17219636142253875,
|
|
"num_tokens": 27972175.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.633493041992187,
|
|
"epoch": 1.2227866473149491,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.00048566291407575073,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.17799410670995713,
|
|
"num_tokens": 27982899.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.639202070236206,
|
|
"epoch": 1.2232402031930334,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00048565154652476937,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17795234322547912,
|
|
"num_tokens": 27993231.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.58167986869812,
|
|
"epoch": 1.2236937590711174,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 0.0004856401746174603,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.17736472338438034,
|
|
"num_tokens": 28003623.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.592493391036987,
|
|
"epoch": 1.2241473149492017,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048562879835405874,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.1699166476726532,
|
|
"num_tokens": 28013878.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.539293432235718,
|
|
"epoch": 1.224600870827286,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004856174177348,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.17718744724988938,
|
|
"num_tokens": 28024224.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.568283557891846,
|
|
"epoch": 1.22505442670537,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004856060327599194,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.17411323636770248,
|
|
"num_tokens": 28034819.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.569042110443116,
|
|
"epoch": 1.2255079825834543,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048559464342965233,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1745307981967926,
|
|
"num_tokens": 28044240.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.626883220672608,
|
|
"epoch": 1.2259615384615385,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004855832497442344,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.1612863466143608,
|
|
"num_tokens": 28055046.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.562499094009399,
|
|
"epoch": 1.2264150943396226,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004855718517039012,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.17647689431905747,
|
|
"num_tokens": 28065272.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.628909778594971,
|
|
"epoch": 1.2268686502177069,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048556044930888844,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.1847059026360512,
|
|
"num_tokens": 28076255.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.5902173042297365,
|
|
"epoch": 1.2273222060957911,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004855490425594319,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.1718058779835701,
|
|
"num_tokens": 28086258.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.577108526229859,
|
|
"epoch": 1.2277757619738752,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004855376314557675,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.17808407545089722,
|
|
"num_tokens": 28096497.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.576297807693481,
|
|
"epoch": 1.2282293178519594,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004855262159981313,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.17770994156599046,
|
|
"num_tokens": 28106282.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.512001419067383,
|
|
"epoch": 1.2286828737300435,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048551479618675925,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.17105621099472046,
|
|
"num_tokens": 28115771.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.646786832809449,
|
|
"epoch": 1.2291364296081277,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048550337202188756,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.1757451429963112,
|
|
"num_tokens": 28125477.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.666293478012085,
|
|
"epoch": 1.229589985486212,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004854919435037525,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.1717785194516182,
|
|
"num_tokens": 28135800.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.525774145126343,
|
|
"epoch": 1.230043541364296,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004854805106325904,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.17402883917093276,
|
|
"num_tokens": 28146779.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.555139207839966,
|
|
"epoch": 1.2304970972423803,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004854690734086378,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.1721974492073059,
|
|
"num_tokens": 28156819.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.613695383071899,
|
|
"epoch": 1.2309506531204644,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004854576318321311,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.17164791524410247,
|
|
"num_tokens": 28168553.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.61791467666626,
|
|
"epoch": 1.2314042089985486,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.00048544618590330685,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.17907538563013076,
|
|
"num_tokens": 28178064.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.644110298156738,
|
|
"epoch": 1.231857764876633,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.00048543473562240194,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.1726391851902008,
|
|
"num_tokens": 28188580.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.630799150466919,
|
|
"epoch": 1.232311320754717,
|
|
"grad_norm": 5.75,
|
|
"learning_rate": 0.000485423280989653,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.16658966690301896,
|
|
"num_tokens": 28199955.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.65954737663269,
|
|
"epoch": 1.2327648766328012,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000485411822005297,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.1691377192735672,
|
|
"num_tokens": 28210506.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.604473209381103,
|
|
"epoch": 1.2332184325108853,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048540035866957097,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.1821328490972519,
|
|
"num_tokens": 28220486.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.648378658294678,
|
|
"epoch": 1.2336719883889695,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004853888909827118,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.16308983862400056,
|
|
"num_tokens": 28232668.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.587193727493286,
|
|
"epoch": 1.2341255442670538,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004853774189449568,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.17219879627227783,
|
|
"num_tokens": 28243733.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.651928329467774,
|
|
"epoch": 1.2345791001451378,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048536594255654315,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.17333347350358963,
|
|
"num_tokens": 28254953.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.61195182800293,
|
|
"epoch": 1.235032656023222,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004853544618177083,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.17475463896989823,
|
|
"num_tokens": 28264959.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.641897296905517,
|
|
"epoch": 1.2354862119013061,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00048534297672868945,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.17468301206827164,
|
|
"num_tokens": 28275509.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.570536947250366,
|
|
"epoch": 1.2359397677793904,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00048533148728972434,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.17754732072353363,
|
|
"num_tokens": 28285983.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.600645112991333,
|
|
"epoch": 1.2363933236574747,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00048531999350105037,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.16587357074022294,
|
|
"num_tokens": 28296178.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.589850425720215,
|
|
"epoch": 1.2368468795355587,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048530849536290537,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.1683177575469017,
|
|
"num_tokens": 28305741.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.583351135253906,
|
|
"epoch": 1.237300435413643,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004852969928755271,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.1744295671582222,
|
|
"num_tokens": 28315607.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.553523206710816,
|
|
"epoch": 1.237753991291727,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048528548603915344,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.17730236947536468,
|
|
"num_tokens": 28327349.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.583177471160889,
|
|
"epoch": 1.2382075471698113,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048527397485402236,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1699524223804474,
|
|
"num_tokens": 28339949.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.632159280776977,
|
|
"epoch": 1.2386611030478956,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048526245932037186,
|
|
"loss": 5.365,
|
|
"mean_token_accuracy": 0.17508769482374192,
|
|
"num_tokens": 28351340.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.51812219619751,
|
|
"epoch": 1.2391146589259796,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00048525093943844013,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.17740751802921295,
|
|
"num_tokens": 28360929.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.525761604309082,
|
|
"epoch": 1.2395682148040639,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004852394152084654,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.17984029799699783,
|
|
"num_tokens": 28370477.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.5181183338165285,
|
|
"epoch": 1.240021770682148,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.000485227886630686,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.18653616011142732,
|
|
"num_tokens": 28380876.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.502352857589722,
|
|
"epoch": 1.2404753265602322,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004852163537053403,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1757717177271843,
|
|
"num_tokens": 28390685.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.56557879447937,
|
|
"epoch": 1.2409288824383164,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004852048164326669,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.17249781042337417,
|
|
"num_tokens": 28400236.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.60340313911438,
|
|
"epoch": 1.2413824383164005,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004851932748129043,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.17916882783174515,
|
|
"num_tokens": 28410353.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.585198068618775,
|
|
"epoch": 1.2418359941944848,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004851817288462912,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.1741696134209633,
|
|
"num_tokens": 28420241.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.54184923171997,
|
|
"epoch": 1.242289550072569,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004851701785330663,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.16846685856580734,
|
|
"num_tokens": 28430610.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.5550336837768555,
|
|
"epoch": 1.242743105950653,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004851586238734687,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.17815205305814744,
|
|
"num_tokens": 28440026.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.591141557693481,
|
|
"epoch": 1.2431966618287373,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004851470648677371,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.16559183597564697,
|
|
"num_tokens": 28450707.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.624572372436523,
|
|
"epoch": 1.2436502177068216,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004851355015161107,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.17137494087219238,
|
|
"num_tokens": 28462378.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.650377941131592,
|
|
"epoch": 1.2441037735849056,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004851239338188286,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.16669329702854158,
|
|
"num_tokens": 28473084.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.557840061187744,
|
|
"epoch": 1.24455732946299,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048511236177612994,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.17402911484241484,
|
|
"num_tokens": 28482767.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.5816985130310055,
|
|
"epoch": 1.245010885341074,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048510078538825413,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.1766592636704445,
|
|
"num_tokens": 28493274.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.6507079124450685,
|
|
"epoch": 1.2454644412191582,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048508920465544056,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.1739680737257004,
|
|
"num_tokens": 28503823.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.45209813117981,
|
|
"epoch": 1.2459179970972425,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004850776195779286,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.17718724757432938,
|
|
"num_tokens": 28514209.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.613685607910156,
|
|
"epoch": 1.2463715529753265,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000485066030155958,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.16931882351636887,
|
|
"num_tokens": 28524665.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.625153398513794,
|
|
"epoch": 1.2468251088534108,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004850544363897684,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17885896563529968,
|
|
"num_tokens": 28533639.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.497832870483398,
|
|
"epoch": 1.2472786647314948,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048504283827959947,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.1729617953300476,
|
|
"num_tokens": 28544469.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.615324258804321,
|
|
"epoch": 1.2477322206095791,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004850312358256912,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.17643998712301254,
|
|
"num_tokens": 28554637.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.542525815963745,
|
|
"epoch": 1.2481857764876634,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004850196290282834,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.17558214962482452,
|
|
"num_tokens": 28564752.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.5779043674469,
|
|
"epoch": 1.2486393323657474,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048500801788761613,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.17437762171030044,
|
|
"num_tokens": 28575007.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.650508308410645,
|
|
"epoch": 1.2490928882438317,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004849964024039296,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17274573892354966,
|
|
"num_tokens": 28584907.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.670906925201416,
|
|
"epoch": 1.2495464441219157,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048498478257746387,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.18125055581331254,
|
|
"num_tokens": 28594244.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.625990772247315,
|
|
"epoch": 1.25,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048497315840845934,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17237695455551147,
|
|
"num_tokens": 28603816.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.62138671875,
|
|
"epoch": 1.2504535558780843,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004849615298971565,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.17015549838542937,
|
|
"num_tokens": 28613067.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.592409896850586,
|
|
"epoch": 1.2509071117561683,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048494989704379556,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.17158761173486708,
|
|
"num_tokens": 28623752.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.540713834762573,
|
|
"epoch": 1.2513606676342526,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004849382598486173,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.17873719930648804,
|
|
"num_tokens": 28633190.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.698855304718018,
|
|
"epoch": 1.2518142235123366,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048492661831186243,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.16575995683670045,
|
|
"num_tokens": 28644567.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.646363115310669,
|
|
"epoch": 1.2522677793904209,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004849149724337715,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.16907308250665665,
|
|
"num_tokens": 28654785.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.526299047470093,
|
|
"epoch": 1.2527213352685052,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048490332221458543,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1709463194012642,
|
|
"num_tokens": 28665286.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.588380002975464,
|
|
"epoch": 1.2531748911465892,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004848916676545452,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17111329585313798,
|
|
"num_tokens": 28675830.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.665946960449219,
|
|
"epoch": 1.2536284470246735,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048488000875389174,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.16648067981004716,
|
|
"num_tokens": 28686640.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.603734540939331,
|
|
"epoch": 1.2540820029027575,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004848683455128663,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.17375490069389343,
|
|
"num_tokens": 28697677.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.594356060028076,
|
|
"epoch": 1.2545355587808418,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048485667793170994,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.17539387792348862,
|
|
"num_tokens": 28708831.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.5950311660766605,
|
|
"epoch": 1.254989114658926,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000484845006010664,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.1703229323029518,
|
|
"num_tokens": 28718959.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.591436815261841,
|
|
"epoch": 1.25544267053701,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004848333297499699,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.1799551621079445,
|
|
"num_tokens": 28728719.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.615367221832275,
|
|
"epoch": 1.2558962264150944,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048482164914986903,
|
|
"loss": 5.4626,
|
|
"mean_token_accuracy": 0.16355045288801193,
|
|
"num_tokens": 28740032.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.569112777709961,
|
|
"epoch": 1.2563497822931784,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048480996421060307,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.17964765876531602,
|
|
"num_tokens": 28749374.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.566294431686401,
|
|
"epoch": 1.2568033381712627,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048479827493241347,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.17251615673303605,
|
|
"num_tokens": 28760038.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.597704887390137,
|
|
"epoch": 1.257256894049347,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048478658131554216,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.17368148714303971,
|
|
"num_tokens": 28770247.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.581388139724732,
|
|
"epoch": 1.2577104499274312,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004847748833602308,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.17661478668451308,
|
|
"num_tokens": 28780251.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.544677972793579,
|
|
"epoch": 1.2581640058055152,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004847631810667215,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.18099457025527954,
|
|
"num_tokens": 28790829.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.493164587020874,
|
|
"epoch": 1.2586175616835993,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004847514744352561,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.17944961339235305,
|
|
"num_tokens": 28801036.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.480087518692017,
|
|
"epoch": 1.2590711175616836,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004847397634660768,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.1799040913581848,
|
|
"num_tokens": 28811013.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.576053714752197,
|
|
"epoch": 1.2595246734397678,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048472804815942575,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.17565877139568328,
|
|
"num_tokens": 28821367.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.593064785003662,
|
|
"epoch": 1.259978229317852,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048471632851554517,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.17698910236358642,
|
|
"num_tokens": 28831077.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.57422251701355,
|
|
"epoch": 1.2604317851959361,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004847046045346775,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.1693313956260681,
|
|
"num_tokens": 28841490.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.591898250579834,
|
|
"epoch": 1.2608853410740204,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048469287621706516,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.16982273012399673,
|
|
"num_tokens": 28852510.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.57936429977417,
|
|
"epoch": 1.2613388969521044,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004846811435629507,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.17442412674427032,
|
|
"num_tokens": 28863388.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.494202566146851,
|
|
"epoch": 1.2617924528301887,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004846694065725768,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.17659474164247513,
|
|
"num_tokens": 28873798.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.588933515548706,
|
|
"epoch": 1.262246008708273,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004846576652461861,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.17719524800777436,
|
|
"num_tokens": 28883482.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.571336030960083,
|
|
"epoch": 1.262699564586357,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048464591958402147,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.17565980404615403,
|
|
"num_tokens": 28893573.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.652734994888306,
|
|
"epoch": 1.2631531204644413,
|
|
"grad_norm": 5.59375,
|
|
"learning_rate": 0.00048463416958632573,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.17066749930381775,
|
|
"num_tokens": 28904064.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.637394189834595,
|
|
"epoch": 1.2636066763425253,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048462241525334206,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.17052133977413178,
|
|
"num_tokens": 28915329.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.586847114562988,
|
|
"epoch": 1.2640602322206096,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004846106565853133,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1688288614153862,
|
|
"num_tokens": 28925228.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.589742755889892,
|
|
"epoch": 1.2645137880986939,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.00048459889358248284,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.17173005044460296,
|
|
"num_tokens": 28935891.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.602288722991943,
|
|
"epoch": 1.264967343976778,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048458712624509383,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.17830158472061158,
|
|
"num_tokens": 28946372.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.611473178863525,
|
|
"epoch": 1.2654208998548622,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00048457535457338964,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.17337343245744705,
|
|
"num_tokens": 28957874.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.6025785446167,
|
|
"epoch": 1.2658744557329462,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004845635785676137,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.1646830677986145,
|
|
"num_tokens": 28968023.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.545039701461792,
|
|
"epoch": 1.2663280116110305,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048455179822800957,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.1761086106300354,
|
|
"num_tokens": 28977744.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.6339164733886715,
|
|
"epoch": 1.2667815674891147,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004845400135548208,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.16729221642017364,
|
|
"num_tokens": 28988875.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.566168642044067,
|
|
"epoch": 1.2672351233671988,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004845282245482912,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.17748188078403473,
|
|
"num_tokens": 28998562.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.605121660232544,
|
|
"epoch": 1.267688679245283,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004845164312086646,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.18036383986473084,
|
|
"num_tokens": 29008783.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.507620191574096,
|
|
"epoch": 1.268142235123367,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004845046335361847,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.17694439440965654,
|
|
"num_tokens": 29019303.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.590313148498535,
|
|
"epoch": 1.2685957910014514,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048449283153109566,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.16927626430988313,
|
|
"num_tokens": 29029843.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.647569561004639,
|
|
"epoch": 1.2690493468795356,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004844810251936413,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1699263259768486,
|
|
"num_tokens": 29040603.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.578702926635742,
|
|
"epoch": 1.2695029027576197,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004844692145240661,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.17437443286180496,
|
|
"num_tokens": 29050599.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.595240592956543,
|
|
"epoch": 1.269956458635704,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004844573995226142,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.17279112488031387,
|
|
"num_tokens": 29061292.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.576063728332519,
|
|
"epoch": 1.270410014513788,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048444558018952984,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.18096554577350615,
|
|
"num_tokens": 29071779.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.5674886226654055,
|
|
"epoch": 1.2708635703918723,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048443375652505754,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.17743561863899232,
|
|
"num_tokens": 29082073.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.5836893081665036,
|
|
"epoch": 1.2713171262699565,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004844219285294418,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.17464204579591752,
|
|
"num_tokens": 29092032.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.536452293395996,
|
|
"epoch": 1.2717706821480406,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048441009620292714,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.18139055967330933,
|
|
"num_tokens": 29102936.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.584950637817383,
|
|
"epoch": 1.2722242380261248,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004843982595457584,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.1767016664147377,
|
|
"num_tokens": 29113385.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.538218832015991,
|
|
"epoch": 1.2726777939042089,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048438641855818026,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.17236390858888626,
|
|
"num_tokens": 29125075.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.606749868392944,
|
|
"epoch": 1.2731313497822931,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004843745732404376,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.17292884588241578,
|
|
"num_tokens": 29135098.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.621056032180786,
|
|
"epoch": 1.2735849056603774,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004843627235927755,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.176491641998291,
|
|
"num_tokens": 29145577.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.535854721069336,
|
|
"epoch": 1.2740384615384617,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004843508696154388,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.17485394179821015,
|
|
"num_tokens": 29155905.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.540239381790161,
|
|
"epoch": 1.2744920174165457,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 0.00048433901130867283,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.17786966264247894,
|
|
"num_tokens": 29164926.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.565501737594604,
|
|
"epoch": 1.2749455732946298,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004843271486727228,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.17572084963321685,
|
|
"num_tokens": 29175050.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.542440462112427,
|
|
"epoch": 1.275399129172714,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00048431528170783395,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.16913863271474838,
|
|
"num_tokens": 29186255.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.603945970535278,
|
|
"epoch": 1.2758526850507983,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.0004843034104142517,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.18160293996334076,
|
|
"num_tokens": 29195639.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.615475225448608,
|
|
"epoch": 1.2763062409288826,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004842915347922216,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.16717389822006226,
|
|
"num_tokens": 29206482.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.617571115493774,
|
|
"epoch": 1.2767597968069666,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004842796548419893,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17026246339082718,
|
|
"num_tokens": 29217433.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.620957708358764,
|
|
"epoch": 1.2772133526850509,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048426777056380035,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.165461266040802,
|
|
"num_tokens": 29226193.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.516555881500244,
|
|
"epoch": 1.277666908563135,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004842558819579006,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.17778911292552949,
|
|
"num_tokens": 29237061.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.512198257446289,
|
|
"epoch": 1.2781204644412192,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004842439890245358,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.1845606416463852,
|
|
"num_tokens": 29247689.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.520582437515259,
|
|
"epoch": 1.2785740203193035,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048423209176395204,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.17814113199710846,
|
|
"num_tokens": 29258235.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.5709623336792,
|
|
"epoch": 1.2790275761973875,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004842201901763954,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.1762159213423729,
|
|
"num_tokens": 29268884.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.5821925640106205,
|
|
"epoch": 1.2794811320754718,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004842082842621118,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.16802155822515488,
|
|
"num_tokens": 29280484.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.636690616607666,
|
|
"epoch": 1.2799346879535558,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004841963740213476,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17644825279712678,
|
|
"num_tokens": 29291199.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.670208406448364,
|
|
"epoch": 1.28038824383164,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004841844594543491,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.1748999461531639,
|
|
"num_tokens": 29302007.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.590766382217407,
|
|
"epoch": 1.2808417997097243,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004841725405613626,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18238283842802047,
|
|
"num_tokens": 29312127.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.5790143489837645,
|
|
"epoch": 1.2812953555878084,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004841606173426347,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.17037187814712523,
|
|
"num_tokens": 29323691.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.574641561508178,
|
|
"epoch": 1.2817489114658926,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.00048414868979841197,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.1665747731924057,
|
|
"num_tokens": 29335203.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.678859043121338,
|
|
"epoch": 1.2822024673439767,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.00048413675792894105,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.17578777819871902,
|
|
"num_tokens": 29346422.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.594743442535401,
|
|
"epoch": 1.282656023222061,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004841248217344686,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.17514521181583403,
|
|
"num_tokens": 29356084.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.506899070739746,
|
|
"epoch": 1.2831095791001452,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004841128812152415,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.17588884979486466,
|
|
"num_tokens": 29366093.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.573301553726196,
|
|
"epoch": 1.2835631349782293,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004841009363715068,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.1706303671002388,
|
|
"num_tokens": 29376621.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.647098398208618,
|
|
"epoch": 1.2840166908563135,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004840889872035115,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1716342732310295,
|
|
"num_tokens": 29387119.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.5658587455749515,
|
|
"epoch": 1.2844702467343976,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004840770337115026,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.17690143287181853,
|
|
"num_tokens": 29396981.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.581387710571289,
|
|
"epoch": 1.2849238026124818,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048406507589572747,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.17793996781110763,
|
|
"num_tokens": 29406737.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.620014095306397,
|
|
"epoch": 1.2853773584905661,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004840531137564331,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.17301466912031174,
|
|
"num_tokens": 29417300.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.620226097106934,
|
|
"epoch": 1.2858309143686502,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004840411472938672,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.1822351783514023,
|
|
"num_tokens": 29426749.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.50346884727478,
|
|
"epoch": 1.2862844702467344,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004840291765082771,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.1771259680390358,
|
|
"num_tokens": 29437264.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.537852430343628,
|
|
"epoch": 1.2867380261248185,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00048401720139991036,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17025234550237656,
|
|
"num_tokens": 29448192.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.609713506698609,
|
|
"epoch": 1.2871915820029027,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004840052219690146,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.18591743111610412,
|
|
"num_tokens": 29457923.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.487228536605835,
|
|
"epoch": 1.287645137880987,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004839932382158376,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.18596986830234527,
|
|
"num_tokens": 29466914.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.531790113449096,
|
|
"epoch": 1.288098693759071,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004839812501406272,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.1714567095041275,
|
|
"num_tokens": 29477648.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.63369517326355,
|
|
"epoch": 1.2885522496371553,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004839692577436313,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17652663439512253,
|
|
"num_tokens": 29487947.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.712900400161743,
|
|
"epoch": 1.2890058055152394,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004839572610250978,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.1679430440068245,
|
|
"num_tokens": 29497667.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.595472431182861,
|
|
"epoch": 1.2894593613933236,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048394525998527496,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.17251573652029037,
|
|
"num_tokens": 29507065.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.613528299331665,
|
|
"epoch": 1.2899129172714079,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004839332546244109,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.1717883124947548,
|
|
"num_tokens": 29517752.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.629713726043701,
|
|
"epoch": 1.2903664731494922,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048392124494275385,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.17212332785129547,
|
|
"num_tokens": 29527894.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.587793636322021,
|
|
"epoch": 1.2908200290275762,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004839092309405523,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.16875882893800737,
|
|
"num_tokens": 29538136.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.598608922958374,
|
|
"epoch": 1.2912735849056602,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.00048389721261805457,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1747458204627037,
|
|
"num_tokens": 29549193.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.530500507354736,
|
|
"epoch": 1.2917271407837445,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048388518997550926,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.1818700060248375,
|
|
"num_tokens": 29558889.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.57679009437561,
|
|
"epoch": 1.2921806966618288,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048387316301316493,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.1677996590733528,
|
|
"num_tokens": 29569691.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.595895290374756,
|
|
"epoch": 1.292634252539913,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004838611317312705,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.1709785968065262,
|
|
"num_tokens": 29580459.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.58565616607666,
|
|
"epoch": 1.293087808417997,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004838490961300745,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.170879827439785,
|
|
"num_tokens": 29590652.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.574022960662842,
|
|
"epoch": 1.2935413642960814,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048383705620982606,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.18456486910581588,
|
|
"num_tokens": 29600353.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.573683357238769,
|
|
"epoch": 1.2939949201741654,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048382501197077405,
|
|
"loss": 5.32,
|
|
"mean_token_accuracy": 0.18218221813440322,
|
|
"num_tokens": 29610561.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.56094446182251,
|
|
"epoch": 1.2944484760522497,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004838129634131675,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.1744862377643585,
|
|
"num_tokens": 29621741.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.595221090316772,
|
|
"epoch": 1.294902031930334,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004838009105372558,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.1733754977583885,
|
|
"num_tokens": 29633097.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.595546388626099,
|
|
"epoch": 1.295355587808418,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048378885334328793,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.16239650547504425,
|
|
"num_tokens": 29644290.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.664061069488525,
|
|
"epoch": 1.2958091436865022,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004837767918315135,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.16826958060264588,
|
|
"num_tokens": 29654977.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.617649936676026,
|
|
"epoch": 1.2962626995645863,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.00048376472600218174,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.1715206876397133,
|
|
"num_tokens": 29665020.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.614870643615722,
|
|
"epoch": 1.2967162554426706,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004837526558555422,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.17420814484357833,
|
|
"num_tokens": 29675098.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.557895946502685,
|
|
"epoch": 1.2971698113207548,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004837405813918446,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.17971768379211425,
|
|
"num_tokens": 29685450.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.542715930938721,
|
|
"epoch": 1.2976233671988389,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048372850261133856,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.17652963995933532,
|
|
"num_tokens": 29694818.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.61685094833374,
|
|
"epoch": 1.2980769230769231,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00048371641951427393,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.17161611020565032,
|
|
"num_tokens": 29705573.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.616137933731079,
|
|
"epoch": 1.2985304789550072,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048370433210090055,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.16940421611070633,
|
|
"num_tokens": 29716366.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.55403962135315,
|
|
"epoch": 1.2989840348330914,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004836922403714683,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.17545078992843627,
|
|
"num_tokens": 29727181.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.5547308921813965,
|
|
"epoch": 1.2994375907111757,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048368014432622746,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.17786243706941604,
|
|
"num_tokens": 29736960.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.564285802841186,
|
|
"epoch": 1.2998911465892597,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.000483668043965428,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.1873780980706215,
|
|
"num_tokens": 29746354.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.573829126358032,
|
|
"epoch": 1.300344702467344,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004836559392893203,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.1724160149693489,
|
|
"num_tokens": 29756627.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.5727660179138185,
|
|
"epoch": 1.300798258345428,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004836438302981545,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18192365765571594,
|
|
"num_tokens": 29766684.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.5299266338348385,
|
|
"epoch": 1.3012518142235123,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004836317169921811,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.17365316897630692,
|
|
"num_tokens": 29776556.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.653978776931763,
|
|
"epoch": 1.3017053701015966,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.00048361959937165075,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.17234432697296143,
|
|
"num_tokens": 29786896.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.641994857788086,
|
|
"epoch": 1.3021589259796806,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004836074774368138,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.1803387701511383,
|
|
"num_tokens": 29797332.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.605131053924561,
|
|
"epoch": 1.302612481857765,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.00048359535118792116,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.17664601057767867,
|
|
"num_tokens": 29806428.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.558047676086426,
|
|
"epoch": 1.303066037735849,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004835832206252235,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.17150520533323288,
|
|
"num_tokens": 29816794.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.636795949935913,
|
|
"epoch": 1.3035195936139332,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004835710857489716,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.17814830988645552,
|
|
"num_tokens": 29827077.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.582400703430176,
|
|
"epoch": 1.3039731494920175,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004835589465594165,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.17814186364412307,
|
|
"num_tokens": 29837868.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.614265441894531,
|
|
"epoch": 1.3044267053701015,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048354680305680926,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.17542893588542938,
|
|
"num_tokens": 29846929.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.527841424942016,
|
|
"epoch": 1.3048802612481858,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048353465524140105,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.1783314049243927,
|
|
"num_tokens": 29857905.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.55200047492981,
|
|
"epoch": 1.3053338171262698,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.000483522503113443,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.1743301570415497,
|
|
"num_tokens": 29868230.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.52324366569519,
|
|
"epoch": 1.305787373004354,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048351034667318634,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.17327929586172103,
|
|
"num_tokens": 29879224.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.626120519638062,
|
|
"epoch": 1.3062409288824384,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004834981859208827,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.16675183176994324,
|
|
"num_tokens": 29890416.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.66015248298645,
|
|
"epoch": 1.3066944847605226,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.00048348602085678346,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.17032576054334642,
|
|
"num_tokens": 29901064.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.730725383758545,
|
|
"epoch": 1.3071480406386067,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048347385148114004,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.17141589671373367,
|
|
"num_tokens": 29911084.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.5188093185424805,
|
|
"epoch": 1.3076015965166907,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00048346167779420436,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.17884353399276734,
|
|
"num_tokens": 29921104.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.587260150909424,
|
|
"epoch": 1.308055152394775,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048344949979622806,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.17668967247009276,
|
|
"num_tokens": 29932014.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.558705139160156,
|
|
"epoch": 1.3085087082728593,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048343731748746294,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.17766952514648438,
|
|
"num_tokens": 29941707.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.539162826538086,
|
|
"epoch": 1.3089622641509435,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000483425130868161,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.17264337688684464,
|
|
"num_tokens": 29952082.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.52536096572876,
|
|
"epoch": 1.3094158200290276,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004834129399385742,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.1933560460805893,
|
|
"num_tokens": 29961744.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.60400242805481,
|
|
"epoch": 1.3098693759071118,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004834007446989548,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18017879426479338,
|
|
"num_tokens": 29972611.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.549803972244263,
|
|
"epoch": 1.3103229317851959,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048338854514955474,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.1845446929335594,
|
|
"num_tokens": 29982660.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.550955057144165,
|
|
"epoch": 1.3107764876632801,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048337634129062655,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.16491775959730148,
|
|
"num_tokens": 29993349.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.618444108963013,
|
|
"epoch": 1.3112300435413644,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00048336413312242255,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.16765930950641633,
|
|
"num_tokens": 30004474.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.631626129150391,
|
|
"epoch": 1.3116835994194485,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048335192064519514,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.1729219973087311,
|
|
"num_tokens": 30015189.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.615939140319824,
|
|
"epoch": 1.3121371552975327,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048333970385919695,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.17484485656023024,
|
|
"num_tokens": 30025491.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.5642561435699465,
|
|
"epoch": 1.3125907111756168,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048332748276468053,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.17495635747909546,
|
|
"num_tokens": 30034683.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.520941114425659,
|
|
"epoch": 1.313044267053701,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004833152573618987,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.1753089800477028,
|
|
"num_tokens": 30044135.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.5774375915527346,
|
|
"epoch": 1.3134978229317853,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00048330302765110436,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.17630247473716737,
|
|
"num_tokens": 30054520.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.620419597625732,
|
|
"epoch": 1.3139513788098693,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00048329079363255024,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.1691085249185562,
|
|
"num_tokens": 30065439.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.61645827293396,
|
|
"epoch": 1.3144049346879536,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.00048327855530648934,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.17591703236103057,
|
|
"num_tokens": 30075362.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.524699974060058,
|
|
"epoch": 1.3148584905660377,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000483266312673175,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.17203290313482283,
|
|
"num_tokens": 30084913.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.588080596923828,
|
|
"epoch": 1.315312046444122,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004832540657328602,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.17741949260234832,
|
|
"num_tokens": 30095704.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.555439853668213,
|
|
"epoch": 1.3157656023222062,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004832418144857982,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.17525641918182372,
|
|
"num_tokens": 30105981.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.537001419067383,
|
|
"epoch": 1.3162191582002902,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048322955893224245,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.17036312073469162,
|
|
"num_tokens": 30115772.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.579875469207764,
|
|
"epoch": 1.3166727140783745,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.00048321729907244626,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.1734536573290825,
|
|
"num_tokens": 30127050.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.598989963531494,
|
|
"epoch": 1.3171262699564585,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004832050349066634,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.17404793351888656,
|
|
"num_tokens": 30138221.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.625929832458496,
|
|
"epoch": 1.3175798258345428,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004831927664351473,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.1705172449350357,
|
|
"num_tokens": 30150181.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.58912501335144,
|
|
"epoch": 1.318033381712627,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004831804936581518,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17455049604177475,
|
|
"num_tokens": 30160521.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.627479076385498,
|
|
"epoch": 1.3184869375907111,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004831682165759305,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17037987262010573,
|
|
"num_tokens": 30170611.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.647074174880982,
|
|
"epoch": 1.3189404934687954,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.00048315593518873757,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.17692942619323732,
|
|
"num_tokens": 30179914.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.575990104675293,
|
|
"epoch": 1.3193940493468794,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004831436494968268,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.17755057066679,
|
|
"num_tokens": 30191426.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.53160662651062,
|
|
"epoch": 1.3198476052249637,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048313135950045234,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.17838724404573442,
|
|
"num_tokens": 30202813.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.514211893081665,
|
|
"epoch": 1.320301161103048,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048311906519986824,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.18271743953227998,
|
|
"num_tokens": 30213044.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.59300012588501,
|
|
"epoch": 1.320754716981132,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.000483106766595329,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.17218518853187562,
|
|
"num_tokens": 30223419.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.600766897201538,
|
|
"epoch": 1.3212082728592163,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004830944636870887,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.16912604719400406,
|
|
"num_tokens": 30233203.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.626376008987426,
|
|
"epoch": 1.3216618287373003,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00048308215647540183,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.16886424869298935,
|
|
"num_tokens": 30244604.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.618494510650635,
|
|
"epoch": 1.3221153846153846,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048306984496052297,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.17318980395793915,
|
|
"num_tokens": 30255355.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.62944016456604,
|
|
"epoch": 1.3225689404934688,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048305752914270665,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.1672905758023262,
|
|
"num_tokens": 30265665.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.630397844314575,
|
|
"epoch": 1.3230224963715531,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00048304520902220767,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.1761367589235306,
|
|
"num_tokens": 30274347.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.607367658615113,
|
|
"epoch": 1.3234760522496372,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004830328845992808,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.18162842839956284,
|
|
"num_tokens": 30284243.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.469470977783203,
|
|
"epoch": 1.3239296081277212,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048302055587418074,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1771307483315468,
|
|
"num_tokens": 30294327.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.516725826263428,
|
|
"epoch": 1.3243831640058055,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004830082228471626,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.17763551324605942,
|
|
"num_tokens": 30304188.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.618366765975952,
|
|
"epoch": 1.3248367198838897,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.00048299588551848146,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.1809214636683464,
|
|
"num_tokens": 30314917.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.578002119064331,
|
|
"epoch": 1.325290275761974,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00048298354388839237,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.17485674619674682,
|
|
"num_tokens": 30325221.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.6580933094024655,
|
|
"epoch": 1.325743831640058,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004829711979571506,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.16982516497373581,
|
|
"num_tokens": 30336196.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.53471188545227,
|
|
"epoch": 1.3261973875181423,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004829588477250115,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.18727820217609406,
|
|
"num_tokens": 30345546.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.517544174194336,
|
|
"epoch": 1.3266509433962264,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004829464931922304,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.1726578325033188,
|
|
"num_tokens": 30355672.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.6081907749176025,
|
|
"epoch": 1.3271044992743106,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048293413435906285,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.17273131310939788,
|
|
"num_tokens": 30366233.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.629884862899781,
|
|
"epoch": 1.327558055152395,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004829217712257644,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.17876290082931517,
|
|
"num_tokens": 30377366.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.5762341022491455,
|
|
"epoch": 1.328011611030479,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00048290940379259073,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.17302599251270295,
|
|
"num_tokens": 30388022.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.579840612411499,
|
|
"epoch": 1.3284651669085632,
|
|
"grad_norm": 7.53125,
|
|
"learning_rate": 0.00048289703205979756,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.17411655634641648,
|
|
"num_tokens": 30399235.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.672154331207276,
|
|
"epoch": 1.3289187227866472,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048288465602764084,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.16967085152864456,
|
|
"num_tokens": 30409112.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.557979011535645,
|
|
"epoch": 1.3293722786647315,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048287227569637645,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.1765489861369133,
|
|
"num_tokens": 30420202.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.613364887237549,
|
|
"epoch": 1.3298258345428158,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048285989106626036,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.17810803204774855,
|
|
"num_tokens": 30431210.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.600608921051025,
|
|
"epoch": 1.3302793904208998,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004828475021375489,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.17770425826311112,
|
|
"num_tokens": 30441291.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.547167205810547,
|
|
"epoch": 1.330732946298984,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004828351089104981,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18351980298757553,
|
|
"num_tokens": 30450285.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.5321026802062985,
|
|
"epoch": 1.3311865021770681,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.00048282271138536424,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.1722715437412262,
|
|
"num_tokens": 30460311.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.680997323989868,
|
|
"epoch": 1.3316400580551524,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004828103095624037,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.16947381645441056,
|
|
"num_tokens": 30470188.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.572077417373658,
|
|
"epoch": 1.3320936139332367,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000482797903441873,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.17391078025102616,
|
|
"num_tokens": 30481406.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.479278564453125,
|
|
"epoch": 1.3325471698113207,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004827854930240288,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.17948488891124725,
|
|
"num_tokens": 30492314.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.58660249710083,
|
|
"epoch": 1.333000725689405,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004827730783091276,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.16671850234270097,
|
|
"num_tokens": 30503273.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.646798706054687,
|
|
"epoch": 1.333454281567489,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00048276065929742616,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.17752225548028946,
|
|
"num_tokens": 30513582.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.576589775085449,
|
|
"epoch": 1.3339078374455733,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004827482359891814,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.17876120358705522,
|
|
"num_tokens": 30523261.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.557085752487183,
|
|
"epoch": 1.3343613933236576,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048273580838465016,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.17147661447525026,
|
|
"num_tokens": 30533774.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.613748359680176,
|
|
"epoch": 1.3348149492017416,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004827233764840894,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17482657581567765,
|
|
"num_tokens": 30544580.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.625464963912964,
|
|
"epoch": 1.3352685050798259,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004827109402877564,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.1773221969604492,
|
|
"num_tokens": 30555105.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.568336868286133,
|
|
"epoch": 1.33572206095791,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004826984997959082,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.16772764623165132,
|
|
"num_tokens": 30564912.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.546491813659668,
|
|
"epoch": 1.3361756168359942,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.000482686055008802,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.1742671862244606,
|
|
"num_tokens": 30575862.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.564079713821411,
|
|
"epoch": 1.3366291727140784,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048267360592669535,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.1716134801506996,
|
|
"num_tokens": 30586951.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.5788383960723875,
|
|
"epoch": 1.3370827285921625,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004826611525498456,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17495224326848985,
|
|
"num_tokens": 30597604.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.642521047592163,
|
|
"epoch": 1.3375362844702468,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004826486948785103,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.17303643524646758,
|
|
"num_tokens": 30608157.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.613686227798462,
|
|
"epoch": 1.3379898403483308,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00048263623291294706,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.17162981629371643,
|
|
"num_tokens": 30618527.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.613192796707153,
|
|
"epoch": 1.338443396226415,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00048262376665341355,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.16945113241672516,
|
|
"num_tokens": 30629253.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.595995950698852,
|
|
"epoch": 1.3388969521044993,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004826112961001677,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.1626031368970871,
|
|
"num_tokens": 30639015.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.691329002380371,
|
|
"epoch": 1.3393505079825834,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00048259882125346735,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.1610155239701271,
|
|
"num_tokens": 30650035.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.590901136398315,
|
|
"epoch": 1.3398040638606676,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048258634211357045,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.17194414436817168,
|
|
"num_tokens": 30659813.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.570027923583984,
|
|
"epoch": 1.3402576197387517,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004825738586807351,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.17335225641727448,
|
|
"num_tokens": 30670243.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.546255826950073,
|
|
"epoch": 1.340711175616836,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048256137095521945,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.1731187880039215,
|
|
"num_tokens": 30680056.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.580109119415283,
|
|
"epoch": 1.3411647314949202,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048254887893728175,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.1779971808195114,
|
|
"num_tokens": 30690536.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.542200756072998,
|
|
"epoch": 1.3416182873730045,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004825363826271804,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.1733024775981903,
|
|
"num_tokens": 30700200.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.511820363998413,
|
|
"epoch": 1.3420718432510885,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004825238820251737,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.17725178897380828,
|
|
"num_tokens": 30710576.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.565164995193482,
|
|
"epoch": 1.3425253991291728,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048251137713152027,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.16702319532632828,
|
|
"num_tokens": 30721495.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.569557046890258,
|
|
"epoch": 1.3429789550072568,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004824988679464787,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.1734679028391838,
|
|
"num_tokens": 30731700.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.629995059967041,
|
|
"epoch": 1.343432510885341,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00048248635447030767,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.16986653208732605,
|
|
"num_tokens": 30743421.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.567506456375122,
|
|
"epoch": 1.3438860667634254,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004824738367032659,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.1790758728981018,
|
|
"num_tokens": 30754238.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.579785871505737,
|
|
"epoch": 1.3443396226415094,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004824613146456123,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17224185913801193,
|
|
"num_tokens": 30763938.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.6040191650390625,
|
|
"epoch": 1.3447931785195937,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004824487882976059,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.1700545772910118,
|
|
"num_tokens": 30773654.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.66545557975769,
|
|
"epoch": 1.3452467343976777,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048243625765950564,
|
|
"loss": 5.3793,
|
|
"mean_token_accuracy": 0.16727219223976136,
|
|
"num_tokens": 30784659.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.543287754058838,
|
|
"epoch": 1.345700290275762,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004824237227315708,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.16864370703697204,
|
|
"num_tokens": 30795194.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.476270246505737,
|
|
"epoch": 1.3461538461538463,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004824111835140604,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.18628957420587539,
|
|
"num_tokens": 30805623.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.5201915264129635,
|
|
"epoch": 1.3466074020319303,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000482398640007234,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.18110164999961853,
|
|
"num_tokens": 30814899.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.555194616317749,
|
|
"epoch": 1.3470609579100146,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048238609221135076,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.16786562353372575,
|
|
"num_tokens": 30825546.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.499044179916382,
|
|
"epoch": 1.3475145137880986,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004823735401266704,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.17715806365013123,
|
|
"num_tokens": 30836406.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.559240770339966,
|
|
"epoch": 1.3479680696661829,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.00048236098375345227,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.17311821430921553,
|
|
"num_tokens": 30847966.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.66569414138794,
|
|
"epoch": 1.3484216255442671,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004823484230919563,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17487807273864747,
|
|
"num_tokens": 30856831.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.487578392028809,
|
|
"epoch": 1.3488751814223512,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048233585814244195,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1836571589112282,
|
|
"num_tokens": 30866076.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.502755832672119,
|
|
"epoch": 1.3493287373004355,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004823232889051693,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.18168337643146515,
|
|
"num_tokens": 30876845.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.527269411087036,
|
|
"epoch": 1.3497822931785195,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048231071538039816,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.17084167152643204,
|
|
"num_tokens": 30887448.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.607729387283325,
|
|
"epoch": 1.3502358490566038,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00048229813756838863,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.1751062110066414,
|
|
"num_tokens": 30898414.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.596131372451782,
|
|
"epoch": 1.350689404934688,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004822855554694007,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.17376189231872557,
|
|
"num_tokens": 30908559.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.57922043800354,
|
|
"epoch": 1.351142960812772,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048227296908369475,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.17814643383026124,
|
|
"num_tokens": 30918655.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.540636777877808,
|
|
"epoch": 1.3515965166908563,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048226037841153104,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.17941174656152725,
|
|
"num_tokens": 30929188.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.617151594161987,
|
|
"epoch": 1.3520500725689404,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004822477834531698,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.17542280852794648,
|
|
"num_tokens": 30939902.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.570489454269409,
|
|
"epoch": 1.3525036284470247,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004822351842088716,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17203953862190247,
|
|
"num_tokens": 30951289.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.6825377464294435,
|
|
"epoch": 1.352957184325109,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004822225806788969,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.16396759450435638,
|
|
"num_tokens": 30961233.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.647076797485352,
|
|
"epoch": 1.353410740203193,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.00048220997286350654,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.18247477412223817,
|
|
"num_tokens": 30971922.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.567844486236572,
|
|
"epoch": 1.3538642960812772,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.00048219736076296114,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.17440518289804458,
|
|
"num_tokens": 30981358.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.580735588073731,
|
|
"epoch": 1.3543178519593613,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004821847443775214,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.1733836606144905,
|
|
"num_tokens": 30991984.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.5941376209259035,
|
|
"epoch": 1.3547714078374455,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00048217212370744853,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.17704341262578965,
|
|
"num_tokens": 31002790.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.499529409408569,
|
|
"epoch": 1.3552249637155298,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.00048215949875300327,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.18547530621290206,
|
|
"num_tokens": 31012827.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.4738743782043455,
|
|
"epoch": 1.3556785195936139,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004821468695144467,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.17176304012537003,
|
|
"num_tokens": 31023075.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.5304771900177006,
|
|
"epoch": 1.3561320754716981,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048213423599204015,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18099177926778792,
|
|
"num_tokens": 31032454.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.6834893226623535,
|
|
"epoch": 1.3565856313497822,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00048212159818604477,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.16614234894514085,
|
|
"num_tokens": 31042498.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.565841150283814,
|
|
"epoch": 1.3570391872278664,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000482108956096722,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.1715633600950241,
|
|
"num_tokens": 31053188.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.568301200866699,
|
|
"epoch": 1.3574927431059507,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.00048209630972433326,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18262624591588975,
|
|
"num_tokens": 31062840.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.6303094863891605,
|
|
"epoch": 1.357946298984035,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048208365906914,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.17723245173692703,
|
|
"num_tokens": 31072646.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.539926385879516,
|
|
"epoch": 1.358399854862119,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048207100413140397,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.17492770701646804,
|
|
"num_tokens": 31082700.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.608774471282959,
|
|
"epoch": 1.3588534107402033,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004820583449113868,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.16961142644286156,
|
|
"num_tokens": 31093743.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.567367315292358,
|
|
"epoch": 1.3593069666182873,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048204568140935023,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.1769140988588333,
|
|
"num_tokens": 31104293.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.527382898330688,
|
|
"epoch": 1.3597605224963716,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004820330136255563,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17653436809778214,
|
|
"num_tokens": 31114244.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.552898788452149,
|
|
"epoch": 1.3602140783744558,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.00048202034156026683,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.17202102094888688,
|
|
"num_tokens": 31123596.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.605963468551636,
|
|
"epoch": 1.36066763425254,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048200766521374396,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.16639875918626784,
|
|
"num_tokens": 31134258.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.36066763425254,
|
|
"eval_entropy": 5.434485418872057,
|
|
"eval_loss": 5.401484966278076,
|
|
"eval_mean_token_accuracy": 0.1792781375904833,
|
|
"eval_num_tokens": 31134258.0,
|
|
"eval_runtime": 26.4259,
|
|
"eval_samples_per_second": 1338.082,
|
|
"eval_steps_per_second": 167.26,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"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": 4.5626844227328e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|