d94c6efa35
Model: fpadovani/swe-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5040957781978576,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.897539186477661,
|
|
"epoch": 0.0004200798151648813,
|
|
"grad_norm": 14.0,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.0815,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8348.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.873638677597046,
|
|
"epoch": 0.0008401596303297626,
|
|
"grad_norm": 13.625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.0885,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17465.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.912403154373169,
|
|
"epoch": 0.001260239445494644,
|
|
"grad_norm": 15.4375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.0641,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 26627.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.9623668670654295,
|
|
"epoch": 0.0016803192606595252,
|
|
"grad_norm": 17.875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.8986,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 36069.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.122641944885254,
|
|
"epoch": 0.002100399075824407,
|
|
"grad_norm": 21.0,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.4962,
|
|
"mean_token_accuracy": 0.00036849312018603084,
|
|
"num_tokens": 44967.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.440350961685181,
|
|
"epoch": 0.002520478890989288,
|
|
"grad_norm": 25.875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.0078,
|
|
"mean_token_accuracy": 0.00010752688394859433,
|
|
"num_tokens": 55132.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.052726125717163,
|
|
"epoch": 0.0029405587061541692,
|
|
"grad_norm": 21.25,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.9064,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 65141.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.193820476531982,
|
|
"epoch": 0.0033606385213190504,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.8374,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 74007.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.727454471588135,
|
|
"epoch": 0.003780718336483932,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6658,
|
|
"mean_token_accuracy": 0.004875225311843678,
|
|
"num_tokens": 83736.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.743746089935303,
|
|
"epoch": 0.004200798151648814,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.4916,
|
|
"mean_token_accuracy": 0.01765382578596473,
|
|
"num_tokens": 92525.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.714706707000733,
|
|
"epoch": 0.004620877966813695,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.3094,
|
|
"mean_token_accuracy": 0.01746684079989791,
|
|
"num_tokens": 102015.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.654456615447998,
|
|
"epoch": 0.005040957781978576,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1455,
|
|
"mean_token_accuracy": 0.019217501021921636,
|
|
"num_tokens": 110887.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.696210289001465,
|
|
"epoch": 0.005461037597143457,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.0256,
|
|
"mean_token_accuracy": 0.018034272640943528,
|
|
"num_tokens": 120442.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.72099323272705,
|
|
"epoch": 0.0058811174123083385,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8848,
|
|
"mean_token_accuracy": 0.029999475181102752,
|
|
"num_tokens": 129297.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.713169956207276,
|
|
"epoch": 0.00630119722747322,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8186,
|
|
"mean_token_accuracy": 0.03141374848783016,
|
|
"num_tokens": 138305.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.702960300445557,
|
|
"epoch": 0.006721277042638101,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7553,
|
|
"mean_token_accuracy": 0.023225654661655427,
|
|
"num_tokens": 147640.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.704542255401611,
|
|
"epoch": 0.007141356857802983,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6696,
|
|
"mean_token_accuracy": 0.02769038388505578,
|
|
"num_tokens": 157633.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.70653486251831,
|
|
"epoch": 0.007561436672967864,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.607,
|
|
"mean_token_accuracy": 0.04190691113471985,
|
|
"num_tokens": 167984.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.694128608703613,
|
|
"epoch": 0.007981516488132745,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4789,
|
|
"mean_token_accuracy": 0.05244061499834061,
|
|
"num_tokens": 176984.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.663659858703614,
|
|
"epoch": 0.008401596303297627,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.3453,
|
|
"mean_token_accuracy": 0.043341046944260594,
|
|
"num_tokens": 185931.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.635926151275635,
|
|
"epoch": 0.008821676118462508,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2908,
|
|
"mean_token_accuracy": 0.04105062447488308,
|
|
"num_tokens": 195065.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.617516040802002,
|
|
"epoch": 0.00924175593362739,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1462,
|
|
"mean_token_accuracy": 0.05056820251047611,
|
|
"num_tokens": 203687.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.578640842437744,
|
|
"epoch": 0.00966183574879227,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0627,
|
|
"mean_token_accuracy": 0.05324659980833531,
|
|
"num_tokens": 212847.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.534226608276366,
|
|
"epoch": 0.010081915563957152,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9326,
|
|
"mean_token_accuracy": 0.05340988412499428,
|
|
"num_tokens": 222593.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.47627763748169,
|
|
"epoch": 0.010501995379122032,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7909,
|
|
"mean_token_accuracy": 0.05306763276457786,
|
|
"num_tokens": 231174.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.402797031402589,
|
|
"epoch": 0.010922075194286915,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6666,
|
|
"mean_token_accuracy": 0.0565425343811512,
|
|
"num_tokens": 239833.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.321593379974365,
|
|
"epoch": 0.011342155009451797,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6377,
|
|
"mean_token_accuracy": 0.05593148916959763,
|
|
"num_tokens": 248794.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.22030849456787,
|
|
"epoch": 0.011762234824616677,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.5488,
|
|
"mean_token_accuracy": 0.05581129565834999,
|
|
"num_tokens": 257123.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.1541109085083,
|
|
"epoch": 0.012182314639781559,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.309,
|
|
"mean_token_accuracy": 0.05627111345529556,
|
|
"num_tokens": 266088.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.05057725906372,
|
|
"epoch": 0.01260239445494644,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.3916,
|
|
"mean_token_accuracy": 0.05131003558635712,
|
|
"num_tokens": 276074.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.931949615478516,
|
|
"epoch": 0.013022474270111321,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.2337,
|
|
"mean_token_accuracy": 0.05355307124555111,
|
|
"num_tokens": 285280.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.78201379776001,
|
|
"epoch": 0.013442554085276202,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.1889,
|
|
"mean_token_accuracy": 0.05086107552051544,
|
|
"num_tokens": 296115.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.592757034301759,
|
|
"epoch": 0.013862633900441084,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.0092,
|
|
"mean_token_accuracy": 0.05353938601911068,
|
|
"num_tokens": 305483.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.374695110321046,
|
|
"epoch": 0.014282713715605966,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9652,
|
|
"mean_token_accuracy": 0.05161282308399677,
|
|
"num_tokens": 314000.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.172936820983887,
|
|
"epoch": 0.014702793530770846,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.9024,
|
|
"mean_token_accuracy": 0.0552643246948719,
|
|
"num_tokens": 323667.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.918990325927734,
|
|
"epoch": 0.015122873345935728,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.858,
|
|
"mean_token_accuracy": 0.052525343000888826,
|
|
"num_tokens": 332695.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.721237659454346,
|
|
"epoch": 0.015542953161100609,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7042,
|
|
"mean_token_accuracy": 0.050673872232437134,
|
|
"num_tokens": 342428.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.52247200012207,
|
|
"epoch": 0.01596303297626549,
|
|
"grad_norm": 0.61328125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7799,
|
|
"mean_token_accuracy": 0.051399941369891164,
|
|
"num_tokens": 353587.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.398729610443116,
|
|
"epoch": 0.01638311279143037,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.7173,
|
|
"mean_token_accuracy": 0.05443600341677666,
|
|
"num_tokens": 362997.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.274804973602295,
|
|
"epoch": 0.016803192606595255,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.7333,
|
|
"mean_token_accuracy": 0.06009506583213806,
|
|
"num_tokens": 372346.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.316196537017822,
|
|
"epoch": 0.017223272421760135,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.621,
|
|
"mean_token_accuracy": 0.054996570199728013,
|
|
"num_tokens": 381575.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.224405288696289,
|
|
"epoch": 0.017643352236925015,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.6806,
|
|
"mean_token_accuracy": 0.05832334831357002,
|
|
"num_tokens": 390706.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.178961277008057,
|
|
"epoch": 0.018063432052089896,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.6844,
|
|
"mean_token_accuracy": 0.056866029649972914,
|
|
"num_tokens": 400000.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.118294048309327,
|
|
"epoch": 0.01848351186725478,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.6249,
|
|
"mean_token_accuracy": 0.06287443153560161,
|
|
"num_tokens": 409447.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.128210067749023,
|
|
"epoch": 0.01890359168241966,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.6104,
|
|
"mean_token_accuracy": 0.06484438478946686,
|
|
"num_tokens": 418417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.050536060333252,
|
|
"epoch": 0.01932367149758454,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5732,
|
|
"mean_token_accuracy": 0.06463442519307136,
|
|
"num_tokens": 427619.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.079150295257568,
|
|
"epoch": 0.019743751312749424,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.616,
|
|
"mean_token_accuracy": 0.061473137512803075,
|
|
"num_tokens": 437931.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.002902173995972,
|
|
"epoch": 0.020163831127914304,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.6568,
|
|
"mean_token_accuracy": 0.06506373398005963,
|
|
"num_tokens": 447595.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.058529567718505,
|
|
"epoch": 0.020583910943079185,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5257,
|
|
"mean_token_accuracy": 0.058850279077887535,
|
|
"num_tokens": 457062.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.02257719039917,
|
|
"epoch": 0.021003990758244065,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.624,
|
|
"mean_token_accuracy": 0.06412565596401691,
|
|
"num_tokens": 466191.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.05047812461853,
|
|
"epoch": 0.02142407057340895,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.5647,
|
|
"mean_token_accuracy": 0.06097288727760315,
|
|
"num_tokens": 475693.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.019621276855469,
|
|
"epoch": 0.02184415038857383,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.589,
|
|
"mean_token_accuracy": 0.06407038681209087,
|
|
"num_tokens": 485173.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.99587049484253,
|
|
"epoch": 0.02226423020373871,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.5069,
|
|
"mean_token_accuracy": 0.06533381156623363,
|
|
"num_tokens": 493985.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.972505903244018,
|
|
"epoch": 0.022684310018903593,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.519,
|
|
"mean_token_accuracy": 0.0665605653077364,
|
|
"num_tokens": 502837.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.982478952407837,
|
|
"epoch": 0.023104389834068473,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4828,
|
|
"mean_token_accuracy": 0.06852602958679199,
|
|
"num_tokens": 511503.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.961443471908569,
|
|
"epoch": 0.023524469649233354,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.6587,
|
|
"mean_token_accuracy": 0.0616368904709816,
|
|
"num_tokens": 521499.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.966269254684448,
|
|
"epoch": 0.023944549464398234,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.426,
|
|
"mean_token_accuracy": 0.06728804372251034,
|
|
"num_tokens": 530067.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.91850700378418,
|
|
"epoch": 0.024364629279563118,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4148,
|
|
"mean_token_accuracy": 0.07034274153411388,
|
|
"num_tokens": 538559.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.979486131668091,
|
|
"epoch": 0.024784709094728,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.6056,
|
|
"mean_token_accuracy": 0.06503808572888374,
|
|
"num_tokens": 547288.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.885135698318481,
|
|
"epoch": 0.02520478890989288,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.4924,
|
|
"mean_token_accuracy": 0.06286945752799511,
|
|
"num_tokens": 557269.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.007584619522095,
|
|
"epoch": 0.025624868725057762,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.5193,
|
|
"mean_token_accuracy": 0.06448328271508216,
|
|
"num_tokens": 567280.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.853135585784912,
|
|
"epoch": 0.026044948540222643,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.382,
|
|
"mean_token_accuracy": 0.06435618139803409,
|
|
"num_tokens": 576609.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.831946516036988,
|
|
"epoch": 0.026465028355387523,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.07741407230496407,
|
|
"num_tokens": 586053.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.793692779541016,
|
|
"epoch": 0.026885108170552403,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.4583,
|
|
"mean_token_accuracy": 0.0726725548505783,
|
|
"num_tokens": 594649.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.9273755073547365,
|
|
"epoch": 0.027305187985717287,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.4408,
|
|
"mean_token_accuracy": 0.06625295169651509,
|
|
"num_tokens": 603445.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.88362865447998,
|
|
"epoch": 0.027725267800882167,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.4937,
|
|
"mean_token_accuracy": 0.06676559969782829,
|
|
"num_tokens": 613611.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.917990875244141,
|
|
"epoch": 0.028145347616047048,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.6535,
|
|
"mean_token_accuracy": 0.06991421952843666,
|
|
"num_tokens": 623024.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.84550929069519,
|
|
"epoch": 0.02856542743121193,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.37,
|
|
"mean_token_accuracy": 0.07066045552492142,
|
|
"num_tokens": 631624.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.743204069137573,
|
|
"epoch": 0.028985507246376812,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3544,
|
|
"mean_token_accuracy": 0.07467443272471427,
|
|
"num_tokens": 640473.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.89313235282898,
|
|
"epoch": 0.029405587061541692,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.483,
|
|
"mean_token_accuracy": 0.07056561335921288,
|
|
"num_tokens": 649692.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.855760765075684,
|
|
"epoch": 0.029825666876706573,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.4521,
|
|
"mean_token_accuracy": 0.07088366113603115,
|
|
"num_tokens": 658236.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.798476648330689,
|
|
"epoch": 0.030245746691871456,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2377,
|
|
"mean_token_accuracy": 0.07707448154687882,
|
|
"num_tokens": 667175.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.8225892066955565,
|
|
"epoch": 0.030665826507036337,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.5145,
|
|
"mean_token_accuracy": 0.07331682369112968,
|
|
"num_tokens": 676456.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.92411093711853,
|
|
"epoch": 0.031085906322201217,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.4959,
|
|
"mean_token_accuracy": 0.07029573023319244,
|
|
"num_tokens": 686881.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.741179084777832,
|
|
"epoch": 0.0315059861373661,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.2754,
|
|
"mean_token_accuracy": 0.0755814753472805,
|
|
"num_tokens": 696045.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.724820518493653,
|
|
"epoch": 0.03192606595253098,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.2387,
|
|
"mean_token_accuracy": 0.08382209464907646,
|
|
"num_tokens": 704729.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.6020232200622555,
|
|
"epoch": 0.032346145767695865,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2979,
|
|
"mean_token_accuracy": 0.07353318221867085,
|
|
"num_tokens": 714331.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.746062755584717,
|
|
"epoch": 0.03276622558286074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.26,
|
|
"mean_token_accuracy": 0.07669057212769985,
|
|
"num_tokens": 722788.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.785710859298706,
|
|
"epoch": 0.033186305398025626,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.3239,
|
|
"mean_token_accuracy": 0.07846143767237664,
|
|
"num_tokens": 731417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.662443017959594,
|
|
"epoch": 0.03360638521319051,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.2961,
|
|
"mean_token_accuracy": 0.07676250785589218,
|
|
"num_tokens": 741034.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.704835367202759,
|
|
"epoch": 0.034026465028355386,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2982,
|
|
"mean_token_accuracy": 0.07422473579645157,
|
|
"num_tokens": 749596.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.664615345001221,
|
|
"epoch": 0.03444654484352027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.2586,
|
|
"mean_token_accuracy": 0.07927079945802688,
|
|
"num_tokens": 758931.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.600234937667847,
|
|
"epoch": 0.03486662465868515,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.1556,
|
|
"mean_token_accuracy": 0.08096722960472107,
|
|
"num_tokens": 767534.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.68730993270874,
|
|
"epoch": 0.03528670447385003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.2278,
|
|
"mean_token_accuracy": 0.07768219709396362,
|
|
"num_tokens": 776456.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.634504795074463,
|
|
"epoch": 0.035706784289014915,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.2673,
|
|
"mean_token_accuracy": 0.07659058347344398,
|
|
"num_tokens": 786172.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.6300970077514645,
|
|
"epoch": 0.03612686410417979,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1534,
|
|
"mean_token_accuracy": 0.08167968951165676,
|
|
"num_tokens": 795081.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.709903621673584,
|
|
"epoch": 0.036546943919344675,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.2139,
|
|
"mean_token_accuracy": 0.07590967863798141,
|
|
"num_tokens": 804259.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.642217683792114,
|
|
"epoch": 0.03696702373450956,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.2158,
|
|
"mean_token_accuracy": 0.07940593808889389,
|
|
"num_tokens": 813463.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.5950026512146,
|
|
"epoch": 0.037387103549674436,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.1477,
|
|
"mean_token_accuracy": 0.08674231953918934,
|
|
"num_tokens": 823029.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.576770305633545,
|
|
"epoch": 0.03780718336483932,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.2023,
|
|
"mean_token_accuracy": 0.07635540775954723,
|
|
"num_tokens": 832902.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.584611654281616,
|
|
"epoch": 0.0382272631800042,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.1523,
|
|
"mean_token_accuracy": 0.07883834913372993,
|
|
"num_tokens": 842162.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.626716089248657,
|
|
"epoch": 0.03864734299516908,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1831,
|
|
"mean_token_accuracy": 0.08037797883152961,
|
|
"num_tokens": 852328.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.5449056148529055,
|
|
"epoch": 0.039067422810333964,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.139,
|
|
"mean_token_accuracy": 0.08323637843132019,
|
|
"num_tokens": 860929.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.549172639846802,
|
|
"epoch": 0.03948750262549885,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.222,
|
|
"mean_token_accuracy": 0.07719254568219185,
|
|
"num_tokens": 869144.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.640847682952881,
|
|
"epoch": 0.039907582440663725,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1591,
|
|
"mean_token_accuracy": 0.08463784530758858,
|
|
"num_tokens": 877447.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.579086351394653,
|
|
"epoch": 0.04032766225582861,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.1205,
|
|
"mean_token_accuracy": 0.08219385743141175,
|
|
"num_tokens": 887020.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.4508629322052,
|
|
"epoch": 0.040747742070993485,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1602,
|
|
"mean_token_accuracy": 0.08283634409308434,
|
|
"num_tokens": 895937.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.572605180740356,
|
|
"epoch": 0.04116782188615837,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1651,
|
|
"mean_token_accuracy": 0.07650997936725616,
|
|
"num_tokens": 905446.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.551622104644776,
|
|
"epoch": 0.04158790170132325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.0659,
|
|
"mean_token_accuracy": 0.0878485307097435,
|
|
"num_tokens": 914547.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.495913028717041,
|
|
"epoch": 0.04200798151648813,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.0595,
|
|
"mean_token_accuracy": 0.08502571135759354,
|
|
"num_tokens": 922900.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.497592973709106,
|
|
"epoch": 0.042428061331653014,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.0901,
|
|
"mean_token_accuracy": 0.08809811025857925,
|
|
"num_tokens": 930876.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.464612245559692,
|
|
"epoch": 0.0428481411468179,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.1198,
|
|
"mean_token_accuracy": 0.08516570031642914,
|
|
"num_tokens": 939871.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.487181520462036,
|
|
"epoch": 0.043268220961982774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.1032,
|
|
"mean_token_accuracy": 0.0852330669760704,
|
|
"num_tokens": 948673.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.419178056716919,
|
|
"epoch": 0.04368830077714766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.0589,
|
|
"mean_token_accuracy": 0.08271693587303161,
|
|
"num_tokens": 957603.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.483588600158692,
|
|
"epoch": 0.04410838059231254,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.1144,
|
|
"mean_token_accuracy": 0.08177880719304084,
|
|
"num_tokens": 967731.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.489073705673218,
|
|
"epoch": 0.04452846040747742,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.1329,
|
|
"mean_token_accuracy": 0.08377009257674217,
|
|
"num_tokens": 977427.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.537723684310913,
|
|
"epoch": 0.0449485402226423,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.1087,
|
|
"mean_token_accuracy": 0.08038406819105148,
|
|
"num_tokens": 986758.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.401149797439575,
|
|
"epoch": 0.045368620037807186,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.1028,
|
|
"mean_token_accuracy": 0.0900042973458767,
|
|
"num_tokens": 996377.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.488600254058838,
|
|
"epoch": 0.04578869985297206,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.1394,
|
|
"mean_token_accuracy": 0.07542204968631268,
|
|
"num_tokens": 1006483.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.352685880661011,
|
|
"epoch": 0.04620877966813695,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.0338,
|
|
"mean_token_accuracy": 0.08245834931731225,
|
|
"num_tokens": 1016132.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.383127737045288,
|
|
"epoch": 0.04662885948330183,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.08636636063456535,
|
|
"num_tokens": 1024970.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.470243072509765,
|
|
"epoch": 0.04704893929846671,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.0674,
|
|
"mean_token_accuracy": 0.08481250628829003,
|
|
"num_tokens": 1034335.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.4651130676269535,
|
|
"epoch": 0.04746901911363159,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.1153,
|
|
"mean_token_accuracy": 0.08971841484308243,
|
|
"num_tokens": 1043954.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.4326441287994385,
|
|
"epoch": 0.04788909892879647,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.0593,
|
|
"mean_token_accuracy": 0.08415772840380668,
|
|
"num_tokens": 1053554.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.493321180343628,
|
|
"epoch": 0.04830917874396135,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.0111,
|
|
"mean_token_accuracy": 0.08667988702654839,
|
|
"num_tokens": 1062008.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.334539842605591,
|
|
"epoch": 0.048729258559126236,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.0738,
|
|
"mean_token_accuracy": 0.08698670640587806,
|
|
"num_tokens": 1070740.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.407914113998413,
|
|
"epoch": 0.04914933837429111,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0599,
|
|
"mean_token_accuracy": 0.0839300949126482,
|
|
"num_tokens": 1079681.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.3771099090576175,
|
|
"epoch": 0.049569418189456,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.9475,
|
|
"mean_token_accuracy": 0.09122345820069314,
|
|
"num_tokens": 1088979.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.326050329208374,
|
|
"epoch": 0.04998949800462088,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.08771323934197425,
|
|
"num_tokens": 1097870.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.320249271392822,
|
|
"epoch": 0.05040957781978576,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.0421,
|
|
"mean_token_accuracy": 0.08429603464901447,
|
|
"num_tokens": 1107948.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.399919700622559,
|
|
"epoch": 0.05082965763495064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.9732,
|
|
"mean_token_accuracy": 0.09062434881925582,
|
|
"num_tokens": 1117032.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.228488159179688,
|
|
"epoch": 0.051249737450115525,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.9617,
|
|
"mean_token_accuracy": 0.08655689135193825,
|
|
"num_tokens": 1127834.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.388462066650391,
|
|
"epoch": 0.0516698172652804,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.0412,
|
|
"mean_token_accuracy": 0.09550752639770507,
|
|
"num_tokens": 1137382.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.257171297073365,
|
|
"epoch": 0.052089897080445285,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8769,
|
|
"mean_token_accuracy": 0.09444506764411927,
|
|
"num_tokens": 1146095.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.268283557891846,
|
|
"epoch": 0.05250997689561017,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.9168,
|
|
"mean_token_accuracy": 0.09104742333292962,
|
|
"num_tokens": 1154981.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.231864309310913,
|
|
"epoch": 0.052930056710775046,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.9162,
|
|
"mean_token_accuracy": 0.09456853494048119,
|
|
"num_tokens": 1164939.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.3547971725463865,
|
|
"epoch": 0.05335013652593993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.0466,
|
|
"mean_token_accuracy": 0.08202817216515541,
|
|
"num_tokens": 1174991.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.341550350189209,
|
|
"epoch": 0.05377021634110481,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.0772,
|
|
"mean_token_accuracy": 0.08350706696510315,
|
|
"num_tokens": 1184885.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.257875394821167,
|
|
"epoch": 0.05419029615626969,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.9751,
|
|
"mean_token_accuracy": 0.08547877669334411,
|
|
"num_tokens": 1193637.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.223678970336914,
|
|
"epoch": 0.054610375971434574,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.778,
|
|
"mean_token_accuracy": 0.09493321552872658,
|
|
"num_tokens": 1202188.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.3337372779846195,
|
|
"epoch": 0.05503045578659945,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8974,
|
|
"mean_token_accuracy": 0.0872666135430336,
|
|
"num_tokens": 1210768.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.218266105651855,
|
|
"epoch": 0.055450535601764335,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.903,
|
|
"mean_token_accuracy": 0.09044937118887901,
|
|
"num_tokens": 1219819.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.269051265716553,
|
|
"epoch": 0.05587061541692922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.9561,
|
|
"mean_token_accuracy": 0.08509430065751075,
|
|
"num_tokens": 1229703.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.323557806015015,
|
|
"epoch": 0.056290695232094096,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.9868,
|
|
"mean_token_accuracy": 0.08851987943053245,
|
|
"num_tokens": 1238942.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.31135516166687,
|
|
"epoch": 0.05671077504725898,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.0196,
|
|
"mean_token_accuracy": 0.090158711373806,
|
|
"num_tokens": 1248943.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.238338661193848,
|
|
"epoch": 0.05713085486242386,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.9121,
|
|
"mean_token_accuracy": 0.09068251103162765,
|
|
"num_tokens": 1257761.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.152073860168457,
|
|
"epoch": 0.05755093467758874,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8534,
|
|
"mean_token_accuracy": 0.0885312557220459,
|
|
"num_tokens": 1267216.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.265845727920532,
|
|
"epoch": 0.057971014492753624,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.952,
|
|
"mean_token_accuracy": 0.08522271737456322,
|
|
"num_tokens": 1277210.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.267448425292969,
|
|
"epoch": 0.05839109430791851,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.08550659716129302,
|
|
"num_tokens": 1285310.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.189469480514527,
|
|
"epoch": 0.058811174123083385,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8822,
|
|
"mean_token_accuracy": 0.09172830283641815,
|
|
"num_tokens": 1294421.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.136290740966797,
|
|
"epoch": 0.05923125393824827,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.7116,
|
|
"mean_token_accuracy": 0.10014490857720375,
|
|
"num_tokens": 1303281.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.132218694686889,
|
|
"epoch": 0.059651333753413145,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.09660332053899764,
|
|
"num_tokens": 1312280.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.105095958709716,
|
|
"epoch": 0.06007141356857803,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.8389,
|
|
"mean_token_accuracy": 0.08850333318114281,
|
|
"num_tokens": 1321243.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.180677127838135,
|
|
"epoch": 0.06049149338374291,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.9284,
|
|
"mean_token_accuracy": 0.09514749199151992,
|
|
"num_tokens": 1330324.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.1717592716217045,
|
|
"epoch": 0.06091157319890779,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7842,
|
|
"mean_token_accuracy": 0.09439062774181366,
|
|
"num_tokens": 1339485.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.2169701099395756,
|
|
"epoch": 0.06133165301407267,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.915,
|
|
"mean_token_accuracy": 0.08555234894156456,
|
|
"num_tokens": 1348640.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.130293321609497,
|
|
"epoch": 0.06175173282923756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.8099,
|
|
"mean_token_accuracy": 0.09767363145947457,
|
|
"num_tokens": 1357581.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.150859022140503,
|
|
"epoch": 0.062171812644402434,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.8829,
|
|
"mean_token_accuracy": 0.0921759732067585,
|
|
"num_tokens": 1367883.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.128716611862183,
|
|
"epoch": 0.06259189245956731,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8294,
|
|
"mean_token_accuracy": 0.08952599465847015,
|
|
"num_tokens": 1376936.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.0383734703063965,
|
|
"epoch": 0.0630119722747322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.09515918046236038,
|
|
"num_tokens": 1386359.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.0808555603027346,
|
|
"epoch": 0.06343205208989708,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.8181,
|
|
"mean_token_accuracy": 0.09296313449740409,
|
|
"num_tokens": 1395223.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.2832927227020265,
|
|
"epoch": 0.06385213190506196,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.9661,
|
|
"mean_token_accuracy": 0.08833524622023106,
|
|
"num_tokens": 1404917.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.180255651473999,
|
|
"epoch": 0.06427221172022685,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.857,
|
|
"mean_token_accuracy": 0.10177302286028862,
|
|
"num_tokens": 1413348.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.025369262695312,
|
|
"epoch": 0.06469229153539173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.8209,
|
|
"mean_token_accuracy": 0.09210879877209663,
|
|
"num_tokens": 1421726.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.136773920059204,
|
|
"epoch": 0.0651123713505566,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.8481,
|
|
"mean_token_accuracy": 0.09178127273917198,
|
|
"num_tokens": 1430686.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.201752138137818,
|
|
"epoch": 0.06553245116572148,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.8283,
|
|
"mean_token_accuracy": 0.0948453463613987,
|
|
"num_tokens": 1439499.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.1434326171875,
|
|
"epoch": 0.06595253098088637,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.8035,
|
|
"mean_token_accuracy": 0.09644952267408372,
|
|
"num_tokens": 1448220.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.982330989837647,
|
|
"epoch": 0.06637261079605125,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.8485,
|
|
"mean_token_accuracy": 0.09032012075185776,
|
|
"num_tokens": 1458217.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.011542701721192,
|
|
"epoch": 0.06679269061121614,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.7437,
|
|
"mean_token_accuracy": 0.09031623676419258,
|
|
"num_tokens": 1467422.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.083204460144043,
|
|
"epoch": 0.06721277042638102,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.7143,
|
|
"mean_token_accuracy": 0.09781065881252289,
|
|
"num_tokens": 1476152.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.017691135406494,
|
|
"epoch": 0.06763285024154589,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.8197,
|
|
"mean_token_accuracy": 0.09335827901959419,
|
|
"num_tokens": 1485248.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.028779029846191,
|
|
"epoch": 0.06805293005671077,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7816,
|
|
"mean_token_accuracy": 0.0929147683084011,
|
|
"num_tokens": 1494248.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.107398557662964,
|
|
"epoch": 0.06847300987187566,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8809,
|
|
"mean_token_accuracy": 0.09237429052591324,
|
|
"num_tokens": 1503565.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.178503799438476,
|
|
"epoch": 0.06889308968704054,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.9674,
|
|
"mean_token_accuracy": 0.08681917861104012,
|
|
"num_tokens": 1513227.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.083085680007935,
|
|
"epoch": 0.06931316950220542,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.7482,
|
|
"mean_token_accuracy": 0.09896269217133521,
|
|
"num_tokens": 1522312.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.000125169754028,
|
|
"epoch": 0.0697332493173703,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.7224,
|
|
"mean_token_accuracy": 0.09859632030129432,
|
|
"num_tokens": 1531720.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.015534973144531,
|
|
"epoch": 0.07015332913253518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7888,
|
|
"mean_token_accuracy": 0.09380378648638725,
|
|
"num_tokens": 1541238.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.136422204971313,
|
|
"epoch": 0.07057340894770006,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.8785,
|
|
"mean_token_accuracy": 0.09427597969770432,
|
|
"num_tokens": 1550875.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.93135290145874,
|
|
"epoch": 0.07099348876286495,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.8248,
|
|
"mean_token_accuracy": 0.09056826308369637,
|
|
"num_tokens": 1560287.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.053813314437866,
|
|
"epoch": 0.07141356857802983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.7055,
|
|
"mean_token_accuracy": 0.10149886757135392,
|
|
"num_tokens": 1569043.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.978960704803467,
|
|
"epoch": 0.07183364839319471,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.09670688211917877,
|
|
"num_tokens": 1578112.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.866673278808594,
|
|
"epoch": 0.07225372820835958,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6514,
|
|
"mean_token_accuracy": 0.10521448627114297,
|
|
"num_tokens": 1586587.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.09016604423523,
|
|
"epoch": 0.07267380802352447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.8069,
|
|
"mean_token_accuracy": 0.09529538303613663,
|
|
"num_tokens": 1595585.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.990141916275024,
|
|
"epoch": 0.07309388783868935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.7599,
|
|
"mean_token_accuracy": 0.09652992263436318,
|
|
"num_tokens": 1605355.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.018218660354615,
|
|
"epoch": 0.07351396765385423,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.7838,
|
|
"mean_token_accuracy": 0.0944277286529541,
|
|
"num_tokens": 1613637.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.990546417236328,
|
|
"epoch": 0.07393404746901912,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.09869495183229446,
|
|
"num_tokens": 1622731.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.067089796066284,
|
|
"epoch": 0.074354127284184,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.7144,
|
|
"mean_token_accuracy": 0.09230813458561897,
|
|
"num_tokens": 1632098.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.908722448348999,
|
|
"epoch": 0.07477420709934887,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.7079,
|
|
"mean_token_accuracy": 0.09467918276786805,
|
|
"num_tokens": 1641259.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.984257411956787,
|
|
"epoch": 0.07519428691451376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.09350861608982086,
|
|
"num_tokens": 1651362.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.942133188247681,
|
|
"epoch": 0.07561436672967864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.09561712741851806,
|
|
"num_tokens": 1660190.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.949711561203003,
|
|
"epoch": 0.07603444654484352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.7202,
|
|
"mean_token_accuracy": 0.09667671620845794,
|
|
"num_tokens": 1669020.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.059488010406494,
|
|
"epoch": 0.0764545263600084,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.7692,
|
|
"mean_token_accuracy": 0.10004925951361657,
|
|
"num_tokens": 1678158.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.941928768157959,
|
|
"epoch": 0.07687460617517328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7751,
|
|
"mean_token_accuracy": 0.08887208923697472,
|
|
"num_tokens": 1687481.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.903632497787475,
|
|
"epoch": 0.07729468599033816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.7248,
|
|
"mean_token_accuracy": 0.10260720252990722,
|
|
"num_tokens": 1696782.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.950085973739624,
|
|
"epoch": 0.07771476580550304,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.10223789662122726,
|
|
"num_tokens": 1706153.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.981480550765991,
|
|
"epoch": 0.07813484562066793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.7583,
|
|
"mean_token_accuracy": 0.09635938182473183,
|
|
"num_tokens": 1715585.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.110754156112671,
|
|
"epoch": 0.07855492543583281,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.09635257050395012,
|
|
"num_tokens": 1724857.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.890129041671753,
|
|
"epoch": 0.0789750052509977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6811,
|
|
"mean_token_accuracy": 0.10242518037557602,
|
|
"num_tokens": 1733528.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.000388526916504,
|
|
"epoch": 0.07939508506616257,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.8096,
|
|
"mean_token_accuracy": 0.09821859821677208,
|
|
"num_tokens": 1742953.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.962129068374634,
|
|
"epoch": 0.07981516488132745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.757,
|
|
"mean_token_accuracy": 0.10171304419636726,
|
|
"num_tokens": 1752155.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.876726579666138,
|
|
"epoch": 0.08023524469649233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6364,
|
|
"mean_token_accuracy": 0.09934233203530311,
|
|
"num_tokens": 1760562.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.884459018707275,
|
|
"epoch": 0.08065532451165722,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6462,
|
|
"mean_token_accuracy": 0.1006347469985485,
|
|
"num_tokens": 1769631.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.902465105056763,
|
|
"epoch": 0.0810754043268221,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.7043,
|
|
"mean_token_accuracy": 0.10013237074017525,
|
|
"num_tokens": 1779080.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.916742420196533,
|
|
"epoch": 0.08149548414198697,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.10164752677083015,
|
|
"num_tokens": 1787830.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.823171949386596,
|
|
"epoch": 0.08191556395715185,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.6048,
|
|
"mean_token_accuracy": 0.10189055874943734,
|
|
"num_tokens": 1796998.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.977118110656738,
|
|
"epoch": 0.08233564377231674,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.6814,
|
|
"mean_token_accuracy": 0.10083219707012177,
|
|
"num_tokens": 1806194.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.672053623199463,
|
|
"epoch": 0.08275572358748162,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.10488267168402672,
|
|
"num_tokens": 1815751.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.7590797424316404,
|
|
"epoch": 0.0831758034026465,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6428,
|
|
"mean_token_accuracy": 0.10192798376083374,
|
|
"num_tokens": 1825379.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.884732866287232,
|
|
"epoch": 0.08359588321781139,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.6025,
|
|
"mean_token_accuracy": 0.10135274231433869,
|
|
"num_tokens": 1834158.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.860666513442993,
|
|
"epoch": 0.08401596303297626,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5689,
|
|
"mean_token_accuracy": 0.10223893150687217,
|
|
"num_tokens": 1842724.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.812324571609497,
|
|
"epoch": 0.08443604284814114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499999998724557,
|
|
"loss": 6.5774,
|
|
"mean_token_accuracy": 0.10202668011188507,
|
|
"num_tokens": 1852485.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.779099035263061,
|
|
"epoch": 0.08485612266330603,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999935430703,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.10559484660625458,
|
|
"num_tokens": 1861303.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.770784664154053,
|
|
"epoch": 0.08527620247847091,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999843758243,
|
|
"loss": 6.5927,
|
|
"mean_token_accuracy": 0.1131505697965622,
|
|
"num_tokens": 1870859.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.940572690963745,
|
|
"epoch": 0.0856962822936358,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999712228196,
|
|
"loss": 6.7566,
|
|
"mean_token_accuracy": 0.09317019283771515,
|
|
"num_tokens": 1880295.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.93710470199585,
|
|
"epoch": 0.08611636210880068,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999540840562,
|
|
"loss": 6.6611,
|
|
"mean_token_accuracy": 0.10422083139419555,
|
|
"num_tokens": 1889193.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.811184549331665,
|
|
"epoch": 0.08653644192396555,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999329595345,
|
|
"loss": 6.7584,
|
|
"mean_token_accuracy": 0.09407720491290092,
|
|
"num_tokens": 1899437.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.87418532371521,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999999078492548,
|
|
"loss": 6.6473,
|
|
"mean_token_accuracy": 0.1043108843266964,
|
|
"num_tokens": 1907882.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.7778688907623295,
|
|
"epoch": 0.08737660155429532,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999998787532176,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.10416635349392891,
|
|
"num_tokens": 1916872.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.838136434555054,
|
|
"epoch": 0.0877966813694602,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999998456714234,
|
|
"loss": 6.7226,
|
|
"mean_token_accuracy": 0.10190053880214692,
|
|
"num_tokens": 1926636.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.815088891983033,
|
|
"epoch": 0.08821676118462508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998086038729,
|
|
"loss": 6.6294,
|
|
"mean_token_accuracy": 0.1084713064134121,
|
|
"num_tokens": 1935962.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.798814964294434,
|
|
"epoch": 0.08863684099978995,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999997675505665,
|
|
"loss": 6.5955,
|
|
"mean_token_accuracy": 0.10102920681238174,
|
|
"num_tokens": 1944600.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.8712811946868895,
|
|
"epoch": 0.08905692081495484,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999997225115052,
|
|
"loss": 6.7682,
|
|
"mean_token_accuracy": 0.09951933771371842,
|
|
"num_tokens": 1954234.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.951000690460205,
|
|
"epoch": 0.08947700063011972,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999996734866896,
|
|
"loss": 6.7171,
|
|
"mean_token_accuracy": 0.09834984764456749,
|
|
"num_tokens": 1964499.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.700433588027954,
|
|
"epoch": 0.0898970804452846,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999996204761206,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.11416423171758652,
|
|
"num_tokens": 1973635.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.754154396057129,
|
|
"epoch": 0.09031716026044949,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999995634797993,
|
|
"loss": 6.5931,
|
|
"mean_token_accuracy": 0.10663349330425262,
|
|
"num_tokens": 1983509.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.815823554992676,
|
|
"epoch": 0.09073724007561437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999995024977265,
|
|
"loss": 6.5793,
|
|
"mean_token_accuracy": 0.10800760760903358,
|
|
"num_tokens": 1992336.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.820423316955567,
|
|
"epoch": 0.09115731989077924,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999994375299034,
|
|
"loss": 6.5959,
|
|
"mean_token_accuracy": 0.10795153826475143,
|
|
"num_tokens": 2001931.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.72901930809021,
|
|
"epoch": 0.09157739970594413,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499999368576331,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.11168377995491027,
|
|
"num_tokens": 2010935.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.699783134460449,
|
|
"epoch": 0.09199747952110901,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999992956370109,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.10683032646775245,
|
|
"num_tokens": 2020587.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.677279663085938,
|
|
"epoch": 0.0924175593362739,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499999218711944,
|
|
"loss": 6.5573,
|
|
"mean_token_accuracy": 0.1078680157661438,
|
|
"num_tokens": 2029743.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.796489238739014,
|
|
"epoch": 0.09283763915143878,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999991378011317,
|
|
"loss": 6.5775,
|
|
"mean_token_accuracy": 0.1102212406694889,
|
|
"num_tokens": 2038468.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.65820722579956,
|
|
"epoch": 0.09325771896660366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999990529045757,
|
|
"loss": 6.4917,
|
|
"mean_token_accuracy": 0.10695874094963073,
|
|
"num_tokens": 2047456.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.895982646942139,
|
|
"epoch": 0.09367779878176853,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999989640222771,
|
|
"loss": 6.8041,
|
|
"mean_token_accuracy": 0.09525922834873199,
|
|
"num_tokens": 2056691.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.853526449203491,
|
|
"epoch": 0.09409787859693342,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499998871154238,
|
|
"loss": 6.5875,
|
|
"mean_token_accuracy": 0.10508395135402679,
|
|
"num_tokens": 2066068.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.754317712783814,
|
|
"epoch": 0.0945179584120983,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999987743004597,
|
|
"loss": 6.5313,
|
|
"mean_token_accuracy": 0.11206126511096955,
|
|
"num_tokens": 2075113.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.816254997253418,
|
|
"epoch": 0.09493803822726318,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999986734609438,
|
|
"loss": 6.6612,
|
|
"mean_token_accuracy": 0.1047824963927269,
|
|
"num_tokens": 2084557.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.785951089859009,
|
|
"epoch": 0.09535811804242807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985686356923,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.10589791536331176,
|
|
"num_tokens": 2093424.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.7812634944915775,
|
|
"epoch": 0.09577819785759294,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499998459824707,
|
|
"loss": 6.6748,
|
|
"mean_token_accuracy": 0.10217821151018143,
|
|
"num_tokens": 2103066.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.756265497207641,
|
|
"epoch": 0.09619827767275782,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049999834702799,
|
|
"loss": 6.5477,
|
|
"mean_token_accuracy": 0.11097522377967835,
|
|
"num_tokens": 2112447.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.820600318908691,
|
|
"epoch": 0.0966183574879227,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999982302455431,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.11053408607840538,
|
|
"num_tokens": 2121949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.731539011001587,
|
|
"epoch": 0.09703843730308759,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999981094773683,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.11045165956020356,
|
|
"num_tokens": 2130464.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.791986989974975,
|
|
"epoch": 0.09745851711825247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499997984723468,
|
|
"loss": 6.627,
|
|
"mean_token_accuracy": 0.10332545191049576,
|
|
"num_tokens": 2139577.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.555002975463867,
|
|
"epoch": 0.09787859693341736,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999978559838441,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.10894591435790062,
|
|
"num_tokens": 2147919.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.623918771743774,
|
|
"epoch": 0.09829867674858223,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999977232584991,
|
|
"loss": 6.5152,
|
|
"mean_token_accuracy": 0.1095739871263504,
|
|
"num_tokens": 2156936.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.789136934280395,
|
|
"epoch": 0.09871875656374711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999975865474354,
|
|
"loss": 6.5864,
|
|
"mean_token_accuracy": 0.10703087151050568,
|
|
"num_tokens": 2165362.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.65335168838501,
|
|
"epoch": 0.099138836378912,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999974458506551,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.10435130968689918,
|
|
"num_tokens": 2173665.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.8575843334197994,
|
|
"epoch": 0.09955891619407688,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499997301168161,
|
|
"loss": 6.4988,
|
|
"mean_token_accuracy": 0.11348986551165581,
|
|
"num_tokens": 2182222.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.672175312042237,
|
|
"epoch": 0.09997899600924176,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999971524999556,
|
|
"loss": 6.5809,
|
|
"mean_token_accuracy": 0.11042713969945908,
|
|
"num_tokens": 2192358.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.7970047950744625,
|
|
"epoch": 0.10039907582440663,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999969998460414,
|
|
"loss": 6.5411,
|
|
"mean_token_accuracy": 0.10771783664822579,
|
|
"num_tokens": 2201889.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.672988796234131,
|
|
"epoch": 0.10081915563957151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999968432064213,
|
|
"loss": 6.54,
|
|
"mean_token_accuracy": 0.12040728628635407,
|
|
"num_tokens": 2211810.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.662283229827881,
|
|
"epoch": 0.1012392354547364,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999966825810979,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.10729209631681443,
|
|
"num_tokens": 2221123.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.682981157302857,
|
|
"epoch": 0.10165931526990128,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999965179700742,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.11437768638134002,
|
|
"num_tokens": 2230129.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.584838199615478,
|
|
"epoch": 0.10207939508506617,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499996349373353,
|
|
"loss": 6.5049,
|
|
"mean_token_accuracy": 0.11030597984790802,
|
|
"num_tokens": 2239929.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.768577909469604,
|
|
"epoch": 0.10249947490023105,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999961767909374,
|
|
"loss": 6.478,
|
|
"mean_token_accuracy": 0.11449568048119545,
|
|
"num_tokens": 2248078.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.615856742858886,
|
|
"epoch": 0.10291955471539592,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999960002228303,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.11093122437596321,
|
|
"num_tokens": 2256975.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.733388185501099,
|
|
"epoch": 0.1033396345305608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999958196690349,
|
|
"loss": 6.4212,
|
|
"mean_token_accuracy": 0.11245058998465537,
|
|
"num_tokens": 2265797.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.668054151535034,
|
|
"epoch": 0.10375971434572569,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999956351295545,
|
|
"loss": 6.5197,
|
|
"mean_token_accuracy": 0.1140691690146923,
|
|
"num_tokens": 2274099.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.614612483978272,
|
|
"epoch": 0.10417979416089057,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999954466043922,
|
|
"loss": 6.4309,
|
|
"mean_token_accuracy": 0.11669434607028961,
|
|
"num_tokens": 2282360.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.6785484790802006,
|
|
"epoch": 0.10459987397605545,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999952540935514,
|
|
"loss": 6.5283,
|
|
"mean_token_accuracy": 0.10534609332680703,
|
|
"num_tokens": 2292714.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.669230937957764,
|
|
"epoch": 0.10501995379122034,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999950575970356,
|
|
"loss": 6.4759,
|
|
"mean_token_accuracy": 0.11022288277745247,
|
|
"num_tokens": 2301633.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.690946578979492,
|
|
"epoch": 0.10544003360638521,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999948571148482,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11288312897086143,
|
|
"num_tokens": 2310067.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.663266944885254,
|
|
"epoch": 0.10586011342155009,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999946526469927,
|
|
"loss": 6.5329,
|
|
"mean_token_accuracy": 0.11119069010019303,
|
|
"num_tokens": 2320090.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.619077062606811,
|
|
"epoch": 0.10628019323671498,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999944441934728,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.11513725593686104,
|
|
"num_tokens": 2329255.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.743935060501099,
|
|
"epoch": 0.10670027305187986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999942317542922,
|
|
"loss": 6.5708,
|
|
"mean_token_accuracy": 0.10842081904411316,
|
|
"num_tokens": 2339535.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.647988319396973,
|
|
"epoch": 0.10712035286704474,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999940153294546,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.11369285136461257,
|
|
"num_tokens": 2348948.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.573079681396484,
|
|
"epoch": 0.10754043268220961,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499993794918964,
|
|
"loss": 6.4903,
|
|
"mean_token_accuracy": 0.11098795756697655,
|
|
"num_tokens": 2359141.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.623832654953003,
|
|
"epoch": 0.1079605124973745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999935705228241,
|
|
"loss": 6.5296,
|
|
"mean_token_accuracy": 0.10813465043902397,
|
|
"num_tokens": 2368906.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.781174278259277,
|
|
"epoch": 0.10838059231253938,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999933421410389,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.11340161636471749,
|
|
"num_tokens": 2377029.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.664435195922851,
|
|
"epoch": 0.10880067212770426,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999931097736125,
|
|
"loss": 6.5678,
|
|
"mean_token_accuracy": 0.10811809226870536,
|
|
"num_tokens": 2387088.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.711423254013061,
|
|
"epoch": 0.10922075194286915,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999928734205492,
|
|
"loss": 6.4748,
|
|
"mean_token_accuracy": 0.11095682382583619,
|
|
"num_tokens": 2395596.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.609859323501587,
|
|
"epoch": 0.10964083175803403,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999926330818528,
|
|
"loss": 6.4489,
|
|
"mean_token_accuracy": 0.11987485438585281,
|
|
"num_tokens": 2404506.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.6314843654632565,
|
|
"epoch": 0.1100609115731989,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999923887575278,
|
|
"loss": 6.4954,
|
|
"mean_token_accuracy": 0.11150062307715417,
|
|
"num_tokens": 2414342.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.703009176254272,
|
|
"epoch": 0.11048099138836379,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999921404475785,
|
|
"loss": 6.4686,
|
|
"mean_token_accuracy": 0.11657750681042671,
|
|
"num_tokens": 2423076.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.580958127975464,
|
|
"epoch": 0.11090107120352867,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999918881520093,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.11714263036847114,
|
|
"num_tokens": 2432492.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.586594104766846,
|
|
"epoch": 0.11132115101869355,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999916318708246,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.11821310296654701,
|
|
"num_tokens": 2441916.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.610158824920655,
|
|
"epoch": 0.11174123083385844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999913716040291,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.11613110527396202,
|
|
"num_tokens": 2450932.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.58526463508606,
|
|
"epoch": 0.11216131064902331,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999911073516272,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.11660609394311905,
|
|
"num_tokens": 2460058.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.543748760223389,
|
|
"epoch": 0.11258139046418819,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999908391136237,
|
|
"loss": 6.3882,
|
|
"mean_token_accuracy": 0.12162717878818512,
|
|
"num_tokens": 2469607.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.594651317596435,
|
|
"epoch": 0.11300147027935308,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999905668900234,
|
|
"loss": 6.4404,
|
|
"mean_token_accuracy": 0.11361290663480758,
|
|
"num_tokens": 2478345.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.574893379211426,
|
|
"epoch": 0.11342155009451796,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499990290680831,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.11955868676304818,
|
|
"num_tokens": 2486662.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.634180545806885,
|
|
"epoch": 0.11384162990968284,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999900104860516,
|
|
"loss": 6.4884,
|
|
"mean_token_accuracy": 0.11496279463171959,
|
|
"num_tokens": 2495392.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.6078431606292725,
|
|
"epoch": 0.11426170972484773,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999897263056898,
|
|
"loss": 6.5187,
|
|
"mean_token_accuracy": 0.11110892221331596,
|
|
"num_tokens": 2505254.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.676256227493286,
|
|
"epoch": 0.1146817895400126,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499989438139751,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.11575900986790658,
|
|
"num_tokens": 2514096.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.550286197662354,
|
|
"epoch": 0.11510186935517748,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999891459882401,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.11746028289198876,
|
|
"num_tokens": 2523635.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.538182258605957,
|
|
"epoch": 0.11552194917034236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999888498511624,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.1144244447350502,
|
|
"num_tokens": 2532528.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.527873754501343,
|
|
"epoch": 0.11594202898550725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999885497285229,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.11667455583810807,
|
|
"num_tokens": 2541893.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.541602611541748,
|
|
"epoch": 0.11636210880067213,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999882456203273,
|
|
"loss": 6.3923,
|
|
"mean_token_accuracy": 0.1184983029961586,
|
|
"num_tokens": 2551551.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.588447904586792,
|
|
"epoch": 0.11678218861583702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999879375265806,
|
|
"loss": 6.347,
|
|
"mean_token_accuracy": 0.11739155948162079,
|
|
"num_tokens": 2560183.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.454002952575683,
|
|
"epoch": 0.11720226843100189,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999876254472886,
|
|
"loss": 6.2601,
|
|
"mean_token_accuracy": 0.12417450621724128,
|
|
"num_tokens": 2568697.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.591037464141846,
|
|
"epoch": 0.11762234824616677,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999873093824565,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.11451651230454445,
|
|
"num_tokens": 2578151.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.704318237304688,
|
|
"epoch": 0.11804242806133165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999869893320902,
|
|
"loss": 6.5716,
|
|
"mean_token_accuracy": 0.11275385171175004,
|
|
"num_tokens": 2585901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.5783727169036865,
|
|
"epoch": 0.11846250787649654,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999866652961952,
|
|
"loss": 6.3901,
|
|
"mean_token_accuracy": 0.11096679419279099,
|
|
"num_tokens": 2595655.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.604079818725586,
|
|
"epoch": 0.11888258769166142,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999863372747773,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.11101334393024445,
|
|
"num_tokens": 2604949.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.592713022232056,
|
|
"epoch": 0.11930266750682629,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999860052678423,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.11833727061748504,
|
|
"num_tokens": 2614260.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.529619216918945,
|
|
"epoch": 0.11972274732199117,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999856692753959,
|
|
"loss": 6.4205,
|
|
"mean_token_accuracy": 0.11050314903259277,
|
|
"num_tokens": 2623740.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.583321142196655,
|
|
"epoch": 0.12014282713715606,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999853292974444,
|
|
"loss": 6.3153,
|
|
"mean_token_accuracy": 0.12103430330753326,
|
|
"num_tokens": 2631998.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.522999906539917,
|
|
"epoch": 0.12056290695232094,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999849853339936,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.12008080482482911,
|
|
"num_tokens": 2641169.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.666995334625244,
|
|
"epoch": 0.12098298676748583,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999846373850497,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.11853480413556099,
|
|
"num_tokens": 2650576.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.456968832015991,
|
|
"epoch": 0.12140306658265071,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999842854506186,
|
|
"loss": 6.4062,
|
|
"mean_token_accuracy": 0.11563461422920226,
|
|
"num_tokens": 2660817.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.559107828140259,
|
|
"epoch": 0.12182314639781558,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999839295307069,
|
|
"loss": 6.3481,
|
|
"mean_token_accuracy": 0.11764338314533233,
|
|
"num_tokens": 2669338.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.621726083755493,
|
|
"epoch": 0.12224322621298046,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999835696253206,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.11631894037127495,
|
|
"num_tokens": 2679108.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.533853530883789,
|
|
"epoch": 0.12266330602814535,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999832057344664,
|
|
"loss": 6.37,
|
|
"mean_token_accuracy": 0.11607012003660203,
|
|
"num_tokens": 2688126.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.420909214019775,
|
|
"epoch": 0.12308338584331023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999828378581504,
|
|
"loss": 6.3282,
|
|
"mean_token_accuracy": 0.12565367370843888,
|
|
"num_tokens": 2697245.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.610960960388184,
|
|
"epoch": 0.12350346565847511,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999824659963793,
|
|
"loss": 6.3873,
|
|
"mean_token_accuracy": 0.11763433516025543,
|
|
"num_tokens": 2705934.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.490250873565674,
|
|
"epoch": 0.12392354547364,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999820901491598,
|
|
"loss": 6.314,
|
|
"mean_token_accuracy": 0.12268458679318428,
|
|
"num_tokens": 2714367.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.484623718261719,
|
|
"epoch": 0.12434362528880487,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999817103164983,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.12056686282157898,
|
|
"num_tokens": 2724366.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.5408772945404055,
|
|
"epoch": 0.12476370510396975,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999813264984017,
|
|
"loss": 6.3547,
|
|
"mean_token_accuracy": 0.11844174638390541,
|
|
"num_tokens": 2733980.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.583751821517945,
|
|
"epoch": 0.12518378491913462,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999809386948767,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.12221027910709381,
|
|
"num_tokens": 2744013.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.452259206771851,
|
|
"epoch": 0.12560386473429952,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999805469059302,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.11441577672958374,
|
|
"num_tokens": 2753385.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.51189775466919,
|
|
"epoch": 0.1260239445494644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999801511315693,
|
|
"loss": 6.2651,
|
|
"mean_token_accuracy": 0.12032239362597466,
|
|
"num_tokens": 2762875.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.593140554428101,
|
|
"epoch": 0.1264440243646293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999797513718007,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.12291451320052146,
|
|
"num_tokens": 2772182.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.4095139503479,
|
|
"epoch": 0.12686410417979416,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999793476266317,
|
|
"loss": 6.2994,
|
|
"mean_token_accuracy": 0.12340676560997962,
|
|
"num_tokens": 2780814.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.818328523635865,
|
|
"epoch": 0.12728418399495905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999789398960695,
|
|
"loss": 6.5676,
|
|
"mean_token_accuracy": 0.1171888455748558,
|
|
"num_tokens": 2791104.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.400639343261719,
|
|
"epoch": 0.12770426381012392,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999785281801212,
|
|
"loss": 6.2622,
|
|
"mean_token_accuracy": 0.12264100611209869,
|
|
"num_tokens": 2800081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.553307294845581,
|
|
"epoch": 0.1281243436252888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499978112478794,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.11860985979437828,
|
|
"num_tokens": 2809096.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.57843770980835,
|
|
"epoch": 0.1285444234404537,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999776927920955,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.12388472035527229,
|
|
"num_tokens": 2818857.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.497845268249511,
|
|
"epoch": 0.12896450325561856,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499977269120033,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.11523956879973411,
|
|
"num_tokens": 2829332.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.516994428634644,
|
|
"epoch": 0.12938458307078346,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499976841462614,
|
|
"loss": 6.3434,
|
|
"mean_token_accuracy": 0.11322477459907532,
|
|
"num_tokens": 2839193.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.506987857818603,
|
|
"epoch": 0.12980466288594833,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499976409819846,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.11825493946671486,
|
|
"num_tokens": 2848535.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.395366477966308,
|
|
"epoch": 0.1302247427011132,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999759741917369,
|
|
"loss": 6.2444,
|
|
"mean_token_accuracy": 0.12733460888266562,
|
|
"num_tokens": 2858090.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.548688650131226,
|
|
"epoch": 0.1306448225162781,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999755345782941,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.11661416217684746,
|
|
"num_tokens": 2866984.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.389467811584472,
|
|
"epoch": 0.13106490233144297,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999750909795256,
|
|
"loss": 6.2012,
|
|
"mean_token_accuracy": 0.12793270647525787,
|
|
"num_tokens": 2876550.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.517248106002808,
|
|
"epoch": 0.13148498214660786,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999746433954394,
|
|
"loss": 6.3019,
|
|
"mean_token_accuracy": 0.12286014333367348,
|
|
"num_tokens": 2885782.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.436316442489624,
|
|
"epoch": 0.13190506196177273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499974191826043,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.13175936564803123,
|
|
"num_tokens": 2894807.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.556414270401001,
|
|
"epoch": 0.1323251417769376,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999737362713448,
|
|
"loss": 6.3319,
|
|
"mean_token_accuracy": 0.12141326144337654,
|
|
"num_tokens": 2904076.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.438077783584594,
|
|
"epoch": 0.1327452215921025,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999732767313527,
|
|
"loss": 6.2301,
|
|
"mean_token_accuracy": 0.12145909070968627,
|
|
"num_tokens": 2913761.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.605003738403321,
|
|
"epoch": 0.13316530140726737,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999728132060746,
|
|
"loss": 6.4615,
|
|
"mean_token_accuracy": 0.11997142881155014,
|
|
"num_tokens": 2922848.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.545976686477661,
|
|
"epoch": 0.13358538122243227,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999723456955192,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.11663061752915382,
|
|
"num_tokens": 2932718.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.370933151245117,
|
|
"epoch": 0.13400546103759714,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999718741996945,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.12183845415711403,
|
|
"num_tokens": 2942686.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.422312498092651,
|
|
"epoch": 0.13442554085276204,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499971398718609,
|
|
"loss": 6.2711,
|
|
"mean_token_accuracy": 0.11760244071483612,
|
|
"num_tokens": 2952096.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.4970005512237545,
|
|
"epoch": 0.1348456206679269,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999709192522708,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.12237487882375717,
|
|
"num_tokens": 2960660.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.604963493347168,
|
|
"epoch": 0.13526570048309178,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999704358006887,
|
|
"loss": 6.3497,
|
|
"mean_token_accuracy": 0.11823863610625267,
|
|
"num_tokens": 2969834.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.454269361495972,
|
|
"epoch": 0.13568578029825668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999699483638712,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.12492895498871803,
|
|
"num_tokens": 2979023.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.496698570251465,
|
|
"epoch": 0.13610586011342155,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999694569418269,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.12362956255674362,
|
|
"num_tokens": 2988083.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.424844694137573,
|
|
"epoch": 0.13652593992858644,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999689615345645,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.12576239481568335,
|
|
"num_tokens": 2997240.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.554689359664917,
|
|
"epoch": 0.1369460197437513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999684621420928,
|
|
"loss": 6.3191,
|
|
"mean_token_accuracy": 0.12176118865609169,
|
|
"num_tokens": 3007077.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.500646114349365,
|
|
"epoch": 0.13736609955891618,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999679587644205,
|
|
"loss": 6.3628,
|
|
"mean_token_accuracy": 0.11905800476670265,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.445851802825928,
|
|
"epoch": 0.13778617937408108,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999674514015568,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.12496163100004196,
|
|
"num_tokens": 3025858.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.520554733276367,
|
|
"epoch": 0.13820625918924595,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999669400535105,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.12024016380310058,
|
|
"num_tokens": 3035537.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.2957807064056395,
|
|
"epoch": 0.13862633900441085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999664247202907,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.12314105778932571,
|
|
"num_tokens": 3044204.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.51614408493042,
|
|
"epoch": 0.13904641881957572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999659054019066,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.1245350755751133,
|
|
"num_tokens": 3053111.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.3797486305236815,
|
|
"epoch": 0.1394664986347406,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999653820983673,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.12539379447698593,
|
|
"num_tokens": 3062456.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.448072814941407,
|
|
"epoch": 0.13988657844990549,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499964854809682,
|
|
"loss": 6.2791,
|
|
"mean_token_accuracy": 0.1257368341088295,
|
|
"num_tokens": 3071132.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.44848141670227,
|
|
"epoch": 0.14030665826507036,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999643235358602,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.13099895641207696,
|
|
"num_tokens": 3080892.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.366451406478882,
|
|
"epoch": 0.14072673808023525,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999637882769112,
|
|
"loss": 6.1829,
|
|
"mean_token_accuracy": 0.12473593726754188,
|
|
"num_tokens": 3089874.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.438631200790406,
|
|
"epoch": 0.14114681789540012,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999632490328447,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.12419775351881981,
|
|
"num_tokens": 3099535.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.457270622253418,
|
|
"epoch": 0.14156689771056502,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999627058036699,
|
|
"loss": 6.2762,
|
|
"mean_token_accuracy": 0.12024275660514831,
|
|
"num_tokens": 3108772.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.486367511749267,
|
|
"epoch": 0.1419869775257299,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999621585893966,
|
|
"loss": 6.2888,
|
|
"mean_token_accuracy": 0.11725226789712906,
|
|
"num_tokens": 3118333.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.429450368881225,
|
|
"epoch": 0.14240705734089476,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999616073900346,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.12171539664268494,
|
|
"num_tokens": 3127356.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.498106622695923,
|
|
"epoch": 0.14282713715605966,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999610522055935,
|
|
"loss": 6.2912,
|
|
"mean_token_accuracy": 0.11646916791796684,
|
|
"num_tokens": 3136859.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.471587181091309,
|
|
"epoch": 0.14324721697122453,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999604930360832,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.11686689779162407,
|
|
"num_tokens": 3146607.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.408087730407715,
|
|
"epoch": 0.14366729678638943,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999599298815136,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.1279582552611828,
|
|
"num_tokens": 3156327.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.365849542617798,
|
|
"epoch": 0.1440873766015543,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004999593627418947,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.13225716799497605,
|
|
"num_tokens": 3165559.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.51579737663269,
|
|
"epoch": 0.14450745641671917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999587916172365,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.11835923567414283,
|
|
"num_tokens": 3173850.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.430272150039673,
|
|
"epoch": 0.14492753623188406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999582165075492,
|
|
"loss": 6.2413,
|
|
"mean_token_accuracy": 0.12055112421512604,
|
|
"num_tokens": 3182838.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.354161643981934,
|
|
"epoch": 0.14534761604704893,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999576374128429,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1231518879532814,
|
|
"num_tokens": 3191692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.491216516494751,
|
|
"epoch": 0.14576769586221383,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999570543331279,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.1253180719912052,
|
|
"num_tokens": 3200069.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.4589770317077635,
|
|
"epoch": 0.1461877756773787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999564672684145,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.11855114102363587,
|
|
"num_tokens": 3209653.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.512481784820556,
|
|
"epoch": 0.14660785549254357,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999558762187131,
|
|
"loss": 6.2232,
|
|
"mean_token_accuracy": 0.13238132372498512,
|
|
"num_tokens": 3218313.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.309611749649048,
|
|
"epoch": 0.14702793530770847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999552811840342,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.12678530514240266,
|
|
"num_tokens": 3227525.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.419345808029175,
|
|
"epoch": 0.14744801512287334,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999546821643884,
|
|
"loss": 6.2824,
|
|
"mean_token_accuracy": 0.12407411858439446,
|
|
"num_tokens": 3237022.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.376602506637573,
|
|
"epoch": 0.14786809493803824,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999540791597861,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.1266619324684143,
|
|
"num_tokens": 3246605.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.292014646530151,
|
|
"epoch": 0.1482881747532031,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999534721702383,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.13051704913377762,
|
|
"num_tokens": 3255587.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.414491844177246,
|
|
"epoch": 0.148708254568368,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999528611957553,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.1258571393787861,
|
|
"num_tokens": 3265669.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.458701848983765,
|
|
"epoch": 0.14912833438353287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999522462363485,
|
|
"loss": 6.2058,
|
|
"mean_token_accuracy": 0.12836851552128792,
|
|
"num_tokens": 3275013.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.390926885604858,
|
|
"epoch": 0.14954841419869774,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999516272920283,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.12579302862286568,
|
|
"num_tokens": 3284723.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.3027690887451175,
|
|
"epoch": 0.14996849401386264,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499951004362806,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.13238742649555207,
|
|
"num_tokens": 3293860.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.337384557723999,
|
|
"epoch": 0.1503885738290275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999503774486924,
|
|
"loss": 6.1876,
|
|
"mean_token_accuracy": 0.1245276965200901,
|
|
"num_tokens": 3303158.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.296294498443603,
|
|
"epoch": 0.1508086536441924,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999497465496987,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.12188991010189057,
|
|
"num_tokens": 3313068.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.346179628372193,
|
|
"epoch": 0.15122873345935728,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499949111665836,
|
|
"loss": 6.21,
|
|
"mean_token_accuracy": 0.12482204511761666,
|
|
"num_tokens": 3321885.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.417145109176635,
|
|
"epoch": 0.15164881327452215,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999484727971158,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.12663445696234704,
|
|
"num_tokens": 3330924.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.3640861988067625,
|
|
"epoch": 0.15206889308968705,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499947829943549,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.12180857658386231,
|
|
"num_tokens": 3340070.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.42901873588562,
|
|
"epoch": 0.15248897290485192,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999471831051474,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.13666835352778434,
|
|
"num_tokens": 3349870.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.384167289733886,
|
|
"epoch": 0.1529090527200168,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999465322819222,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.1196154922246933,
|
|
"num_tokens": 3359573.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.420805263519287,
|
|
"epoch": 0.15332913253518168,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999458774738851,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.1329035244882107,
|
|
"num_tokens": 3368577.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.3645374298095705,
|
|
"epoch": 0.15374921235034655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999452186810476,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.13094222992658616,
|
|
"num_tokens": 3377801.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.414077711105347,
|
|
"epoch": 0.15416929216551145,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999445559034214,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.12632885575294495,
|
|
"num_tokens": 3386666.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.492283153533935,
|
|
"epoch": 0.15458937198067632,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999438891410181,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.12365243062376977,
|
|
"num_tokens": 3396086.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.3361475467681885,
|
|
"epoch": 0.15500945179584122,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999432183938496,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.12596381455659866,
|
|
"num_tokens": 3404894.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.407006740570068,
|
|
"epoch": 0.1554295316110061,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999425436619279,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.12557967007160187,
|
|
"num_tokens": 3414172.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.476001453399658,
|
|
"epoch": 0.15584961142617096,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499941864945265,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.12348362207412719,
|
|
"num_tokens": 3423409.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.296181011199951,
|
|
"epoch": 0.15626969124133586,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999411822438726,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.12874680012464523,
|
|
"num_tokens": 3433047.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.446085119247437,
|
|
"epoch": 0.15668977105650073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499940495557763,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.12680488154292108,
|
|
"num_tokens": 3442490.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.367494440078735,
|
|
"epoch": 0.15710985087166562,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999398048869485,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.1263427644968033,
|
|
"num_tokens": 3451804.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.448274326324463,
|
|
"epoch": 0.1575299306868305,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499939110231441,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.12612806633114815,
|
|
"num_tokens": 3461481.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.3886480808258055,
|
|
"epoch": 0.1579500105019954,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999384115912531,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.12860373705625533,
|
|
"num_tokens": 3471798.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.294258403778076,
|
|
"epoch": 0.15837009031716026,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499937708966397,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.1269647814333439,
|
|
"num_tokens": 3481386.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.380875062942505,
|
|
"epoch": 0.15879017013232513,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999370023568853,
|
|
"loss": 6.1648,
|
|
"mean_token_accuracy": 0.1258099302649498,
|
|
"num_tokens": 3489981.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.298674488067627,
|
|
"epoch": 0.15921024994749003,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999362917627304,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.1279548816382885,
|
|
"num_tokens": 3498551.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.364571666717529,
|
|
"epoch": 0.1596303297626549,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999355771839448,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.12712288051843643,
|
|
"num_tokens": 3507921.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.472431182861328,
|
|
"epoch": 0.1600504095778198,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999348586205414,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12473546266555786,
|
|
"num_tokens": 3517570.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.44771819114685,
|
|
"epoch": 0.16047048939298467,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999341360725327,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.12144239619374275,
|
|
"num_tokens": 3526774.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.367665719985962,
|
|
"epoch": 0.16089056920814954,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999334095399317,
|
|
"loss": 6.2164,
|
|
"mean_token_accuracy": 0.13476391285657882,
|
|
"num_tokens": 3535319.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.29778151512146,
|
|
"epoch": 0.16131064902331443,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999326790227512,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.12915017306804658,
|
|
"num_tokens": 3544468.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.263013315200806,
|
|
"epoch": 0.1617307288384793,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999319445210041,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.13183464705944062,
|
|
"num_tokens": 3553529.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.341449880599976,
|
|
"epoch": 0.1621508086536442,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999312060347034,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.1265263617038727,
|
|
"num_tokens": 3563053.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.272969150543213,
|
|
"epoch": 0.16257088846880907,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999304635638621,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.13436255902051925,
|
|
"num_tokens": 3571877.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.305766344070435,
|
|
"epoch": 0.16299096828397394,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999297171084935,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1326524868607521,
|
|
"num_tokens": 3581496.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.313105726242066,
|
|
"epoch": 0.16341104809913884,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999289666686109,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.1272105999290943,
|
|
"num_tokens": 3590752.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.1983654499053955,
|
|
"epoch": 0.1638311279143037,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999282122442274,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.13213918060064317,
|
|
"num_tokens": 3599885.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.440747499465942,
|
|
"epoch": 0.1642512077294686,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999274538353564,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.12646706998348237,
|
|
"num_tokens": 3610039.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.272910118103027,
|
|
"epoch": 0.16467128754463348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999266914420114,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.12781383618712425,
|
|
"num_tokens": 3619954.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.3279284000396725,
|
|
"epoch": 0.16509136735979837,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499925925064206,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.13286505788564681,
|
|
"num_tokens": 3628164.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.360192775726318,
|
|
"epoch": 0.16551144717496324,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999251547019535,
|
|
"loss": 6.2577,
|
|
"mean_token_accuracy": 0.12934610545635222,
|
|
"num_tokens": 3636778.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.414323568344116,
|
|
"epoch": 0.16593152699012811,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999243803552678,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.1297714054584503,
|
|
"num_tokens": 3647046.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.239211511611939,
|
|
"epoch": 0.166351606805293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999236020241625,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.12911003157496453,
|
|
"num_tokens": 3656130.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.400930309295655,
|
|
"epoch": 0.16677168662045788,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999228197086514,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.12356689870357514,
|
|
"num_tokens": 3666145.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.2993443489074705,
|
|
"epoch": 0.16719176643562278,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999220334087484,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.12334830835461616,
|
|
"num_tokens": 3676722.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.383305788040161,
|
|
"epoch": 0.16761184625078765,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999212431244673,
|
|
"loss": 6.2353,
|
|
"mean_token_accuracy": 0.12262691259384155,
|
|
"num_tokens": 3685880.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.260931539535522,
|
|
"epoch": 0.16803192606595252,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999204488558222,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.13560437187552452,
|
|
"num_tokens": 3695167.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.341617202758789,
|
|
"epoch": 0.16845200588111742,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999196506028273,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.13033221215009688,
|
|
"num_tokens": 3703700.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.330134630203247,
|
|
"epoch": 0.1688720856962823,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999188483654965,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.1314982570707798,
|
|
"num_tokens": 3712825.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.2663736820220945,
|
|
"epoch": 0.16929216551144718,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999180421438442,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.13337414115667343,
|
|
"num_tokens": 3721807.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.426154756546021,
|
|
"epoch": 0.16971224532661205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999172319378846,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.12170653715729714,
|
|
"num_tokens": 3730502.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.357564783096313,
|
|
"epoch": 0.17013232514177692,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999164177476319,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.13129208087921143,
|
|
"num_tokens": 3739696.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.183953857421875,
|
|
"epoch": 0.17055240495694182,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999155995731009,
|
|
"loss": 6.1493,
|
|
"mean_token_accuracy": 0.1318361982703209,
|
|
"num_tokens": 3748675.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.50171127319336,
|
|
"epoch": 0.1709724847721067,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999147774143057,
|
|
"loss": 6.2267,
|
|
"mean_token_accuracy": 0.12189607992768288,
|
|
"num_tokens": 3757714.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.228915214538574,
|
|
"epoch": 0.1713925645872716,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499913951271261,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.13067708387970925,
|
|
"num_tokens": 3767589.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.328529357910156,
|
|
"epoch": 0.17181264440243646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999131211439816,
|
|
"loss": 6.1523,
|
|
"mean_token_accuracy": 0.13088449314236641,
|
|
"num_tokens": 3777261.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.358458805084228,
|
|
"epoch": 0.17223272421760136,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499912287032482,
|
|
"loss": 6.105,
|
|
"mean_token_accuracy": 0.13954608961939813,
|
|
"num_tokens": 3786658.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.194888353347778,
|
|
"epoch": 0.17265280403276623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499911448936777,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.1387820027768612,
|
|
"num_tokens": 3794977.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.274205017089844,
|
|
"epoch": 0.1730728838479311,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999106068568816,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.1296847067773342,
|
|
"num_tokens": 3805138.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.353550148010254,
|
|
"epoch": 0.173492963663096,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999097607928106,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.13772593289613724,
|
|
"num_tokens": 3814444.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.28287091255188,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999089107445788,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1331343598663807,
|
|
"num_tokens": 3822859.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.187959289550781,
|
|
"epoch": 0.17433312329342576,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999080567122016,
|
|
"loss": 6.0928,
|
|
"mean_token_accuracy": 0.13325781002640724,
|
|
"num_tokens": 3833159.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.2891417980194095,
|
|
"epoch": 0.17475320310859063,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999071986956941,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.13443495854735374,
|
|
"num_tokens": 3842136.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.291293048858643,
|
|
"epoch": 0.1751732829237555,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999063366950713,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.1292753279209137,
|
|
"num_tokens": 3851406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.308997011184692,
|
|
"epoch": 0.1755933627389204,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999054707103486,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.1310033306479454,
|
|
"num_tokens": 3861061.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.280231618881226,
|
|
"epoch": 0.17601344255408527,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999046007415412,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.1290605030953884,
|
|
"num_tokens": 3870357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.3239013671875,
|
|
"epoch": 0.17643352236925017,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999037267886646,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.1301138088107109,
|
|
"num_tokens": 3879393.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.217884635925293,
|
|
"epoch": 0.17685360218441504,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999028488517343,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.13041476532816887,
|
|
"num_tokens": 3888030.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.330727005004883,
|
|
"epoch": 0.1772736819995799,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999019669307659,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.14087287336587906,
|
|
"num_tokens": 3897430.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.268360662460327,
|
|
"epoch": 0.1776937618147448,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999010810257749,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.12782176434993744,
|
|
"num_tokens": 3907711.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.222604417800904,
|
|
"epoch": 0.17811384162990967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999001911367771,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.13519175425171853,
|
|
"num_tokens": 3915816.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.279330682754517,
|
|
"epoch": 0.17853392144507457,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998992972637883,
|
|
"loss": 6.1784,
|
|
"mean_token_accuracy": 0.12573839649558066,
|
|
"num_tokens": 3925162.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.312918043136596,
|
|
"epoch": 0.17895400126023944,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998983994068242,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.12800241634249687,
|
|
"num_tokens": 3934476.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.257489347457886,
|
|
"epoch": 0.17937408107540434,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998974975659006,
|
|
"loss": 6.117,
|
|
"mean_token_accuracy": 0.13179219737648964,
|
|
"num_tokens": 3943501.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.269851350784302,
|
|
"epoch": 0.1797941608905692,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998965917410338,
|
|
"loss": 6.105,
|
|
"mean_token_accuracy": 0.12811433225870134,
|
|
"num_tokens": 3953663.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.263305425643921,
|
|
"epoch": 0.18021424070573408,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998956819322397,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.1344923309981823,
|
|
"num_tokens": 3962634.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.2131294250488285,
|
|
"epoch": 0.18063432052089898,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998947681395343,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.1363943800330162,
|
|
"num_tokens": 3972496.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.464788103103638,
|
|
"epoch": 0.18105440033606385,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499893850362934,
|
|
"loss": 6.3219,
|
|
"mean_token_accuracy": 0.12087765410542488,
|
|
"num_tokens": 3980724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.291199588775635,
|
|
"epoch": 0.18147448015122875,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998929286024548,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.12979334518313407,
|
|
"num_tokens": 3989842.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.278742074966431,
|
|
"epoch": 0.18189455996639362,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998920028581133,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.14321179836988449,
|
|
"num_tokens": 3998534.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.2926966667175295,
|
|
"epoch": 0.18231463978155849,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998910731299258,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.12944981455802917,
|
|
"num_tokens": 4007677.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.248470973968506,
|
|
"epoch": 0.18273471959672338,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998901394179085,
|
|
"loss": 6.1367,
|
|
"mean_token_accuracy": 0.12592731565237045,
|
|
"num_tokens": 4016347.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.264119005203247,
|
|
"epoch": 0.18315479941188825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998892017220784,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.13742422610521315,
|
|
"num_tokens": 4025199.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.263695335388183,
|
|
"epoch": 0.18357487922705315,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998882600424519,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.12306004837155342,
|
|
"num_tokens": 4033933.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.230836820602417,
|
|
"epoch": 0.18399495904221802,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998873143790455,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.13827981501817704,
|
|
"num_tokens": 4042891.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.326285457611084,
|
|
"epoch": 0.1844150388573829,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998863647318763,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.13076284304261207,
|
|
"num_tokens": 4051123.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.218794679641723,
|
|
"epoch": 0.1848351186725478,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998854111009608,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.12811416238546372,
|
|
"num_tokens": 4060025.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.201221132278443,
|
|
"epoch": 0.18525519848771266,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998844534863161,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.12775525376200675,
|
|
"num_tokens": 4069363.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.318734121322632,
|
|
"epoch": 0.18567527830287756,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998834918879592,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.13352699503302573,
|
|
"num_tokens": 4078855.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.284113597869873,
|
|
"epoch": 0.18609535811804243,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499882526305907,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.13283827975392343,
|
|
"num_tokens": 4087801.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.278976345062256,
|
|
"epoch": 0.18651543793320732,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998815567401765,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.13487844318151473,
|
|
"num_tokens": 4096949.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.322417879104615,
|
|
"epoch": 0.1869355177483722,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998805831907851,
|
|
"loss": 6.092,
|
|
"mean_token_accuracy": 0.12811465859413146,
|
|
"num_tokens": 4105399.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.261762046813965,
|
|
"epoch": 0.18735559756353706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998796056577501,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.12984329760074614,
|
|
"num_tokens": 4113873.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.17222752571106,
|
|
"epoch": 0.18777567737870196,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998786241410886,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.13395953848958014,
|
|
"num_tokens": 4123528.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.337759065628052,
|
|
"epoch": 0.18819575719386683,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499877638640818,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.12952830642461777,
|
|
"num_tokens": 4133370.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.218608713150024,
|
|
"epoch": 0.18861583700903173,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499876649156956,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.13578148186206818,
|
|
"num_tokens": 4142370.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.224829864501953,
|
|
"epoch": 0.1890359168241966,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998756556895196,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.13433386385440826,
|
|
"num_tokens": 4152367.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.281910085678101,
|
|
"epoch": 0.18945599663936147,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499874658238527,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.134437657892704,
|
|
"num_tokens": 4161126.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.240273094177246,
|
|
"epoch": 0.18987607645452637,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998736568039957,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.13461074903607367,
|
|
"num_tokens": 4169910.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.2365155696868895,
|
|
"epoch": 0.19029615626969124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998726513859432,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.1260552354156971,
|
|
"num_tokens": 4179893.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.301045608520508,
|
|
"epoch": 0.19071623608485613,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998716419843875,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.13841021955013275,
|
|
"num_tokens": 4190065.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.13691897392273,
|
|
"epoch": 0.191136315900021,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998706285993465,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.13612305223941804,
|
|
"num_tokens": 4198395.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.308142518997192,
|
|
"epoch": 0.19155639571518587,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998696112308381,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.13221055194735526,
|
|
"num_tokens": 4207555.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.1573583602905275,
|
|
"epoch": 0.19197647553035077,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998685898788803,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.13469478338956833,
|
|
"num_tokens": 4216533.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.334969472885132,
|
|
"epoch": 0.19239655534551564,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998675645434914,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.134019573032856,
|
|
"num_tokens": 4225575.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.167663669586181,
|
|
"epoch": 0.19281663516068054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998665352246891,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.14072284027934073,
|
|
"num_tokens": 4234306.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.1863524436950685,
|
|
"epoch": 0.1932367149758454,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998655019224921,
|
|
"loss": 6.1102,
|
|
"mean_token_accuracy": 0.13416126370429993,
|
|
"num_tokens": 4243998.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.274348163604737,
|
|
"epoch": 0.19365679479101028,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998644646369185,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.13099471628665924,
|
|
"num_tokens": 4253653.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.157945919036865,
|
|
"epoch": 0.19407687460617518,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998634233679865,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.12541876286268233,
|
|
"num_tokens": 4263305.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.220145130157471,
|
|
"epoch": 0.19449695442134005,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499862378115715,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.13993363454937935,
|
|
"num_tokens": 4272212.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.2961366176605225,
|
|
"epoch": 0.19491703423650494,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998613288801221,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.12927026972174643,
|
|
"num_tokens": 4281445.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.306110906600952,
|
|
"epoch": 0.1953371140516698,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998602756612267,
|
|
"loss": 6.0867,
|
|
"mean_token_accuracy": 0.13294345438480376,
|
|
"num_tokens": 4290938.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.204567623138428,
|
|
"epoch": 0.1957571938668347,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998592184590471,
|
|
"loss": 6.1218,
|
|
"mean_token_accuracy": 0.13037385493516923,
|
|
"num_tokens": 4300022.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.182180976867675,
|
|
"epoch": 0.19617727368199958,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998581572736024,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.13552708327770233,
|
|
"num_tokens": 4308910.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.136313104629517,
|
|
"epoch": 0.19659735349716445,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998570921049112,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.1380659468472004,
|
|
"num_tokens": 4317136.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.223579549789429,
|
|
"epoch": 0.19701743331232935,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998560229529924,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.1369388960301876,
|
|
"num_tokens": 4326163.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.337650966644287,
|
|
"epoch": 0.19743751312749422,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998549498178649,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.1331799015402794,
|
|
"num_tokens": 4335837.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.207294178009033,
|
|
"epoch": 0.19785759294265912,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998538726995477,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.13218674436211586,
|
|
"num_tokens": 4345108.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.251865100860596,
|
|
"epoch": 0.198277672757824,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049985279159806,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.13030959963798522,
|
|
"num_tokens": 4353761.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.238997983932495,
|
|
"epoch": 0.19869775257298886,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998517065134208,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.1309155412018299,
|
|
"num_tokens": 4363244.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.240653324127197,
|
|
"epoch": 0.19911783238815375,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998506174456494,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.13212330862879754,
|
|
"num_tokens": 4373034.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.222096681594849,
|
|
"epoch": 0.19953791220331862,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998495243947653,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.12821247354149817,
|
|
"num_tokens": 4382554.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.245941638946533,
|
|
"epoch": 0.19995799201848352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998484273607875,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.1390307828783989,
|
|
"num_tokens": 4391001.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.051425838470459,
|
|
"epoch": 0.2003780718336484,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998473263437356,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.13520744293928147,
|
|
"num_tokens": 4400632.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.14297890663147,
|
|
"epoch": 0.20079815164881326,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499846221343629,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.13219423592090607,
|
|
"num_tokens": 4409565.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.155060577392578,
|
|
"epoch": 0.20121823146397816,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998451123604875,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.14023150131106377,
|
|
"num_tokens": 4418384.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.256305456161499,
|
|
"epoch": 0.20163831127914303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998439993943306,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.1406387820839882,
|
|
"num_tokens": 4427581.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.275782299041748,
|
|
"epoch": 0.20205839109430793,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998428824451779,
|
|
"loss": 6.0884,
|
|
"mean_token_accuracy": 0.12875301465392114,
|
|
"num_tokens": 4436572.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.213010787963867,
|
|
"epoch": 0.2024784709094728,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998417615130495,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.12865509316325188,
|
|
"num_tokens": 4445230.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.289054584503174,
|
|
"epoch": 0.2028985507246377,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998406365979649,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.13029074743390084,
|
|
"num_tokens": 4454251.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.1775250911712645,
|
|
"epoch": 0.20331863053980256,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998395076999443,
|
|
"loss": 5.9922,
|
|
"mean_token_accuracy": 0.13723801597952842,
|
|
"num_tokens": 4463949.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.2511374950408936,
|
|
"epoch": 0.20373871035496743,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998383748190076,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.1281643107533455,
|
|
"num_tokens": 4473373.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.318125200271607,
|
|
"epoch": 0.20415879017013233,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998372379551748,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.13771012797951698,
|
|
"num_tokens": 4482303.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.15513801574707,
|
|
"epoch": 0.2045788699852972,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998360971084663,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.1334059588611126,
|
|
"num_tokens": 4491214.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.118799161911011,
|
|
"epoch": 0.2049989498004621,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998349522789019,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.14181319028139114,
|
|
"num_tokens": 4500099.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.1538893699646,
|
|
"epoch": 0.20541902961562697,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998338034665021,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.13947194814682007,
|
|
"num_tokens": 4509893.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.1470013618469235,
|
|
"epoch": 0.20583910943079184,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998326506712872,
|
|
"loss": 5.9665,
|
|
"mean_token_accuracy": 0.1369723781943321,
|
|
"num_tokens": 4518606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.206533908843994,
|
|
"epoch": 0.20625918924595674,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998314938932778,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.1360008053481579,
|
|
"num_tokens": 4528392.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.256601238250733,
|
|
"epoch": 0.2066792690611216,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998303331324943,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.13803394809365271,
|
|
"num_tokens": 4536983.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.104164505004883,
|
|
"epoch": 0.2070993488762865,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998291683889571,
|
|
"loss": 5.9373,
|
|
"mean_token_accuracy": 0.14096372500061988,
|
|
"num_tokens": 4544967.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.204864883422852,
|
|
"epoch": 0.20751942869145137,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499827999662687,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.13221748918294907,
|
|
"num_tokens": 4554646.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.243742561340332,
|
|
"epoch": 0.20793950850661624,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998268269537046,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.13807824179530143,
|
|
"num_tokens": 4564040.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.120432043075562,
|
|
"epoch": 0.20835958832178114,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998256502620308,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.14363139793276786,
|
|
"num_tokens": 4573758.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.265066432952881,
|
|
"epoch": 0.208779668136946,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998244695876864,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.1315403826534748,
|
|
"num_tokens": 4582097.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.097950839996338,
|
|
"epoch": 0.2091997479521109,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998232849306921,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.1351850524544716,
|
|
"num_tokens": 4590687.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.293486022949219,
|
|
"epoch": 0.20961982776727578,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998220962910693,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.13292664289474487,
|
|
"num_tokens": 4599497.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.173567104339599,
|
|
"epoch": 0.21003990758244068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998209036688386,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.13765107467770576,
|
|
"num_tokens": 4607958.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.268425703048706,
|
|
"epoch": 0.21045998739760555,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998197070640216,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.129291183501482,
|
|
"num_tokens": 4617515.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.28843879699707,
|
|
"epoch": 0.21088006721277042,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998185064766391,
|
|
"loss": 6.0059,
|
|
"mean_token_accuracy": 0.1318512476980686,
|
|
"num_tokens": 4627037.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.095378351211548,
|
|
"epoch": 0.21130014702793531,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998173019067127,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.1362810969352722,
|
|
"num_tokens": 4637393.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.151039409637451,
|
|
"epoch": 0.21172022684310018,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998160933542633,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.12635309770703315,
|
|
"num_tokens": 4646832.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.288768529891968,
|
|
"epoch": 0.21214030665826508,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998148808193128,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.13684087693691255,
|
|
"num_tokens": 4655719.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.185772228240967,
|
|
"epoch": 0.21256038647342995,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998136643018823,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.13462624847888946,
|
|
"num_tokens": 4665364.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.2163975715637205,
|
|
"epoch": 0.21298046628859482,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998124438019935,
|
|
"loss": 6.0079,
|
|
"mean_token_accuracy": 0.13166589960455893,
|
|
"num_tokens": 4674760.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.0905904293060305,
|
|
"epoch": 0.21340054610375972,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998112193196681,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.13693561255931855,
|
|
"num_tokens": 4683900.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.067295026779175,
|
|
"epoch": 0.2138206259189246,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998099908549277,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.13006317764520645,
|
|
"num_tokens": 4693915.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.123124837875366,
|
|
"epoch": 0.2142407057340895,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499808758407794,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1404764860868454,
|
|
"num_tokens": 4703102.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.155497789382935,
|
|
"epoch": 0.21466078554925436,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998075219782889,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.13892892748117447,
|
|
"num_tokens": 4712925.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.1989946365356445,
|
|
"epoch": 0.21508086536441923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998062815664344,
|
|
"loss": 5.9819,
|
|
"mean_token_accuracy": 0.13216783180832864,
|
|
"num_tokens": 4722641.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.098575496673584,
|
|
"epoch": 0.21550094517958412,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998050371722524,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.13535310626029967,
|
|
"num_tokens": 4732603.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.0733263969421385,
|
|
"epoch": 0.215921024994749,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998037887957649,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.1405107393860817,
|
|
"num_tokens": 4742644.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.274937391281128,
|
|
"epoch": 0.2163411048099139,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998025364369939,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.13099505975842476,
|
|
"num_tokens": 4751482.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.293144750595093,
|
|
"epoch": 0.21676118462507876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998012800959619,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.13207904621958733,
|
|
"num_tokens": 4760593.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.261121511459351,
|
|
"epoch": 0.21718126444024366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998000197726909,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.13794807344675064,
|
|
"num_tokens": 4769294.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.1975377082824705,
|
|
"epoch": 0.21760134425540853,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997987554672033,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.13557377234101295,
|
|
"num_tokens": 4779239.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.179704809188843,
|
|
"epoch": 0.2180214240705734,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997974871795215,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.13279528692364692,
|
|
"num_tokens": 4788211.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.169263744354248,
|
|
"epoch": 0.2184415038857383,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499796214909668,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.14151790514588355,
|
|
"num_tokens": 4797921.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.179717254638672,
|
|
"epoch": 0.21886158370090317,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997949386576653,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.13185311183333398,
|
|
"num_tokens": 4807772.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.09913649559021,
|
|
"epoch": 0.21928166351606806,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499793658423536,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.1336025021970272,
|
|
"num_tokens": 4817999.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.236963701248169,
|
|
"epoch": 0.21970174333123293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997923742073028,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.14284878820180893,
|
|
"num_tokens": 4826679.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.087517356872558,
|
|
"epoch": 0.2201218231463978,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997910860089884,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.13721209689974784,
|
|
"num_tokens": 4834998.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.181451654434204,
|
|
"epoch": 0.2205419029615627,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997897938286156,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.140488101541996,
|
|
"num_tokens": 4843635.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.164580821990967,
|
|
"epoch": 0.22096198277672757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997884976662075,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.13446614518761635,
|
|
"num_tokens": 4852027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.231269407272339,
|
|
"epoch": 0.22138206259189247,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997871975217868,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.14198934510350228,
|
|
"num_tokens": 4861244.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.045923233032227,
|
|
"epoch": 0.22180214240705734,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997858933953768,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.14127301722764968,
|
|
"num_tokens": 4869902.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.087070560455322,
|
|
"epoch": 0.2222222222222222,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997845852870004,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.14420521035790443,
|
|
"num_tokens": 4878502.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.088281726837158,
|
|
"epoch": 0.2226423020373871,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997832731966806,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.14226024821400643,
|
|
"num_tokens": 4888348.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.156372451782227,
|
|
"epoch": 0.22306238185255198,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997819571244411,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.14085667207837105,
|
|
"num_tokens": 4897302.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.102771759033203,
|
|
"epoch": 0.22348246166771688,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997806370703049,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.1412481315433979,
|
|
"num_tokens": 4907078.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.086454391479492,
|
|
"epoch": 0.22390254148288175,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997793130342954,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.14060726314783095,
|
|
"num_tokens": 4917489.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.059194183349609,
|
|
"epoch": 0.22432262129804661,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997779850164363,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.13854166269302368,
|
|
"num_tokens": 4927073.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.217087936401367,
|
|
"epoch": 0.2247427011132115,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997766530167508,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.13044301494956018,
|
|
"num_tokens": 4935464.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.28878345489502,
|
|
"epoch": 0.22516278092837638,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997753170352627,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.13435352668166162,
|
|
"num_tokens": 4944718.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.156159353256226,
|
|
"epoch": 0.22558286074354128,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997739770719955,
|
|
"loss": 6.0181,
|
|
"mean_token_accuracy": 0.13306965455412864,
|
|
"num_tokens": 4954223.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.152837419509888,
|
|
"epoch": 0.22600294055870615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499772633126973,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.13488989993929862,
|
|
"num_tokens": 4963371.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.077383518218994,
|
|
"epoch": 0.22642302037387105,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997712852002192,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.14509259015321732,
|
|
"num_tokens": 4972973.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.145831155776977,
|
|
"epoch": 0.22684310018903592,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997699332917578,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.12881803661584854,
|
|
"num_tokens": 4982808.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.264477157592774,
|
|
"epoch": 0.2272631800042008,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997685774016127,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.13483983278274536,
|
|
"num_tokens": 4992427.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.240380764007568,
|
|
"epoch": 0.22768325981936569,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499767217529808,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.1287289910018444,
|
|
"num_tokens": 5003562.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.103500318527222,
|
|
"epoch": 0.22810333963453056,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997658536763678,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.13835748061537742,
|
|
"num_tokens": 5013429.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.204726886749268,
|
|
"epoch": 0.22852341944969545,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997644858413163,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.13989441394805907,
|
|
"num_tokens": 5022045.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.083020782470703,
|
|
"epoch": 0.22894349926486032,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997631140246775,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.14418582767248153,
|
|
"num_tokens": 5032260.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.0916870594024655,
|
|
"epoch": 0.2293635790800252,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499761738226476,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.1432834282517433,
|
|
"num_tokens": 5041688.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.093435859680175,
|
|
"epoch": 0.2297836588951901,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499760358446736,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.13241263329982758,
|
|
"num_tokens": 5051005.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.205419874191284,
|
|
"epoch": 0.23020373871035496,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499758974685482,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.13710809499025345,
|
|
"num_tokens": 5060084.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.123983669281006,
|
|
"epoch": 0.23062381852551986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997575869427385,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.14109890162944794,
|
|
"num_tokens": 5069081.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.1220703125,
|
|
"epoch": 0.23104389834068473,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00049975619521853,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.13786115869879723,
|
|
"num_tokens": 5078597.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.122048711776733,
|
|
"epoch": 0.2314639781558496,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997547995128814,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.14226307570934296,
|
|
"num_tokens": 5087607.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.144302225112915,
|
|
"epoch": 0.2318840579710145,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997533998258171,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.14107478111982347,
|
|
"num_tokens": 5097412.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.224723386764526,
|
|
"epoch": 0.23230413778617937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997519961573622,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.13255186080932618,
|
|
"num_tokens": 5105817.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.279865074157715,
|
|
"epoch": 0.23272421760134426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997505885075414,
|
|
"loss": 6.0941,
|
|
"mean_token_accuracy": 0.13345747739076613,
|
|
"num_tokens": 5114958.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.129254007339478,
|
|
"epoch": 0.23314429741650913,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997491768763795,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.13575156703591346,
|
|
"num_tokens": 5123728.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.134473133087158,
|
|
"epoch": 0.23356437723167403,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997477612639018,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.13159941956400872,
|
|
"num_tokens": 5134099.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.231441497802734,
|
|
"epoch": 0.2339844570468389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997463416701332,
|
|
"loss": 6.0689,
|
|
"mean_token_accuracy": 0.1301489420235157,
|
|
"num_tokens": 5142934.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.0879510879516605,
|
|
"epoch": 0.23440453686200377,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997449180950989,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.15564696341753007,
|
|
"num_tokens": 5151835.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.114243698120117,
|
|
"epoch": 0.23482461667716867,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997434905388241,
|
|
"loss": 5.9528,
|
|
"mean_token_accuracy": 0.14443679004907609,
|
|
"num_tokens": 5161136.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.104035425186157,
|
|
"epoch": 0.23524469649233354,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499742059001334,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.14185608699917793,
|
|
"num_tokens": 5170741.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.075469923019409,
|
|
"epoch": 0.23566477630749844,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997406234826541,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.14401806518435478,
|
|
"num_tokens": 5180549.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.064437532424927,
|
|
"epoch": 0.2360848561226633,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997391839828098,
|
|
"loss": 5.8936,
|
|
"mean_token_accuracy": 0.14641853421926498,
|
|
"num_tokens": 5189486.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.1467596054077145,
|
|
"epoch": 0.23650493593782818,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997377405018266,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.1352544255554676,
|
|
"num_tokens": 5198525.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.114045858383179,
|
|
"epoch": 0.23692501575299307,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00049973629303973,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.13799095004796982,
|
|
"num_tokens": 5207124.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.020995473861694,
|
|
"epoch": 0.23734509556815794,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997348415965457,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.14437564313411713,
|
|
"num_tokens": 5216529.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.182903099060058,
|
|
"epoch": 0.23776517538332284,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997333861722995,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.14223513826727868,
|
|
"num_tokens": 5225796.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.194612598419189,
|
|
"epoch": 0.2381852551984877,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499731926767017,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.14215042740106582,
|
|
"num_tokens": 5233876.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.092140197753906,
|
|
"epoch": 0.23860533501365258,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997304633807242,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.13835923075675965,
|
|
"num_tokens": 5244782.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.103197765350342,
|
|
"epoch": 0.23902541482881748,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997289960134468,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.14274498224258422,
|
|
"num_tokens": 5253453.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.109802532196045,
|
|
"epoch": 0.23944549464398235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997275246652111,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.1414198510348797,
|
|
"num_tokens": 5262355.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.074161100387573,
|
|
"epoch": 0.23986557445914725,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499726049336043,
|
|
"loss": 5.884,
|
|
"mean_token_accuracy": 0.14384180679917336,
|
|
"num_tokens": 5271959.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.123191499710083,
|
|
"epoch": 0.24028565427431212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997245700259686,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.14565154165029526,
|
|
"num_tokens": 5281393.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.1445637226104735,
|
|
"epoch": 0.240705734089477,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997230867350141,
|
|
"loss": 6.0674,
|
|
"mean_token_accuracy": 0.13226635977625847,
|
|
"num_tokens": 5290979.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.2341917037963865,
|
|
"epoch": 0.24112581390464188,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997215994632059,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.14298992082476616,
|
|
"num_tokens": 5300263.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.114161205291748,
|
|
"epoch": 0.24154589371980675,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997201082105704,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.13639863729476928,
|
|
"num_tokens": 5309522.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.144821310043335,
|
|
"epoch": 0.24196597353497165,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997186129771338,
|
|
"loss": 6.0256,
|
|
"mean_token_accuracy": 0.1396084174513817,
|
|
"num_tokens": 5319770.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.21076397895813,
|
|
"epoch": 0.24238605335013652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997171137629226,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.1428602673113346,
|
|
"num_tokens": 5328400.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.059879302978516,
|
|
"epoch": 0.24280613316530142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997156105679636,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.1514780417084694,
|
|
"num_tokens": 5336338.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.016794109344483,
|
|
"epoch": 0.2432262129804663,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997141033922832,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.13949262946844102,
|
|
"num_tokens": 5345391.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.142647981643677,
|
|
"epoch": 0.24364629279563116,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997125922359081,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.13398301377892494,
|
|
"num_tokens": 5354709.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.111950016021728,
|
|
"epoch": 0.24406637261079606,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997110770988652,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.14174696654081345,
|
|
"num_tokens": 5363738.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.079838371276855,
|
|
"epoch": 0.24448645242596093,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997095579811813,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.13893039748072625,
|
|
"num_tokens": 5373583.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.187237548828125,
|
|
"epoch": 0.24490653224112582,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997080348828833,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.13840119615197183,
|
|
"num_tokens": 5383486.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.126826524734497,
|
|
"epoch": 0.2453266120562907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997065078039981,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.1391638047993183,
|
|
"num_tokens": 5391974.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.164314794540405,
|
|
"epoch": 0.24574669187145556,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997049767445529,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.1359800137579441,
|
|
"num_tokens": 5400882.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.199448156356811,
|
|
"epoch": 0.24616677168662046,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997034417045746,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.13757251799106598,
|
|
"num_tokens": 5410538.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.0790434837341305,
|
|
"epoch": 0.24658685150178533,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997019026840907,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.14040058851242065,
|
|
"num_tokens": 5419406.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.975088357925415,
|
|
"epoch": 0.24700693131695023,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997003596831282,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.1371507503092289,
|
|
"num_tokens": 5428817.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.196776390075684,
|
|
"epoch": 0.2474270111321151,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996988127017145,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.13953725397586822,
|
|
"num_tokens": 5438277.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.091228246688843,
|
|
"epoch": 0.24784709094728,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996972617398772,
|
|
"loss": 6.0034,
|
|
"mean_token_accuracy": 0.13882646411657334,
|
|
"num_tokens": 5447440.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.129848289489746,
|
|
"epoch": 0.24826717076244487,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996957067976435,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.13761287704110145,
|
|
"num_tokens": 5455988.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.139088869094849,
|
|
"epoch": 0.24868725057760974,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996941478750411,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.14046952053904532,
|
|
"num_tokens": 5464996.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.173188400268555,
|
|
"epoch": 0.24910733039277463,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996925849720975,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.13539182469248773,
|
|
"num_tokens": 5474174.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.202445459365845,
|
|
"epoch": 0.2495274102079395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996910180888405,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.14169209375977515,
|
|
"num_tokens": 5482838.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.113552713394165,
|
|
"epoch": 0.2499474900231044,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996894472252977,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.13861241191625595,
|
|
"num_tokens": 5491616.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.091303777694702,
|
|
"epoch": 0.25036756983826924,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996878723814973,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.13805645182728768,
|
|
"num_tokens": 5500942.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.159912872314453,
|
|
"epoch": 0.25078764965343414,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996862935574667,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.13720250651240348,
|
|
"num_tokens": 5510078.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.035575675964355,
|
|
"epoch": 0.25120772946859904,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996847107532342,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.13990190252661705,
|
|
"num_tokens": 5518924.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.1541543960571286,
|
|
"epoch": 0.25162780928376394,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996831239688277,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.135651333630085,
|
|
"num_tokens": 5527385.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.980669641494751,
|
|
"epoch": 0.2520478890989288,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996815332042754,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14832203537225724,
|
|
"num_tokens": 5536781.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2520478890989288,
|
|
"eval_entropy": 5.811351248549843,
|
|
"eval_loss": 5.969449043273926,
|
|
"eval_mean_token_accuracy": 0.14523225678583587,
|
|
"eval_num_tokens": 5536781.0,
|
|
"eval_runtime": 20.9301,
|
|
"eval_samples_per_second": 1785.275,
|
|
"eval_steps_per_second": 223.171,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.094974756240845,
|
|
"epoch": 0.2524679689140937,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996799384596054,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.13971033170819283,
|
|
"num_tokens": 5545893.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.159230375289917,
|
|
"epoch": 0.2528880487292586,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996783397348461,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.1357440948486328,
|
|
"num_tokens": 5555818.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.10536036491394,
|
|
"epoch": 0.2533081285444234,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996767370300256,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14052527099847795,
|
|
"num_tokens": 5565331.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.084013175964356,
|
|
"epoch": 0.2537282083595883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996751303451724,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.1431153953075409,
|
|
"num_tokens": 5574003.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.077633428573608,
|
|
"epoch": 0.2541482881747532,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996735196803149,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.1457200452685356,
|
|
"num_tokens": 5582517.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.136652421951294,
|
|
"epoch": 0.2545683679899181,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996719050354818,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.13732432797551156,
|
|
"num_tokens": 5591952.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.048459148406982,
|
|
"epoch": 0.25498844780508295,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996702864107015,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.1418526716530323,
|
|
"num_tokens": 5601460.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.284002351760864,
|
|
"epoch": 0.25540852762024785,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996686638060028,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.13265891820192338,
|
|
"num_tokens": 5610776.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.0990218162536625,
|
|
"epoch": 0.25582860743541275,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996670372214144,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.14587848633527756,
|
|
"num_tokens": 5619627.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.947749042510987,
|
|
"epoch": 0.2562486872505776,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996654066569651,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.14839987307786942,
|
|
"num_tokens": 5628969.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.065955305099488,
|
|
"epoch": 0.2566687670657425,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996637721126839,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.1424746796488762,
|
|
"num_tokens": 5638629.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.107337474822998,
|
|
"epoch": 0.2570888468809074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996621335885996,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.14037469550967216,
|
|
"num_tokens": 5647571.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.1402346134185795,
|
|
"epoch": 0.2575089266960722,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996604910847413,
|
|
"loss": 5.8758,
|
|
"mean_token_accuracy": 0.1501998595893383,
|
|
"num_tokens": 5656709.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.089657640457153,
|
|
"epoch": 0.2579290065112371,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499658844601138,
|
|
"loss": 6.0454,
|
|
"mean_token_accuracy": 0.1388375774025917,
|
|
"num_tokens": 5665714.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.122017049789429,
|
|
"epoch": 0.258349086326402,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499657194137819,
|
|
"loss": 6.0085,
|
|
"mean_token_accuracy": 0.14038632139563562,
|
|
"num_tokens": 5675854.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.120520496368409,
|
|
"epoch": 0.2587691661415669,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996555396948136,
|
|
"loss": 5.8388,
|
|
"mean_token_accuracy": 0.13863911256194114,
|
|
"num_tokens": 5685690.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.04867787361145,
|
|
"epoch": 0.25918924595673176,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996538812721509,
|
|
"loss": 5.8979,
|
|
"mean_token_accuracy": 0.14566717743873597,
|
|
"num_tokens": 5695766.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.1084822654724125,
|
|
"epoch": 0.25960932577189666,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996522188698603,
|
|
"loss": 5.9477,
|
|
"mean_token_accuracy": 0.14305482804775238,
|
|
"num_tokens": 5704365.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.1373619556427,
|
|
"epoch": 0.26002940558706156,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996505524879714,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.1344648614525795,
|
|
"num_tokens": 5713345.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.0922935962677,
|
|
"epoch": 0.2604494854022264,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996488821265137,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.14658251106739045,
|
|
"num_tokens": 5722907.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.012635898590088,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996472077855166,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.1446256823837757,
|
|
"num_tokens": 5731589.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.104847145080567,
|
|
"epoch": 0.2612896450325562,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049964552946501,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.14166852980852127,
|
|
"num_tokens": 5739922.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.955222845077515,
|
|
"epoch": 0.2617097248477211,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996438471650235,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.14593275487422944,
|
|
"num_tokens": 5749206.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.058114147186279,
|
|
"epoch": 0.26212980466288593,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996421608855869,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.14658411368727683,
|
|
"num_tokens": 5758803.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.108597993850708,
|
|
"epoch": 0.26254988447805083,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996404706267301,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.1372783973813057,
|
|
"num_tokens": 5768368.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.006940793991089,
|
|
"epoch": 0.26296996429321573,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499638776388483,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.15118449479341506,
|
|
"num_tokens": 5776707.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.002774715423584,
|
|
"epoch": 0.26339004410838057,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996370781708757,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.1297268383204937,
|
|
"num_tokens": 5787037.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.140283203125,
|
|
"epoch": 0.26381012392354547,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996353759739382,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.14406516328454017,
|
|
"num_tokens": 5796630.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.036018514633179,
|
|
"epoch": 0.26423020373871037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996336697977007,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.14153894111514093,
|
|
"num_tokens": 5806402.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.037613487243652,
|
|
"epoch": 0.2646502835538752,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996319596421933,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.14679263159632683,
|
|
"num_tokens": 5815742.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.028949451446533,
|
|
"epoch": 0.2650703633690401,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996302455074466,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.14230084121227266,
|
|
"num_tokens": 5824915.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.096432209014893,
|
|
"epoch": 0.265490443184205,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996285273934906,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.1397813640534878,
|
|
"num_tokens": 5834978.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.111389875411987,
|
|
"epoch": 0.2659105229993699,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499626805300356,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.14250660091638565,
|
|
"num_tokens": 5845684.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.151995420455933,
|
|
"epoch": 0.26633060281453474,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996250792280732,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.13529476448893546,
|
|
"num_tokens": 5854905.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.133824729919434,
|
|
"epoch": 0.26675068262969964,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996233491766727,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.13773170113563538,
|
|
"num_tokens": 5863654.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.108005428314209,
|
|
"epoch": 0.26717076244486454,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996216151461854,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14263901710510254,
|
|
"num_tokens": 5872442.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.124168252944946,
|
|
"epoch": 0.2675908422600294,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996198771366417,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1422991782426834,
|
|
"num_tokens": 5882372.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.892281866073608,
|
|
"epoch": 0.2680109220751943,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996181351480726,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.14947764426469803,
|
|
"num_tokens": 5891113.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.995995616912841,
|
|
"epoch": 0.2684310018903592,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996163891805089,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.14690565466880798,
|
|
"num_tokens": 5899582.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.141474914550781,
|
|
"epoch": 0.2688510817055241,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996146392339815,
|
|
"loss": 5.9025,
|
|
"mean_token_accuracy": 0.13870225176215173,
|
|
"num_tokens": 5908938.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.058559274673462,
|
|
"epoch": 0.2692711615206889,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996128853085215,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.14446185976266862,
|
|
"num_tokens": 5918055.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.094514513015747,
|
|
"epoch": 0.2696912413358538,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996111274041598,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.14117878526449204,
|
|
"num_tokens": 5926744.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.07371563911438,
|
|
"epoch": 0.2701113211510187,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996093655209277,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.1441202089190483,
|
|
"num_tokens": 5936521.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.157954692840576,
|
|
"epoch": 0.27053140096618356,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996075996588563,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.1351262703537941,
|
|
"num_tokens": 5945010.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.07440071105957,
|
|
"epoch": 0.27095148078134845,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499605829817977,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.14755850434303283,
|
|
"num_tokens": 5953766.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.051190042495728,
|
|
"epoch": 0.27137156059651335,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499604055998321,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.14777183532714844,
|
|
"num_tokens": 5962168.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.972162342071533,
|
|
"epoch": 0.2717916404116782,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996022781999198,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.14441936314105988,
|
|
"num_tokens": 5971627.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.052579498291015,
|
|
"epoch": 0.2722117202268431,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499600496422805,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.14112165570259094,
|
|
"num_tokens": 5981775.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.032028532028198,
|
|
"epoch": 0.272631800042008,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499598710667008,
|
|
"loss": 5.8729,
|
|
"mean_token_accuracy": 0.14314236044883727,
|
|
"num_tokens": 5991097.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.038925361633301,
|
|
"epoch": 0.2730518798571729,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995969209325604,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.13474914729595183,
|
|
"num_tokens": 5999517.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.042639112472534,
|
|
"epoch": 0.2734719596723377,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995951272194941,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.13345034569501876,
|
|
"num_tokens": 6008545.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.164342308044434,
|
|
"epoch": 0.2738920394875026,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995933295278407,
|
|
"loss": 5.8797,
|
|
"mean_token_accuracy": 0.13910974860191344,
|
|
"num_tokens": 6017366.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.04072585105896,
|
|
"epoch": 0.2743121193026675,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995915278576321,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.14348409026861192,
|
|
"num_tokens": 6025597.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.078993320465088,
|
|
"epoch": 0.27473219911783237,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995897222089004,
|
|
"loss": 5.9484,
|
|
"mean_token_accuracy": 0.14113520383834838,
|
|
"num_tokens": 6034239.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.241492223739624,
|
|
"epoch": 0.27515227893299726,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995879125816772,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.14251597672700883,
|
|
"num_tokens": 6043837.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.017462110519409,
|
|
"epoch": 0.27557235874816216,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995860989759949,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.1499466359615326,
|
|
"num_tokens": 6053217.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.126773357391357,
|
|
"epoch": 0.27599243856332706,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995842813918855,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.14304194226861,
|
|
"num_tokens": 6061553.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.039501285552978,
|
|
"epoch": 0.2764125183784919,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995824598293812,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.14597292095422745,
|
|
"num_tokens": 6070080.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.095096731185913,
|
|
"epoch": 0.2768325981936568,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995806342885142,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.1479337990283966,
|
|
"num_tokens": 6078438.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.091133499145508,
|
|
"epoch": 0.2772526780088217,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499578804769317,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.1408208929002285,
|
|
"num_tokens": 6087794.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.1423423290252686,
|
|
"epoch": 0.27767275782398654,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995769712718218,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.14154492914676667,
|
|
"num_tokens": 6096709.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.03666353225708,
|
|
"epoch": 0.27809283763915144,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995751337960613,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.13932624831795692,
|
|
"num_tokens": 6105866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.069159746170044,
|
|
"epoch": 0.27851291745431633,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995732923420679,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.14724719822406768,
|
|
"num_tokens": 6114882.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.9742859363555905,
|
|
"epoch": 0.2789329972694812,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995714469098743,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.14107296913862227,
|
|
"num_tokens": 6123978.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.065083360671997,
|
|
"epoch": 0.2793530770846461,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499569597499513,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.14292607307434083,
|
|
"num_tokens": 6133246.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.032466030120849,
|
|
"epoch": 0.27977315689981097,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995677441110172,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.14654416292905809,
|
|
"num_tokens": 6142865.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.065610027313232,
|
|
"epoch": 0.28019323671497587,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995658867444192,
|
|
"loss": 5.9007,
|
|
"mean_token_accuracy": 0.1368338242173195,
|
|
"num_tokens": 6152492.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.032893276214599,
|
|
"epoch": 0.2806133165301407,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995640253997523,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.13812195584177972,
|
|
"num_tokens": 6161953.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.920506429672241,
|
|
"epoch": 0.2810333963453056,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995621600770492,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.15040778815746308,
|
|
"num_tokens": 6171467.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.0409363269805905,
|
|
"epoch": 0.2814534761604705,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004995602907763431,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.14080849960446357,
|
|
"num_tokens": 6180646.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.033467626571655,
|
|
"epoch": 0.28187355597563535,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995584174976672,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.13724913001060485,
|
|
"num_tokens": 6189832.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.980023050308228,
|
|
"epoch": 0.28229363579080025,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995565402410544,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15104614943265915,
|
|
"num_tokens": 6198339.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.0385888576507565,
|
|
"epoch": 0.28271371560596514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995546590065383,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.14058903455734253,
|
|
"num_tokens": 6207564.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.024218225479126,
|
|
"epoch": 0.28313379542113004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995527737941518,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.14139530062675476,
|
|
"num_tokens": 6216056.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.981421661376953,
|
|
"epoch": 0.2835538752362949,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995508846039287,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.14600031226873397,
|
|
"num_tokens": 6225573.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.090993881225586,
|
|
"epoch": 0.2839739550514598,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995489914359023,
|
|
"loss": 5.9921,
|
|
"mean_token_accuracy": 0.13607787638902663,
|
|
"num_tokens": 6235057.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.113264799118042,
|
|
"epoch": 0.2843940348666247,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995470942901061,
|
|
"loss": 5.8982,
|
|
"mean_token_accuracy": 0.14372147843241692,
|
|
"num_tokens": 6244164.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.123813199996948,
|
|
"epoch": 0.2848141146817895,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995451931665738,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.14370959922671317,
|
|
"num_tokens": 6253095.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.027105283737183,
|
|
"epoch": 0.2852341944969544,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499543288065339,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.1425433225929737,
|
|
"num_tokens": 6261134.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.999712657928467,
|
|
"epoch": 0.2856542743121193,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995413789864354,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.14678002744913102,
|
|
"num_tokens": 6270384.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.960616159439087,
|
|
"epoch": 0.28607435412728416,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995394659298971,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.15043452978134156,
|
|
"num_tokens": 6279702.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.005735635757446,
|
|
"epoch": 0.28649443394244906,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995375488957576,
|
|
"loss": 5.8309,
|
|
"mean_token_accuracy": 0.13979510068893433,
|
|
"num_tokens": 6288297.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.013660907745361,
|
|
"epoch": 0.28691451375761395,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499535627884051,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.13572793826460838,
|
|
"num_tokens": 6297288.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.181674480438232,
|
|
"epoch": 0.28733459357277885,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995337028948115,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.13616690784692764,
|
|
"num_tokens": 6306719.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.01987738609314,
|
|
"epoch": 0.2877546733879437,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995317739280731,
|
|
"loss": 5.7786,
|
|
"mean_token_accuracy": 0.15149419456720353,
|
|
"num_tokens": 6316639.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.0435620784759525,
|
|
"epoch": 0.2881747532031086,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995298409838699,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.14308716356754303,
|
|
"num_tokens": 6326879.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.951386880874634,
|
|
"epoch": 0.2885948330182735,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499527904062236,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.147957743704319,
|
|
"num_tokens": 6335729.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.049512481689453,
|
|
"epoch": 0.28901491283343833,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995259631632061,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.13639168068766594,
|
|
"num_tokens": 6345154.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.043827152252197,
|
|
"epoch": 0.28943499264860323,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995240182868143,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.14297354817390442,
|
|
"num_tokens": 6354309.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.9356239318847654,
|
|
"epoch": 0.2898550724637681,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995220694330951,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.14842799976468085,
|
|
"num_tokens": 6363389.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.005477046966552,
|
|
"epoch": 0.290275152278933,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995201166020832,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.14157460033893585,
|
|
"num_tokens": 6372475.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.111435508728027,
|
|
"epoch": 0.29069523209409787,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499518159793813,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.15400618463754653,
|
|
"num_tokens": 6380906.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.945709609985352,
|
|
"epoch": 0.29111531190926276,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499516199008319,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.1436382308602333,
|
|
"num_tokens": 6390085.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.070226430892944,
|
|
"epoch": 0.29153539172442766,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995142342456364,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.14058329910039902,
|
|
"num_tokens": 6399441.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.092825603485108,
|
|
"epoch": 0.2919554715395925,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995122655057997,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.14255323261022568,
|
|
"num_tokens": 6408995.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.959508466720581,
|
|
"epoch": 0.2923755513547574,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995102927888437,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.15224269554018974,
|
|
"num_tokens": 6418080.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.040865230560303,
|
|
"epoch": 0.2927956311699223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995083160948036,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.13958164304494858,
|
|
"num_tokens": 6426732.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.988566875457764,
|
|
"epoch": 0.29321571098508714,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995063354237141,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14826264083385468,
|
|
"num_tokens": 6435957.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.052132320404053,
|
|
"epoch": 0.29363579080025204,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995043507756107,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.14379840195178986,
|
|
"num_tokens": 6445642.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.018087530136109,
|
|
"epoch": 0.29405587061541694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995023621505282,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.1442800186574459,
|
|
"num_tokens": 6454664.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.923487854003906,
|
|
"epoch": 0.29447595043058183,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499500369548502,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.14537445902824403,
|
|
"num_tokens": 6463224.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.171301317214966,
|
|
"epoch": 0.2948960302457467,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994983729695674,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.13893685415387153,
|
|
"num_tokens": 6473112.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.045923900604248,
|
|
"epoch": 0.2953161100609116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994963724137595,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.1453737996518612,
|
|
"num_tokens": 6482062.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.005832099914551,
|
|
"epoch": 0.29573618987607647,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994943678811142,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.1401112914085388,
|
|
"num_tokens": 6490568.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.070190906524658,
|
|
"epoch": 0.2961562696912413,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994923593716667,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.14401544779539108,
|
|
"num_tokens": 6500815.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.988713598251342,
|
|
"epoch": 0.2965763495064062,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.1514952600002289,
|
|
"num_tokens": 6509529.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.968388557434082,
|
|
"epoch": 0.2969964293215711,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994883304225077,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.1457517549395561,
|
|
"num_tokens": 6517934.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.0856983184814455,
|
|
"epoch": 0.297416509136736,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994863099828675,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.14552584439516067,
|
|
"num_tokens": 6526098.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.9941321849823,
|
|
"epoch": 0.29783658895190085,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499484285566568,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1432398647069931,
|
|
"num_tokens": 6535831.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.94168758392334,
|
|
"epoch": 0.29825666876706575,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994822571736449,
|
|
"loss": 5.7625,
|
|
"mean_token_accuracy": 0.14396894872188568,
|
|
"num_tokens": 6545704.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.0284003734588625,
|
|
"epoch": 0.29867674858223064,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994802248041342,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.14962279424071312,
|
|
"num_tokens": 6554423.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.024318981170654,
|
|
"epoch": 0.2990968283973955,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499478188458072,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.1454595111310482,
|
|
"num_tokens": 6563989.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.043286228179932,
|
|
"epoch": 0.2995169082125604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994761481354943,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.14439435824751853,
|
|
"num_tokens": 6572745.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.224496841430664,
|
|
"epoch": 0.2999369880277253,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994741038364371,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.1366976760327816,
|
|
"num_tokens": 6581723.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.943874788284302,
|
|
"epoch": 0.3003570678428901,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994720555609369,
|
|
"loss": 5.7171,
|
|
"mean_token_accuracy": 0.14883559197187424,
|
|
"num_tokens": 6590342.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.911714887619018,
|
|
"epoch": 0.300777147658055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994700033090297,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.15467880815267562,
|
|
"num_tokens": 6599206.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.1032740592956545,
|
|
"epoch": 0.3011972274732199,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499467947080752,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.1365446515381336,
|
|
"num_tokens": 6608947.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.099864816665649,
|
|
"epoch": 0.3016173072883848,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994658868761402,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.14974160194396974,
|
|
"num_tokens": 6618378.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.99675874710083,
|
|
"epoch": 0.30203738710354966,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994638226952307,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.1387033462524414,
|
|
"num_tokens": 6627527.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.10715618133545,
|
|
"epoch": 0.30245746691871456,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994617545380604,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.14276407659053802,
|
|
"num_tokens": 6636964.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.94628529548645,
|
|
"epoch": 0.30287754673387945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994596824046656,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.14509298652410507,
|
|
"num_tokens": 6646074.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.038099336624145,
|
|
"epoch": 0.3032976265490443,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499457606295083,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.14421509206295013,
|
|
"num_tokens": 6655027.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.900383329391479,
|
|
"epoch": 0.3037177063642092,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994555262093495,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.1515209808945656,
|
|
"num_tokens": 6663747.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.1385828971862795,
|
|
"epoch": 0.3041377861793741,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499453442147502,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.13430312201380729,
|
|
"num_tokens": 6672922.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.011907768249512,
|
|
"epoch": 0.304557865994539,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994513541095773,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.15209768787026406,
|
|
"num_tokens": 6682233.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.979143190383911,
|
|
"epoch": 0.30497794580970383,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994492620956126,
|
|
"loss": 5.858,
|
|
"mean_token_accuracy": 0.1495204821228981,
|
|
"num_tokens": 6691593.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.0055419921875,
|
|
"epoch": 0.30539802562486873,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994471661056445,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.15055460929870607,
|
|
"num_tokens": 6701318.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.076199960708618,
|
|
"epoch": 0.3058181054400336,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994450661397106,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.14739347100257874,
|
|
"num_tokens": 6710059.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.129534769058227,
|
|
"epoch": 0.30623818525519847,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499442962197848,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.13774683177471161,
|
|
"num_tokens": 6719811.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.9699358463287355,
|
|
"epoch": 0.30665826507036337,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994408542800937,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.1469706729054451,
|
|
"num_tokens": 6728789.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.977092027664185,
|
|
"epoch": 0.30707834488552826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994387423864855,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.14784644544124603,
|
|
"num_tokens": 6737706.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.975707149505615,
|
|
"epoch": 0.3074984247006931,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994366265170603,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.16093844026327134,
|
|
"num_tokens": 6746861.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.098724269866944,
|
|
"epoch": 0.307918504515858,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994345066718558,
|
|
"loss": 5.9542,
|
|
"mean_token_accuracy": 0.13871566131711005,
|
|
"num_tokens": 6755242.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.0416632175445555,
|
|
"epoch": 0.3083385843310229,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994323828509098,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.14007208868861198,
|
|
"num_tokens": 6764549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.993009233474732,
|
|
"epoch": 0.3087586641461878,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994302550542596,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.15204267650842668,
|
|
"num_tokens": 6774123.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.879176998138428,
|
|
"epoch": 0.30917874396135264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499428123281943,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.15400367826223374,
|
|
"num_tokens": 6782922.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.992125606536865,
|
|
"epoch": 0.30959882377651754,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994259875339978,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.14591203182935714,
|
|
"num_tokens": 6792042.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.150802707672119,
|
|
"epoch": 0.31001890359168244,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994238478104617,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.14117644280195235,
|
|
"num_tokens": 6800994.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.969630241394043,
|
|
"epoch": 0.3104389834068473,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994217041113727,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.14889054223895073,
|
|
"num_tokens": 6809938.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.048539876937866,
|
|
"epoch": 0.3108590632220122,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994195564367688,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.14025204703211785,
|
|
"num_tokens": 6820289.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.0517502784729,
|
|
"epoch": 0.3112791430371771,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994174047866882,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.14613612070679666,
|
|
"num_tokens": 6830068.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.912678909301758,
|
|
"epoch": 0.3116992228523419,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994152491611686,
|
|
"loss": 5.8273,
|
|
"mean_token_accuracy": 0.14581120014190674,
|
|
"num_tokens": 6838591.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.982998657226562,
|
|
"epoch": 0.3121193026675068,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994130895602485,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.14477218091487884,
|
|
"num_tokens": 6847796.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.063366651535034,
|
|
"epoch": 0.3125393824826717,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499410925983966,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.1452285960316658,
|
|
"num_tokens": 6856585.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.898049783706665,
|
|
"epoch": 0.3129594622978366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994087584323596,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.15066958963871002,
|
|
"num_tokens": 6865757.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.990089702606201,
|
|
"epoch": 0.31337954211300145,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994065869054676,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.14529856890439988,
|
|
"num_tokens": 6875371.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.091077661514282,
|
|
"epoch": 0.31379962192816635,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994044114033283,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.14080470502376558,
|
|
"num_tokens": 6884050.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.091219329833985,
|
|
"epoch": 0.31421970174333125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994022319259806,
|
|
"loss": 5.8638,
|
|
"mean_token_accuracy": 0.14875171110033988,
|
|
"num_tokens": 6893079.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.994270372390747,
|
|
"epoch": 0.3146397815584961,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994000484734629,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.14748625531792642,
|
|
"num_tokens": 6903100.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.005830955505371,
|
|
"epoch": 0.315059861373661,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993978610458137,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.14891340732574462,
|
|
"num_tokens": 6912164.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.970021390914917,
|
|
"epoch": 0.3154799411888259,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993956696430721,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.14630623608827592,
|
|
"num_tokens": 6921183.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.014796590805053,
|
|
"epoch": 0.3159000210039908,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993934742652768,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.1476880669593811,
|
|
"num_tokens": 6931325.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.025224351882935,
|
|
"epoch": 0.3163201008191556,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993912749124665,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.15172581374645233,
|
|
"num_tokens": 6940234.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.975033617019653,
|
|
"epoch": 0.3167401806343205,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993890715846804,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.14686811119318008,
|
|
"num_tokens": 6949067.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.006247806549072,
|
|
"epoch": 0.3171602604494854,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993868642819574,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.14386743307113647,
|
|
"num_tokens": 6959085.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.984570598602295,
|
|
"epoch": 0.31758034026465026,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993846530043367,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.14338204190135,
|
|
"num_tokens": 6967392.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.983299684524536,
|
|
"epoch": 0.31800042007981516,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993824377518574,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.1506180763244629,
|
|
"num_tokens": 6976369.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.051072645187378,
|
|
"epoch": 0.31842049989498006,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993802185245587,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.1495169520378113,
|
|
"num_tokens": 6985889.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.973819303512573,
|
|
"epoch": 0.3188405797101449,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049937799532248,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.13678822666406631,
|
|
"num_tokens": 6995396.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.154268550872803,
|
|
"epoch": 0.3192606595253098,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993757681456607,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.14265349358320237,
|
|
"num_tokens": 7004666.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.029079341888428,
|
|
"epoch": 0.3196807393404747,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993735369941401,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.13829794898629189,
|
|
"num_tokens": 7014608.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.041004323959351,
|
|
"epoch": 0.3201008191556396,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993713018679579,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.14656506404280661,
|
|
"num_tokens": 7023671.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.019459915161133,
|
|
"epoch": 0.32052089897080444,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993690627671536,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.13951837345957757,
|
|
"num_tokens": 7033786.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.97732892036438,
|
|
"epoch": 0.32094097878596933,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993668196917669,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.15004572570323943,
|
|
"num_tokens": 7042162.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.027564477920532,
|
|
"epoch": 0.32136105860113423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993645726418375,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.14644107297062875,
|
|
"num_tokens": 7051903.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.969810867309571,
|
|
"epoch": 0.3217811384162991,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993623216174053,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.1605222076177597,
|
|
"num_tokens": 7060229.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.917182302474975,
|
|
"epoch": 0.32220121823146397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049936006661851,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.14710989743471145,
|
|
"num_tokens": 7069040.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.992334508895874,
|
|
"epoch": 0.32262129804662887,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993578076451917,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1498522937297821,
|
|
"num_tokens": 7078409.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.879006052017212,
|
|
"epoch": 0.32304137786179377,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993555446974903,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.14535705298185347,
|
|
"num_tokens": 7087983.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.901397848129273,
|
|
"epoch": 0.3234614576769586,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499353277775446,
|
|
"loss": 5.7473,
|
|
"mean_token_accuracy": 0.15219927430152894,
|
|
"num_tokens": 7097277.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.960507011413574,
|
|
"epoch": 0.3238815374921235,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993510068790989,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.16467221826314926,
|
|
"num_tokens": 7105918.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.879998397827149,
|
|
"epoch": 0.3243016173072884,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993487320084892,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.15136535316705704,
|
|
"num_tokens": 7115049.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.982763433456421,
|
|
"epoch": 0.32472169712245325,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993464531636573,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.14752050638198852,
|
|
"num_tokens": 7124862.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.8926033020019535,
|
|
"epoch": 0.32514177693761814,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993441703446435,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.15468737334012986,
|
|
"num_tokens": 7133280.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.015898132324219,
|
|
"epoch": 0.32556185675278304,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993418835514882,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.14468531757593156,
|
|
"num_tokens": 7142446.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.991433334350586,
|
|
"epoch": 0.3259819365679479,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993395927842321,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.14096677601337432,
|
|
"num_tokens": 7152143.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.059468841552734,
|
|
"epoch": 0.3264020163831128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993372980429155,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.1420806512236595,
|
|
"num_tokens": 7162046.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.982543849945069,
|
|
"epoch": 0.3268220961982777,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993349993275792,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.1508569300174713,
|
|
"num_tokens": 7171557.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.789723920822143,
|
|
"epoch": 0.3272421760134426,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993326966382639,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.15062906444072724,
|
|
"num_tokens": 7180927.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.92172474861145,
|
|
"epoch": 0.3276622558286074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993303899750104,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.14762243777513503,
|
|
"num_tokens": 7189552.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.041365337371826,
|
|
"epoch": 0.3280823356437723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993280793378595,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.14609607309103012,
|
|
"num_tokens": 7197857.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.951012849807739,
|
|
"epoch": 0.3285024154589372,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993257647268522,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.15203747153282166,
|
|
"num_tokens": 7206785.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.97521710395813,
|
|
"epoch": 0.32892249527410206,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993234461420295,
|
|
"loss": 5.8492,
|
|
"mean_token_accuracy": 0.14864396750926973,
|
|
"num_tokens": 7216360.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.943229389190674,
|
|
"epoch": 0.32934257508926695,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993211235834326,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.16730980798602105,
|
|
"num_tokens": 7224890.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.844398403167725,
|
|
"epoch": 0.32976265490443185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993187970511023,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1706005111336708,
|
|
"num_tokens": 7234442.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.963161754608154,
|
|
"epoch": 0.33018273471959675,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993164665450801,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.14895002990961076,
|
|
"num_tokens": 7244023.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.904555988311768,
|
|
"epoch": 0.3306028145347616,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993141320654072,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.15213721096515656,
|
|
"num_tokens": 7253548.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.913322687149048,
|
|
"epoch": 0.3310228943499265,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499311793612125,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.15264057517051696,
|
|
"num_tokens": 7262962.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.002100086212158,
|
|
"epoch": 0.3314429741650914,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993094511852748,
|
|
"loss": 5.7999,
|
|
"mean_token_accuracy": 0.14923355728387833,
|
|
"num_tokens": 7272234.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.9879292964935305,
|
|
"epoch": 0.33186305398025623,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993071047848983,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.14813442677259445,
|
|
"num_tokens": 7281524.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.884419012069702,
|
|
"epoch": 0.3322831337954211,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993047544110368,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.15349545404314996,
|
|
"num_tokens": 7289601.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.788786172866821,
|
|
"epoch": 0.332703213610586,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993024000637321,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.1583729490637779,
|
|
"num_tokens": 7298508.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.918163013458252,
|
|
"epoch": 0.33312329342575087,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993000417430259,
|
|
"loss": 5.8565,
|
|
"mean_token_accuracy": 0.1440684713423252,
|
|
"num_tokens": 7309065.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.068691110610962,
|
|
"epoch": 0.33354337324091576,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00049929767944896,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.14953403770923615,
|
|
"num_tokens": 7319669.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.0281017303466795,
|
|
"epoch": 0.33396345305608066,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992953131815761,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.1508055806159973,
|
|
"num_tokens": 7328425.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.922671604156494,
|
|
"epoch": 0.33438353287124556,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992929429409164,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15846544951200486,
|
|
"num_tokens": 7337369.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.8830712795257565,
|
|
"epoch": 0.3348036126864104,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992905687270225,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.1513069674372673,
|
|
"num_tokens": 7346829.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.999729156494141,
|
|
"epoch": 0.3352236925015753,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992881905399368,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1449328303337097,
|
|
"num_tokens": 7355976.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.988975906372071,
|
|
"epoch": 0.3356437723167402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992858083797013,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.14504586905241013,
|
|
"num_tokens": 7365210.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.991175603866577,
|
|
"epoch": 0.33606385213190504,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992834222463581,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.13908673748373984,
|
|
"num_tokens": 7374175.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.972196435928344,
|
|
"epoch": 0.33648393194706994,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992810321399496,
|
|
"loss": 5.8636,
|
|
"mean_token_accuracy": 0.14633251801133157,
|
|
"num_tokens": 7383302.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.040848684310913,
|
|
"epoch": 0.33690401176223483,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992786380605182,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.14676400497555733,
|
|
"num_tokens": 7392746.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.938001918792724,
|
|
"epoch": 0.33732409157739973,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992762400081062,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.15358891040086747,
|
|
"num_tokens": 7401604.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.918675374984741,
|
|
"epoch": 0.3377441713925646,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992738379827559,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.14934294447302818,
|
|
"num_tokens": 7410594.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.007134819030762,
|
|
"epoch": 0.33816425120772947,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992714319845101,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.15554973632097244,
|
|
"num_tokens": 7418831.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.873322439193726,
|
|
"epoch": 0.33858433102289437,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992690220134116,
|
|
"loss": 5.7446,
|
|
"mean_token_accuracy": 0.15233736038208007,
|
|
"num_tokens": 7427731.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.057994699478149,
|
|
"epoch": 0.3390044108380592,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992666080695027,
|
|
"loss": 5.8518,
|
|
"mean_token_accuracy": 0.1464371532201767,
|
|
"num_tokens": 7436447.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.948624610900879,
|
|
"epoch": 0.3394244906532241,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992641901528262,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.15126800090074538,
|
|
"num_tokens": 7445352.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.9620507717132565,
|
|
"epoch": 0.339844570468389,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992617682634252,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.15263011008501054,
|
|
"num_tokens": 7454298.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.97614221572876,
|
|
"epoch": 0.34026465028355385,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992593424013424,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.14937392994761467,
|
|
"num_tokens": 7463543.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.002068901062012,
|
|
"epoch": 0.34068473009871875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992569125666209,
|
|
"loss": 5.8464,
|
|
"mean_token_accuracy": 0.14506482928991318,
|
|
"num_tokens": 7472701.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.06530499458313,
|
|
"epoch": 0.34110480991388364,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992544787593037,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.14331392347812652,
|
|
"num_tokens": 7481123.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.987830924987793,
|
|
"epoch": 0.34152488972904854,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992520409794338,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.14786751866340636,
|
|
"num_tokens": 7490439.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.97078309059143,
|
|
"epoch": 0.3419449695442134,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992495992270544,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.15085898339748383,
|
|
"num_tokens": 7499326.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.969767665863037,
|
|
"epoch": 0.3423650493593783,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992471535022089,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.14518282786011696,
|
|
"num_tokens": 7509407.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.964113235473633,
|
|
"epoch": 0.3427851291745432,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992447038049405,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.14494732469320298,
|
|
"num_tokens": 7518443.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.919957160949707,
|
|
"epoch": 0.343205208989708,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992422501352927,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.15868185311555863,
|
|
"num_tokens": 7527609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.9979315280914305,
|
|
"epoch": 0.3436252888048729,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992397924933089,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.14575055539608,
|
|
"num_tokens": 7536890.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.9897191524505615,
|
|
"epoch": 0.3440453686200378,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992373308790325,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.15681823194026948,
|
|
"num_tokens": 7546509.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.846250724792481,
|
|
"epoch": 0.3444654484352027,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992348652925074,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.14950673207640647,
|
|
"num_tokens": 7555336.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.961744737625122,
|
|
"epoch": 0.34488552825036756,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992323957337771,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.14984272718429564,
|
|
"num_tokens": 7565210.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.007063913345337,
|
|
"epoch": 0.34530560806553245,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992299222028855,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.15445573925971984,
|
|
"num_tokens": 7574516.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.898674392700196,
|
|
"epoch": 0.34572568788069735,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992274446998761,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.15527215451002122,
|
|
"num_tokens": 7583219.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.95861120223999,
|
|
"epoch": 0.3461457676958622,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992249632247929,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.1425651490688324,
|
|
"num_tokens": 7592050.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.043584823608398,
|
|
"epoch": 0.3465658475110271,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992224777776802,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.14657285809516907,
|
|
"num_tokens": 7600718.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.957071924209595,
|
|
"epoch": 0.346985927326192,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992199883585816,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.14970231726765632,
|
|
"num_tokens": 7609191.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.986074066162109,
|
|
"epoch": 0.34740600714135683,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992174949675413,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.14882247895002365,
|
|
"num_tokens": 7618509.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.975029325485229,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992149976046037,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.150260391831398,
|
|
"num_tokens": 7627851.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.925207090377808,
|
|
"epoch": 0.3482461667716866,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992124962698128,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.14737849459052085,
|
|
"num_tokens": 7636748.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.972150611877441,
|
|
"epoch": 0.3486662465868515,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499209990963213,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.1522408828139305,
|
|
"num_tokens": 7645436.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.006196355819702,
|
|
"epoch": 0.34908632640201637,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992074816848487,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.14600287303328513,
|
|
"num_tokens": 7655414.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.8425483226776125,
|
|
"epoch": 0.34950640621718126,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992049684347642,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.15359618812799453,
|
|
"num_tokens": 7664295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.967918491363525,
|
|
"epoch": 0.34992648603234616,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992024512130042,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.1513090416789055,
|
|
"num_tokens": 7673295.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.854374551773072,
|
|
"epoch": 0.350346565847511,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991999300196132,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.1478977158665657,
|
|
"num_tokens": 7682932.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.003021907806397,
|
|
"epoch": 0.3507666456626759,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991974048546359,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.14676762744784355,
|
|
"num_tokens": 7692105.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.946457290649414,
|
|
"epoch": 0.3511867254778408,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499194875718117,
|
|
"loss": 5.7816,
|
|
"mean_token_accuracy": 0.14983211755752562,
|
|
"num_tokens": 7701294.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.9310308456420895,
|
|
"epoch": 0.3516068052930057,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991923426101013,
|
|
"loss": 5.7713,
|
|
"mean_token_accuracy": 0.14655268639326097,
|
|
"num_tokens": 7710964.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.007804489135742,
|
|
"epoch": 0.35202688510817054,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991898055306337,
|
|
"loss": 5.8946,
|
|
"mean_token_accuracy": 0.14021267369389534,
|
|
"num_tokens": 7719938.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.032896995544434,
|
|
"epoch": 0.35244696492333544,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991872644797591,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.14767822921276091,
|
|
"num_tokens": 7729129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.918514633178711,
|
|
"epoch": 0.35286704473850034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991847194575226,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.14519443809986116,
|
|
"num_tokens": 7738506.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.051172924041748,
|
|
"epoch": 0.3532871245536652,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991821704639693,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.14418965578079224,
|
|
"num_tokens": 7749320.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.062065458297729,
|
|
"epoch": 0.3537072043688301,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991796174991443,
|
|
"loss": 5.7829,
|
|
"mean_token_accuracy": 0.14587843269109727,
|
|
"num_tokens": 7758735.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.849421215057373,
|
|
"epoch": 0.354127284183995,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991770605630927,
|
|
"loss": 5.751,
|
|
"mean_token_accuracy": 0.15034677758812903,
|
|
"num_tokens": 7767556.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.936790323257446,
|
|
"epoch": 0.3545473639991598,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991744996558599,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.15403031408786774,
|
|
"num_tokens": 7776615.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.955025720596313,
|
|
"epoch": 0.3549674438143247,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991719347774913,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.1537439852952957,
|
|
"num_tokens": 7785288.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.960596990585327,
|
|
"epoch": 0.3553875236294896,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991693659280324,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.1543234631419182,
|
|
"num_tokens": 7794381.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.904143905639648,
|
|
"epoch": 0.3558076034446545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991667931075284,
|
|
"loss": 5.6835,
|
|
"mean_token_accuracy": 0.14821650087833405,
|
|
"num_tokens": 7803265.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.919279670715332,
|
|
"epoch": 0.35622768325981935,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991642163160252,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.15157712996006012,
|
|
"num_tokens": 7812445.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.0007213115692135,
|
|
"epoch": 0.35664776307498425,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991616355535684,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.15207020044326783,
|
|
"num_tokens": 7822073.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.957857275009156,
|
|
"epoch": 0.35706784289014915,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991590508202036,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.15158121064305305,
|
|
"num_tokens": 7831193.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.963643503189087,
|
|
"epoch": 0.357487922705314,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991564621159766,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.14848409742116928,
|
|
"num_tokens": 7840311.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.973238897323609,
|
|
"epoch": 0.3579080025204789,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991538694409334,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.14516036435961724,
|
|
"num_tokens": 7849622.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.913772773742676,
|
|
"epoch": 0.3583280823356438,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991512727951198,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.1450696036219597,
|
|
"num_tokens": 7859494.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.065109920501709,
|
|
"epoch": 0.3587481621508087,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991486721785818,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.1437905862927437,
|
|
"num_tokens": 7868526.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.933383369445801,
|
|
"epoch": 0.3591682419659735,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991460675913655,
|
|
"loss": 5.7167,
|
|
"mean_token_accuracy": 0.14970996454358101,
|
|
"num_tokens": 7877631.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.946811819076538,
|
|
"epoch": 0.3595883217811384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499143459033517,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.15149033516645433,
|
|
"num_tokens": 7886814.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.832566404342652,
|
|
"epoch": 0.3600084015963033,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991408465050825,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.15575773864984513,
|
|
"num_tokens": 7896337.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.902747249603271,
|
|
"epoch": 0.36042848141146816,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991382300061084,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.14084347635507583,
|
|
"num_tokens": 7906071.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.995443725585938,
|
|
"epoch": 0.36084856122663306,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991356095366409,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.15023995712399482,
|
|
"num_tokens": 7915003.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.958809423446655,
|
|
"epoch": 0.36126864104179796,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991329850967266,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.15122520327568054,
|
|
"num_tokens": 7924408.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.900264692306519,
|
|
"epoch": 0.3616887208569628,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991303566864118,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1535492181777954,
|
|
"num_tokens": 7934717.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.847307777404785,
|
|
"epoch": 0.3621088006721277,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991277243057431,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.14550352916121484,
|
|
"num_tokens": 7944278.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.89778242111206,
|
|
"epoch": 0.3625288804872926,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991250879547673,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.15223362892866135,
|
|
"num_tokens": 7953344.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.903073406219482,
|
|
"epoch": 0.3629489603024575,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991224476335309,
|
|
"loss": 5.7762,
|
|
"mean_token_accuracy": 0.14970767721533776,
|
|
"num_tokens": 7962869.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.026950740814209,
|
|
"epoch": 0.36336904011762233,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991198033420807,
|
|
"loss": 5.7736,
|
|
"mean_token_accuracy": 0.14771935492753982,
|
|
"num_tokens": 7971981.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.912839651107788,
|
|
"epoch": 0.36378911993278723,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991171550804636,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.14824195951223373,
|
|
"num_tokens": 7980979.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.94692907333374,
|
|
"epoch": 0.36420919974795213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991145028487266,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.1460677921772003,
|
|
"num_tokens": 7989607.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.898593473434448,
|
|
"epoch": 0.36462927956311697,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991118466469165,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.15354615002870559,
|
|
"num_tokens": 7998356.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.863179397583008,
|
|
"epoch": 0.36504935937828187,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991091864750805,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.15553184300661088,
|
|
"num_tokens": 8007596.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.962289476394654,
|
|
"epoch": 0.36546943919344677,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991065223332655,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.14825710654258728,
|
|
"num_tokens": 8016493.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.949162864685059,
|
|
"epoch": 0.36588951900861166,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991038542215191,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.14747046008706094,
|
|
"num_tokens": 8025867.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.890843343734741,
|
|
"epoch": 0.3663095988237765,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991011821398882,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.15656512528657912,
|
|
"num_tokens": 8036251.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.949850082397461,
|
|
"epoch": 0.3667296786389414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990985060884202,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.1522827535867691,
|
|
"num_tokens": 8045647.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.987407255172729,
|
|
"epoch": 0.3671497584541063,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990958260671627,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.1425602063536644,
|
|
"num_tokens": 8056025.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.904713535308838,
|
|
"epoch": 0.36756983826927114,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990931420761629,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.15707799047231674,
|
|
"num_tokens": 8065029.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.966267681121826,
|
|
"epoch": 0.36798991808443604,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990904541154685,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.16287750899791717,
|
|
"num_tokens": 8073249.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.987148952484131,
|
|
"epoch": 0.36840999789960094,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990877621851271,
|
|
"loss": 5.8252,
|
|
"mean_token_accuracy": 0.1494595602154732,
|
|
"num_tokens": 8082039.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.861302328109741,
|
|
"epoch": 0.3688300777147658,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990850662851863,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.15636952966451645,
|
|
"num_tokens": 8090011.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.960203027725219,
|
|
"epoch": 0.3692501575299307,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990823664156941,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.1592693328857422,
|
|
"num_tokens": 8099934.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.991479682922363,
|
|
"epoch": 0.3696702373450956,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990796625766981,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.1480449065566063,
|
|
"num_tokens": 8108969.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.9183997631073,
|
|
"epoch": 0.3700903171602605,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990769547682462,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.15052928328514098,
|
|
"num_tokens": 8117372.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.994330787658692,
|
|
"epoch": 0.3705103969754253,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990742429903866,
|
|
"loss": 5.8896,
|
|
"mean_token_accuracy": 0.14699996411800384,
|
|
"num_tokens": 8127108.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.001091718673706,
|
|
"epoch": 0.3709304767905902,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499071527243167,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.14656655341386796,
|
|
"num_tokens": 8137392.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.959682178497315,
|
|
"epoch": 0.3713505566057551,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990688075266357,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.15625606924295427,
|
|
"num_tokens": 8146257.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.867766714096069,
|
|
"epoch": 0.37177063642091995,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990660838408409,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.1495484985411167,
|
|
"num_tokens": 8154952.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.991319561004639,
|
|
"epoch": 0.37219071623608485,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990633561858308,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.1485943764448166,
|
|
"num_tokens": 8164365.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.964152002334595,
|
|
"epoch": 0.37261079605124975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990606245616537,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.1534093663096428,
|
|
"num_tokens": 8172614.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.937890291213989,
|
|
"epoch": 0.37303087586641465,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990578889683579,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.14677512943744658,
|
|
"num_tokens": 8182445.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.963037729263306,
|
|
"epoch": 0.3734509556815795,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990551494059921,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.1528533488512039,
|
|
"num_tokens": 8191871.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.989839935302735,
|
|
"epoch": 0.3738710354967444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990524058746047,
|
|
"loss": 5.8572,
|
|
"mean_token_accuracy": 0.15349839329719545,
|
|
"num_tokens": 8200658.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.928804111480713,
|
|
"epoch": 0.3742911153119093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990496583742443,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.15008518993854522,
|
|
"num_tokens": 8209776.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.890834903717041,
|
|
"epoch": 0.3747111951270741,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990469069049596,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.15505637228488922,
|
|
"num_tokens": 8219401.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.889174842834473,
|
|
"epoch": 0.375131274942239,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990441514667993,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.15405186712741853,
|
|
"num_tokens": 8228762.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.968860626220703,
|
|
"epoch": 0.3755513547574039,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990413920598121,
|
|
"loss": 5.7636,
|
|
"mean_token_accuracy": 0.15373183339834212,
|
|
"num_tokens": 8236612.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.943127727508545,
|
|
"epoch": 0.37597143457256876,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990386286840471,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.14784819036722183,
|
|
"num_tokens": 8245043.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.054802799224854,
|
|
"epoch": 0.37639151438773366,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990358613395532,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.1462250158190727,
|
|
"num_tokens": 8255270.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.998329496383667,
|
|
"epoch": 0.37681159420289856,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990330900263792,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.14600027352571487,
|
|
"num_tokens": 8264761.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.965425777435303,
|
|
"epoch": 0.37723167401806346,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990303147445745,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.15009373426437378,
|
|
"num_tokens": 8274308.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.8652503967285154,
|
|
"epoch": 0.3776517538332283,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990275354941881,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.16007554829120635,
|
|
"num_tokens": 8283323.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.926560640335083,
|
|
"epoch": 0.3780718336483932,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990247522752694,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.14134320095181466,
|
|
"num_tokens": 8293452.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.975225973129272,
|
|
"epoch": 0.3784919134635581,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990219650878674,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.15657551288604737,
|
|
"num_tokens": 8302941.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.864366960525513,
|
|
"epoch": 0.37891199327872294,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004990191739320318,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.1629151314496994,
|
|
"num_tokens": 8311811.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.829625272750855,
|
|
"epoch": 0.37933207309388783,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990163788078117,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.16099839359521867,
|
|
"num_tokens": 8321130.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.864146566390991,
|
|
"epoch": 0.37975215290905273,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990135797152569,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.15075407326221466,
|
|
"num_tokens": 8330233.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.879518222808838,
|
|
"epoch": 0.3801722327242176,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990107766544169,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.15840827226638793,
|
|
"num_tokens": 8338585.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.919932222366333,
|
|
"epoch": 0.38059231253938247,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990079696253413,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.15791035294532776,
|
|
"num_tokens": 8346618.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.939203500747681,
|
|
"epoch": 0.38101239235454737,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990051586280799,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.15326298028230667,
|
|
"num_tokens": 8356273.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.922527170181274,
|
|
"epoch": 0.38143247216971227,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990023436626824,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.15422383397817613,
|
|
"num_tokens": 8366668.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.001941728591919,
|
|
"epoch": 0.3818525519848771,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989995247291988,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.15321157723665238,
|
|
"num_tokens": 8375610.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.933878087997437,
|
|
"epoch": 0.382272631800042,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989967018276789,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.1544783115386963,
|
|
"num_tokens": 8384455.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.826741123199463,
|
|
"epoch": 0.3826927116152069,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989938749581727,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.15217722058296204,
|
|
"num_tokens": 8393868.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.93110761642456,
|
|
"epoch": 0.38311279143037175,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004989910441207305,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.14792898297309875,
|
|
"num_tokens": 8402916.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.909101343154907,
|
|
"epoch": 0.38353287124553664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989882093154023,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.15420530289411544,
|
|
"num_tokens": 8411649.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.909681701660157,
|
|
"epoch": 0.38395295106070154,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989853705422381,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.14452365189790725,
|
|
"num_tokens": 8420393.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.895758485794067,
|
|
"epoch": 0.38437303087586644,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989825278012886,
|
|
"loss": 5.6875,
|
|
"mean_token_accuracy": 0.15371473133563995,
|
|
"num_tokens": 8429404.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.917196273803711,
|
|
"epoch": 0.3847931106910313,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498979681092604,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.1492347776889801,
|
|
"num_tokens": 8438299.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.835894346237183,
|
|
"epoch": 0.3852131905061962,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989768304162345,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.15611978322267533,
|
|
"num_tokens": 8447392.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.929430866241455,
|
|
"epoch": 0.3856332703213611,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004989739757722308,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.1487022116780281,
|
|
"num_tokens": 8456361.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.930190563201904,
|
|
"epoch": 0.3860533501365259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989711171606436,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.1564156025648117,
|
|
"num_tokens": 8465548.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.932565641403198,
|
|
"epoch": 0.3864734299516908,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989682545815232,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.15004338324069977,
|
|
"num_tokens": 8474454.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.86793704032898,
|
|
"epoch": 0.3868935097668557,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989653880349207,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.15498715043067932,
|
|
"num_tokens": 8482694.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.911267232894898,
|
|
"epoch": 0.38731358958202056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989625175208864,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.14617059528827667,
|
|
"num_tokens": 8491162.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.838245964050293,
|
|
"epoch": 0.38773366939718545,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989596430394717,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.16923634558916092,
|
|
"num_tokens": 8500716.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.836051511764526,
|
|
"epoch": 0.38815374921235035,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498956764590727,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.15317125618457794,
|
|
"num_tokens": 8508871.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.983802938461304,
|
|
"epoch": 0.38857382902751525,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989538821747037,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.1454290270805359,
|
|
"num_tokens": 8518450.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.942924976348877,
|
|
"epoch": 0.3889939088426801,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989509957914527,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.14524921625852585,
|
|
"num_tokens": 8528238.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.879286861419677,
|
|
"epoch": 0.389413988657845,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989481054410251,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.1511693000793457,
|
|
"num_tokens": 8537587.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.879880046844482,
|
|
"epoch": 0.3898340684730099,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989452111234721,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.1519084557890892,
|
|
"num_tokens": 8547703.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.887255001068115,
|
|
"epoch": 0.39025414828817473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498942312838845,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.15363839119672776,
|
|
"num_tokens": 8557001.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.827616882324219,
|
|
"epoch": 0.3906742281033396,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989394105871952,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.1651986852288246,
|
|
"num_tokens": 8565638.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.949290990829468,
|
|
"epoch": 0.3910943079185045,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498936504368574,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.15302542299032212,
|
|
"num_tokens": 8574428.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.850303411483765,
|
|
"epoch": 0.3915143877336694,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989335941830329,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.15317893475294114,
|
|
"num_tokens": 8583157.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.870885944366455,
|
|
"epoch": 0.39193446754883426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989306800306236,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.14882708638906478,
|
|
"num_tokens": 8592382.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.876427268981933,
|
|
"epoch": 0.39235454736399916,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989277619113975,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.15828215777873994,
|
|
"num_tokens": 8601058.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.938532400131225,
|
|
"epoch": 0.39277462717916406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989248398254065,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.14732256829738616,
|
|
"num_tokens": 8609479.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.900654602050781,
|
|
"epoch": 0.3931947069943289,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989219137727021,
|
|
"loss": 5.7294,
|
|
"mean_token_accuracy": 0.1546520099043846,
|
|
"num_tokens": 8618860.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.897889614105225,
|
|
"epoch": 0.3936147868094938,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989189837533365,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.15630604475736617,
|
|
"num_tokens": 8627462.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.992354822158814,
|
|
"epoch": 0.3940348666246587,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004989160497673613,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.146843983232975,
|
|
"num_tokens": 8637569.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.945879602432251,
|
|
"epoch": 0.39445494643982354,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989131118148286,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.14983191341161728,
|
|
"num_tokens": 8645440.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.849710083007812,
|
|
"epoch": 0.39487502625498844,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989101698957904,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.1551379680633545,
|
|
"num_tokens": 8655077.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.917178297042847,
|
|
"epoch": 0.39529510607015333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989072240102988,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.15438668057322502,
|
|
"num_tokens": 8663126.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.974384880065918,
|
|
"epoch": 0.39571518588531823,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989042741584061,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.15212598592042922,
|
|
"num_tokens": 8672386.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.768937015533448,
|
|
"epoch": 0.3961352657004831,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989013203401645,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.1561252072453499,
|
|
"num_tokens": 8681930.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.873412132263184,
|
|
"epoch": 0.396555345515648,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988983625556264,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.15193997621536254,
|
|
"num_tokens": 8690993.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.8479430198669435,
|
|
"epoch": 0.39697542533081287,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988954008048438,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.15675423592329024,
|
|
"num_tokens": 8699497.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.041143608093262,
|
|
"epoch": 0.3973955051459777,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988924350878697,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.14092395827174187,
|
|
"num_tokens": 8709274.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.993929195404053,
|
|
"epoch": 0.3978155849611426,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988894654047563,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.1469295635819435,
|
|
"num_tokens": 8718158.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.827867841720581,
|
|
"epoch": 0.3982356647763075,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988864917555562,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.1548566371202469,
|
|
"num_tokens": 8727459.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.879483222961426,
|
|
"epoch": 0.3986557445914724,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988835141403224,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.15677372515201568,
|
|
"num_tokens": 8737614.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.8809814453125,
|
|
"epoch": 0.39907582440663725,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988805325591073,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.15506676733493804,
|
|
"num_tokens": 8746799.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.892252826690674,
|
|
"epoch": 0.39949590422180214,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988775470119639,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.1494814820587635,
|
|
"num_tokens": 8756555.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.835883665084839,
|
|
"epoch": 0.39991598403696704,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988745574989451,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1567599043250084,
|
|
"num_tokens": 8765849.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.027160596847534,
|
|
"epoch": 0.4003360638521319,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988715640201036,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.14386038482189178,
|
|
"num_tokens": 8775713.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.901659107208252,
|
|
"epoch": 0.4007561436672968,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988685665754928,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.15384853333234788,
|
|
"num_tokens": 8784717.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.849430847167969,
|
|
"epoch": 0.4011762234824617,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988655651651656,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.15288221091032028,
|
|
"num_tokens": 8794388.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.8477579116821286,
|
|
"epoch": 0.4015963032976265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988625597891751,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.15216539055109024,
|
|
"num_tokens": 8802436.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.939417314529419,
|
|
"epoch": 0.4020163831127914,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988595504475746,
|
|
"loss": 5.6698,
|
|
"mean_token_accuracy": 0.15575191825628282,
|
|
"num_tokens": 8811184.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.918405437469483,
|
|
"epoch": 0.4024364629279563,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988565371404175,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.1554136499762535,
|
|
"num_tokens": 8820525.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.843054962158203,
|
|
"epoch": 0.4028565427431212,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988535198677571,
|
|
"loss": 5.6217,
|
|
"mean_token_accuracy": 0.15804577022790908,
|
|
"num_tokens": 8828928.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.970369100570679,
|
|
"epoch": 0.40327662255828606,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988504986296469,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.14200191348791122,
|
|
"num_tokens": 8838615.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.933490657806397,
|
|
"epoch": 0.40369670237345096,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988474734261404,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.14515041634440423,
|
|
"num_tokens": 8848709.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.920221948623658,
|
|
"epoch": 0.40411678218861585,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988444442572911,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.14759574979543685,
|
|
"num_tokens": 8858277.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.874279880523682,
|
|
"epoch": 0.4045368620037807,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988414111231528,
|
|
"loss": 5.707,
|
|
"mean_token_accuracy": 0.15657222270965576,
|
|
"num_tokens": 8868436.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.909940195083618,
|
|
"epoch": 0.4049569418189456,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000498838374023779,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.14395527988672258,
|
|
"num_tokens": 8877740.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.964693403244018,
|
|
"epoch": 0.4053770216341105,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004988353329592239,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.1548558935523033,
|
|
"num_tokens": 8887408.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.922537040710449,
|
|
"epoch": 0.4057971014492754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988322879295409,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.14574310183525085,
|
|
"num_tokens": 8897141.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.805268859863281,
|
|
"epoch": 0.40621718126444023,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988292389347844,
|
|
"loss": 5.6104,
|
|
"mean_token_accuracy": 0.16397565603256226,
|
|
"num_tokens": 8905747.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.965035152435303,
|
|
"epoch": 0.40663726107960513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498826185975008,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.15198375433683395,
|
|
"num_tokens": 8914926.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.8813001155853275,
|
|
"epoch": 0.40705734089477,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988231290502662,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.15258675962686538,
|
|
"num_tokens": 8923956.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.9237809658050535,
|
|
"epoch": 0.40747742070993487,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988200681606127,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.14926957190036774,
|
|
"num_tokens": 8932654.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.894003057479859,
|
|
"epoch": 0.40789750052509977,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498817003306102,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.1597268909215927,
|
|
"num_tokens": 8941716.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.817833948135376,
|
|
"epoch": 0.40831758034026466,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988139344867884,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.1522026114165783,
|
|
"num_tokens": 8950377.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.875721025466919,
|
|
"epoch": 0.4087376601554295,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988108617027261,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.15545763820409775,
|
|
"num_tokens": 8959857.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.833681583404541,
|
|
"epoch": 0.4091577399705944,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988077849539698,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.15625977516174316,
|
|
"num_tokens": 8968272.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.867157077789306,
|
|
"epoch": 0.4095778197857593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988047042405736,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.16176266372203826,
|
|
"num_tokens": 8977445.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.968780374526977,
|
|
"epoch": 0.4099978996009242,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988016195625924,
|
|
"loss": 5.76,
|
|
"mean_token_accuracy": 0.14859384894371033,
|
|
"num_tokens": 8987315.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.913091421127319,
|
|
"epoch": 0.41041797941608904,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987985309200807,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.1500951334834099,
|
|
"num_tokens": 8998119.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.845153284072876,
|
|
"epoch": 0.41083805923125394,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987954383130934,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.1648591250181198,
|
|
"num_tokens": 9007167.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.868191337585449,
|
|
"epoch": 0.41125813904641884,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498792341741685,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1461891144514084,
|
|
"num_tokens": 9016690.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.933396625518799,
|
|
"epoch": 0.4116782188615837,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987892412059106,
|
|
"loss": 5.7776,
|
|
"mean_token_accuracy": 0.1512982115149498,
|
|
"num_tokens": 9026117.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.841189861297607,
|
|
"epoch": 0.4120982986767486,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987861367058251,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.1527989387512207,
|
|
"num_tokens": 9035754.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.89400463104248,
|
|
"epoch": 0.4125183784919135,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987830282414833,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15465910285711287,
|
|
"num_tokens": 9045453.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.913017749786377,
|
|
"epoch": 0.41293845830707837,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004987799158129404,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.15383710861206054,
|
|
"num_tokens": 9056045.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.873713541030884,
|
|
"epoch": 0.4133585381222432,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987767994202516,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.149123851954937,
|
|
"num_tokens": 9065728.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.842416429519654,
|
|
"epoch": 0.4137786179374081,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987736790634719,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.1515074759721756,
|
|
"num_tokens": 9075522.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.839908504486084,
|
|
"epoch": 0.414198697752573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987705547426568,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.14872333407402039,
|
|
"num_tokens": 9084412.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.913540363311768,
|
|
"epoch": 0.41461877756773785,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987674264578615,
|
|
"loss": 5.7332,
|
|
"mean_token_accuracy": 0.14811609983444213,
|
|
"num_tokens": 9094289.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.8725332736969,
|
|
"epoch": 0.41503885738290275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987642942091414,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15519289672374725,
|
|
"num_tokens": 9103124.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.8630242347717285,
|
|
"epoch": 0.41545893719806765,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987611579965523,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.1533403366804123,
|
|
"num_tokens": 9112794.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.913699436187744,
|
|
"epoch": 0.4158790170132325,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004987580178201492,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.1595202386379242,
|
|
"num_tokens": 9122718.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.891729164123535,
|
|
"epoch": 0.4162990968283974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987548736799882,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.1482948213815689,
|
|
"num_tokens": 9131855.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.892034864425659,
|
|
"epoch": 0.4167191766435623,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987517255761248,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.15863611847162246,
|
|
"num_tokens": 9141102.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.8408544063568115,
|
|
"epoch": 0.4171392564587272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987485735086148,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.15845317095518113,
|
|
"num_tokens": 9150552.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.915563631057739,
|
|
"epoch": 0.417559336273892,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498745417477514,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.15274149924516678,
|
|
"num_tokens": 9160105.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.851050758361817,
|
|
"epoch": 0.4179794160890569,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987422574828784,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.15457934886217117,
|
|
"num_tokens": 9169367.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.845413064956665,
|
|
"epoch": 0.4183994959042218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987390935247639,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.16090269088745118,
|
|
"num_tokens": 9177872.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.878557348251343,
|
|
"epoch": 0.41881957571938666,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987359256032265,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1481206126511097,
|
|
"num_tokens": 9187879.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.854932594299316,
|
|
"epoch": 0.41923965553455156,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987327537183225,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.15052096396684647,
|
|
"num_tokens": 9198281.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.8744182109832765,
|
|
"epoch": 0.41965973534971646,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004987295778701078,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.1535363718867302,
|
|
"num_tokens": 9207670.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.941969966888427,
|
|
"epoch": 0.42007981516488135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498726398058639,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.15731745064258576,
|
|
"num_tokens": 9216995.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.869586181640625,
|
|
"epoch": 0.4204998949800462,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004987232142839723,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.14722964018583298,
|
|
"num_tokens": 9227330.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.857760953903198,
|
|
"epoch": 0.4209199747952111,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987200265461638,
|
|
"loss": 5.6921,
|
|
"mean_token_accuracy": 0.160021048784256,
|
|
"num_tokens": 9236666.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.903905725479126,
|
|
"epoch": 0.421340054610376,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987168348452705,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.15569491684436798,
|
|
"num_tokens": 9246388.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.847051525115967,
|
|
"epoch": 0.42176013442554083,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987136391813485,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.16386419981718064,
|
|
"num_tokens": 9255239.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.802522277832031,
|
|
"epoch": 0.42218021424070573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987104395544547,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.15661859810352324,
|
|
"num_tokens": 9264468.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.871787643432617,
|
|
"epoch": 0.42260029405587063,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987072359646455,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.15836804807186128,
|
|
"num_tokens": 9274140.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.8818848609924315,
|
|
"epoch": 0.42302037387103547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987040284119778,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.15363640189170838,
|
|
"num_tokens": 9283539.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.812870168685913,
|
|
"epoch": 0.42344045368620037,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987008168965087,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.15175789594650269,
|
|
"num_tokens": 9292664.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.904106283187867,
|
|
"epoch": 0.42386053350136527,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986976014182946,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.15362361818552017,
|
|
"num_tokens": 9302814.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.973753833770752,
|
|
"epoch": 0.42428061331653016,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986943819773927,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.15095529705286026,
|
|
"num_tokens": 9312654.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.961247158050537,
|
|
"epoch": 0.424700693131695,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049869115857386,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.15128740966320037,
|
|
"num_tokens": 9322271.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.890190887451172,
|
|
"epoch": 0.4251207729468599,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004986879312077536,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.15066271498799325,
|
|
"num_tokens": 9331341.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.8575903415679935,
|
|
"epoch": 0.4255408527620248,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986846998791308,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.15662601292133332,
|
|
"num_tokens": 9339863.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.815864372253418,
|
|
"epoch": 0.42596093257718964,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986814645880485,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.15884864330291748,
|
|
"num_tokens": 9349488.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.82549033164978,
|
|
"epoch": 0.42638101239235454,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986782253345645,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.15622432827949523,
|
|
"num_tokens": 9357977.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.88819260597229,
|
|
"epoch": 0.42680109220751944,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986749821187358,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.15062530636787413,
|
|
"num_tokens": 9367449.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.933618497848511,
|
|
"epoch": 0.42722117202268434,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049867173494062,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.15464712232351302,
|
|
"num_tokens": 9377070.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.820448541641236,
|
|
"epoch": 0.4276412518378492,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986684838002744,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.1470932886004448,
|
|
"num_tokens": 9385881.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.8892427444458,
|
|
"epoch": 0.4280613316530141,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986652286977569,
|
|
"loss": 5.6922,
|
|
"mean_token_accuracy": 0.14868162721395492,
|
|
"num_tokens": 9395159.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.860781717300415,
|
|
"epoch": 0.428481411468179,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004986619696331252,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1528971217572689,
|
|
"num_tokens": 9404590.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.8955230712890625,
|
|
"epoch": 0.4289014912833438,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986587066064367,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.15910475552082062,
|
|
"num_tokens": 9414452.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.946217107772827,
|
|
"epoch": 0.4293215710985087,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004986554396177494,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.14509906619787216,
|
|
"num_tokens": 9424004.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.867961645126343,
|
|
"epoch": 0.4297416509136736,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986521686671212,
|
|
"loss": 5.6669,
|
|
"mean_token_accuracy": 0.16597846299409866,
|
|
"num_tokens": 9433487.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.847635078430176,
|
|
"epoch": 0.43016173072883845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049864889375461,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.15033599734306335,
|
|
"num_tokens": 9442742.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.905732250213623,
|
|
"epoch": 0.43058181054400335,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986456148802738,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.15171840339899062,
|
|
"num_tokens": 9452550.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.9744799613952635,
|
|
"epoch": 0.43100189035916825,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986423320441707,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.14951937571167945,
|
|
"num_tokens": 9461920.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.8919281482696535,
|
|
"epoch": 0.43142197017433315,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986390452463588,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.14998603016138076,
|
|
"num_tokens": 9470817.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.724545240402222,
|
|
"epoch": 0.431842049989498,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986357544868964,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.15861552208662033,
|
|
"num_tokens": 9479936.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.891957855224609,
|
|
"epoch": 0.4322621298046629,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986324597658418,
|
|
"loss": 5.647,
|
|
"mean_token_accuracy": 0.15907271206378937,
|
|
"num_tokens": 9489818.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.789335918426514,
|
|
"epoch": 0.4326822096198278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986291610832533,
|
|
"loss": 5.65,
|
|
"mean_token_accuracy": 0.15387662947177888,
|
|
"num_tokens": 9499688.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.953478908538818,
|
|
"epoch": 0.4331022894349926,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986258584391892,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15160334408283233,
|
|
"num_tokens": 9509581.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.943544149398804,
|
|
"epoch": 0.4335223692501575,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986225518337084,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.15453668758273126,
|
|
"num_tokens": 9518556.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.779713249206543,
|
|
"epoch": 0.4339424490653224,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986192412668692,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.15138726085424423,
|
|
"num_tokens": 9527612.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.834102582931519,
|
|
"epoch": 0.4343625288804873,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986159267387302,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.16340289860963822,
|
|
"num_tokens": 9535882.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.829035234451294,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986126082493502,
|
|
"loss": 5.6932,
|
|
"mean_token_accuracy": 0.15901082158088684,
|
|
"num_tokens": 9544799.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.856446266174316,
|
|
"epoch": 0.43520268851081706,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986092857987881,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.15803252607584,
|
|
"num_tokens": 9553805.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.8282328128814695,
|
|
"epoch": 0.43562276832598196,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986059593871026,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.15629224628210067,
|
|
"num_tokens": 9563493.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.88116488456726,
|
|
"epoch": 0.4360428481411468,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986026290143527,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.15083191096782683,
|
|
"num_tokens": 9572297.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.01215090751648,
|
|
"epoch": 0.4364629279563117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985992946805973,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.14679813981056214,
|
|
"num_tokens": 9581967.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.860457944869995,
|
|
"epoch": 0.4368830077714766,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985959563858955,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.15618911683559417,
|
|
"num_tokens": 9590885.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.920520925521851,
|
|
"epoch": 0.43730308758664144,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985926141303066,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.15353824943304062,
|
|
"num_tokens": 9599247.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.904012393951416,
|
|
"epoch": 0.43772316740180633,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985892679138896,
|
|
"loss": 5.6055,
|
|
"mean_token_accuracy": 0.1609176740050316,
|
|
"num_tokens": 9608296.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.878478050231934,
|
|
"epoch": 0.43814324721697123,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985859177367038,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.15502529889345168,
|
|
"num_tokens": 9616734.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.882960367202759,
|
|
"epoch": 0.43856332703213613,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004985825635988087,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.15253912508487702,
|
|
"num_tokens": 9626246.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.820113277435302,
|
|
"epoch": 0.43898340684730097,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985792055002635,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.1569197416305542,
|
|
"num_tokens": 9634963.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.904363775253296,
|
|
"epoch": 0.43940348666246587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985758434411278,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.15850198715925218,
|
|
"num_tokens": 9643615.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.883202981948853,
|
|
"epoch": 0.43982356647763077,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985724774214613,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.15674181655049324,
|
|
"num_tokens": 9653306.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.843471193313599,
|
|
"epoch": 0.4402436462927956,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985691074413233,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.15597492307424546,
|
|
"num_tokens": 9662389.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.821241474151611,
|
|
"epoch": 0.4406637261079605,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985657335007739,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.1512298621237278,
|
|
"num_tokens": 9671183.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.886975622177124,
|
|
"epoch": 0.4410838059231254,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985623555998725,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.16423219591379165,
|
|
"num_tokens": 9680544.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.857367658615113,
|
|
"epoch": 0.4415038857382903,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985589737386791,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.1553041160106659,
|
|
"num_tokens": 9690137.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.809094667434692,
|
|
"epoch": 0.44192396555345514,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985555879172535,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.15782568752765655,
|
|
"num_tokens": 9699149.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.934548234939575,
|
|
"epoch": 0.44234404536862004,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498552198135656,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.16048139780759813,
|
|
"num_tokens": 9709308.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.857599496841431,
|
|
"epoch": 0.44276412518378494,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985488043939462,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.15583646297454834,
|
|
"num_tokens": 9718462.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.84532356262207,
|
|
"epoch": 0.4431842049989498,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985454066921846,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.1588665559887886,
|
|
"num_tokens": 9727626.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.721759366989136,
|
|
"epoch": 0.4436042848141147,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985420050304312,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.1551545485854149,
|
|
"num_tokens": 9737091.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.822771167755127,
|
|
"epoch": 0.4440243646292796,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985385994087462,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.15709339901804925,
|
|
"num_tokens": 9746135.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.899721670150757,
|
|
"epoch": 0.4444444444444444,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985351898271901,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.15749678909778594,
|
|
"num_tokens": 9754549.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.891132783889771,
|
|
"epoch": 0.4448645242596093,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985317762858231,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.14913515299558638,
|
|
"num_tokens": 9764219.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.863654899597168,
|
|
"epoch": 0.4452846040747742,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498528358784706,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.1614499032497406,
|
|
"num_tokens": 9772234.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.825886964797974,
|
|
"epoch": 0.4457046838899391,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498524937323899,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.16151614040136336,
|
|
"num_tokens": 9781417.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.958418083190918,
|
|
"epoch": 0.44612476370510395,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985215119034628,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.14706624820828437,
|
|
"num_tokens": 9791286.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.83896541595459,
|
|
"epoch": 0.44654484352026885,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985180825234582,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.15418604761362076,
|
|
"num_tokens": 9802157.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.961184072494507,
|
|
"epoch": 0.44696492333543375,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985146491839459,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.1454138860106468,
|
|
"num_tokens": 9812646.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.93065824508667,
|
|
"epoch": 0.4473850031505986,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985112118849865,
|
|
"loss": 5.7505,
|
|
"mean_token_accuracy": 0.1481009006500244,
|
|
"num_tokens": 9822274.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.776948642730713,
|
|
"epoch": 0.4478050829657635,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985077706266412,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.15706712752580643,
|
|
"num_tokens": 9831337.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.817965841293335,
|
|
"epoch": 0.4482251627809284,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985043254089708,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.14964559227228164,
|
|
"num_tokens": 9840798.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.79916353225708,
|
|
"epoch": 0.44864524259609323,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985008762320364,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.15808326303958892,
|
|
"num_tokens": 9850117.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.808034658432007,
|
|
"epoch": 0.4490653224112581,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498497423095899,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.1625373423099518,
|
|
"num_tokens": 9858227.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.813161182403564,
|
|
"epoch": 0.449485402226423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004984939660006199,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.15393247902393342,
|
|
"num_tokens": 9867157.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.847505283355713,
|
|
"epoch": 0.4499054820415879,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984905049462602,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.15501179546117783,
|
|
"num_tokens": 9877045.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.961196565628052,
|
|
"epoch": 0.45032556185675277,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984870399328814,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.1546921819448471,
|
|
"num_tokens": 9886637.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.801573133468628,
|
|
"epoch": 0.45074564167191766,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984835709605446,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.16214425712823868,
|
|
"num_tokens": 9895601.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.878483295440674,
|
|
"epoch": 0.45116572148708256,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984800980293116,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.15574561953544616,
|
|
"num_tokens": 9904775.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.883770704269409,
|
|
"epoch": 0.4515858013022474,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984766211392435,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.1528709352016449,
|
|
"num_tokens": 9913795.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.857630348205566,
|
|
"epoch": 0.4520058811174123,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984731402904024,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.15977992564439775,
|
|
"num_tokens": 9922576.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.829555082321167,
|
|
"epoch": 0.4524259609325772,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984696554828496,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.1608197048306465,
|
|
"num_tokens": 9930971.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.845896244049072,
|
|
"epoch": 0.4528460407477421,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984661667166468,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.15930829644203187,
|
|
"num_tokens": 9939628.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.826462650299073,
|
|
"epoch": 0.45326612056290694,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984626739918561,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.16187043488025665,
|
|
"num_tokens": 9948397.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.897841453552246,
|
|
"epoch": 0.45368620037807184,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004984591773085391,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1579720750451088,
|
|
"num_tokens": 9957683.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.910743761062622,
|
|
"epoch": 0.45410628019323673,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984556766667578,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.15666956454515457,
|
|
"num_tokens": 9966756.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.825371026992798,
|
|
"epoch": 0.4545263600084016,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984521720665743,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.15819198042154312,
|
|
"num_tokens": 9976000.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.866469955444336,
|
|
"epoch": 0.4549464398235665,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984486635080507,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.16008011251688004,
|
|
"num_tokens": 9985509.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.797957992553711,
|
|
"epoch": 0.45536651963873137,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984451509912489,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.15894405841827391,
|
|
"num_tokens": 9994342.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.786969327926636,
|
|
"epoch": 0.4557865994538962,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004984416345162315,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.15164350271224974,
|
|
"num_tokens": 10004249.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.855116987228394,
|
|
"epoch": 0.4562066792690611,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984381140830605,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.15875716507434845,
|
|
"num_tokens": 10012430.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.869373321533203,
|
|
"epoch": 0.456626759084226,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984345896917984,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.15343497991561889,
|
|
"num_tokens": 10021434.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.851734781265259,
|
|
"epoch": 0.4570468388993909,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004984310613425076,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.159539994597435,
|
|
"num_tokens": 10030473.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.888415145874023,
|
|
"epoch": 0.45746691871455575,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984275290352506,
|
|
"loss": 5.6459,
|
|
"mean_token_accuracy": 0.15975773483514785,
|
|
"num_tokens": 10039057.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.906418371200561,
|
|
"epoch": 0.45788699852972065,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984239927700899,
|
|
"loss": 5.7257,
|
|
"mean_token_accuracy": 0.15392611026763917,
|
|
"num_tokens": 10047998.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.940126276016235,
|
|
"epoch": 0.45830707834488554,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984204525470883,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.14976596385240554,
|
|
"num_tokens": 10057479.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.804240036010742,
|
|
"epoch": 0.4587271581600504,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984169083663084,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.15475388765335082,
|
|
"num_tokens": 10067754.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.835357999801635,
|
|
"epoch": 0.4591472379752153,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984133602278129,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.1532885193824768,
|
|
"num_tokens": 10076815.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.961859178543091,
|
|
"epoch": 0.4595673177903802,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498409808131665,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.15364886671304703,
|
|
"num_tokens": 10086300.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.828978395462036,
|
|
"epoch": 0.4599873976055451,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984062520779272,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.15949156731367112,
|
|
"num_tokens": 10095383.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.7631326675415036,
|
|
"epoch": 0.4604074774207099,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984026920666628,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16033411771059036,
|
|
"num_tokens": 10103971.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.845707273483276,
|
|
"epoch": 0.4608275572358748,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004983991280979347,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.16333702802658082,
|
|
"num_tokens": 10113028.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.881896495819092,
|
|
"epoch": 0.4612476370510397,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983955601718061,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.15939705371856688,
|
|
"num_tokens": 10121890.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.889582633972168,
|
|
"epoch": 0.46166771686620456,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983919882883401,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.1580561488866806,
|
|
"num_tokens": 10131655.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.924855709075928,
|
|
"epoch": 0.46208779668136946,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983884124476,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.15681440383195877,
|
|
"num_tokens": 10140778.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.877159309387207,
|
|
"epoch": 0.46250787649653435,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983848326496494,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.15238432586193085,
|
|
"num_tokens": 10150229.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.874773073196411,
|
|
"epoch": 0.4629279563116992,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983812488945513,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.155783973634243,
|
|
"num_tokens": 10158939.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.835632228851319,
|
|
"epoch": 0.4633480361268641,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983776611823696,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.15373607724905014,
|
|
"num_tokens": 10168383.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.781601142883301,
|
|
"epoch": 0.463768115942029,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983740695131676,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.16217319369316102,
|
|
"num_tokens": 10178678.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.814817571640015,
|
|
"epoch": 0.4641881957571939,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498370473887009,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.15971693769097328,
|
|
"num_tokens": 10188964.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.860387706756592,
|
|
"epoch": 0.46460827557235873,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983668743039573,
|
|
"loss": 5.6544,
|
|
"mean_token_accuracy": 0.16176948100328445,
|
|
"num_tokens": 10198333.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.823429822921753,
|
|
"epoch": 0.46502835538752363,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983632707640766,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.15528512597084046,
|
|
"num_tokens": 10207876.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.837881183624267,
|
|
"epoch": 0.4654484352026885,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983596632674306,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.16058907508850098,
|
|
"num_tokens": 10216822.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.89295072555542,
|
|
"epoch": 0.46586851501785337,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983560518140831,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.1498328372836113,
|
|
"num_tokens": 10226887.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.870006895065307,
|
|
"epoch": 0.46628859483301827,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004983524364040982,
|
|
"loss": 5.5705,
|
|
"mean_token_accuracy": 0.16448622196912766,
|
|
"num_tokens": 10235935.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.8303587436676025,
|
|
"epoch": 0.46670867464818316,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983488170375399,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.16216835826635362,
|
|
"num_tokens": 10245590.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.7766870021820065,
|
|
"epoch": 0.46712875446334806,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983451937144723,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.15672850459814072,
|
|
"num_tokens": 10255104.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.665926456451416,
|
|
"epoch": 0.4675488342785129,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983415664349595,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.17375965118408204,
|
|
"num_tokens": 10264236.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.877076864242554,
|
|
"epoch": 0.4679689140936778,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983379351990659,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.1592295229434967,
|
|
"num_tokens": 10273335.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.77634220123291,
|
|
"epoch": 0.4683889939088427,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004983343000068559,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.16145434379577636,
|
|
"num_tokens": 10282206.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.734559774398804,
|
|
"epoch": 0.46880907372400754,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983306608583937,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.17214130163192748,
|
|
"num_tokens": 10290056.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.843502569198608,
|
|
"epoch": 0.46922915353917244,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983270177537438,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.15954413563013076,
|
|
"num_tokens": 10299726.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.810264730453492,
|
|
"epoch": 0.46964923335433734,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983233706929708,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.15892852544784547,
|
|
"num_tokens": 10308696.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.862246799468994,
|
|
"epoch": 0.4700693131695022,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983197196761392,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.14815479144454002,
|
|
"num_tokens": 10317845.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.828830194473267,
|
|
"epoch": 0.4704893929846671,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983160647033139,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.16088498681783675,
|
|
"num_tokens": 10326563.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.822518301010132,
|
|
"epoch": 0.470909472799832,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983124057745595,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.15862844586372377,
|
|
"num_tokens": 10335931.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.762676143646241,
|
|
"epoch": 0.47132955261499687,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983087428899408,
|
|
"loss": 5.5949,
|
|
"mean_token_accuracy": 0.15312879234552385,
|
|
"num_tokens": 10344984.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.84120922088623,
|
|
"epoch": 0.4717496324301617,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983050760495227,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.15357797592878342,
|
|
"num_tokens": 10353522.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.845833110809326,
|
|
"epoch": 0.4721697122453266,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983014052533702,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.15998404920101167,
|
|
"num_tokens": 10363527.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.777768898010254,
|
|
"epoch": 0.4725897920604915,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982977305015481,
|
|
"loss": 5.5728,
|
|
"mean_token_accuracy": 0.15610021501779556,
|
|
"num_tokens": 10372040.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.841713190078735,
|
|
"epoch": 0.47300987187565635,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982940517941219,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.15774558037519454,
|
|
"num_tokens": 10381279.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.853977680206299,
|
|
"epoch": 0.47342995169082125,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982903691311564,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.15029727220535277,
|
|
"num_tokens": 10390608.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.7988402366638185,
|
|
"epoch": 0.47385003150598615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982866825127172,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.16449746191501619,
|
|
"num_tokens": 10399851.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.867706441879273,
|
|
"epoch": 0.47427011132115104,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982829919388692,
|
|
"loss": 5.7887,
|
|
"mean_token_accuracy": 0.14914158508181571,
|
|
"num_tokens": 10410425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.776743412017822,
|
|
"epoch": 0.4746901911363159,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982792974096781,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16128528863191605,
|
|
"num_tokens": 10418783.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.915902757644654,
|
|
"epoch": 0.4751102709514808,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000498275598925209,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.15162914544343947,
|
|
"num_tokens": 10427360.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.907740354537964,
|
|
"epoch": 0.4755303507666457,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982718964855277,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.15605778843164445,
|
|
"num_tokens": 10436613.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.824285364151001,
|
|
"epoch": 0.4759504305818105,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982681900907,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.1537246122956276,
|
|
"num_tokens": 10445055.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.7850565910339355,
|
|
"epoch": 0.4763705103969754,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000498264479740791,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.16351223587989808,
|
|
"num_tokens": 10454516.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.895203351974487,
|
|
"epoch": 0.4767905902121403,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004982607654358668,
|
|
"loss": 5.6981,
|
|
"mean_token_accuracy": 0.15540930181741713,
|
|
"num_tokens": 10463771.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.829155921936035,
|
|
"epoch": 0.47721067002730516,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000498257047175993,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.15894964784383775,
|
|
"num_tokens": 10473783.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.822129917144776,
|
|
"epoch": 0.47763074984247006,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982533249612357,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.15907904505729675,
|
|
"num_tokens": 10483424.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.735984182357788,
|
|
"epoch": 0.47805082965763496,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982495987916607,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.16477657556533815,
|
|
"num_tokens": 10492536.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.813406753540039,
|
|
"epoch": 0.47847090947279985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982458686673339,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1593659669160843,
|
|
"num_tokens": 10501616.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.93604531288147,
|
|
"epoch": 0.4788909892879647,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982421345883217,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.15468072444200515,
|
|
"num_tokens": 10511190.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.774876070022583,
|
|
"epoch": 0.4793110691031296,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982383965546898,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.15240147411823274,
|
|
"num_tokens": 10520310.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.855574083328247,
|
|
"epoch": 0.4797311489182945,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982346545665048,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.1570914402604103,
|
|
"num_tokens": 10528711.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.828868722915649,
|
|
"epoch": 0.48015122873345933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982309086238328,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.15123532563447953,
|
|
"num_tokens": 10538484.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.844063568115234,
|
|
"epoch": 0.48057130854862423,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982271587267403,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.1559097334742546,
|
|
"num_tokens": 10547623.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.850908041000366,
|
|
"epoch": 0.48099138836378913,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982234048752935,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.1569741114974022,
|
|
"num_tokens": 10556234.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.9303936004638675,
|
|
"epoch": 0.481411468178954,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498219647069559,
|
|
"loss": 5.8031,
|
|
"mean_token_accuracy": 0.149222881346941,
|
|
"num_tokens": 10566308.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.862217617034912,
|
|
"epoch": 0.48183154799411887,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982158853096035,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.1512727364897728,
|
|
"num_tokens": 10575212.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.835469961166382,
|
|
"epoch": 0.48225162780928377,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982121195954935,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1651215985417366,
|
|
"num_tokens": 10584590.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.801496887207032,
|
|
"epoch": 0.48267170762444866,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982083499272957,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.16047275960445403,
|
|
"num_tokens": 10593997.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.821460342407226,
|
|
"epoch": 0.4830917874396135,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982045763050768,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.15620884150266648,
|
|
"num_tokens": 10603299.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.863379764556885,
|
|
"epoch": 0.4835118672547784,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004982007987289041,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.15687449425458908,
|
|
"num_tokens": 10613546.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.822661638259888,
|
|
"epoch": 0.4839319470699433,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981970171988439,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.16541317775845527,
|
|
"num_tokens": 10622966.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.828573179244995,
|
|
"epoch": 0.48435202688510814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004981932317149636,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.15333941504359244,
|
|
"num_tokens": 10633441.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.888944625854492,
|
|
"epoch": 0.48477210670027304,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049818944227733,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.15536948442459106,
|
|
"num_tokens": 10643124.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.874996185302734,
|
|
"epoch": 0.48519218651543794,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981856488860105,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.14975375980138778,
|
|
"num_tokens": 10652517.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.824694728851318,
|
|
"epoch": 0.48561226633060284,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981818515410721,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.1480187088251114,
|
|
"num_tokens": 10663352.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.810465860366821,
|
|
"epoch": 0.4860323461457677,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981780502425821,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.15300920158624648,
|
|
"num_tokens": 10672430.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.845775556564331,
|
|
"epoch": 0.4864524259609326,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981742449906079,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.1613398462533951,
|
|
"num_tokens": 10681908.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.840546178817749,
|
|
"epoch": 0.4868725057760975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981704357852168,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.15710638910532,
|
|
"num_tokens": 10691259.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.816694116592407,
|
|
"epoch": 0.4872925855912623,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981666226264764,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.1578466773033142,
|
|
"num_tokens": 10699668.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.808956050872803,
|
|
"epoch": 0.4877126654064272,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004981628055144542,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.16105588674545288,
|
|
"num_tokens": 10709146.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.8652105808258055,
|
|
"epoch": 0.4881327452215921,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981589844492177,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.1511348471045494,
|
|
"num_tokens": 10718724.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.8189291000366214,
|
|
"epoch": 0.488552825036757,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981551594308349,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.15741762444376944,
|
|
"num_tokens": 10728101.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.91320481300354,
|
|
"epoch": 0.48897290485192185,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981513304593733,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.16215446591377258,
|
|
"num_tokens": 10736750.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.888871526718139,
|
|
"epoch": 0.48939298466708675,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981474975349006,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.15442975759506225,
|
|
"num_tokens": 10746914.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.866163349151611,
|
|
"epoch": 0.48981306448225165,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498143660657485,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15946730375289916,
|
|
"num_tokens": 10755786.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.732654571533203,
|
|
"epoch": 0.4902331442974165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004981398198271944,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.16208673119544983,
|
|
"num_tokens": 10764821.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.8535669326782225,
|
|
"epoch": 0.4906532241125814,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981359750440968,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.15754470974206924,
|
|
"num_tokens": 10773569.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.786517763137818,
|
|
"epoch": 0.4910733039277463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981321263082603,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.1573310151696205,
|
|
"num_tokens": 10782298.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.761690998077393,
|
|
"epoch": 0.4914933837429111,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000498128273619753,
|
|
"loss": 5.5705,
|
|
"mean_token_accuracy": 0.16008659899234773,
|
|
"num_tokens": 10792087.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.80288519859314,
|
|
"epoch": 0.491913463558076,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981244169786433,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.15478396266698838,
|
|
"num_tokens": 10801641.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.914400911331176,
|
|
"epoch": 0.4923335433732409,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981205563849994,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.15336815193295478,
|
|
"num_tokens": 10811612.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.819022130966187,
|
|
"epoch": 0.4927536231884058,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981166918388897,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.1595151573419571,
|
|
"num_tokens": 10821608.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.741395044326782,
|
|
"epoch": 0.49317370300357066,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981128233403828,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.16548489332199096,
|
|
"num_tokens": 10830679.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.786447334289551,
|
|
"epoch": 0.49359378281873556,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000498108950889547,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.15901205837726592,
|
|
"num_tokens": 10839669.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.854657602310181,
|
|
"epoch": 0.49401386263390046,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981050744864512,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.15820209830999374,
|
|
"num_tokens": 10849666.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.776970052719117,
|
|
"epoch": 0.4944339424490653,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981011941311638,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.16672125905752183,
|
|
"num_tokens": 10858225.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.745939016342163,
|
|
"epoch": 0.4948540222642302,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980973098237535,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.15611702501773833,
|
|
"num_tokens": 10867466.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.851855373382568,
|
|
"epoch": 0.4952741020793951,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980934215642894,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.16179797202348709,
|
|
"num_tokens": 10875850.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.7541014671325685,
|
|
"epoch": 0.49569418189456,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049808952935284,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16514879912137986,
|
|
"num_tokens": 10885154.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.800168514251709,
|
|
"epoch": 0.49611426170972484,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980856331894747,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.15418792963027955,
|
|
"num_tokens": 10894080.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.813483572006225,
|
|
"epoch": 0.49653434152488973,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980817330742621,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.15561991333961486,
|
|
"num_tokens": 10903248.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.844412422180175,
|
|
"epoch": 0.49695442134005463,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980778290072716,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.16167805790901185,
|
|
"num_tokens": 10912939.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.842522192001343,
|
|
"epoch": 0.4973745011552195,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980739209885722,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.15903968065977098,
|
|
"num_tokens": 10921505.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.840193128585815,
|
|
"epoch": 0.49779458097038437,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980700090182331,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.15969687849283218,
|
|
"num_tokens": 10931861.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.907305431365967,
|
|
"epoch": 0.49821466078554927,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980660930963238,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.15740073174238206,
|
|
"num_tokens": 10940810.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.757447147369385,
|
|
"epoch": 0.4986347406007141,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980621732229133,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.15881143212318422,
|
|
"num_tokens": 10949514.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.834470319747925,
|
|
"epoch": 0.499054820415879,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980582493980714,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.14656566232442855,
|
|
"num_tokens": 10959161.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.808456516265869,
|
|
"epoch": 0.4994749002310439,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980543216218674,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.17089201658964157,
|
|
"num_tokens": 10968983.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.847827053070068,
|
|
"epoch": 0.4998949800462088,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004980503898943711,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.15717339664697647,
|
|
"num_tokens": 10978044.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.825947999954224,
|
|
"epoch": 0.5003150598613737,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980464542156519,
|
|
"loss": 5.6317,
|
|
"mean_token_accuracy": 0.16252256333827972,
|
|
"num_tokens": 10986980.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.819803857803345,
|
|
"epoch": 0.5007351396765385,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980425145857796,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.1698974922299385,
|
|
"num_tokens": 10995163.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.767242860794068,
|
|
"epoch": 0.5011552194917034,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498038571004824,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.1690700516104698,
|
|
"num_tokens": 11003722.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.714049768447876,
|
|
"epoch": 0.5015752993068683,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980346234728549,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.16594353169202805,
|
|
"num_tokens": 11013176.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.8587408542633055,
|
|
"epoch": 0.5019953791220332,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980306719899424,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.155168816447258,
|
|
"num_tokens": 11022636.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.788705062866211,
|
|
"epoch": 0.5024154589371981,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980267165561564,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.16169780045747756,
|
|
"num_tokens": 11031896.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.778947973251343,
|
|
"epoch": 0.502835538752363,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004980227571715669,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.15644263625144958,
|
|
"num_tokens": 11040802.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.795914840698242,
|
|
"epoch": 0.5032556185675279,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980187938362441,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.1557212933897972,
|
|
"num_tokens": 11049701.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.845397663116455,
|
|
"epoch": 0.5036756983826927,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004980148265502581,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.14954705834388732,
|
|
"num_tokens": 11059555.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.861802339553833,
|
|
"epoch": 0.5040957781978576,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980108553136795,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.16013213694095613,
|
|
"num_tokens": 11068940.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5040957781978576,
|
|
"eval_entropy": 5.670633745714113,
|
|
"eval_loss": 5.616561412811279,
|
|
"eval_mean_token_accuracy": 0.16696001174898584,
|
|
"eval_num_tokens": 11068940.0,
|
|
"eval_runtime": 20.941,
|
|
"eval_samples_per_second": 1784.347,
|
|
"eval_steps_per_second": 223.055,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119020,
|
|
"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": 2398509142179840.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|