d94c6efa35
Model: fpadovani/swe-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2520478890989288,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.897539186477661,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1203541354414080.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|