8ed496b588
Model: fpadovani/swe-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5040957781978576,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.253151750564575,
|
|
"epoch": 0.0004200798151648813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.8984,
|
|
"mean_token_accuracy": 0.09029425084590911,
|
|
"num_tokens": 8348.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.219348526000976,
|
|
"epoch": 0.0008401596303297626,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.9563,
|
|
"mean_token_accuracy": 0.0939315177500248,
|
|
"num_tokens": 17465.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.203219985961914,
|
|
"epoch": 0.001260239445494644,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9004,
|
|
"mean_token_accuracy": 0.08940818756818772,
|
|
"num_tokens": 26627.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.224360418319702,
|
|
"epoch": 0.0016803192606595252,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.9259,
|
|
"mean_token_accuracy": 0.09512931853532791,
|
|
"num_tokens": 36069.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.186052703857422,
|
|
"epoch": 0.002100399075824407,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.09390396177768708,
|
|
"num_tokens": 44967.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.151274633407593,
|
|
"epoch": 0.002520478890989288,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.964,
|
|
"mean_token_accuracy": 0.08688623458147049,
|
|
"num_tokens": 55132.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.053877639770508,
|
|
"epoch": 0.0029405587061541692,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.7637,
|
|
"mean_token_accuracy": 0.09662552699446678,
|
|
"num_tokens": 65141.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.099168729782105,
|
|
"epoch": 0.0033606385213190504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.8446,
|
|
"mean_token_accuracy": 0.09567792639136315,
|
|
"num_tokens": 74007.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.140014743804931,
|
|
"epoch": 0.003780718336483932,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.8569,
|
|
"mean_token_accuracy": 0.09555562734603881,
|
|
"num_tokens": 83736.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.1646524429321286,
|
|
"epoch": 0.004200798151648814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.8505,
|
|
"mean_token_accuracy": 0.09592381715774537,
|
|
"num_tokens": 92525.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.107996654510498,
|
|
"epoch": 0.004620877966813695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.09664912968873977,
|
|
"num_tokens": 102015.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.137420606613159,
|
|
"epoch": 0.005040957781978576,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.9768,
|
|
"mean_token_accuracy": 0.0867392435669899,
|
|
"num_tokens": 110887.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.134914398193359,
|
|
"epoch": 0.005461037597143457,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.9024,
|
|
"mean_token_accuracy": 0.08935272470116615,
|
|
"num_tokens": 120442.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.1443713188171385,
|
|
"epoch": 0.0058811174123083385,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.8989,
|
|
"mean_token_accuracy": 0.09712273105978966,
|
|
"num_tokens": 129297.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.160055351257324,
|
|
"epoch": 0.00630119722747322,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.8507,
|
|
"mean_token_accuracy": 0.09877990111708641,
|
|
"num_tokens": 138305.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.141705083847046,
|
|
"epoch": 0.006721277042638101,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.8372,
|
|
"mean_token_accuracy": 0.09292416870594025,
|
|
"num_tokens": 147640.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.002462768554688,
|
|
"epoch": 0.007141356857802983,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.75,
|
|
"mean_token_accuracy": 0.09611514061689377,
|
|
"num_tokens": 157633.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.100855731964112,
|
|
"epoch": 0.007561436672967864,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.08827547580003739,
|
|
"num_tokens": 167984.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.129158973693848,
|
|
"epoch": 0.007981516488132745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.8948,
|
|
"mean_token_accuracy": 0.099730733782053,
|
|
"num_tokens": 176984.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.069277429580689,
|
|
"epoch": 0.008401596303297627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.7542,
|
|
"mean_token_accuracy": 0.0975344181060791,
|
|
"num_tokens": 185931.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.183401107788086,
|
|
"epoch": 0.008821676118462508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.8312,
|
|
"mean_token_accuracy": 0.09061248749494552,
|
|
"num_tokens": 195065.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.100264024734497,
|
|
"epoch": 0.00924175593362739,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.09686729088425636,
|
|
"num_tokens": 203687.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.042130661010742,
|
|
"epoch": 0.00966183574879227,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.8491,
|
|
"mean_token_accuracy": 0.09541062936186791,
|
|
"num_tokens": 212847.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.127160167694091,
|
|
"epoch": 0.010081915563957152,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.8242,
|
|
"mean_token_accuracy": 0.0955698125064373,
|
|
"num_tokens": 222593.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.0331028461456295,
|
|
"epoch": 0.010501995379122032,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.711,
|
|
"mean_token_accuracy": 0.0981454961001873,
|
|
"num_tokens": 231174.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.9479889392852785,
|
|
"epoch": 0.010922075194286915,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.663,
|
|
"mean_token_accuracy": 0.10388810336589813,
|
|
"num_tokens": 239833.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.190658855438232,
|
|
"epoch": 0.011342155009451797,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.951,
|
|
"mean_token_accuracy": 0.0949922852218151,
|
|
"num_tokens": 248794.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.251979541778565,
|
|
"epoch": 0.011762234824616677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.09376412332057953,
|
|
"num_tokens": 257123.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.008625459671021,
|
|
"epoch": 0.012182314639781559,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.10136394873261452,
|
|
"num_tokens": 266088.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.118732166290283,
|
|
"epoch": 0.01260239445494644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.9922,
|
|
"mean_token_accuracy": 0.08856561928987502,
|
|
"num_tokens": 276074.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.265724229812622,
|
|
"epoch": 0.013022474270111321,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.8415,
|
|
"mean_token_accuracy": 0.09575222656130791,
|
|
"num_tokens": 285280.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.09201340675354,
|
|
"epoch": 0.013442554085276202,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.9508,
|
|
"mean_token_accuracy": 0.08855971023440361,
|
|
"num_tokens": 296115.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.172540521621704,
|
|
"epoch": 0.013862633900441084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.7833,
|
|
"mean_token_accuracy": 0.09475113973021507,
|
|
"num_tokens": 305483.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.142146444320678,
|
|
"epoch": 0.014282713715605966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.798,
|
|
"mean_token_accuracy": 0.09611742347478866,
|
|
"num_tokens": 314000.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.191121196746826,
|
|
"epoch": 0.014702793530770846,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8719,
|
|
"mean_token_accuracy": 0.09523176699876786,
|
|
"num_tokens": 323667.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.111018800735474,
|
|
"epoch": 0.015122873345935728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.9126,
|
|
"mean_token_accuracy": 0.09633364677429199,
|
|
"num_tokens": 332695.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.152137660980225,
|
|
"epoch": 0.015542953161100609,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.7081,
|
|
"mean_token_accuracy": 0.09874472171068191,
|
|
"num_tokens": 342428.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.018444013595581,
|
|
"epoch": 0.01596303297626549,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.9196,
|
|
"mean_token_accuracy": 0.09128761291503906,
|
|
"num_tokens": 353587.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.154490900039673,
|
|
"epoch": 0.01638311279143037,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.8259,
|
|
"mean_token_accuracy": 0.09795344024896621,
|
|
"num_tokens": 362997.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.170652723312378,
|
|
"epoch": 0.016803192606595255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.8563,
|
|
"mean_token_accuracy": 0.09546189531683921,
|
|
"num_tokens": 372346.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.110174036026001,
|
|
"epoch": 0.017223272421760135,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.741,
|
|
"mean_token_accuracy": 0.09936807751655578,
|
|
"num_tokens": 381575.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.106418037414551,
|
|
"epoch": 0.017643352236925015,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.09433561563491821,
|
|
"num_tokens": 390706.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.192156839370727,
|
|
"epoch": 0.018063432052089896,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.8516,
|
|
"mean_token_accuracy": 0.0938378892838955,
|
|
"num_tokens": 400000.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.9766045093536375,
|
|
"epoch": 0.01848351186725478,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.10025399252772331,
|
|
"num_tokens": 409447.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.228094434738159,
|
|
"epoch": 0.01890359168241966,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.7628,
|
|
"mean_token_accuracy": 0.09841207265853882,
|
|
"num_tokens": 418417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.980171537399292,
|
|
"epoch": 0.01932367149758454,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.10002906545996666,
|
|
"num_tokens": 427619.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.174957370758056,
|
|
"epoch": 0.019743751312749424,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.8595,
|
|
"mean_token_accuracy": 0.09506258964538575,
|
|
"num_tokens": 437931.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.124919366836548,
|
|
"epoch": 0.020163831127914304,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.8624,
|
|
"mean_token_accuracy": 0.10153809040784836,
|
|
"num_tokens": 447595.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.076248693466186,
|
|
"epoch": 0.020583910943079185,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.09595257192850112,
|
|
"num_tokens": 457062.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.11194372177124,
|
|
"epoch": 0.021003990758244065,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.09663526639342308,
|
|
"num_tokens": 466191.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.119431734085083,
|
|
"epoch": 0.02142407057340895,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.09689914286136628,
|
|
"num_tokens": 475693.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.101942634582519,
|
|
"epoch": 0.02184415038857383,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8733,
|
|
"mean_token_accuracy": 0.0926995851099491,
|
|
"num_tokens": 485173.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.02587628364563,
|
|
"epoch": 0.02226423020373871,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.7261,
|
|
"mean_token_accuracy": 0.1030467577278614,
|
|
"num_tokens": 493985.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.204363059997559,
|
|
"epoch": 0.022684310018903593,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8283,
|
|
"mean_token_accuracy": 0.09744107499718666,
|
|
"num_tokens": 502837.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.018724775314331,
|
|
"epoch": 0.023104389834068473,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.7299,
|
|
"mean_token_accuracy": 0.10230938643217087,
|
|
"num_tokens": 511503.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.203450679779053,
|
|
"epoch": 0.023524469649233354,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9591,
|
|
"mean_token_accuracy": 0.09394779950380325,
|
|
"num_tokens": 521499.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.085290002822876,
|
|
"epoch": 0.023944549464398234,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.7304,
|
|
"mean_token_accuracy": 0.09568566456437111,
|
|
"num_tokens": 530067.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.13321099281311,
|
|
"epoch": 0.024364629279563118,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.7422,
|
|
"mean_token_accuracy": 0.10064690634608268,
|
|
"num_tokens": 538559.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.135575151443481,
|
|
"epoch": 0.024784709094728,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9403,
|
|
"mean_token_accuracy": 0.09277286529541015,
|
|
"num_tokens": 547288.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.132419538497925,
|
|
"epoch": 0.02520478890989288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8165,
|
|
"mean_token_accuracy": 0.09548124819993972,
|
|
"num_tokens": 557269.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.107891798019409,
|
|
"epoch": 0.025624868725057762,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8392,
|
|
"mean_token_accuracy": 0.09125733524560928,
|
|
"num_tokens": 567280.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.009502935409546,
|
|
"epoch": 0.026044948540222643,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.6443,
|
|
"mean_token_accuracy": 0.0992837019264698,
|
|
"num_tokens": 576609.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.9137735843658445,
|
|
"epoch": 0.026465028355387523,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.627,
|
|
"mean_token_accuracy": 0.1031131848692894,
|
|
"num_tokens": 586053.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.00633134841919,
|
|
"epoch": 0.026885108170552403,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8295,
|
|
"mean_token_accuracy": 0.09749070778489113,
|
|
"num_tokens": 594649.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.084966850280762,
|
|
"epoch": 0.027305187985717287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.7142,
|
|
"mean_token_accuracy": 0.09451463893055916,
|
|
"num_tokens": 603445.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.088579750061035,
|
|
"epoch": 0.027725267800882167,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8658,
|
|
"mean_token_accuracy": 0.09315285831689835,
|
|
"num_tokens": 613611.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.3623809814453125,
|
|
"epoch": 0.028145347616047048,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.0713,
|
|
"mean_token_accuracy": 0.0919966921210289,
|
|
"num_tokens": 623024.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.999190092086792,
|
|
"epoch": 0.02856542743121193,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7385,
|
|
"mean_token_accuracy": 0.1017606370151043,
|
|
"num_tokens": 631624.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.994140338897705,
|
|
"epoch": 0.028985507246376812,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.6633,
|
|
"mean_token_accuracy": 0.10479742139577866,
|
|
"num_tokens": 640473.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.0762580871582035,
|
|
"epoch": 0.029405587061541692,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9006,
|
|
"mean_token_accuracy": 0.09429975003004074,
|
|
"num_tokens": 649692.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.142873811721802,
|
|
"epoch": 0.029825666876706573,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8377,
|
|
"mean_token_accuracy": 0.09720863476395607,
|
|
"num_tokens": 658236.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.952843904495239,
|
|
"epoch": 0.030245746691871456,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.6251,
|
|
"mean_token_accuracy": 0.09688405320048332,
|
|
"num_tokens": 667175.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.14975872039795,
|
|
"epoch": 0.030665826507036337,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9438,
|
|
"mean_token_accuracy": 0.09247877895832061,
|
|
"num_tokens": 676456.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.224644327163697,
|
|
"epoch": 0.031085906322201217,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.926,
|
|
"mean_token_accuracy": 0.08845363929867744,
|
|
"num_tokens": 686881.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.932204675674439,
|
|
"epoch": 0.0315059861373661,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.6985,
|
|
"mean_token_accuracy": 0.09394535645842553,
|
|
"num_tokens": 696045.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.965549278259277,
|
|
"epoch": 0.03192606595253098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.10160319805145264,
|
|
"num_tokens": 704729.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.985969495773316,
|
|
"epoch": 0.032346145767695865,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7426,
|
|
"mean_token_accuracy": 0.0950203962624073,
|
|
"num_tokens": 714331.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.101364660263061,
|
|
"epoch": 0.03276622558286074,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.6912,
|
|
"mean_token_accuracy": 0.10189466029405594,
|
|
"num_tokens": 722788.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.007110738754273,
|
|
"epoch": 0.033186305398025626,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7849,
|
|
"mean_token_accuracy": 0.10113223120570183,
|
|
"num_tokens": 731417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.0138044357299805,
|
|
"epoch": 0.03360638521319051,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.09411026313900947,
|
|
"num_tokens": 741034.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.00489068031311,
|
|
"epoch": 0.034026465028355386,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7516,
|
|
"mean_token_accuracy": 0.09877323731780052,
|
|
"num_tokens": 749596.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.017527103424072,
|
|
"epoch": 0.03444654484352027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7218,
|
|
"mean_token_accuracy": 0.09416642934083938,
|
|
"num_tokens": 758931.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.871344518661499,
|
|
"epoch": 0.03486662465868515,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.6216,
|
|
"mean_token_accuracy": 0.10105381533503532,
|
|
"num_tokens": 767534.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.960817480087281,
|
|
"epoch": 0.03528670447385003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.10064006224274635,
|
|
"num_tokens": 776456.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.008622884750366,
|
|
"epoch": 0.035706784289014915,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7646,
|
|
"mean_token_accuracy": 0.09697613269090652,
|
|
"num_tokens": 786172.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.960406351089477,
|
|
"epoch": 0.03612686410417979,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6658,
|
|
"mean_token_accuracy": 0.10456070601940155,
|
|
"num_tokens": 795081.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.916972398757935,
|
|
"epoch": 0.036546943919344675,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6979,
|
|
"mean_token_accuracy": 0.09141508191823959,
|
|
"num_tokens": 804259.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.980181550979614,
|
|
"epoch": 0.03696702373450956,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7251,
|
|
"mean_token_accuracy": 0.0985159382224083,
|
|
"num_tokens": 813463.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.952114248275757,
|
|
"epoch": 0.037387103549674436,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.10426531285047531,
|
|
"num_tokens": 823029.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.91859712600708,
|
|
"epoch": 0.03780718336483932,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7327,
|
|
"mean_token_accuracy": 0.0944428451359272,
|
|
"num_tokens": 832902.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.92227520942688,
|
|
"epoch": 0.0382272631800042,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6724,
|
|
"mean_token_accuracy": 0.10073406398296356,
|
|
"num_tokens": 842162.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.979531192779541,
|
|
"epoch": 0.03864734299516908,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.0995998091995716,
|
|
"num_tokens": 852328.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.8678590774536135,
|
|
"epoch": 0.039067422810333964,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6831,
|
|
"mean_token_accuracy": 0.1023336872458458,
|
|
"num_tokens": 860929.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.0033402919769285,
|
|
"epoch": 0.03948750262549885,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7492,
|
|
"mean_token_accuracy": 0.09593449011445046,
|
|
"num_tokens": 869144.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.003532409667969,
|
|
"epoch": 0.039907582440663725,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.705,
|
|
"mean_token_accuracy": 0.10385636389255523,
|
|
"num_tokens": 877447.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.86921706199646,
|
|
"epoch": 0.04032766225582861,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6601,
|
|
"mean_token_accuracy": 0.09642177075147629,
|
|
"num_tokens": 887020.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.996332120895386,
|
|
"epoch": 0.040747742070993485,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.0975713811814785,
|
|
"num_tokens": 895937.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.852901887893677,
|
|
"epoch": 0.04116782188615837,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7267,
|
|
"mean_token_accuracy": 0.09650165066123009,
|
|
"num_tokens": 905446.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.893301010131836,
|
|
"epoch": 0.04158790170132325,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6036,
|
|
"mean_token_accuracy": 0.10643761828541756,
|
|
"num_tokens": 914547.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.915640449523925,
|
|
"epoch": 0.04200798151648813,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6263,
|
|
"mean_token_accuracy": 0.10527556240558625,
|
|
"num_tokens": 922900.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.947235059738159,
|
|
"epoch": 0.042428061331653014,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6686,
|
|
"mean_token_accuracy": 0.10355583727359771,
|
|
"num_tokens": 930876.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.88210015296936,
|
|
"epoch": 0.0428481411468179,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7087,
|
|
"mean_token_accuracy": 0.10312066823244095,
|
|
"num_tokens": 939871.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.947447443008423,
|
|
"epoch": 0.043268220961982774,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.695,
|
|
"mean_token_accuracy": 0.10180827602744102,
|
|
"num_tokens": 948673.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.816449880599976,
|
|
"epoch": 0.04368830077714766,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.09842450320720672,
|
|
"num_tokens": 957603.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.928069686889648,
|
|
"epoch": 0.04410838059231254,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7274,
|
|
"mean_token_accuracy": 0.09575201719999313,
|
|
"num_tokens": 967731.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.940513849258423,
|
|
"epoch": 0.04452846040747742,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7098,
|
|
"mean_token_accuracy": 0.10156730636954307,
|
|
"num_tokens": 977427.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.883533573150634,
|
|
"epoch": 0.0449485402226423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7126,
|
|
"mean_token_accuracy": 0.09694371595978737,
|
|
"num_tokens": 986758.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.054216384887695,
|
|
"epoch": 0.045368620037807186,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7073,
|
|
"mean_token_accuracy": 0.10619494765996933,
|
|
"num_tokens": 996377.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.823930788040161,
|
|
"epoch": 0.04578869985297206,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.09864854142069816,
|
|
"num_tokens": 1006483.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.839679384231568,
|
|
"epoch": 0.04620877966813695,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6608,
|
|
"mean_token_accuracy": 0.09898171871900559,
|
|
"num_tokens": 1016132.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.886328125,
|
|
"epoch": 0.04662885948330183,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5878,
|
|
"mean_token_accuracy": 0.10534627884626388,
|
|
"num_tokens": 1024970.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.892021656036377,
|
|
"epoch": 0.04704893929846671,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7043,
|
|
"mean_token_accuracy": 0.0967423141002655,
|
|
"num_tokens": 1034335.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.914703607559204,
|
|
"epoch": 0.04746901911363159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.756,
|
|
"mean_token_accuracy": 0.10775318518280982,
|
|
"num_tokens": 1043954.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.942829847335815,
|
|
"epoch": 0.04788909892879647,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.10058957412838936,
|
|
"num_tokens": 1053554.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.854119396209716,
|
|
"epoch": 0.04830917874396135,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.10385002046823502,
|
|
"num_tokens": 1062008.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.868479824066162,
|
|
"epoch": 0.048729258559126236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7048,
|
|
"mean_token_accuracy": 0.10346106439828873,
|
|
"num_tokens": 1070740.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.8440343856811525,
|
|
"epoch": 0.04914933837429111,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7057,
|
|
"mean_token_accuracy": 0.10240900367498398,
|
|
"num_tokens": 1079681.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.858892154693604,
|
|
"epoch": 0.049569418189456,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5847,
|
|
"mean_token_accuracy": 0.10450911447405815,
|
|
"num_tokens": 1088979.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.772767686843872,
|
|
"epoch": 0.04998949800462088,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5832,
|
|
"mean_token_accuracy": 0.10501813441514969,
|
|
"num_tokens": 1097870.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.856569433212281,
|
|
"epoch": 0.05040957781978576,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.714,
|
|
"mean_token_accuracy": 0.09948427230119705,
|
|
"num_tokens": 1107948.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.876928329467773,
|
|
"epoch": 0.05082965763495064,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.1076712541282177,
|
|
"num_tokens": 1117032.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.769250106811524,
|
|
"epoch": 0.051249737450115525,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5928,
|
|
"mean_token_accuracy": 0.10671919211745262,
|
|
"num_tokens": 1127834.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.948690032958984,
|
|
"epoch": 0.0516698172652804,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.695,
|
|
"mean_token_accuracy": 0.11499854996800422,
|
|
"num_tokens": 1137382.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.77532000541687,
|
|
"epoch": 0.052089897080445285,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5422,
|
|
"mean_token_accuracy": 0.11223937124013901,
|
|
"num_tokens": 1146095.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.723394155502319,
|
|
"epoch": 0.05250997689561017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5822,
|
|
"mean_token_accuracy": 0.10564726367592811,
|
|
"num_tokens": 1154981.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.776411151885986,
|
|
"epoch": 0.052930056710775046,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6153,
|
|
"mean_token_accuracy": 0.10753953084349632,
|
|
"num_tokens": 1164939.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.936794233322144,
|
|
"epoch": 0.05335013652593993,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.09790047407150268,
|
|
"num_tokens": 1174991.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.818718576431275,
|
|
"epoch": 0.05377021634110481,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.78,
|
|
"mean_token_accuracy": 0.09581352695822716,
|
|
"num_tokens": 1184885.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.859689378738404,
|
|
"epoch": 0.05419029615626969,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6652,
|
|
"mean_token_accuracy": 0.10177846625447273,
|
|
"num_tokens": 1193637.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.70958137512207,
|
|
"epoch": 0.054610375971434574,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4505,
|
|
"mean_token_accuracy": 0.11398516818881035,
|
|
"num_tokens": 1202188.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.731061363220215,
|
|
"epoch": 0.05503045578659945,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.10111142173409463,
|
|
"num_tokens": 1210768.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.75755124092102,
|
|
"epoch": 0.055450535601764335,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5885,
|
|
"mean_token_accuracy": 0.10299575850367546,
|
|
"num_tokens": 1219819.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.8775472164154055,
|
|
"epoch": 0.05587061541692922,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.6507,
|
|
"mean_token_accuracy": 0.09766614213585853,
|
|
"num_tokens": 1229703.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.829215049743652,
|
|
"epoch": 0.056290695232094096,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6863,
|
|
"mean_token_accuracy": 0.09930930510163308,
|
|
"num_tokens": 1238942.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.886805677413941,
|
|
"epoch": 0.05671077504725898,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.7475,
|
|
"mean_token_accuracy": 0.09512239620089531,
|
|
"num_tokens": 1248943.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.774325275421143,
|
|
"epoch": 0.05713085486242386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6164,
|
|
"mean_token_accuracy": 0.10321223735809326,
|
|
"num_tokens": 1257761.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.6621216297149655,
|
|
"epoch": 0.05755093467758874,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5622,
|
|
"mean_token_accuracy": 0.10228212624788284,
|
|
"num_tokens": 1267216.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.826507520675659,
|
|
"epoch": 0.057971014492753624,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6587,
|
|
"mean_token_accuracy": 0.1079720102250576,
|
|
"num_tokens": 1277210.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.737741279602051,
|
|
"epoch": 0.05839109430791851,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5588,
|
|
"mean_token_accuracy": 0.10001136437058449,
|
|
"num_tokens": 1285310.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.800521755218506,
|
|
"epoch": 0.058811174123083385,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5887,
|
|
"mean_token_accuracy": 0.10580191239714623,
|
|
"num_tokens": 1294421.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.603023052215576,
|
|
"epoch": 0.05923125393824827,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4007,
|
|
"mean_token_accuracy": 0.11451570391654968,
|
|
"num_tokens": 1303281.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.694077110290527,
|
|
"epoch": 0.059651333753413145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5884,
|
|
"mean_token_accuracy": 0.1103569135069847,
|
|
"num_tokens": 1312280.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.703026485443115,
|
|
"epoch": 0.06007141356857803,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5455,
|
|
"mean_token_accuracy": 0.10655389800667762,
|
|
"num_tokens": 1321243.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.783720779418945,
|
|
"epoch": 0.06049149338374291,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.6752,
|
|
"mean_token_accuracy": 0.10890973284840584,
|
|
"num_tokens": 1330324.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.716011047363281,
|
|
"epoch": 0.06091157319890779,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4895,
|
|
"mean_token_accuracy": 0.11130202338099479,
|
|
"num_tokens": 1339485.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.763300609588623,
|
|
"epoch": 0.06133165301407267,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.09835303947329521,
|
|
"num_tokens": 1348640.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.686880588531494,
|
|
"epoch": 0.06175173282923756,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5352,
|
|
"mean_token_accuracy": 0.10910931676626205,
|
|
"num_tokens": 1357581.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.789766788482666,
|
|
"epoch": 0.062171812644402434,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6092,
|
|
"mean_token_accuracy": 0.10686837136745453,
|
|
"num_tokens": 1367883.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.689715576171875,
|
|
"epoch": 0.06259189245956731,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5732,
|
|
"mean_token_accuracy": 0.10044000372290611,
|
|
"num_tokens": 1376936.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.619902896881103,
|
|
"epoch": 0.0630119722747322,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5013,
|
|
"mean_token_accuracy": 0.10585071742534638,
|
|
"num_tokens": 1386359.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.691353893280029,
|
|
"epoch": 0.06343205208989708,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5614,
|
|
"mean_token_accuracy": 0.10925468727946282,
|
|
"num_tokens": 1395223.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.756776332855225,
|
|
"epoch": 0.06385213190506196,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7048,
|
|
"mean_token_accuracy": 0.10100763738155365,
|
|
"num_tokens": 1404917.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.7892101287841795,
|
|
"epoch": 0.06427221172022685,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.11203819289803504,
|
|
"num_tokens": 1413348.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.617217540740967,
|
|
"epoch": 0.06469229153539173,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.10595368966460228,
|
|
"num_tokens": 1421726.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.699965381622315,
|
|
"epoch": 0.0651123713505566,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.10766990706324578,
|
|
"num_tokens": 1430686.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.773920488357544,
|
|
"epoch": 0.06553245116572148,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5765,
|
|
"mean_token_accuracy": 0.10770290642976761,
|
|
"num_tokens": 1439499.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.685867691040039,
|
|
"epoch": 0.06595253098088637,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.10584950372576714,
|
|
"num_tokens": 1448220.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.635032224655151,
|
|
"epoch": 0.06637261079605125,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5914,
|
|
"mean_token_accuracy": 0.09675629287958146,
|
|
"num_tokens": 1458217.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.699159860610962,
|
|
"epoch": 0.06679269061121614,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.10567129477858543,
|
|
"num_tokens": 1467422.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.620410299301147,
|
|
"epoch": 0.06721277042638102,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4767,
|
|
"mean_token_accuracy": 0.11094664260745049,
|
|
"num_tokens": 1476152.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.650699758529663,
|
|
"epoch": 0.06763285024154589,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5738,
|
|
"mean_token_accuracy": 0.1043787069618702,
|
|
"num_tokens": 1485248.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.619400262832642,
|
|
"epoch": 0.06805293005671077,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.10442669913172722,
|
|
"num_tokens": 1494248.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.722617673873901,
|
|
"epoch": 0.06847300987187566,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.6573,
|
|
"mean_token_accuracy": 0.10585515722632408,
|
|
"num_tokens": 1503565.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.83908371925354,
|
|
"epoch": 0.06889308968704054,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.745,
|
|
"mean_token_accuracy": 0.10003346055746079,
|
|
"num_tokens": 1513227.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.658945035934448,
|
|
"epoch": 0.06931316950220542,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.10508675500750542,
|
|
"num_tokens": 1522312.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.637969160079956,
|
|
"epoch": 0.0697332493173703,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.10670675709843636,
|
|
"num_tokens": 1531720.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.6340169429779055,
|
|
"epoch": 0.07015332913253518,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.5721,
|
|
"mean_token_accuracy": 0.10074454993009567,
|
|
"num_tokens": 1541238.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.695564794540405,
|
|
"epoch": 0.07057340894770006,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.6648,
|
|
"mean_token_accuracy": 0.10375690832734108,
|
|
"num_tokens": 1550875.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.645870971679687,
|
|
"epoch": 0.07099348876286495,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.10648187175393105,
|
|
"num_tokens": 1560287.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.6967510223388675,
|
|
"epoch": 0.07141356857802983,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.4978,
|
|
"mean_token_accuracy": 0.11105224043130875,
|
|
"num_tokens": 1569043.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.554346418380737,
|
|
"epoch": 0.07183364839319471,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.11203170269727707,
|
|
"num_tokens": 1578112.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.515066003799438,
|
|
"epoch": 0.07225372820835958,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4364,
|
|
"mean_token_accuracy": 0.11132391095161438,
|
|
"num_tokens": 1586587.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.742719125747681,
|
|
"epoch": 0.07267380802352447,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5978,
|
|
"mean_token_accuracy": 0.10682642236351966,
|
|
"num_tokens": 1595585.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.641049814224243,
|
|
"epoch": 0.07309388783868935,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.10661023184657097,
|
|
"num_tokens": 1605355.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.638308906555176,
|
|
"epoch": 0.07351396765385423,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.10184741988778115,
|
|
"num_tokens": 1613637.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.658770608901977,
|
|
"epoch": 0.07393404746901912,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.10806669145822526,
|
|
"num_tokens": 1622731.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.610404300689697,
|
|
"epoch": 0.074354127284184,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.10660439133644103,
|
|
"num_tokens": 1632098.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.581112480163574,
|
|
"epoch": 0.07477420709934887,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.10190015733242035,
|
|
"num_tokens": 1641259.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.669602966308593,
|
|
"epoch": 0.07519428691451376,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5769,
|
|
"mean_token_accuracy": 0.103199552744627,
|
|
"num_tokens": 1651362.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.581767272949219,
|
|
"epoch": 0.07561436672967864,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4893,
|
|
"mean_token_accuracy": 0.1063641555607319,
|
|
"num_tokens": 1660190.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.573458099365235,
|
|
"epoch": 0.07603444654484352,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5473,
|
|
"mean_token_accuracy": 0.10238413438200951,
|
|
"num_tokens": 1669020.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.650429916381836,
|
|
"epoch": 0.0764545263600084,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.1067358523607254,
|
|
"num_tokens": 1678158.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.640725135803223,
|
|
"epoch": 0.07687460617517328,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.5723,
|
|
"mean_token_accuracy": 0.10445328801870346,
|
|
"num_tokens": 1687481.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.5850495338439945,
|
|
"epoch": 0.07729468599033816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.5327,
|
|
"mean_token_accuracy": 0.11253217458724976,
|
|
"num_tokens": 1696782.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.555831384658814,
|
|
"epoch": 0.07771476580550304,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.528,
|
|
"mean_token_accuracy": 0.10824255496263505,
|
|
"num_tokens": 1706153.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.625135850906372,
|
|
"epoch": 0.07813484562066793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.559,
|
|
"mean_token_accuracy": 0.1069357268512249,
|
|
"num_tokens": 1715585.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.768569469451904,
|
|
"epoch": 0.07855492543583281,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.6818,
|
|
"mean_token_accuracy": 0.10121209248900413,
|
|
"num_tokens": 1724857.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.553330516815185,
|
|
"epoch": 0.0789750052509977,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.11398640796542167,
|
|
"num_tokens": 1733528.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.64405460357666,
|
|
"epoch": 0.07939508506616257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.10737027525901795,
|
|
"num_tokens": 1742953.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.612694597244262,
|
|
"epoch": 0.07981516488132745,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.5605,
|
|
"mean_token_accuracy": 0.11337294653058053,
|
|
"num_tokens": 1752155.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.579654312133789,
|
|
"epoch": 0.08023524469649233,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.10857293009757996,
|
|
"num_tokens": 1760562.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.568000841140747,
|
|
"epoch": 0.08065532451165722,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4953,
|
|
"mean_token_accuracy": 0.10662117302417755,
|
|
"num_tokens": 1769631.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.530600309371948,
|
|
"epoch": 0.0810754043268221,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.513,
|
|
"mean_token_accuracy": 0.10268357619643212,
|
|
"num_tokens": 1779080.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.608699893951416,
|
|
"epoch": 0.08149548414198697,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.1082501009106636,
|
|
"num_tokens": 1787830.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.3936583518981935,
|
|
"epoch": 0.08191556395715185,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4399,
|
|
"mean_token_accuracy": 0.10422300174832344,
|
|
"num_tokens": 1796998.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.6043681621551515,
|
|
"epoch": 0.08233564377231674,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.5165,
|
|
"mean_token_accuracy": 0.1103883646428585,
|
|
"num_tokens": 1806194.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.372901821136475,
|
|
"epoch": 0.08275572358748162,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4139,
|
|
"mean_token_accuracy": 0.11206447035074234,
|
|
"num_tokens": 1815751.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.442894506454468,
|
|
"epoch": 0.0831758034026465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.4907,
|
|
"mean_token_accuracy": 0.11046408414840699,
|
|
"num_tokens": 1825379.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.55560712814331,
|
|
"epoch": 0.08359588321781139,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.10851948186755181,
|
|
"num_tokens": 1834158.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.516812181472778,
|
|
"epoch": 0.08401596303297626,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4132,
|
|
"mean_token_accuracy": 0.10896480083465576,
|
|
"num_tokens": 1842724.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.518254280090332,
|
|
"epoch": 0.08443604284814114,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999998724557,
|
|
"loss": 6.4359,
|
|
"mean_token_accuracy": 0.11062911972403526,
|
|
"num_tokens": 1852485.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.472753667831421,
|
|
"epoch": 0.08485612266330603,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999999935430703,
|
|
"loss": 6.4668,
|
|
"mean_token_accuracy": 0.11211320757865906,
|
|
"num_tokens": 1861303.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.340228652954101,
|
|
"epoch": 0.08527620247847091,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999843758243,
|
|
"loss": 6.4328,
|
|
"mean_token_accuracy": 0.11544003784656524,
|
|
"num_tokens": 1870859.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.671287488937378,
|
|
"epoch": 0.0856962822936358,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999712228196,
|
|
"loss": 6.6205,
|
|
"mean_token_accuracy": 0.0996169812977314,
|
|
"num_tokens": 1880295.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.63971586227417,
|
|
"epoch": 0.08611636210880068,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999540840562,
|
|
"loss": 6.5111,
|
|
"mean_token_accuracy": 0.11260380744934081,
|
|
"num_tokens": 1889193.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.493311834335327,
|
|
"epoch": 0.08653644192396555,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999329595345,
|
|
"loss": 6.6021,
|
|
"mean_token_accuracy": 0.09916243478655815,
|
|
"num_tokens": 1899437.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.5729930877685545,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999078492548,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.10446131974458694,
|
|
"num_tokens": 1907882.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.492805910110474,
|
|
"epoch": 0.08737660155429532,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998787532176,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.1126400038599968,
|
|
"num_tokens": 1916872.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.506380701065064,
|
|
"epoch": 0.0877966813694602,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999998456714234,
|
|
"loss": 6.5924,
|
|
"mean_token_accuracy": 0.11272363439202308,
|
|
"num_tokens": 1926636.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.5269097805023195,
|
|
"epoch": 0.08821676118462508,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999998086038729,
|
|
"loss": 6.4905,
|
|
"mean_token_accuracy": 0.10973675772547722,
|
|
"num_tokens": 1935962.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.491125774383545,
|
|
"epoch": 0.08863684099978995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997675505665,
|
|
"loss": 6.4506,
|
|
"mean_token_accuracy": 0.11091897338628769,
|
|
"num_tokens": 1944600.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.560743236541748,
|
|
"epoch": 0.08905692081495484,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999997225115052,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.10566280484199524,
|
|
"num_tokens": 1954234.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.71457724571228,
|
|
"epoch": 0.08947700063011972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999996734866896,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.10413395762443542,
|
|
"num_tokens": 1964499.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.307662582397461,
|
|
"epoch": 0.0898970804452846,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999996204761206,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.11687865033745766,
|
|
"num_tokens": 1973635.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.497924661636352,
|
|
"epoch": 0.09031716026044949,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999995634797993,
|
|
"loss": 6.4546,
|
|
"mean_token_accuracy": 0.11474235132336616,
|
|
"num_tokens": 1983509.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.480887317657471,
|
|
"epoch": 0.09073724007561437,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999995024977265,
|
|
"loss": 6.4317,
|
|
"mean_token_accuracy": 0.11495376154780387,
|
|
"num_tokens": 1992336.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.518788290023804,
|
|
"epoch": 0.09115731989077924,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999994375299034,
|
|
"loss": 6.467,
|
|
"mean_token_accuracy": 0.11141329482197762,
|
|
"num_tokens": 2001931.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.396731853485107,
|
|
"epoch": 0.09157739970594413,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499999368576331,
|
|
"loss": 6.3268,
|
|
"mean_token_accuracy": 0.11944503113627433,
|
|
"num_tokens": 2010935.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.410158395767212,
|
|
"epoch": 0.09199747952110901,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999992956370109,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.1134261205792427,
|
|
"num_tokens": 2020587.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.34518141746521,
|
|
"epoch": 0.0924175593362739,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499999218711944,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.11149835661053657,
|
|
"num_tokens": 2029743.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.548259019851685,
|
|
"epoch": 0.09283763915143878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999991378011317,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.11465151533484459,
|
|
"num_tokens": 2038468.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.381483364105224,
|
|
"epoch": 0.09325771896660366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999990529045757,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.11419494673609734,
|
|
"num_tokens": 2047456.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.610185289382935,
|
|
"epoch": 0.09367779878176853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999989640222771,
|
|
"loss": 6.6665,
|
|
"mean_token_accuracy": 0.09994395300745965,
|
|
"num_tokens": 2056691.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.5219189643859865,
|
|
"epoch": 0.09409787859693342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499998871154238,
|
|
"loss": 6.4644,
|
|
"mean_token_accuracy": 0.10945621505379677,
|
|
"num_tokens": 2066068.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.522899913787842,
|
|
"epoch": 0.0945179584120983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999987743004597,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.11605900377035142,
|
|
"num_tokens": 2075113.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.463716268539429,
|
|
"epoch": 0.09493803822726318,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999986734609438,
|
|
"loss": 6.5424,
|
|
"mean_token_accuracy": 0.11121912077069282,
|
|
"num_tokens": 2084557.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.5195088386535645,
|
|
"epoch": 0.09535811804242807,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999985686356923,
|
|
"loss": 6.4293,
|
|
"mean_token_accuracy": 0.10896992832422256,
|
|
"num_tokens": 2093424.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.501124429702759,
|
|
"epoch": 0.09577819785759294,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499998459824707,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.10720071643590927,
|
|
"num_tokens": 2103066.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.485859060287476,
|
|
"epoch": 0.09619827767275782,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049999834702799,
|
|
"loss": 6.4218,
|
|
"mean_token_accuracy": 0.11379043385386467,
|
|
"num_tokens": 2112447.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.421380949020386,
|
|
"epoch": 0.0966183574879227,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999982302455431,
|
|
"loss": 6.4471,
|
|
"mean_token_accuracy": 0.11498942598700523,
|
|
"num_tokens": 2121949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.473872327804566,
|
|
"epoch": 0.09703843730308759,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999981094773683,
|
|
"loss": 6.3538,
|
|
"mean_token_accuracy": 0.11318295449018478,
|
|
"num_tokens": 2130464.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.440775918960571,
|
|
"epoch": 0.09745851711825247,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499997984723468,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.10744207352399826,
|
|
"num_tokens": 2139577.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.234747648239136,
|
|
"epoch": 0.09787859693341736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999978559838441,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.11980548799037934,
|
|
"num_tokens": 2147919.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.425514888763428,
|
|
"epoch": 0.09829867674858223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999977232584991,
|
|
"loss": 6.411,
|
|
"mean_token_accuracy": 0.11489588171243667,
|
|
"num_tokens": 2156936.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.470327949523925,
|
|
"epoch": 0.09871875656374711,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999975865474354,
|
|
"loss": 6.474,
|
|
"mean_token_accuracy": 0.11181759610772132,
|
|
"num_tokens": 2165362.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.40549669265747,
|
|
"epoch": 0.099138836378912,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999974458506551,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.11321083605289459,
|
|
"num_tokens": 2173665.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.484990215301513,
|
|
"epoch": 0.09955891619407688,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499997301168161,
|
|
"loss": 6.3547,
|
|
"mean_token_accuracy": 0.1165615513920784,
|
|
"num_tokens": 2182222.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.47981333732605,
|
|
"epoch": 0.09997899600924176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999971524999556,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.11381722316145897,
|
|
"num_tokens": 2192358.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.44229564666748,
|
|
"epoch": 0.10039907582440663,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999969998460414,
|
|
"loss": 6.4519,
|
|
"mean_token_accuracy": 0.11379328668117523,
|
|
"num_tokens": 2201889.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.39982123374939,
|
|
"epoch": 0.10081915563957151,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999968432064213,
|
|
"loss": 6.4571,
|
|
"mean_token_accuracy": 0.11692695915699006,
|
|
"num_tokens": 2211810.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.344041538238526,
|
|
"epoch": 0.1012392354547364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966825810979,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.11303748413920403,
|
|
"num_tokens": 2221123.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.35064206123352,
|
|
"epoch": 0.10165931526990128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999965179700742,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.11802673861384391,
|
|
"num_tokens": 2230129.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.3616985321044925,
|
|
"epoch": 0.10207939508506617,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499996349373353,
|
|
"loss": 6.3828,
|
|
"mean_token_accuracy": 0.11236807405948639,
|
|
"num_tokens": 2239929.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.4787780284881595,
|
|
"epoch": 0.10249947490023105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999961767909374,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.11246357783675194,
|
|
"num_tokens": 2248078.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.329130172729492,
|
|
"epoch": 0.10291955471539592,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999960002228303,
|
|
"loss": 6.4464,
|
|
"mean_token_accuracy": 0.11457708552479744,
|
|
"num_tokens": 2256975.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.41359543800354,
|
|
"epoch": 0.1033396345305608,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999958196690349,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.11755945533514023,
|
|
"num_tokens": 2265797.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.318053436279297,
|
|
"epoch": 0.10375971434572569,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999956351295545,
|
|
"loss": 6.407,
|
|
"mean_token_accuracy": 0.12029065862298012,
|
|
"num_tokens": 2274099.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.369567108154297,
|
|
"epoch": 0.10417979416089057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999954466043922,
|
|
"loss": 6.3363,
|
|
"mean_token_accuracy": 0.11501603052020073,
|
|
"num_tokens": 2282360.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.357530832290649,
|
|
"epoch": 0.10459987397605545,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999952540935514,
|
|
"loss": 6.427,
|
|
"mean_token_accuracy": 0.10687654167413711,
|
|
"num_tokens": 2292714.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.4097044467926025,
|
|
"epoch": 0.10501995379122034,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999950575970356,
|
|
"loss": 6.3634,
|
|
"mean_token_accuracy": 0.11621319502592087,
|
|
"num_tokens": 2301633.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.369806289672852,
|
|
"epoch": 0.10544003360638521,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999948571148482,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.12026969790458679,
|
|
"num_tokens": 2310067.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.404969978332519,
|
|
"epoch": 0.10586011342155009,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999946526469927,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.11556015834212303,
|
|
"num_tokens": 2320090.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.372836637496948,
|
|
"epoch": 0.10628019323671498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999944441934728,
|
|
"loss": 6.3703,
|
|
"mean_token_accuracy": 0.1213706873357296,
|
|
"num_tokens": 2329255.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.461856746673584,
|
|
"epoch": 0.10670027305187986,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999942317542922,
|
|
"loss": 6.4648,
|
|
"mean_token_accuracy": 0.11396320164203644,
|
|
"num_tokens": 2339535.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.327042865753174,
|
|
"epoch": 0.10712035286704474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999940153294546,
|
|
"loss": 6.3664,
|
|
"mean_token_accuracy": 0.11329737976193428,
|
|
"num_tokens": 2348948.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.429010534286499,
|
|
"epoch": 0.10754043268220961,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499993794918964,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.11255929544568062,
|
|
"num_tokens": 2359141.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.310593366622925,
|
|
"epoch": 0.1079605124973745,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999935705228241,
|
|
"loss": 6.4541,
|
|
"mean_token_accuracy": 0.11158784702420235,
|
|
"num_tokens": 2368906.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.527987766265869,
|
|
"epoch": 0.10838059231253938,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999933421410389,
|
|
"loss": 6.4033,
|
|
"mean_token_accuracy": 0.11808300763368607,
|
|
"num_tokens": 2377029.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.42291259765625,
|
|
"epoch": 0.10880067212770426,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999931097736125,
|
|
"loss": 6.4774,
|
|
"mean_token_accuracy": 0.11096713319420815,
|
|
"num_tokens": 2387088.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.416878700256348,
|
|
"epoch": 0.10922075194286915,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999928734205492,
|
|
"loss": 6.3793,
|
|
"mean_token_accuracy": 0.11391115635633468,
|
|
"num_tokens": 2395596.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.3132000923156735,
|
|
"epoch": 0.10964083175803403,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999926330818528,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.12021223455667496,
|
|
"num_tokens": 2404506.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.388805866241455,
|
|
"epoch": 0.1100609115731989,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999923887575278,
|
|
"loss": 6.4068,
|
|
"mean_token_accuracy": 0.11463478580117226,
|
|
"num_tokens": 2414342.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.404540014266968,
|
|
"epoch": 0.11048099138836379,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999921404475785,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.11288373470306397,
|
|
"num_tokens": 2423076.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.345643043518066,
|
|
"epoch": 0.11090107120352867,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999918881520093,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.12194343283772469,
|
|
"num_tokens": 2432492.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.29752926826477,
|
|
"epoch": 0.11132115101869355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999916318708246,
|
|
"loss": 6.2719,
|
|
"mean_token_accuracy": 0.12224209308624268,
|
|
"num_tokens": 2441916.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.3799408912658695,
|
|
"epoch": 0.11174123083385844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999913716040291,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.12352623343467713,
|
|
"num_tokens": 2450932.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.248048543930054,
|
|
"epoch": 0.11216131064902331,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999911073516272,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.11721153929829597,
|
|
"num_tokens": 2460058.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.305795478820801,
|
|
"epoch": 0.11258139046418819,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999908391136237,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.11657693609595299,
|
|
"num_tokens": 2469607.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.403741073608399,
|
|
"epoch": 0.11300147027935308,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999905668900234,
|
|
"loss": 6.3338,
|
|
"mean_token_accuracy": 0.11997214257717133,
|
|
"num_tokens": 2478345.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.354722595214843,
|
|
"epoch": 0.11342155009451796,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499990290680831,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.12181988656520844,
|
|
"num_tokens": 2486662.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.314315986633301,
|
|
"epoch": 0.11384162990968284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999900104860516,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.1190257914364338,
|
|
"num_tokens": 2495392.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.396038579940796,
|
|
"epoch": 0.11426170972484773,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999897263056898,
|
|
"loss": 6.4374,
|
|
"mean_token_accuracy": 0.11400101035833358,
|
|
"num_tokens": 2505254.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.415481328964233,
|
|
"epoch": 0.1146817895400126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499989438139751,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.12410487607121468,
|
|
"num_tokens": 2514096.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.27006311416626,
|
|
"epoch": 0.11510186935517748,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999891459882401,
|
|
"loss": 6.2694,
|
|
"mean_token_accuracy": 0.11747925281524658,
|
|
"num_tokens": 2523635.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.264933919906616,
|
|
"epoch": 0.11552194917034236,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999888498511624,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.11789564937353134,
|
|
"num_tokens": 2532528.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.311061573028565,
|
|
"epoch": 0.11594202898550725,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999885497285229,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.1151455245912075,
|
|
"num_tokens": 2541893.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.299208688735962,
|
|
"epoch": 0.11636210880067213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999882456203273,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.12206007465720177,
|
|
"num_tokens": 2551551.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.300058650970459,
|
|
"epoch": 0.11678218861583702,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999879375265806,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.11834143102169037,
|
|
"num_tokens": 2560183.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.282702207565308,
|
|
"epoch": 0.11720226843100189,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999876254472886,
|
|
"loss": 6.1445,
|
|
"mean_token_accuracy": 0.12687626332044602,
|
|
"num_tokens": 2568697.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.272518634796143,
|
|
"epoch": 0.11762234824616677,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999873093824565,
|
|
"loss": 6.3599,
|
|
"mean_token_accuracy": 0.11727140471339226,
|
|
"num_tokens": 2578151.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.458877515792847,
|
|
"epoch": 0.11804242806133165,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999869893320902,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.11793015375733376,
|
|
"num_tokens": 2585901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.321643972396851,
|
|
"epoch": 0.11846250787649654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999866652961952,
|
|
"loss": 6.3084,
|
|
"mean_token_accuracy": 0.11437714174389839,
|
|
"num_tokens": 2595655.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.353274202346801,
|
|
"epoch": 0.11888258769166142,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999863372747773,
|
|
"loss": 6.2695,
|
|
"mean_token_accuracy": 0.11410242393612861,
|
|
"num_tokens": 2604949.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.335246944427491,
|
|
"epoch": 0.11930266750682629,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999860052678423,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.11986073330044747,
|
|
"num_tokens": 2614260.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.268476724624634,
|
|
"epoch": 0.11972274732199117,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999856692753959,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.11452461034059525,
|
|
"num_tokens": 2623740.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.361990165710449,
|
|
"epoch": 0.12014282713715606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999853292974444,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.11876029148697853,
|
|
"num_tokens": 2631998.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.266280698776245,
|
|
"epoch": 0.12056290695232094,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999849853339936,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.12363618090748787,
|
|
"num_tokens": 2641169.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.410887956619263,
|
|
"epoch": 0.12098298676748583,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999846373850497,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.12586963474750518,
|
|
"num_tokens": 2650576.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.177606773376465,
|
|
"epoch": 0.12140306658265071,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999842854506186,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.11797089278697967,
|
|
"num_tokens": 2660817.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.282220935821533,
|
|
"epoch": 0.12182314639781558,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999839295307069,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.1204748846590519,
|
|
"num_tokens": 2669338.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.330542469024659,
|
|
"epoch": 0.12224322621298046,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999835696253206,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.11790118813514709,
|
|
"num_tokens": 2679108.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.36133828163147,
|
|
"epoch": 0.12266330602814535,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999832057344664,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.11782214790582657,
|
|
"num_tokens": 2688126.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.110802221298218,
|
|
"epoch": 0.12308338584331023,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999828378581504,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.1267126329243183,
|
|
"num_tokens": 2697245.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.332847547531128,
|
|
"epoch": 0.12350346565847511,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999824659963793,
|
|
"loss": 6.3012,
|
|
"mean_token_accuracy": 0.12391207665205002,
|
|
"num_tokens": 2705934.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.2204491138458256,
|
|
"epoch": 0.12392354547364,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999820901491598,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.12465188652276993,
|
|
"num_tokens": 2714367.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.265383291244507,
|
|
"epoch": 0.12434362528880487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999817103164983,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.12172888666391372,
|
|
"num_tokens": 2724366.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.282348680496216,
|
|
"epoch": 0.12476370510396975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999813264984017,
|
|
"loss": 6.284,
|
|
"mean_token_accuracy": 0.11969415470957756,
|
|
"num_tokens": 2733980.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.340108251571655,
|
|
"epoch": 0.12518378491913462,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999809386948767,
|
|
"loss": 6.2714,
|
|
"mean_token_accuracy": 0.12543393298983574,
|
|
"num_tokens": 2744013.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.2037091732025145,
|
|
"epoch": 0.12560386473429952,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999805469059302,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.11714137867093086,
|
|
"num_tokens": 2753385.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.296666240692138,
|
|
"epoch": 0.1260239445494644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999801511315693,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.12192152738571167,
|
|
"num_tokens": 2762875.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.284714651107788,
|
|
"epoch": 0.1264440243646293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999797513718007,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.12598440870642663,
|
|
"num_tokens": 2772182.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.161528825759888,
|
|
"epoch": 0.12686410417979416,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999793476266317,
|
|
"loss": 6.2127,
|
|
"mean_token_accuracy": 0.12566941007971763,
|
|
"num_tokens": 2780814.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.568186330795288,
|
|
"epoch": 0.12728418399495905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999789398960695,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.11876541525125503,
|
|
"num_tokens": 2791104.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.092951726913452,
|
|
"epoch": 0.12770426381012392,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999785281801212,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.12290481179952621,
|
|
"num_tokens": 2800081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.291093444824218,
|
|
"epoch": 0.1281243436252888,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499978112478794,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.12357923462986946,
|
|
"num_tokens": 2809096.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.3231532096862795,
|
|
"epoch": 0.1285444234404537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999776927920955,
|
|
"loss": 6.2832,
|
|
"mean_token_accuracy": 0.11848211586475373,
|
|
"num_tokens": 2818857.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.26645565032959,
|
|
"epoch": 0.12896450325561856,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499977269120033,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.11801103353500367,
|
|
"num_tokens": 2829332.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.273476028442383,
|
|
"epoch": 0.12938458307078346,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499976841462614,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.1197669893503189,
|
|
"num_tokens": 2839193.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.308599948883057,
|
|
"epoch": 0.12980466288594833,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499976409819846,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.11774821653962135,
|
|
"num_tokens": 2848535.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.131243658065796,
|
|
"epoch": 0.1302247427011132,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999759741917369,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.12612850666046144,
|
|
"num_tokens": 2858090.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.301682853698731,
|
|
"epoch": 0.1306448225162781,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999755345782941,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.1226440578699112,
|
|
"num_tokens": 2866984.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.184937286376953,
|
|
"epoch": 0.13106490233144297,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999750909795256,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.12440444529056549,
|
|
"num_tokens": 2876550.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.258828830718994,
|
|
"epoch": 0.13148498214660786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999746433954394,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.12188669666647911,
|
|
"num_tokens": 2885782.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.217999792098999,
|
|
"epoch": 0.13190506196177273,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499974191826043,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.1303790420293808,
|
|
"num_tokens": 2894807.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.286883115768433,
|
|
"epoch": 0.1323251417769376,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999737362713448,
|
|
"loss": 6.2503,
|
|
"mean_token_accuracy": 0.12286639586091042,
|
|
"num_tokens": 2904076.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.20257887840271,
|
|
"epoch": 0.1327452215921025,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999732767313527,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.12661461755633355,
|
|
"num_tokens": 2913761.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.346931409835816,
|
|
"epoch": 0.13316530140726737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999728132060746,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.12459043636918068,
|
|
"num_tokens": 2922848.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.276056003570557,
|
|
"epoch": 0.13358538122243227,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999723456955192,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.1242086909711361,
|
|
"num_tokens": 2932718.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.151839303970337,
|
|
"epoch": 0.13400546103759714,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999718741996945,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.12332009747624398,
|
|
"num_tokens": 2942686.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.2299316883087155,
|
|
"epoch": 0.13442554085276204,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499971398718609,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.12265397682785988,
|
|
"num_tokens": 2952096.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.27053918838501,
|
|
"epoch": 0.1348456206679269,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999709192522708,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.12414331436157226,
|
|
"num_tokens": 2960660.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.299257707595825,
|
|
"epoch": 0.13526570048309178,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999704358006887,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.1208350658416748,
|
|
"num_tokens": 2969834.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.205888414382935,
|
|
"epoch": 0.13568578029825668,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999699483638712,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.12345886677503586,
|
|
"num_tokens": 2979023.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.2445619106292725,
|
|
"epoch": 0.13610586011342155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999694569418269,
|
|
"loss": 6.2532,
|
|
"mean_token_accuracy": 0.12339803278446197,
|
|
"num_tokens": 2988083.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.20722599029541,
|
|
"epoch": 0.13652593992858644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999689615345645,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.1274717427790165,
|
|
"num_tokens": 2997240.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.2464118003845215,
|
|
"epoch": 0.1369460197437513,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999684621420928,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.12297938466072082,
|
|
"num_tokens": 3007077.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.293700885772705,
|
|
"epoch": 0.13736609955891618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999679587644205,
|
|
"loss": 6.2787,
|
|
"mean_token_accuracy": 0.1208807609975338,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.17975435256958,
|
|
"epoch": 0.13778617937408108,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999674514015568,
|
|
"loss": 6.2054,
|
|
"mean_token_accuracy": 0.1252801388502121,
|
|
"num_tokens": 3025858.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.2544519901275635,
|
|
"epoch": 0.13820625918924595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999669400535105,
|
|
"loss": 6.1887,
|
|
"mean_token_accuracy": 0.11709433272480965,
|
|
"num_tokens": 3035537.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.045716142654419,
|
|
"epoch": 0.13862633900441085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999664247202907,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.12171815410256386,
|
|
"num_tokens": 3044204.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.264136171340942,
|
|
"epoch": 0.13904641881957572,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999659054019066,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.1242525890469551,
|
|
"num_tokens": 3053111.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.191974449157715,
|
|
"epoch": 0.1394664986347406,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999653820983673,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.12419796586036683,
|
|
"num_tokens": 3062456.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.188469123840332,
|
|
"epoch": 0.13988657844990549,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499964854809682,
|
|
"loss": 6.2114,
|
|
"mean_token_accuracy": 0.12520652115345002,
|
|
"num_tokens": 3071132.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.217535066604614,
|
|
"epoch": 0.14030665826507036,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999643235358602,
|
|
"loss": 6.1733,
|
|
"mean_token_accuracy": 0.12733130380511284,
|
|
"num_tokens": 3080892.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.150455570220947,
|
|
"epoch": 0.14072673808023525,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999637882769112,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.13008806556463243,
|
|
"num_tokens": 3089874.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.232478332519531,
|
|
"epoch": 0.14114681789540012,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999632490328447,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.12480302304029464,
|
|
"num_tokens": 3099535.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.220491170883179,
|
|
"epoch": 0.14156689771056502,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999627058036699,
|
|
"loss": 6.1932,
|
|
"mean_token_accuracy": 0.12512605339288713,
|
|
"num_tokens": 3108772.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.254866027832032,
|
|
"epoch": 0.1419869775257299,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999621585893966,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.11818314492702484,
|
|
"num_tokens": 3118333.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.258799934387207,
|
|
"epoch": 0.14240705734089476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999616073900346,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.1175099603831768,
|
|
"num_tokens": 3127356.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.158872365951538,
|
|
"epoch": 0.14282713715605966,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999610522055935,
|
|
"loss": 6.2288,
|
|
"mean_token_accuracy": 0.12072905600070953,
|
|
"num_tokens": 3136859.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.2665447235107425,
|
|
"epoch": 0.14324721697122453,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999604930360832,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.11907806620001793,
|
|
"num_tokens": 3146607.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.134842443466186,
|
|
"epoch": 0.14366729678638943,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999599298815136,
|
|
"loss": 6.1946,
|
|
"mean_token_accuracy": 0.12945861145853996,
|
|
"num_tokens": 3156327.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.1354063034057615,
|
|
"epoch": 0.1440873766015543,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004999593627418947,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.13011169731616973,
|
|
"num_tokens": 3165559.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.2760594367980955,
|
|
"epoch": 0.14450745641671917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999587916172365,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.11565925851464272,
|
|
"num_tokens": 3173850.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.219358253479004,
|
|
"epoch": 0.14492753623188406,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999582165075492,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.12041235193610192,
|
|
"num_tokens": 3182838.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.098177671432495,
|
|
"epoch": 0.14534761604704893,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999576374128429,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.12102061733603478,
|
|
"num_tokens": 3191692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.281035900115967,
|
|
"epoch": 0.14576769586221383,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999570543331279,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.12320142686367035,
|
|
"num_tokens": 3200069.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.174470567703247,
|
|
"epoch": 0.1461877756773787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999564672684145,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.11924844831228257,
|
|
"num_tokens": 3209653.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.267424774169922,
|
|
"epoch": 0.14660785549254357,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999558762187131,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.1311913624405861,
|
|
"num_tokens": 3218313.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.102459383010864,
|
|
"epoch": 0.14702793530770847,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999552811840342,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.12970734164118766,
|
|
"num_tokens": 3227525.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.164451694488525,
|
|
"epoch": 0.14744801512287334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999546821643884,
|
|
"loss": 6.2098,
|
|
"mean_token_accuracy": 0.12783958092331887,
|
|
"num_tokens": 3237022.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.150622081756592,
|
|
"epoch": 0.14786809493803824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999540791597861,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.1278826355934143,
|
|
"num_tokens": 3246605.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.106969261169434,
|
|
"epoch": 0.1482881747532031,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999534721702383,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.13145939782261848,
|
|
"num_tokens": 3255587.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.141215419769287,
|
|
"epoch": 0.148708254568368,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999528611957553,
|
|
"loss": 6.1666,
|
|
"mean_token_accuracy": 0.1264194056391716,
|
|
"num_tokens": 3265669.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.255412673950195,
|
|
"epoch": 0.14912833438353287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999522462363485,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.13116262778639792,
|
|
"num_tokens": 3275013.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.1518439769744875,
|
|
"epoch": 0.14954841419869774,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999516272920283,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.1255984991788864,
|
|
"num_tokens": 3284723.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.11306095123291,
|
|
"epoch": 0.14996849401386264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499951004362806,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.12718486189842224,
|
|
"num_tokens": 3293860.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.046157026290894,
|
|
"epoch": 0.1503885738290275,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999503774486924,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.1226385310292244,
|
|
"num_tokens": 3303158.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.138220262527466,
|
|
"epoch": 0.1508086536441924,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999497465496987,
|
|
"loss": 6.0637,
|
|
"mean_token_accuracy": 0.12298208549618721,
|
|
"num_tokens": 3313068.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.1492797374725345,
|
|
"epoch": 0.15122873345935728,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499949111665836,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.12638431563973426,
|
|
"num_tokens": 3321885.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.2002543926239015,
|
|
"epoch": 0.15164881327452215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999484727971158,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.12693015187978746,
|
|
"num_tokens": 3330924.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.14166145324707,
|
|
"epoch": 0.15206889308968705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499947829943549,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.12311631590127944,
|
|
"num_tokens": 3340070.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.207650995254516,
|
|
"epoch": 0.15248897290485192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999471831051474,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.13365908414125444,
|
|
"num_tokens": 3349870.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.160492658615112,
|
|
"epoch": 0.1529090527200168,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999465322819222,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.12209457084536553,
|
|
"num_tokens": 3359573.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.222156381607055,
|
|
"epoch": 0.15332913253518168,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999458774738851,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.13460491448640824,
|
|
"num_tokens": 3368577.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.116939735412598,
|
|
"epoch": 0.15374921235034655,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999452186810476,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.13111207485198975,
|
|
"num_tokens": 3377801.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.230794095993042,
|
|
"epoch": 0.15416929216551145,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999445559034214,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.12796897292137147,
|
|
"num_tokens": 3386666.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.314156770706177,
|
|
"epoch": 0.15458937198067632,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999438891410181,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.12008170932531356,
|
|
"num_tokens": 3396086.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.129251384735108,
|
|
"epoch": 0.15500945179584122,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999432183938496,
|
|
"loss": 6.2244,
|
|
"mean_token_accuracy": 0.13115857616066934,
|
|
"num_tokens": 3404894.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.144184207916259,
|
|
"epoch": 0.1554295316110061,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999425436619279,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.12016721740365029,
|
|
"num_tokens": 3414172.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.27680606842041,
|
|
"epoch": 0.15584961142617096,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499941864945265,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.12068818733096123,
|
|
"num_tokens": 3423409.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.115350151062012,
|
|
"epoch": 0.15626969124133586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999411822438726,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.12664692029356955,
|
|
"num_tokens": 3433047.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.1765364646911625,
|
|
"epoch": 0.15668977105650073,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499940495557763,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.12646402716636657,
|
|
"num_tokens": 3442490.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.212595748901367,
|
|
"epoch": 0.15710985087166562,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999398048869485,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.12634197920560836,
|
|
"num_tokens": 3451804.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.19734468460083,
|
|
"epoch": 0.1575299306868305,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499939110231441,
|
|
"loss": 6.1767,
|
|
"mean_token_accuracy": 0.1279009036719799,
|
|
"num_tokens": 3461481.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.233086156845093,
|
|
"epoch": 0.1579500105019954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999384115912531,
|
|
"loss": 6.2344,
|
|
"mean_token_accuracy": 0.12624539732933043,
|
|
"num_tokens": 3471798.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.015159845352173,
|
|
"epoch": 0.15837009031716026,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499937708966397,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.12552440091967582,
|
|
"num_tokens": 3481386.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.193439149856568,
|
|
"epoch": 0.15879017013232513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999370023568853,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.12572901472449302,
|
|
"num_tokens": 3489981.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.112298202514649,
|
|
"epoch": 0.15921024994749003,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999362917627304,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.1290791854262352,
|
|
"num_tokens": 3498551.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.154214668273926,
|
|
"epoch": 0.1596303297626549,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999355771839448,
|
|
"loss": 6.0678,
|
|
"mean_token_accuracy": 0.13199156373739243,
|
|
"num_tokens": 3507921.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.25932993888855,
|
|
"epoch": 0.1600504095778198,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999348586205414,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.12772736102342605,
|
|
"num_tokens": 3517570.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.199037790298462,
|
|
"epoch": 0.16047048939298467,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999341360725327,
|
|
"loss": 6.2333,
|
|
"mean_token_accuracy": 0.12291170060634612,
|
|
"num_tokens": 3526774.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.160675954818726,
|
|
"epoch": 0.16089056920814954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999334095399317,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.13550060987472534,
|
|
"num_tokens": 3535319.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.045867156982422,
|
|
"epoch": 0.16131064902331443,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999326790227512,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.13111512288451194,
|
|
"num_tokens": 3544468.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.046793222427368,
|
|
"epoch": 0.1617307288384793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999319445210041,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.13604443669319152,
|
|
"num_tokens": 3553529.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.111843824386597,
|
|
"epoch": 0.1621508086536442,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999312060347034,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.12906411960721015,
|
|
"num_tokens": 3563053.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.050889587402343,
|
|
"epoch": 0.16257088846880907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999304635638621,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.13277052119374275,
|
|
"num_tokens": 3571877.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.067962026596069,
|
|
"epoch": 0.16299096828397394,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999297171084935,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.1285587027668953,
|
|
"num_tokens": 3581496.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.136378002166748,
|
|
"epoch": 0.16341104809913884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999289666686109,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.12886847257614137,
|
|
"num_tokens": 3590752.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.010327911376953,
|
|
"epoch": 0.1638311279143037,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999282122442274,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.13124383464455605,
|
|
"num_tokens": 3599885.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.264139842987061,
|
|
"epoch": 0.1642512077294686,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999274538353564,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.12521142810583114,
|
|
"num_tokens": 3610039.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.073106908798218,
|
|
"epoch": 0.16467128754463348,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999266914420114,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.12478168606758118,
|
|
"num_tokens": 3619954.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.187624120712281,
|
|
"epoch": 0.16509136735979837,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499925925064206,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.13393656834959983,
|
|
"num_tokens": 3628164.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.205664491653442,
|
|
"epoch": 0.16551144717496324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999251547019535,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.13081590309739113,
|
|
"num_tokens": 3636778.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.189227771759033,
|
|
"epoch": 0.16593152699012811,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999243803552678,
|
|
"loss": 6.1562,
|
|
"mean_token_accuracy": 0.1314916841685772,
|
|
"num_tokens": 3647046.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.080912733078003,
|
|
"epoch": 0.166351606805293,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999236020241625,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.12676682993769645,
|
|
"num_tokens": 3656130.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.122231149673462,
|
|
"epoch": 0.16677168662045788,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999228197086514,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.12139208093285561,
|
|
"num_tokens": 3666145.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.180514907836914,
|
|
"epoch": 0.16719176643562278,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999220334087484,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.12297596782445908,
|
|
"num_tokens": 3676722.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.160478258132935,
|
|
"epoch": 0.16761184625078765,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999212431244673,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.12390567734837532,
|
|
"num_tokens": 3685880.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.056979942321777,
|
|
"epoch": 0.16803192606595252,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999204488558222,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.13338653817772866,
|
|
"num_tokens": 3695167.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.132491636276245,
|
|
"epoch": 0.16845200588111742,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999196506028273,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.12816390842199327,
|
|
"num_tokens": 3703700.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.12127537727356,
|
|
"epoch": 0.1688720856962823,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999188483654965,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.13127523884177209,
|
|
"num_tokens": 3712825.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.0288161277771,
|
|
"epoch": 0.16929216551144718,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999180421438442,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.13027536049485205,
|
|
"num_tokens": 3721807.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.227120208740234,
|
|
"epoch": 0.16971224532661205,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999172319378846,
|
|
"loss": 6.215,
|
|
"mean_token_accuracy": 0.12012537494301796,
|
|
"num_tokens": 3730502.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.142453145980835,
|
|
"epoch": 0.17013232514177692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999164177476319,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.13319698646664618,
|
|
"num_tokens": 3739696.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.983246898651123,
|
|
"epoch": 0.17055240495694182,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999155995731009,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.12937767952680587,
|
|
"num_tokens": 3748675.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.279529285430908,
|
|
"epoch": 0.1709724847721067,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999147774143057,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.12119651660323143,
|
|
"num_tokens": 3757714.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.021195363998413,
|
|
"epoch": 0.1713925645872716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499913951271261,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.13538317754864693,
|
|
"num_tokens": 3767589.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.069708347320557,
|
|
"epoch": 0.17181264440243646,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999131211439816,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.1307745970785618,
|
|
"num_tokens": 3777261.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.199843311309815,
|
|
"epoch": 0.17223272421760136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499912287032482,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.138626891374588,
|
|
"num_tokens": 3786658.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.944658851623535,
|
|
"epoch": 0.17265280403276623,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499911448936777,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.13718581050634385,
|
|
"num_tokens": 3794977.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.036355209350586,
|
|
"epoch": 0.1730728838479311,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999106068568816,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.12767373770475388,
|
|
"num_tokens": 3805138.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.216224002838135,
|
|
"epoch": 0.173492963663096,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999097607928106,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.13682154789566994,
|
|
"num_tokens": 3814444.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.071376657485962,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999089107445788,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.12884577140212058,
|
|
"num_tokens": 3822859.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.008500671386718,
|
|
"epoch": 0.17433312329342576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999080567122016,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.13177087977528573,
|
|
"num_tokens": 3833159.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.108531808853149,
|
|
"epoch": 0.17475320310859063,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999071986956941,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.132802564650774,
|
|
"num_tokens": 3842136.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.1049566745758055,
|
|
"epoch": 0.1751732829237555,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999063366950713,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.12718930542469026,
|
|
"num_tokens": 3851406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.059695482254028,
|
|
"epoch": 0.1755933627389204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999054707103486,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.13101131469011307,
|
|
"num_tokens": 3861061.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.151092004776001,
|
|
"epoch": 0.17601344255408527,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999046007415412,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.12858548611402512,
|
|
"num_tokens": 3870357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.117391204833984,
|
|
"epoch": 0.17643352236925017,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999037267886646,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.1312727876007557,
|
|
"num_tokens": 3879393.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.020799350738526,
|
|
"epoch": 0.17685360218441504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999028488517343,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.1310334399342537,
|
|
"num_tokens": 3888030.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.100592184066772,
|
|
"epoch": 0.1772736819995799,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999019669307659,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.13095394000411034,
|
|
"num_tokens": 3897430.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.128114986419678,
|
|
"epoch": 0.1776937618147448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999010810257749,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.1252062700688839,
|
|
"num_tokens": 3907711.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.000101137161255,
|
|
"epoch": 0.17811384162990967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999001911367771,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.13599146604537965,
|
|
"num_tokens": 3915816.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.115037250518799,
|
|
"epoch": 0.17853392144507457,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998992972637883,
|
|
"loss": 6.1562,
|
|
"mean_token_accuracy": 0.12152478694915772,
|
|
"num_tokens": 3925162.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.161215543746948,
|
|
"epoch": 0.17895400126023944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998983994068242,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.13381896317005157,
|
|
"num_tokens": 3934476.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.025839996337891,
|
|
"epoch": 0.17937408107540434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998974975659006,
|
|
"loss": 6.0854,
|
|
"mean_token_accuracy": 0.1257789060473442,
|
|
"num_tokens": 3943501.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.134726524353027,
|
|
"epoch": 0.1797941608905692,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998965917410338,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.12519558221101762,
|
|
"num_tokens": 3953663.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.026215839385986,
|
|
"epoch": 0.18021424070573408,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998956819322397,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.1311854176223278,
|
|
"num_tokens": 3962634.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.095232534408569,
|
|
"epoch": 0.18063432052089898,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998947681395343,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.13477237224578859,
|
|
"num_tokens": 3972496.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.216877603530884,
|
|
"epoch": 0.18105440033606385,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499893850362934,
|
|
"loss": 6.294,
|
|
"mean_token_accuracy": 0.12388142496347428,
|
|
"num_tokens": 3980724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.148508739471436,
|
|
"epoch": 0.18147448015122875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998929286024548,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.12675963416695596,
|
|
"num_tokens": 3989842.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.089916467666626,
|
|
"epoch": 0.18189455996639362,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998920028581133,
|
|
"loss": 6.0396,
|
|
"mean_token_accuracy": 0.13960086852312087,
|
|
"num_tokens": 3998534.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.071965646743775,
|
|
"epoch": 0.18231463978155849,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998910731299258,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.12839170619845391,
|
|
"num_tokens": 4007677.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.075281476974487,
|
|
"epoch": 0.18273471959672338,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998901394179085,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.1271742030978203,
|
|
"num_tokens": 4016347.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.099024391174316,
|
|
"epoch": 0.18315479941188825,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998892017220784,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.13410005643963813,
|
|
"num_tokens": 4025199.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.039233541488647,
|
|
"epoch": 0.18357487922705315,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998882600424519,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.12497256994247437,
|
|
"num_tokens": 4033933.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.077206420898437,
|
|
"epoch": 0.18399495904221802,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998873143790455,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.14159614518284797,
|
|
"num_tokens": 4042891.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.073574495315552,
|
|
"epoch": 0.1844150388573829,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998863647318763,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.12677306681871414,
|
|
"num_tokens": 4051123.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.040490913391113,
|
|
"epoch": 0.1848351186725478,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998854111009608,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.12666793614625932,
|
|
"num_tokens": 4060025.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.00008749961853,
|
|
"epoch": 0.18525519848771266,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998844534863161,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.12744748294353486,
|
|
"num_tokens": 4069363.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.136739826202392,
|
|
"epoch": 0.18567527830287756,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998834918879592,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.1333842933177948,
|
|
"num_tokens": 4078855.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.1249613761901855,
|
|
"epoch": 0.18609535811804243,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499882526305907,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.1307423233985901,
|
|
"num_tokens": 4087801.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.088332986831665,
|
|
"epoch": 0.18651543793320732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998815567401765,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1286585159599781,
|
|
"num_tokens": 4096949.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.1469251155853275,
|
|
"epoch": 0.1869355177483722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998805831907851,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.13261425495147705,
|
|
"num_tokens": 4105399.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.030412244796753,
|
|
"epoch": 0.18735559756353706,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998796056577501,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.12757696062326432,
|
|
"num_tokens": 4113873.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.031377696990967,
|
|
"epoch": 0.18777567737870196,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998786241410886,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.13365804105997087,
|
|
"num_tokens": 4123528.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.171572303771972,
|
|
"epoch": 0.18819575719386683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499877638640818,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.1285923771560192,
|
|
"num_tokens": 4133370.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.986340188980103,
|
|
"epoch": 0.18861583700903173,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499876649156956,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.13429070338606836,
|
|
"num_tokens": 4142370.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.028431034088134,
|
|
"epoch": 0.1890359168241966,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998756556895196,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.13125480934977532,
|
|
"num_tokens": 4152367.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.113050174713135,
|
|
"epoch": 0.18945599663936147,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499874658238527,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.1346374697983265,
|
|
"num_tokens": 4161126.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.028095388412476,
|
|
"epoch": 0.18987607645452637,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998736568039957,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.13207067623734475,
|
|
"num_tokens": 4169910.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.0694433689117435,
|
|
"epoch": 0.19029615626969124,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998726513859432,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.12696689143776893,
|
|
"num_tokens": 4179893.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.183452177047729,
|
|
"epoch": 0.19071623608485613,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998716419843875,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.1379365175962448,
|
|
"num_tokens": 4190065.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.935803985595703,
|
|
"epoch": 0.191136315900021,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998706285993465,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.13346357494592667,
|
|
"num_tokens": 4198395.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.13513503074646,
|
|
"epoch": 0.19155639571518587,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998696112308381,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.1285228006541729,
|
|
"num_tokens": 4207555.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.988098859786987,
|
|
"epoch": 0.19197647553035077,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998685898788803,
|
|
"loss": 6.0031,
|
|
"mean_token_accuracy": 0.13245714083313942,
|
|
"num_tokens": 4216533.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.156089878082275,
|
|
"epoch": 0.19239655534551564,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998675645434914,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.13477368876338006,
|
|
"num_tokens": 4225575.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.991475677490234,
|
|
"epoch": 0.19281663516068054,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998665352246891,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.1395990490913391,
|
|
"num_tokens": 4234306.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.991662073135376,
|
|
"epoch": 0.1932367149758454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998655019224921,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.13282228037714958,
|
|
"num_tokens": 4243998.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.109613370895386,
|
|
"epoch": 0.19365679479101028,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998644646369185,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.1297495998442173,
|
|
"num_tokens": 4253653.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.980562829971314,
|
|
"epoch": 0.19407687460617518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998634233679865,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.12498517185449601,
|
|
"num_tokens": 4263305.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.036490631103516,
|
|
"epoch": 0.19449695442134005,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499862378115715,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.13776571899652482,
|
|
"num_tokens": 4272212.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.152922439575195,
|
|
"epoch": 0.19491703423650494,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998613288801221,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.12971725761890412,
|
|
"num_tokens": 4281445.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.123716592788696,
|
|
"epoch": 0.1953371140516698,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998602756612267,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.13039504289627074,
|
|
"num_tokens": 4290938.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.004360866546631,
|
|
"epoch": 0.1957571938668347,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998592184590471,
|
|
"loss": 6.0764,
|
|
"mean_token_accuracy": 0.13114980682730676,
|
|
"num_tokens": 4300022.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.995278835296631,
|
|
"epoch": 0.19617727368199958,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998581572736024,
|
|
"loss": 5.9693,
|
|
"mean_token_accuracy": 0.1386754259467125,
|
|
"num_tokens": 4308910.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.990830326080323,
|
|
"epoch": 0.19659735349716445,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998570921049112,
|
|
"loss": 5.964,
|
|
"mean_token_accuracy": 0.13531014919281006,
|
|
"num_tokens": 4317136.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.019982814788818,
|
|
"epoch": 0.19701743331232935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998560229529924,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.13840724304318427,
|
|
"num_tokens": 4326163.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.181583261489868,
|
|
"epoch": 0.19743751312749422,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998549498178649,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.13239141255617143,
|
|
"num_tokens": 4335837.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.1028111457824705,
|
|
"epoch": 0.19785759294265912,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998538726995477,
|
|
"loss": 6.0502,
|
|
"mean_token_accuracy": 0.13465801179409026,
|
|
"num_tokens": 4345108.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.11204948425293,
|
|
"epoch": 0.198277672757824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049985279159806,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.13041200041770934,
|
|
"num_tokens": 4353761.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.025763607025146,
|
|
"epoch": 0.19869775257298886,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998517065134208,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.1321948856115341,
|
|
"num_tokens": 4363244.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.045213079452514,
|
|
"epoch": 0.19911783238815375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998506174456494,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.1313652828335762,
|
|
"num_tokens": 4373034.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.018647909164429,
|
|
"epoch": 0.19953791220331862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998495243947653,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.12499892637133599,
|
|
"num_tokens": 4382554.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.050378942489624,
|
|
"epoch": 0.19995799201848352,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998484273607875,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.13378100991249084,
|
|
"num_tokens": 4391001.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.911934089660645,
|
|
"epoch": 0.2003780718336484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998473263437356,
|
|
"loss": 5.9179,
|
|
"mean_token_accuracy": 0.13600271940231323,
|
|
"num_tokens": 4400632.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.02356653213501,
|
|
"epoch": 0.20079815164881326,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499846221343629,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.12660589516162873,
|
|
"num_tokens": 4409565.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.01599760055542,
|
|
"epoch": 0.20121823146397816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998451123604875,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.13648212924599648,
|
|
"num_tokens": 4418384.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.052209377288818,
|
|
"epoch": 0.20163831127914303,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998439993943306,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.13455061092972756,
|
|
"num_tokens": 4427581.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.126885080337525,
|
|
"epoch": 0.20205839109430793,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998428824451779,
|
|
"loss": 6.0655,
|
|
"mean_token_accuracy": 0.12827305421233176,
|
|
"num_tokens": 4436572.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.031488513946533,
|
|
"epoch": 0.2024784709094728,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998417615130495,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.13068403899669648,
|
|
"num_tokens": 4445230.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.176716995239258,
|
|
"epoch": 0.2028985507246377,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998406365979649,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.13211808502674102,
|
|
"num_tokens": 4454251.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.0446735382080075,
|
|
"epoch": 0.20331863053980256,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998395076999443,
|
|
"loss": 5.9835,
|
|
"mean_token_accuracy": 0.13375458046793937,
|
|
"num_tokens": 4463949.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.100032329559326,
|
|
"epoch": 0.20373871035496743,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998383748190076,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.12677136287093163,
|
|
"num_tokens": 4473373.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.1406354904174805,
|
|
"epoch": 0.20415879017013233,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004998372379551748,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.1297541990876198,
|
|
"num_tokens": 4482303.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.960326719284057,
|
|
"epoch": 0.2045788699852972,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998360971084663,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.13114270120859145,
|
|
"num_tokens": 4491214.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.993530750274658,
|
|
"epoch": 0.2049989498004621,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998349522789019,
|
|
"loss": 5.8971,
|
|
"mean_token_accuracy": 0.13634659722447395,
|
|
"num_tokens": 4500099.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.949355411529541,
|
|
"epoch": 0.20541902961562697,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998338034665021,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.13802963197231294,
|
|
"num_tokens": 4509893.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.010091781616211,
|
|
"epoch": 0.20583910943079184,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998326506712872,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.1345847800374031,
|
|
"num_tokens": 4518606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.054938316345215,
|
|
"epoch": 0.20625918924595674,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998314938932778,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.13336761966347693,
|
|
"num_tokens": 4528392.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.06166090965271,
|
|
"epoch": 0.2066792690611216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998303331324943,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.13653545677661896,
|
|
"num_tokens": 4536983.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.900071907043457,
|
|
"epoch": 0.2070993488762865,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998291683889571,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.14012753888964652,
|
|
"num_tokens": 4544967.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.0055500030517575,
|
|
"epoch": 0.20751942869145137,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499827999662687,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.1313713811337948,
|
|
"num_tokens": 4554646.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.090430212020874,
|
|
"epoch": 0.20793950850661624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998268269537046,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.13576155975461007,
|
|
"num_tokens": 4564040.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.014799499511719,
|
|
"epoch": 0.20835958832178114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998256502620308,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.13742104843258857,
|
|
"num_tokens": 4573758.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.133381319046021,
|
|
"epoch": 0.208779668136946,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998244695876864,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.13331351354718207,
|
|
"num_tokens": 4582097.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.951827907562256,
|
|
"epoch": 0.2091997479521109,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998232849306921,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.13623687997460365,
|
|
"num_tokens": 4590687.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.113849639892578,
|
|
"epoch": 0.20961982776727578,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998220962910693,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.1295908585190773,
|
|
"num_tokens": 4599497.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.004902267456055,
|
|
"epoch": 0.21003990758244068,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998209036688386,
|
|
"loss": 5.9761,
|
|
"mean_token_accuracy": 0.13407944440841674,
|
|
"num_tokens": 4607958.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.0813335418701175,
|
|
"epoch": 0.21045998739760555,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998197070640216,
|
|
"loss": 6.1175,
|
|
"mean_token_accuracy": 0.1263462521135807,
|
|
"num_tokens": 4617515.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.137440729141235,
|
|
"epoch": 0.21088006721277042,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998185064766391,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.1353794366121292,
|
|
"num_tokens": 4627037.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.9435793399810795,
|
|
"epoch": 0.21130014702793531,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998173019067127,
|
|
"loss": 5.9898,
|
|
"mean_token_accuracy": 0.13374351039528848,
|
|
"num_tokens": 4637393.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.990574741363526,
|
|
"epoch": 0.21172022684310018,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998160933542633,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.1225339263677597,
|
|
"num_tokens": 4646832.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.078363418579102,
|
|
"epoch": 0.21214030665826508,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998148808193128,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.1361754283308983,
|
|
"num_tokens": 4655719.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.027440595626831,
|
|
"epoch": 0.21256038647342995,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998136643018823,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.13285491690039636,
|
|
"num_tokens": 4665364.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.0071735858917235,
|
|
"epoch": 0.21298046628859482,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998124438019935,
|
|
"loss": 5.9795,
|
|
"mean_token_accuracy": 0.13230021819472312,
|
|
"num_tokens": 4674760.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.971972846984864,
|
|
"epoch": 0.21340054610375972,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998112193196681,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.1363543339073658,
|
|
"num_tokens": 4683900.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.9554856300354,
|
|
"epoch": 0.2138206259189246,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998099908549277,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.12749610617756843,
|
|
"num_tokens": 4693915.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.917505264282227,
|
|
"epoch": 0.2142407057340895,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499808758407794,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.14476394206285476,
|
|
"num_tokens": 4703102.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.020478820800781,
|
|
"epoch": 0.21466078554925436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998075219782889,
|
|
"loss": 6.0403,
|
|
"mean_token_accuracy": 0.13109349682927132,
|
|
"num_tokens": 4712925.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.050074434280395,
|
|
"epoch": 0.21508086536441923,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998062815664344,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.13155975714325904,
|
|
"num_tokens": 4722641.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.953602123260498,
|
|
"epoch": 0.21550094517958412,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998050371722524,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.12833617106080056,
|
|
"num_tokens": 4732603.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.983808517456055,
|
|
"epoch": 0.215921024994749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998037887957649,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.1358911283314228,
|
|
"num_tokens": 4742644.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.108869409561157,
|
|
"epoch": 0.2163411048099139,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998025364369939,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.1304102584719658,
|
|
"num_tokens": 4751482.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.196333599090576,
|
|
"epoch": 0.21676118462507876,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998012800959619,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.13010098412632942,
|
|
"num_tokens": 4760593.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.040443658828735,
|
|
"epoch": 0.21718126444024366,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998000197726909,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.13714693188667298,
|
|
"num_tokens": 4769294.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.037139892578125,
|
|
"epoch": 0.21760134425540853,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997987554672033,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.1388247735798359,
|
|
"num_tokens": 4779239.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.028454113006592,
|
|
"epoch": 0.2180214240705734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997974871795215,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.1312641680240631,
|
|
"num_tokens": 4788211.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.064166069030762,
|
|
"epoch": 0.2184415038857383,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499796214909668,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.13773878663778305,
|
|
"num_tokens": 4797921.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.0709045886993405,
|
|
"epoch": 0.21886158370090317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997949386576653,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.1314603127539158,
|
|
"num_tokens": 4807772.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.99371829032898,
|
|
"epoch": 0.21928166351606806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499793658423536,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.13455276489257811,
|
|
"num_tokens": 4817999.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.059015130996704,
|
|
"epoch": 0.21970174333123293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997923742073028,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.14437463730573655,
|
|
"num_tokens": 4826679.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.943931245803833,
|
|
"epoch": 0.2201218231463978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997910860089884,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.13589627295732498,
|
|
"num_tokens": 4834998.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.057482719421387,
|
|
"epoch": 0.2205419029615627,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997897938286156,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.13643529042601585,
|
|
"num_tokens": 4843635.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.018534517288208,
|
|
"epoch": 0.22096198277672757,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997884976662075,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.1327926956117153,
|
|
"num_tokens": 4852027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.1170580863952635,
|
|
"epoch": 0.22138206259189247,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997871975217868,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.14027014896273612,
|
|
"num_tokens": 4861244.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.881848526000977,
|
|
"epoch": 0.22180214240705734,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997858933953768,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.13821944668889047,
|
|
"num_tokens": 4869902.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.9110313892364506,
|
|
"epoch": 0.2222222222222222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997845852870004,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.1410742297768593,
|
|
"num_tokens": 4878502.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.945323467254639,
|
|
"epoch": 0.2226423020373871,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997832731966806,
|
|
"loss": 5.9249,
|
|
"mean_token_accuracy": 0.1411375291645527,
|
|
"num_tokens": 4888348.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.97375717163086,
|
|
"epoch": 0.22306238185255198,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997819571244411,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.13679953366518022,
|
|
"num_tokens": 4897302.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.008918142318725,
|
|
"epoch": 0.22348246166771688,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997806370703049,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.13776542693376542,
|
|
"num_tokens": 4907078.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.947820472717285,
|
|
"epoch": 0.22390254148288175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997793130342954,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.13728704303503036,
|
|
"num_tokens": 4917489.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.903385925292969,
|
|
"epoch": 0.22432262129804661,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997779850164363,
|
|
"loss": 5.9513,
|
|
"mean_token_accuracy": 0.1372543305158615,
|
|
"num_tokens": 4927073.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.074141645431519,
|
|
"epoch": 0.2247427011132115,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997766530167508,
|
|
"loss": 6.0449,
|
|
"mean_token_accuracy": 0.13193764314055442,
|
|
"num_tokens": 4935464.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.150123214721679,
|
|
"epoch": 0.22516278092837638,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997753170352627,
|
|
"loss": 6.1293,
|
|
"mean_token_accuracy": 0.13081697300076484,
|
|
"num_tokens": 4944718.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.070659351348877,
|
|
"epoch": 0.22558286074354128,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997739770719955,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.13340400233864785,
|
|
"num_tokens": 4954223.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.978194713592529,
|
|
"epoch": 0.22600294055870615,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499772633126973,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.12924405336380004,
|
|
"num_tokens": 4963371.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.975288677215576,
|
|
"epoch": 0.22642302037387105,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997712852002192,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.1422348402440548,
|
|
"num_tokens": 4972973.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.000183725357056,
|
|
"epoch": 0.22684310018903592,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997699332917578,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.12485837489366532,
|
|
"num_tokens": 4982808.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.124313545227051,
|
|
"epoch": 0.2272631800042008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997685774016127,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.13304658830165864,
|
|
"num_tokens": 4992427.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.108034229278564,
|
|
"epoch": 0.22768325981936569,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499767217529808,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.12314376682043075,
|
|
"num_tokens": 5003562.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.024952030181884,
|
|
"epoch": 0.22810333963453056,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997658536763678,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.13965026810765266,
|
|
"num_tokens": 5013429.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.031959342956543,
|
|
"epoch": 0.22852341944969545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997644858413163,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.1369493454694748,
|
|
"num_tokens": 5022045.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.9200338363647464,
|
|
"epoch": 0.22894349926486032,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997631140246775,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.14441144168376924,
|
|
"num_tokens": 5032260.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.958108282089233,
|
|
"epoch": 0.2293635790800252,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499761738226476,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.1375686287879944,
|
|
"num_tokens": 5041688.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.965337133407592,
|
|
"epoch": 0.2297836588951901,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499760358446736,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.13241190686821938,
|
|
"num_tokens": 5051005.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.077162218093872,
|
|
"epoch": 0.23020373871035496,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499758974685482,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.13544429317116738,
|
|
"num_tokens": 5060084.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.981188869476318,
|
|
"epoch": 0.23062381852551986,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997575869427385,
|
|
"loss": 5.953,
|
|
"mean_token_accuracy": 0.13910676240921022,
|
|
"num_tokens": 5069081.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.978755378723145,
|
|
"epoch": 0.23104389834068473,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049975619521853,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.13454415425658225,
|
|
"num_tokens": 5078597.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.911752319335937,
|
|
"epoch": 0.2314639781558496,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997547995128814,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.13646793067455293,
|
|
"num_tokens": 5087607.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.035622882843017,
|
|
"epoch": 0.2318840579710145,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004997533998258171,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.13701630160212516,
|
|
"num_tokens": 5097412.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.060332536697388,
|
|
"epoch": 0.23230413778617937,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997519961573622,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.1287323147058487,
|
|
"num_tokens": 5105817.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.132694864273072,
|
|
"epoch": 0.23272421760134426,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997505885075414,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.13087237104773522,
|
|
"num_tokens": 5114958.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.002990245819092,
|
|
"epoch": 0.23314429741650913,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997491768763795,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.13458002656698226,
|
|
"num_tokens": 5123728.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.000336790084839,
|
|
"epoch": 0.23356437723167403,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997477612639018,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.12724062129855157,
|
|
"num_tokens": 5134099.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.150645542144775,
|
|
"epoch": 0.2339844570468389,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997463416701332,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.12823428884148597,
|
|
"num_tokens": 5142934.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.973050594329834,
|
|
"epoch": 0.23440453686200377,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997449180950989,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.15188876092433928,
|
|
"num_tokens": 5151835.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.945583391189575,
|
|
"epoch": 0.23482461667716867,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997434905388241,
|
|
"loss": 5.9533,
|
|
"mean_token_accuracy": 0.14123927503824235,
|
|
"num_tokens": 5161136.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.966424179077149,
|
|
"epoch": 0.23524469649233354,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499742059001334,
|
|
"loss": 5.887,
|
|
"mean_token_accuracy": 0.141261176019907,
|
|
"num_tokens": 5170741.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.931414556503296,
|
|
"epoch": 0.23566477630749844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997406234826541,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.14311096221208572,
|
|
"num_tokens": 5180549.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.932320833206177,
|
|
"epoch": 0.2360848561226633,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997391839828098,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.14145613387227057,
|
|
"num_tokens": 5189486.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.9496715545654295,
|
|
"epoch": 0.23650493593782818,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997377405018266,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.1311965249478817,
|
|
"num_tokens": 5198525.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.014245939254761,
|
|
"epoch": 0.23692501575299307,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049973629303973,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.13539923653006553,
|
|
"num_tokens": 5207124.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.944891500473022,
|
|
"epoch": 0.23734509556815794,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997348415965457,
|
|
"loss": 5.85,
|
|
"mean_token_accuracy": 0.1407323271036148,
|
|
"num_tokens": 5216529.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.993428897857666,
|
|
"epoch": 0.23776517538332284,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997333861722995,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.138421493768692,
|
|
"num_tokens": 5225796.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.012037515640259,
|
|
"epoch": 0.2381852551984877,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499731926767017,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.13556732088327408,
|
|
"num_tokens": 5233876.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.9344642639160154,
|
|
"epoch": 0.23860533501365258,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997304633807242,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.12836523801088334,
|
|
"num_tokens": 5244782.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.987623119354248,
|
|
"epoch": 0.23902541482881748,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997289960134468,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.1335374064743519,
|
|
"num_tokens": 5253453.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.978561115264893,
|
|
"epoch": 0.23944549464398235,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997275246652111,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.14111838340759278,
|
|
"num_tokens": 5262355.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.952275371551513,
|
|
"epoch": 0.23986557445914725,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499726049336043,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.1419723652303219,
|
|
"num_tokens": 5271959.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.006475210189819,
|
|
"epoch": 0.24028565427431212,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997245700259686,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.1432231843471527,
|
|
"num_tokens": 5281393.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.981584358215332,
|
|
"epoch": 0.240705734089477,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997230867350141,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.13176842033863068,
|
|
"num_tokens": 5290979.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.072908639907837,
|
|
"epoch": 0.24112581390464188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997215994632059,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.13976021558046342,
|
|
"num_tokens": 5300263.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.99395980834961,
|
|
"epoch": 0.24154589371980675,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997201082105704,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.13117292299866676,
|
|
"num_tokens": 5309522.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.010568284988404,
|
|
"epoch": 0.24196597353497165,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997186129771338,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.13696857616305352,
|
|
"num_tokens": 5319770.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.136290264129639,
|
|
"epoch": 0.24238605335013652,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997171137629226,
|
|
"loss": 6.0295,
|
|
"mean_token_accuracy": 0.1379177153110504,
|
|
"num_tokens": 5328400.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.855829429626465,
|
|
"epoch": 0.24280613316530142,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997156105679636,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.14593008533120155,
|
|
"num_tokens": 5336338.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.898982286453247,
|
|
"epoch": 0.2432262129804663,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997141033922832,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.13418934270739555,
|
|
"num_tokens": 5345391.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.035576057434082,
|
|
"epoch": 0.24364629279563116,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997125922359081,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.13234915360808372,
|
|
"num_tokens": 5354709.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.013994407653809,
|
|
"epoch": 0.24406637261079606,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997110770988652,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.1399741917848587,
|
|
"num_tokens": 5363738.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.9528099536895756,
|
|
"epoch": 0.24448645242596093,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997095579811813,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.13593828454613685,
|
|
"num_tokens": 5373583.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.03057632446289,
|
|
"epoch": 0.24490653224112582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997080348828833,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.1340787522494793,
|
|
"num_tokens": 5383486.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.969451522827148,
|
|
"epoch": 0.2453266120562907,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997065078039981,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.1328844092786312,
|
|
"num_tokens": 5391974.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.031870555877686,
|
|
"epoch": 0.24574669187145556,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997049767445529,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.13087670058012008,
|
|
"num_tokens": 5400882.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.1388874530792235,
|
|
"epoch": 0.24616677168662046,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997034417045746,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.13255189657211303,
|
|
"num_tokens": 5410538.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.891916513442993,
|
|
"epoch": 0.24658685150178533,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997019026840907,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.1406748116016388,
|
|
"num_tokens": 5419406.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.81290192604065,
|
|
"epoch": 0.24700693131695023,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997003596831282,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.13368260413408278,
|
|
"num_tokens": 5428817.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.030734586715698,
|
|
"epoch": 0.2474270111321151,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996988127017145,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.1356920287013054,
|
|
"num_tokens": 5438277.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.991678762435913,
|
|
"epoch": 0.24784709094728,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996972617398772,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.13253712952136992,
|
|
"num_tokens": 5447440.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.990732574462891,
|
|
"epoch": 0.24826717076244487,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996957067976435,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.13873122334480287,
|
|
"num_tokens": 5455988.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.013759565353394,
|
|
"epoch": 0.24868725057760974,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996941478750411,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.13479771465063095,
|
|
"num_tokens": 5464996.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.04653902053833,
|
|
"epoch": 0.24910733039277463,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996925849720975,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.12909941822290422,
|
|
"num_tokens": 5474174.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.1094592094421385,
|
|
"epoch": 0.2495274102079395,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996910180888405,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.14010420814156532,
|
|
"num_tokens": 5482838.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.933987855911255,
|
|
"epoch": 0.2499474900231044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996894472252977,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.13611237108707427,
|
|
"num_tokens": 5491616.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.946248006820679,
|
|
"epoch": 0.25036756983826924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996878723814973,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.13201134279370308,
|
|
"num_tokens": 5500942.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.011964797973633,
|
|
"epoch": 0.25078764965343414,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996862935574667,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.13369757011532785,
|
|
"num_tokens": 5510078.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.91240873336792,
|
|
"epoch": 0.25120772946859904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996847107532342,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.13632848113775253,
|
|
"num_tokens": 5518924.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.007929849624634,
|
|
"epoch": 0.25162780928376394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996831239688277,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.13016238808631897,
|
|
"num_tokens": 5527385.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.906063604354858,
|
|
"epoch": 0.2520478890989288,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996815332042754,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.14219059348106383,
|
|
"num_tokens": 5536781.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2520478890989288,
|
|
"eval_entropy": 5.731865753634434,
|
|
"eval_loss": 5.98077917098999,
|
|
"eval_mean_token_accuracy": 0.14166069063261308,
|
|
"eval_num_tokens": 5536781.0,
|
|
"eval_runtime": 27.289,
|
|
"eval_samples_per_second": 1369.272,
|
|
"eval_steps_per_second": 171.168,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.928550434112549,
|
|
"epoch": 0.2524679689140937,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996799384596054,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.13845922499895097,
|
|
"num_tokens": 5545893.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.047553873062133,
|
|
"epoch": 0.2528880487292586,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996783397348461,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.13133809193968773,
|
|
"num_tokens": 5555818.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.98364634513855,
|
|
"epoch": 0.2533081285444234,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996767370300256,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.13684593588113786,
|
|
"num_tokens": 5565331.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.016663599014282,
|
|
"epoch": 0.2537282083595883,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996751303451724,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.1414400041103363,
|
|
"num_tokens": 5574003.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.934581279754639,
|
|
"epoch": 0.2541482881747532,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996735196803149,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.14427052065730095,
|
|
"num_tokens": 5582517.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.937156009674072,
|
|
"epoch": 0.2545683679899181,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996719050354818,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.1350693427026272,
|
|
"num_tokens": 5591952.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.999459314346313,
|
|
"epoch": 0.25498844780508295,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996702864107015,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.1392418310046196,
|
|
"num_tokens": 5601460.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.104486131668091,
|
|
"epoch": 0.25540852762024785,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996686638060028,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.13465244546532631,
|
|
"num_tokens": 5610776.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.98651351928711,
|
|
"epoch": 0.25582860743541275,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996670372214144,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.1381534829735756,
|
|
"num_tokens": 5619627.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.846577882766724,
|
|
"epoch": 0.2562486872505776,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996654066569651,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.1441572315990925,
|
|
"num_tokens": 5628969.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.9285993576049805,
|
|
"epoch": 0.2566687670657425,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996637721126839,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.13785991445183754,
|
|
"num_tokens": 5638629.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.003174924850464,
|
|
"epoch": 0.2570888468809074,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996621335885996,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.13731449097394943,
|
|
"num_tokens": 5647571.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.987164306640625,
|
|
"epoch": 0.2575089266960722,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004996604910847413,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.14926859214901925,
|
|
"num_tokens": 5656709.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.953637361526489,
|
|
"epoch": 0.2579290065112371,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499658844601138,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.1354634039103985,
|
|
"num_tokens": 5665714.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.097519016265869,
|
|
"epoch": 0.258349086326402,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499657194137819,
|
|
"loss": 6.0234,
|
|
"mean_token_accuracy": 0.13649424612522126,
|
|
"num_tokens": 5675854.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.9704999923706055,
|
|
"epoch": 0.2587691661415669,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996555396948136,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.13540665656328202,
|
|
"num_tokens": 5685690.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.92389030456543,
|
|
"epoch": 0.25918924595673176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996538812721509,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.1428774431347847,
|
|
"num_tokens": 5695766.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.918001127243042,
|
|
"epoch": 0.25960932577189666,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996522188698603,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.13920465260744094,
|
|
"num_tokens": 5704365.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.103138256072998,
|
|
"epoch": 0.26002940558706156,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996505524879714,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13200636729598045,
|
|
"num_tokens": 5713345.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.0067219734191895,
|
|
"epoch": 0.2604494854022264,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996488821265137,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.1430236168205738,
|
|
"num_tokens": 5722907.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.831529951095581,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996472077855166,
|
|
"loss": 5.898,
|
|
"mean_token_accuracy": 0.14116744548082352,
|
|
"num_tokens": 5731589.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.962000036239624,
|
|
"epoch": 0.2612896450325562,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049964552946501,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.13415754735469818,
|
|
"num_tokens": 5739922.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.892115211486816,
|
|
"epoch": 0.2617097248477211,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996438471650235,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.14354836270213128,
|
|
"num_tokens": 5749206.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.935215997695923,
|
|
"epoch": 0.26212980466288593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996421608855869,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.1430413119494915,
|
|
"num_tokens": 5758803.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.921274280548095,
|
|
"epoch": 0.26254988447805083,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996404706267301,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.1340932957828045,
|
|
"num_tokens": 5768368.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.895799207687378,
|
|
"epoch": 0.26296996429321573,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499638776388483,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.14530150592327118,
|
|
"num_tokens": 5776707.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.956259107589721,
|
|
"epoch": 0.26339004410838057,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996370781708757,
|
|
"loss": 5.9872,
|
|
"mean_token_accuracy": 0.13445577397942543,
|
|
"num_tokens": 5787037.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.948802375793457,
|
|
"epoch": 0.26381012392354547,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996353759739382,
|
|
"loss": 5.9353,
|
|
"mean_token_accuracy": 0.14012779742479325,
|
|
"num_tokens": 5796630.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.918614721298217,
|
|
"epoch": 0.26423020373871037,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996336697977007,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.13389407992362976,
|
|
"num_tokens": 5806402.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.899946784973144,
|
|
"epoch": 0.2646502835538752,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996319596421933,
|
|
"loss": 5.8948,
|
|
"mean_token_accuracy": 0.14252272099256516,
|
|
"num_tokens": 5815742.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.881059455871582,
|
|
"epoch": 0.2650703633690401,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996302455074466,
|
|
"loss": 5.9116,
|
|
"mean_token_accuracy": 0.13981909155845643,
|
|
"num_tokens": 5824915.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.034554386138916,
|
|
"epoch": 0.265490443184205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996285273934906,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.13784030005335807,
|
|
"num_tokens": 5834978.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.000072288513183,
|
|
"epoch": 0.2659105229993699,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499626805300356,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.13608634248375892,
|
|
"num_tokens": 5845684.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.076979541778565,
|
|
"epoch": 0.26633060281453474,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996250792280732,
|
|
"loss": 5.9723,
|
|
"mean_token_accuracy": 0.131855096668005,
|
|
"num_tokens": 5854905.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.017704057693481,
|
|
"epoch": 0.26675068262969964,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996233491766727,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.1348758891224861,
|
|
"num_tokens": 5863654.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.958924627304077,
|
|
"epoch": 0.26717076244486454,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996216151461854,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.14263538494706154,
|
|
"num_tokens": 5872442.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.007285785675049,
|
|
"epoch": 0.2675908422600294,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004996198771366417,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.14180114939808847,
|
|
"num_tokens": 5882372.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.762058162689209,
|
|
"epoch": 0.2680109220751943,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996181351480726,
|
|
"loss": 5.7096,
|
|
"mean_token_accuracy": 0.1481250509619713,
|
|
"num_tokens": 5891113.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.856069707870484,
|
|
"epoch": 0.2684310018903592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996163891805089,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.14241180717945098,
|
|
"num_tokens": 5899582.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.006877613067627,
|
|
"epoch": 0.2688510817055241,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996146392339815,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.13792204037308692,
|
|
"num_tokens": 5908938.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.92903504371643,
|
|
"epoch": 0.2692711615206889,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996128853085215,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.14175159782171248,
|
|
"num_tokens": 5918055.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.962112808227539,
|
|
"epoch": 0.2696912413358538,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996111274041598,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.1343413420021534,
|
|
"num_tokens": 5926744.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.949939441680908,
|
|
"epoch": 0.2701113211510187,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996093655209277,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.13674649894237517,
|
|
"num_tokens": 5936521.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.075492525100708,
|
|
"epoch": 0.27053140096618356,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996075996588563,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.1298151694238186,
|
|
"num_tokens": 5945010.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.941525030136108,
|
|
"epoch": 0.27095148078134845,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499605829817977,
|
|
"loss": 5.9212,
|
|
"mean_token_accuracy": 0.13907130137085916,
|
|
"num_tokens": 5953766.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.937248849868775,
|
|
"epoch": 0.27137156059651335,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499604055998321,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.14228671863675119,
|
|
"num_tokens": 5962168.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.887500286102295,
|
|
"epoch": 0.2717916404116782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996022781999198,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.14494396820664407,
|
|
"num_tokens": 5971627.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.927862691879272,
|
|
"epoch": 0.2722117202268431,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499600496422805,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.13576936945319176,
|
|
"num_tokens": 5981775.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.942725610733032,
|
|
"epoch": 0.272631800042008,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499598710667008,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.1394686594605446,
|
|
"num_tokens": 5991097.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.9221861362457275,
|
|
"epoch": 0.2730518798571729,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995969209325604,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.1354317285120487,
|
|
"num_tokens": 5999517.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.942779064178467,
|
|
"epoch": 0.2734719596723377,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995951272194941,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.13176682814955712,
|
|
"num_tokens": 6008545.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.00344705581665,
|
|
"epoch": 0.2738920394875026,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995933295278407,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.13847036063671112,
|
|
"num_tokens": 6017366.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.900600910186768,
|
|
"epoch": 0.2743121193026675,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995915278576321,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.14386921525001525,
|
|
"num_tokens": 6025597.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.0085962295532225,
|
|
"epoch": 0.27473219911783237,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995897222089004,
|
|
"loss": 5.9437,
|
|
"mean_token_accuracy": 0.1424303874373436,
|
|
"num_tokens": 6034239.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.0732769012451175,
|
|
"epoch": 0.27515227893299726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995879125816772,
|
|
"loss": 5.9769,
|
|
"mean_token_accuracy": 0.13496886044740677,
|
|
"num_tokens": 6043837.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.846703004837036,
|
|
"epoch": 0.27557235874816216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995860989759949,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.14464289993047713,
|
|
"num_tokens": 6053217.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.013448190689087,
|
|
"epoch": 0.27599243856332706,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995842813918855,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.141995108127594,
|
|
"num_tokens": 6061553.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.900888109207154,
|
|
"epoch": 0.2764125183784919,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995824598293812,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.14140584841370582,
|
|
"num_tokens": 6070080.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.960742044448852,
|
|
"epoch": 0.2768325981936568,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995806342885142,
|
|
"loss": 5.9653,
|
|
"mean_token_accuracy": 0.14112535640597343,
|
|
"num_tokens": 6078438.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.993828868865966,
|
|
"epoch": 0.2772526780088217,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499578804769317,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.13578373640775682,
|
|
"num_tokens": 6087794.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.002421045303345,
|
|
"epoch": 0.27767275782398654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995769712718218,
|
|
"loss": 5.9684,
|
|
"mean_token_accuracy": 0.13969296216964722,
|
|
"num_tokens": 6096709.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.897220087051392,
|
|
"epoch": 0.27809283763915144,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995751337960613,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.14022547677159308,
|
|
"num_tokens": 6105866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.0129883766174315,
|
|
"epoch": 0.27851291745431633,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995732923420679,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.1446751207113266,
|
|
"num_tokens": 6114882.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.85595121383667,
|
|
"epoch": 0.2789329972694812,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995714469098743,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.1394299313426018,
|
|
"num_tokens": 6123978.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.841559362411499,
|
|
"epoch": 0.2793530770846461,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499569597499513,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.1420348674058914,
|
|
"num_tokens": 6133246.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.949489116668701,
|
|
"epoch": 0.27977315689981097,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995677441110172,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.1390916422009468,
|
|
"num_tokens": 6142865.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.958270597457886,
|
|
"epoch": 0.28019323671497587,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995658867444192,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.13403844311833382,
|
|
"num_tokens": 6152492.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.9247795104980465,
|
|
"epoch": 0.2806133165301407,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995640253997523,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.13453099131584167,
|
|
"num_tokens": 6161953.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.869791507720947,
|
|
"epoch": 0.2810333963453056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995621600770492,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.14543831422924997,
|
|
"num_tokens": 6171467.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.874020433425903,
|
|
"epoch": 0.2814534761604705,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995602907763431,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.1376187428832054,
|
|
"num_tokens": 6180646.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.929383373260498,
|
|
"epoch": 0.28187355597563535,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995584174976672,
|
|
"loss": 5.8713,
|
|
"mean_token_accuracy": 0.1346499465405941,
|
|
"num_tokens": 6189832.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.927767086029053,
|
|
"epoch": 0.28229363579080025,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995565402410544,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.14761848300695418,
|
|
"num_tokens": 6198339.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.892761945724487,
|
|
"epoch": 0.28271371560596514,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995546590065383,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.1422846756875515,
|
|
"num_tokens": 6207564.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.9255454540252686,
|
|
"epoch": 0.28313379542113004,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995527737941518,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.13853738307952881,
|
|
"num_tokens": 6216056.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.896576976776123,
|
|
"epoch": 0.2835538752362949,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004995508846039287,
|
|
"loss": 5.8965,
|
|
"mean_token_accuracy": 0.13626314997673034,
|
|
"num_tokens": 6225573.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.006501722335815,
|
|
"epoch": 0.2839739550514598,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995489914359023,
|
|
"loss": 6.0096,
|
|
"mean_token_accuracy": 0.13380790427327155,
|
|
"num_tokens": 6235057.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.008948469161988,
|
|
"epoch": 0.2843940348666247,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004995470942901061,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.13976462185382843,
|
|
"num_tokens": 6244164.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.019155550003052,
|
|
"epoch": 0.2848141146817895,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004995451931665738,
|
|
"loss": 5.9344,
|
|
"mean_token_accuracy": 0.13991687223315238,
|
|
"num_tokens": 6253095.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.957593202590942,
|
|
"epoch": 0.2852341944969544,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499543288065339,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.13952580690383912,
|
|
"num_tokens": 6261134.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.833978176116943,
|
|
"epoch": 0.2856542743121193,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995413789864354,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.14211501479148864,
|
|
"num_tokens": 6270384.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.952889156341553,
|
|
"epoch": 0.28607435412728416,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995394659298971,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14977512061595916,
|
|
"num_tokens": 6279702.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.889900207519531,
|
|
"epoch": 0.28649443394244906,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995375488957576,
|
|
"loss": 5.8612,
|
|
"mean_token_accuracy": 0.13872572034597397,
|
|
"num_tokens": 6288297.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.9331536293029785,
|
|
"epoch": 0.28691451375761395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499535627884051,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.13464640453457832,
|
|
"num_tokens": 6297288.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.120673799514771,
|
|
"epoch": 0.28733459357277885,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995337028948115,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.13250542506575586,
|
|
"num_tokens": 6306719.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.837868595123291,
|
|
"epoch": 0.2877546733879437,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995317739280731,
|
|
"loss": 5.8018,
|
|
"mean_token_accuracy": 0.14693671017885207,
|
|
"num_tokens": 6316639.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.928999614715576,
|
|
"epoch": 0.2881747532031086,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995298409838699,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.1393180750310421,
|
|
"num_tokens": 6326879.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.877130842208862,
|
|
"epoch": 0.2885948330182735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499527904062236,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.14481945633888244,
|
|
"num_tokens": 6335729.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.915560340881347,
|
|
"epoch": 0.28901491283343833,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995259631632061,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.13230996280908586,
|
|
"num_tokens": 6345154.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.962369394302368,
|
|
"epoch": 0.28943499264860323,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995240182868143,
|
|
"loss": 5.8479,
|
|
"mean_token_accuracy": 0.14117665588855743,
|
|
"num_tokens": 6354309.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.844361209869385,
|
|
"epoch": 0.2898550724637681,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995220694330951,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.14228973686695098,
|
|
"num_tokens": 6363389.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.88813967704773,
|
|
"epoch": 0.290275152278933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995201166020832,
|
|
"loss": 5.8844,
|
|
"mean_token_accuracy": 0.13614363521337508,
|
|
"num_tokens": 6372475.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.972552013397217,
|
|
"epoch": 0.29069523209409787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499518159793813,
|
|
"loss": 5.8329,
|
|
"mean_token_accuracy": 0.14460824504494668,
|
|
"num_tokens": 6380906.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.866478300094604,
|
|
"epoch": 0.29111531190926276,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499516199008319,
|
|
"loss": 5.8563,
|
|
"mean_token_accuracy": 0.14013876989483834,
|
|
"num_tokens": 6390085.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.941966962814331,
|
|
"epoch": 0.29153539172442766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995142342456364,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.13554606810212136,
|
|
"num_tokens": 6399441.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.016114854812622,
|
|
"epoch": 0.2919554715395925,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995122655057997,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.13846278935670853,
|
|
"num_tokens": 6408995.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.820221567153931,
|
|
"epoch": 0.2923755513547574,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995102927888437,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.1459552101790905,
|
|
"num_tokens": 6418080.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.911068105697632,
|
|
"epoch": 0.2927956311699223,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995083160948036,
|
|
"loss": 5.9075,
|
|
"mean_token_accuracy": 0.13615152686834336,
|
|
"num_tokens": 6426732.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.973341417312622,
|
|
"epoch": 0.29321571098508714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995063354237141,
|
|
"loss": 5.9199,
|
|
"mean_token_accuracy": 0.14315774142742158,
|
|
"num_tokens": 6435957.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.914236402511596,
|
|
"epoch": 0.29363579080025204,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004995043507756107,
|
|
"loss": 5.864,
|
|
"mean_token_accuracy": 0.13712269440293312,
|
|
"num_tokens": 6445642.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.931887197494507,
|
|
"epoch": 0.29405587061541694,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995023621505282,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.1387566529214382,
|
|
"num_tokens": 6454664.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.8483740329742435,
|
|
"epoch": 0.29447595043058183,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499500369548502,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.13878127932548523,
|
|
"num_tokens": 6463224.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.101959562301635,
|
|
"epoch": 0.2948960302457467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994983729695674,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.13270595893263817,
|
|
"num_tokens": 6473112.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.9638348579406735,
|
|
"epoch": 0.2953161100609116,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994963724137595,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.14195917025208474,
|
|
"num_tokens": 6482062.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.8792516708374025,
|
|
"epoch": 0.29573618987607647,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004994943678811142,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.13623269721865655,
|
|
"num_tokens": 6490568.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.920031452178955,
|
|
"epoch": 0.2961562696912413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994923593716667,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.1400933049619198,
|
|
"num_tokens": 6500815.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.929981470108032,
|
|
"epoch": 0.2965763495064062,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.1481688842177391,
|
|
"num_tokens": 6509529.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.864474868774414,
|
|
"epoch": 0.2969964293215711,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994883304225077,
|
|
"loss": 5.8729,
|
|
"mean_token_accuracy": 0.13643766716122627,
|
|
"num_tokens": 6517934.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.941485595703125,
|
|
"epoch": 0.297416509136736,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994863099828675,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.13737112134695054,
|
|
"num_tokens": 6526098.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.857544040679931,
|
|
"epoch": 0.29783658895190085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499484285566568,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.13825918808579446,
|
|
"num_tokens": 6535831.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.862282800674438,
|
|
"epoch": 0.29825666876706575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994822571736449,
|
|
"loss": 5.7848,
|
|
"mean_token_accuracy": 0.138202403485775,
|
|
"num_tokens": 6545704.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.923550367355347,
|
|
"epoch": 0.29867674858223064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994802248041342,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.14043487086892129,
|
|
"num_tokens": 6554423.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.915227842330933,
|
|
"epoch": 0.2990968283973955,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499478188458072,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.14151394963264466,
|
|
"num_tokens": 6563989.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.978702878952026,
|
|
"epoch": 0.2995169082125604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004994761481354943,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.1372433789074421,
|
|
"num_tokens": 6572745.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.085881900787354,
|
|
"epoch": 0.2999369880277253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994741038364371,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.1347330242395401,
|
|
"num_tokens": 6581723.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.837055253982544,
|
|
"epoch": 0.3003570678428901,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994720555609369,
|
|
"loss": 5.7255,
|
|
"mean_token_accuracy": 0.14691844433546067,
|
|
"num_tokens": 6590342.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.793679332733154,
|
|
"epoch": 0.300777147658055,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994700033090297,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.14932364374399185,
|
|
"num_tokens": 6599206.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.014719247817993,
|
|
"epoch": 0.3011972274732199,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499467947080752,
|
|
"loss": 6.1117,
|
|
"mean_token_accuracy": 0.1273707590997219,
|
|
"num_tokens": 6608947.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.987322616577148,
|
|
"epoch": 0.3016173072883848,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994658868761402,
|
|
"loss": 5.8883,
|
|
"mean_token_accuracy": 0.14657592847943307,
|
|
"num_tokens": 6618378.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.946252870559692,
|
|
"epoch": 0.30203738710354966,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994638226952307,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.1343943029642105,
|
|
"num_tokens": 6627527.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.973345470428467,
|
|
"epoch": 0.30245746691871456,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994617545380604,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.1394343391060829,
|
|
"num_tokens": 6636964.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.846103811264038,
|
|
"epoch": 0.30287754673387945,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994596824046656,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.14053009524941446,
|
|
"num_tokens": 6646074.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.920796251296997,
|
|
"epoch": 0.3032976265490443,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499457606295083,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.14094351455569268,
|
|
"num_tokens": 6655027.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.804931497573852,
|
|
"epoch": 0.3037177063642092,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994555262093495,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.1544790118932724,
|
|
"num_tokens": 6663747.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.0041478157043455,
|
|
"epoch": 0.3041377861793741,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499453442147502,
|
|
"loss": 6.0113,
|
|
"mean_token_accuracy": 0.13213684484362603,
|
|
"num_tokens": 6672922.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.917838859558105,
|
|
"epoch": 0.304557865994539,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994513541095773,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.14857635647058487,
|
|
"num_tokens": 6682233.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.912606573104858,
|
|
"epoch": 0.30497794580970383,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994492620956126,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.1396655946969986,
|
|
"num_tokens": 6691593.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.919918155670166,
|
|
"epoch": 0.30539802562486873,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994471661056445,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.14072583466768265,
|
|
"num_tokens": 6701318.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.009689807891846,
|
|
"epoch": 0.3058181054400336,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994450661397106,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.1426208183169365,
|
|
"num_tokens": 6710059.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.047525215148926,
|
|
"epoch": 0.30623818525519847,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499442962197848,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.13458139076828957,
|
|
"num_tokens": 6719811.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.868422555923462,
|
|
"epoch": 0.30665826507036337,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004994408542800937,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.14217756688594818,
|
|
"num_tokens": 6728789.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.868635082244873,
|
|
"epoch": 0.30707834488552826,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994387423864855,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.14152047485113145,
|
|
"num_tokens": 6737706.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.855863761901856,
|
|
"epoch": 0.3074984247006931,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994366265170603,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.15381008386611938,
|
|
"num_tokens": 6746861.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.958421134948731,
|
|
"epoch": 0.307918504515858,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994345066718558,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.13055020123720168,
|
|
"num_tokens": 6755242.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.003214979171753,
|
|
"epoch": 0.3083385843310229,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994323828509098,
|
|
"loss": 5.9324,
|
|
"mean_token_accuracy": 0.13040165677666665,
|
|
"num_tokens": 6764549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.916761636734009,
|
|
"epoch": 0.3087586641461878,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994302550542596,
|
|
"loss": 5.9094,
|
|
"mean_token_accuracy": 0.145879103243351,
|
|
"num_tokens": 6774123.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.818877267837524,
|
|
"epoch": 0.30917874396135264,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499428123281943,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.14885310381650924,
|
|
"num_tokens": 6782922.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.8812672138214115,
|
|
"epoch": 0.30959882377651754,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994259875339978,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.13911449760198594,
|
|
"num_tokens": 6792042.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.0224377632141115,
|
|
"epoch": 0.31001890359168244,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994238478104617,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.13841390311717988,
|
|
"num_tokens": 6800994.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.922906446456909,
|
|
"epoch": 0.3104389834068473,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994217041113727,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.14270309880375862,
|
|
"num_tokens": 6809938.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.951845121383667,
|
|
"epoch": 0.3108590632220122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994195564367688,
|
|
"loss": 5.9849,
|
|
"mean_token_accuracy": 0.1360231176018715,
|
|
"num_tokens": 6820289.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.994351577758789,
|
|
"epoch": 0.3112791430371771,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994174047866882,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.14149386510252954,
|
|
"num_tokens": 6830068.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.771749830245971,
|
|
"epoch": 0.3116992228523419,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994152491611686,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.1437979094684124,
|
|
"num_tokens": 6838591.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.865754890441894,
|
|
"epoch": 0.3121193026675068,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994130895602485,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.13915161341428756,
|
|
"num_tokens": 6847796.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.016102695465088,
|
|
"epoch": 0.3125393824826717,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499410925983966,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.14341016113758087,
|
|
"num_tokens": 6856585.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.82035460472107,
|
|
"epoch": 0.3129594622978366,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994087584323596,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.1492151916027069,
|
|
"num_tokens": 6865757.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.874684762954712,
|
|
"epoch": 0.31337954211300145,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994065869054676,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.13963879272341728,
|
|
"num_tokens": 6875371.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.973430156707764,
|
|
"epoch": 0.31379962192816635,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994044114033283,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.1317138932645321,
|
|
"num_tokens": 6884050.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.9677238941192625,
|
|
"epoch": 0.31421970174333125,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994022319259806,
|
|
"loss": 5.8772,
|
|
"mean_token_accuracy": 0.14338692352175714,
|
|
"num_tokens": 6893079.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.878354215621949,
|
|
"epoch": 0.3146397815584961,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994000484734629,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.14075467139482498,
|
|
"num_tokens": 6903100.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.928855514526367,
|
|
"epoch": 0.315059861373661,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993978610458137,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.14158818423748015,
|
|
"num_tokens": 6912164.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.849039506912232,
|
|
"epoch": 0.3154799411888259,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993956696430721,
|
|
"loss": 5.8489,
|
|
"mean_token_accuracy": 0.13852613866329194,
|
|
"num_tokens": 6921183.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.947899580001831,
|
|
"epoch": 0.3159000210039908,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993934742652768,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.13974586948752404,
|
|
"num_tokens": 6931325.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.930049276351928,
|
|
"epoch": 0.3163201008191556,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993912749124665,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.14738105684518815,
|
|
"num_tokens": 6940234.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.850810146331787,
|
|
"epoch": 0.3167401806343205,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993890715846804,
|
|
"loss": 5.9136,
|
|
"mean_token_accuracy": 0.1437673717737198,
|
|
"num_tokens": 6949067.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.959416913986206,
|
|
"epoch": 0.3171602604494854,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993868642819574,
|
|
"loss": 5.8851,
|
|
"mean_token_accuracy": 0.13802511468529702,
|
|
"num_tokens": 6959085.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.905188941955567,
|
|
"epoch": 0.31758034026465026,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993846530043367,
|
|
"loss": 5.9143,
|
|
"mean_token_accuracy": 0.1347965881228447,
|
|
"num_tokens": 6967392.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.903332805633545,
|
|
"epoch": 0.31800042007981516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993824377518574,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.1488291099667549,
|
|
"num_tokens": 6976369.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.983600234985351,
|
|
"epoch": 0.31842049989498006,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993802185245587,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.14806569889187812,
|
|
"num_tokens": 6985889.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.85070834159851,
|
|
"epoch": 0.3188405797101449,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049937799532248,
|
|
"loss": 5.8915,
|
|
"mean_token_accuracy": 0.1322341412305832,
|
|
"num_tokens": 6995396.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.083252477645874,
|
|
"epoch": 0.3192606595253098,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993757681456607,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.13651170060038567,
|
|
"num_tokens": 7004666.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.98352370262146,
|
|
"epoch": 0.3196807393404747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993735369941401,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.13378495275974273,
|
|
"num_tokens": 7014608.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.872314596176148,
|
|
"epoch": 0.3201008191556396,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993713018679579,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.13734248280525208,
|
|
"num_tokens": 7023671.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.887682008743286,
|
|
"epoch": 0.32052089897080444,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993690627671536,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.13631067648530007,
|
|
"num_tokens": 7033786.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.925025987625122,
|
|
"epoch": 0.32094097878596933,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993668196917669,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.14422772228717803,
|
|
"num_tokens": 7042162.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.993115663528442,
|
|
"epoch": 0.32136105860113423,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993645726418375,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.13835487216711045,
|
|
"num_tokens": 7051903.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.828875875473022,
|
|
"epoch": 0.3217811384162991,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993623216174053,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.15191829651594163,
|
|
"num_tokens": 7060229.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.8507789134979244,
|
|
"epoch": 0.32220121823146397,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049936006661851,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.13942239433526993,
|
|
"num_tokens": 7069040.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.9059672355651855,
|
|
"epoch": 0.32262129804662887,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993578076451917,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.1418701082468033,
|
|
"num_tokens": 7078409.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.73867621421814,
|
|
"epoch": 0.32304137786179377,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993555446974903,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.13865280598402024,
|
|
"num_tokens": 7087983.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.833849382400513,
|
|
"epoch": 0.3234614576769586,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000499353277775446,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.14864109456539154,
|
|
"num_tokens": 7097277.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.906425857543946,
|
|
"epoch": 0.3238815374921235,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993510068790989,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.15845565646886825,
|
|
"num_tokens": 7105918.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.729353284835815,
|
|
"epoch": 0.3243016173072884,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993487320084892,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.15123388469219207,
|
|
"num_tokens": 7115049.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.881364727020264,
|
|
"epoch": 0.32472169712245325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993464531636573,
|
|
"loss": 5.848,
|
|
"mean_token_accuracy": 0.1397578552365303,
|
|
"num_tokens": 7124862.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.853383731842041,
|
|
"epoch": 0.32514177693761814,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993441703446435,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.14876592308282852,
|
|
"num_tokens": 7133280.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.926945161819458,
|
|
"epoch": 0.32556185675278304,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993418835514882,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.13614385947585106,
|
|
"num_tokens": 7142446.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.948226881027222,
|
|
"epoch": 0.3259819365679479,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993395927842321,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.1408906787633896,
|
|
"num_tokens": 7152143.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.944639015197754,
|
|
"epoch": 0.3264020163831128,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993372980429155,
|
|
"loss": 5.9314,
|
|
"mean_token_accuracy": 0.13912539780139924,
|
|
"num_tokens": 7162046.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.925892972946167,
|
|
"epoch": 0.3268220961982777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993349993275792,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.141475647687912,
|
|
"num_tokens": 7171557.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.751782655715942,
|
|
"epoch": 0.3272421760134426,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993326966382639,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.14672790616750717,
|
|
"num_tokens": 7180927.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.833934020996094,
|
|
"epoch": 0.3276622558286074,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004993303899750104,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.14524296969175338,
|
|
"num_tokens": 7189552.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.929954242706299,
|
|
"epoch": 0.3280823356437723,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004993280793378595,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.14072833955287933,
|
|
"num_tokens": 7197857.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.886449480056763,
|
|
"epoch": 0.3285024154589372,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993257647268522,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.15043871477246284,
|
|
"num_tokens": 7206785.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.909309577941895,
|
|
"epoch": 0.32892249527410206,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993234461420295,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.13852151483297348,
|
|
"num_tokens": 7216360.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.842478799819946,
|
|
"epoch": 0.32934257508926695,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993211235834326,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.16384934931993483,
|
|
"num_tokens": 7224890.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.758263874053955,
|
|
"epoch": 0.32976265490443185,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993187970511023,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.16684153228998183,
|
|
"num_tokens": 7234442.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.873496627807617,
|
|
"epoch": 0.33018273471959675,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993164665450801,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.14423306286334991,
|
|
"num_tokens": 7244023.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.877293682098388,
|
|
"epoch": 0.3306028145347616,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993141320654072,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.14760554879903792,
|
|
"num_tokens": 7253548.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.862598562240601,
|
|
"epoch": 0.3310228943499265,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499311793612125,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.14365085512399672,
|
|
"num_tokens": 7262962.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.9090534210205075,
|
|
"epoch": 0.3314429741650914,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993094511852748,
|
|
"loss": 5.8412,
|
|
"mean_token_accuracy": 0.1450173959136009,
|
|
"num_tokens": 7272234.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.899152231216431,
|
|
"epoch": 0.33186305398025623,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993071047848983,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.1440458543598652,
|
|
"num_tokens": 7281524.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.8174926280975345,
|
|
"epoch": 0.3322831337954211,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993047544110368,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.1493962250649929,
|
|
"num_tokens": 7289601.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.727307987213135,
|
|
"epoch": 0.332703213610586,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004993024000637321,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15279524326324462,
|
|
"num_tokens": 7298508.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.863152980804443,
|
|
"epoch": 0.33312329342575087,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993000417430259,
|
|
"loss": 5.899,
|
|
"mean_token_accuracy": 0.14116615280508996,
|
|
"num_tokens": 7309065.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.987276601791382,
|
|
"epoch": 0.33354337324091576,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049929767944896,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.14180676117539406,
|
|
"num_tokens": 7319669.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.944264316558838,
|
|
"epoch": 0.33396345305608066,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992953131815761,
|
|
"loss": 5.8675,
|
|
"mean_token_accuracy": 0.14308214634656907,
|
|
"num_tokens": 7328425.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.837700128555298,
|
|
"epoch": 0.33438353287124556,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992929429409164,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1491951271891594,
|
|
"num_tokens": 7337369.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.8214014053344725,
|
|
"epoch": 0.3348036126864104,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992905687270225,
|
|
"loss": 5.8183,
|
|
"mean_token_accuracy": 0.1459653303027153,
|
|
"num_tokens": 7346829.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.947172021865844,
|
|
"epoch": 0.3352236925015753,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992881905399368,
|
|
"loss": 5.8631,
|
|
"mean_token_accuracy": 0.14260231107473373,
|
|
"num_tokens": 7355976.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.880902576446533,
|
|
"epoch": 0.3356437723167402,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992858083797013,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.13988892063498498,
|
|
"num_tokens": 7365210.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.887827444076538,
|
|
"epoch": 0.33606385213190504,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992834222463581,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.1366453118622303,
|
|
"num_tokens": 7374175.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.9429937362670895,
|
|
"epoch": 0.33648393194706994,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992810321399496,
|
|
"loss": 5.9143,
|
|
"mean_token_accuracy": 0.13915260806679725,
|
|
"num_tokens": 7383302.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.919287061691284,
|
|
"epoch": 0.33690401176223483,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992786380605182,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.1387575164437294,
|
|
"num_tokens": 7392746.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.856390810012817,
|
|
"epoch": 0.33732409157739973,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992762400081062,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.1431375488638878,
|
|
"num_tokens": 7401604.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.85037088394165,
|
|
"epoch": 0.3377441713925646,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992738379827559,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.14066973105072975,
|
|
"num_tokens": 7410594.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.8780660152435305,
|
|
"epoch": 0.33816425120772947,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992714319845101,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.15344746708869933,
|
|
"num_tokens": 7418831.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.772813749313355,
|
|
"epoch": 0.33858433102289437,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992690220134116,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.1462782494723797,
|
|
"num_tokens": 7427731.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.971381282806396,
|
|
"epoch": 0.3390044108380592,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992666080695027,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.13779002502560617,
|
|
"num_tokens": 7436447.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.921543741226197,
|
|
"epoch": 0.3394244906532241,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992641901528262,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.14552520364522933,
|
|
"num_tokens": 7445352.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.886599731445313,
|
|
"epoch": 0.339844570468389,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992617682634252,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.14520843252539634,
|
|
"num_tokens": 7454298.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.877497959136963,
|
|
"epoch": 0.34026465028355385,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992593424013424,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.14371060207486153,
|
|
"num_tokens": 7463543.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.891790342330933,
|
|
"epoch": 0.34068473009871875,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992569125666209,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.1396215297281742,
|
|
"num_tokens": 7472701.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.004440689086914,
|
|
"epoch": 0.34110480991388364,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992544787593037,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.13958193585276604,
|
|
"num_tokens": 7481123.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.980106163024902,
|
|
"epoch": 0.34152488972904854,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992520409794338,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.1414543256163597,
|
|
"num_tokens": 7490439.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.900824117660522,
|
|
"epoch": 0.3419449695442134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992495992270544,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.14631813019514084,
|
|
"num_tokens": 7499326.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.891779184341431,
|
|
"epoch": 0.3423650493593783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992471535022089,
|
|
"loss": 5.8633,
|
|
"mean_token_accuracy": 0.14064768627285956,
|
|
"num_tokens": 7509407.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.933660221099854,
|
|
"epoch": 0.3427851291745432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992447038049405,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.14266983717679976,
|
|
"num_tokens": 7518443.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.83581509590149,
|
|
"epoch": 0.343205208989708,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992422501352927,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.14985841438174247,
|
|
"num_tokens": 7527609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.924132442474365,
|
|
"epoch": 0.3436252888048729,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992397924933089,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.13954362720251084,
|
|
"num_tokens": 7536890.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.917565202713012,
|
|
"epoch": 0.3440453686200378,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004992373308790325,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.14937977269291877,
|
|
"num_tokens": 7546509.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.8026703834533695,
|
|
"epoch": 0.3444654484352027,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992348652925074,
|
|
"loss": 5.8363,
|
|
"mean_token_accuracy": 0.14076031297445296,
|
|
"num_tokens": 7555336.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.921528148651123,
|
|
"epoch": 0.34488552825036756,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992323957337771,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.14651144444942474,
|
|
"num_tokens": 7565210.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.882741546630859,
|
|
"epoch": 0.34530560806553245,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992299222028855,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.1487639456987381,
|
|
"num_tokens": 7574516.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.829581546783447,
|
|
"epoch": 0.34572568788069735,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992274446998761,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.15058319717645646,
|
|
"num_tokens": 7583219.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.973264932632446,
|
|
"epoch": 0.3461457676958622,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992249632247929,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.13624709472060204,
|
|
"num_tokens": 7592050.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.926892328262329,
|
|
"epoch": 0.3465658475110271,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992224777776802,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.14514639526605605,
|
|
"num_tokens": 7600718.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.865804290771484,
|
|
"epoch": 0.346985927326192,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992199883585816,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.14894086718559266,
|
|
"num_tokens": 7609191.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.919741106033325,
|
|
"epoch": 0.34740600714135683,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004992174949675413,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.14337126538157463,
|
|
"num_tokens": 7618509.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.859026050567627,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004992149976046037,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.1422334760427475,
|
|
"num_tokens": 7627851.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.82733941078186,
|
|
"epoch": 0.3482461667716866,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004992124962698128,
|
|
"loss": 5.8424,
|
|
"mean_token_accuracy": 0.14138613119721413,
|
|
"num_tokens": 7636748.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.9045960903167725,
|
|
"epoch": 0.3486662465868515,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000499209990963213,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.14405173510313035,
|
|
"num_tokens": 7645436.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.942763233184815,
|
|
"epoch": 0.34908632640201637,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004992074816848487,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.1420220673084259,
|
|
"num_tokens": 7655414.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.806369590759277,
|
|
"epoch": 0.34950640621718126,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004992049684347642,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.1479445531964302,
|
|
"num_tokens": 7664295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.8392486572265625,
|
|
"epoch": 0.34992648603234616,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992024512130042,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.14557857811450958,
|
|
"num_tokens": 7673295.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.829631280899048,
|
|
"epoch": 0.350346565847511,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991999300196132,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.14183629676699638,
|
|
"num_tokens": 7682932.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.967007064819336,
|
|
"epoch": 0.3507666456626759,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991974048546359,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.1410795919597149,
|
|
"num_tokens": 7692105.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.839569425582885,
|
|
"epoch": 0.3511867254778408,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000499194875718117,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.14473577067255974,
|
|
"num_tokens": 7701294.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.905254983901978,
|
|
"epoch": 0.3516068052930057,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004991923426101013,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.13896411135792733,
|
|
"num_tokens": 7710964.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.987090635299682,
|
|
"epoch": 0.35202688510817054,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991898055306337,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.13461354821920396,
|
|
"num_tokens": 7719938.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.921365547180176,
|
|
"epoch": 0.35244696492333544,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991872644797591,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.13835739120841026,
|
|
"num_tokens": 7729129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.872485494613647,
|
|
"epoch": 0.35286704473850034,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991847194575226,
|
|
"loss": 5.8744,
|
|
"mean_token_accuracy": 0.135695618391037,
|
|
"num_tokens": 7738506.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.9815671920776365,
|
|
"epoch": 0.3532871245536652,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004991821704639693,
|
|
"loss": 5.9756,
|
|
"mean_token_accuracy": 0.1382329933345318,
|
|
"num_tokens": 7749320.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.020629215240478,
|
|
"epoch": 0.3537072043688301,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991796174991443,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14441338777542115,
|
|
"num_tokens": 7758735.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.784712409973144,
|
|
"epoch": 0.354127284183995,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991770605630927,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.14566663056612014,
|
|
"num_tokens": 7767556.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.859303379058838,
|
|
"epoch": 0.3545473639991598,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004991744996558599,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.14865762144327163,
|
|
"num_tokens": 7776615.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.8661195755004885,
|
|
"epoch": 0.3549674438143247,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991719347774913,
|
|
"loss": 5.8425,
|
|
"mean_token_accuracy": 0.1501207634806633,
|
|
"num_tokens": 7785288.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.876074028015137,
|
|
"epoch": 0.3553875236294896,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991693659280324,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.14568567126989365,
|
|
"num_tokens": 7794381.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.80495433807373,
|
|
"epoch": 0.3558076034446545,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991667931075284,
|
|
"loss": 5.7286,
|
|
"mean_token_accuracy": 0.14424108862876892,
|
|
"num_tokens": 7803265.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.866269779205322,
|
|
"epoch": 0.35622768325981935,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991642163160252,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.14268068224191666,
|
|
"num_tokens": 7812445.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.940937805175781,
|
|
"epoch": 0.35664776307498425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991616355535684,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.14912385791540145,
|
|
"num_tokens": 7822073.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.912532901763916,
|
|
"epoch": 0.35706784289014915,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991590508202036,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.14509293287992478,
|
|
"num_tokens": 7831193.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.9145135402679445,
|
|
"epoch": 0.357487922705314,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991564621159766,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.1429229497909546,
|
|
"num_tokens": 7840311.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.863569116592407,
|
|
"epoch": 0.3579080025204789,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004991538694409334,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.13731356635689734,
|
|
"num_tokens": 7849622.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.866101455688477,
|
|
"epoch": 0.3583280823356438,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991512727951198,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.14157909527420998,
|
|
"num_tokens": 7859494.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.04155158996582,
|
|
"epoch": 0.3587481621508087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991486721785818,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.13783199936151505,
|
|
"num_tokens": 7868526.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.926672124862671,
|
|
"epoch": 0.3591682419659735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991460675913655,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.145780511200428,
|
|
"num_tokens": 7877631.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.883526086807251,
|
|
"epoch": 0.3595883217811384,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499143459033517,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.14927242919802666,
|
|
"num_tokens": 7886814.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.745771408081055,
|
|
"epoch": 0.3600084015963033,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991408465050825,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.1510879337787628,
|
|
"num_tokens": 7896337.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.832517528533936,
|
|
"epoch": 0.36042848141146816,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991382300061084,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.13439226746559144,
|
|
"num_tokens": 7906071.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.962070560455322,
|
|
"epoch": 0.36084856122663306,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991356095366409,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.14356234297156334,
|
|
"num_tokens": 7915003.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.901134014129639,
|
|
"epoch": 0.36126864104179796,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991329850967266,
|
|
"loss": 5.7553,
|
|
"mean_token_accuracy": 0.14801599234342575,
|
|
"num_tokens": 7924408.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.79054274559021,
|
|
"epoch": 0.3616887208569628,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991303566864118,
|
|
"loss": 5.7258,
|
|
"mean_token_accuracy": 0.14961198195815087,
|
|
"num_tokens": 7934717.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.805612707138062,
|
|
"epoch": 0.3621088006721277,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004991277243057431,
|
|
"loss": 5.7802,
|
|
"mean_token_accuracy": 0.14127594009041786,
|
|
"num_tokens": 7944278.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.852519369125366,
|
|
"epoch": 0.3625288804872926,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991250879547673,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.147132358700037,
|
|
"num_tokens": 7953344.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.814604616165161,
|
|
"epoch": 0.3629489603024575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991224476335309,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.14245626628398894,
|
|
"num_tokens": 7962869.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.943966865539551,
|
|
"epoch": 0.36336904011762233,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991198033420807,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.14347591027617454,
|
|
"num_tokens": 7971981.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.808311653137207,
|
|
"epoch": 0.36378911993278723,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991171550804636,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.14206481873989105,
|
|
"num_tokens": 7980979.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.905320501327514,
|
|
"epoch": 0.36420919974795213,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991145028487266,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.14277459532022477,
|
|
"num_tokens": 7989607.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.837810134887695,
|
|
"epoch": 0.36462927956311697,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991118466469165,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1493909515440464,
|
|
"num_tokens": 7998356.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.851336050033569,
|
|
"epoch": 0.36504935937828187,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991091864750805,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.15024245530366898,
|
|
"num_tokens": 8007596.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.901401472091675,
|
|
"epoch": 0.36546943919344677,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991065223332655,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.14087127447128295,
|
|
"num_tokens": 8016493.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.870211553573609,
|
|
"epoch": 0.36588951900861166,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991038542215191,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.13674163743853568,
|
|
"num_tokens": 8025867.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.875178384780884,
|
|
"epoch": 0.3663095988237765,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991011821398882,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.14893437176942825,
|
|
"num_tokens": 8036251.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.93429970741272,
|
|
"epoch": 0.3667296786389414,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990985060884202,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.14601994007825853,
|
|
"num_tokens": 8045647.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.862146234512329,
|
|
"epoch": 0.3671497584541063,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990958260671627,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.13680800497531892,
|
|
"num_tokens": 8056025.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.831518173217773,
|
|
"epoch": 0.36756983826927114,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004990931420761629,
|
|
"loss": 5.801,
|
|
"mean_token_accuracy": 0.14898931458592415,
|
|
"num_tokens": 8065029.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.986507749557495,
|
|
"epoch": 0.36798991808443604,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990904541154685,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.1577958881855011,
|
|
"num_tokens": 8073249.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.926363086700439,
|
|
"epoch": 0.36840999789960094,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990877621851271,
|
|
"loss": 5.8958,
|
|
"mean_token_accuracy": 0.14099107980728148,
|
|
"num_tokens": 8082039.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.77527756690979,
|
|
"epoch": 0.3688300777147658,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004990850662851863,
|
|
"loss": 5.7314,
|
|
"mean_token_accuracy": 0.14939506947994233,
|
|
"num_tokens": 8090011.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.903356552124023,
|
|
"epoch": 0.3692501575299307,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990823664156941,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1503001019358635,
|
|
"num_tokens": 8099934.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.969454669952393,
|
|
"epoch": 0.3696702373450956,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990796625766981,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.14106032997369766,
|
|
"num_tokens": 8108969.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.791495323181152,
|
|
"epoch": 0.3700903171602605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990769547682462,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.14634729623794557,
|
|
"num_tokens": 8117372.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.0099778175354,
|
|
"epoch": 0.3705103969754253,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990742429903866,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.13980280980467796,
|
|
"num_tokens": 8127108.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.983245754241944,
|
|
"epoch": 0.3709304767905902,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499071527243167,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.13901495784521103,
|
|
"num_tokens": 8137392.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.866679716110229,
|
|
"epoch": 0.3713505566057551,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004990688075266357,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.15010641515254974,
|
|
"num_tokens": 8146257.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.818060064315796,
|
|
"epoch": 0.37177063642091995,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990660838408409,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.14406471997499465,
|
|
"num_tokens": 8154952.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.896796941757202,
|
|
"epoch": 0.37219071623608485,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990633561858308,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.14199803844094278,
|
|
"num_tokens": 8164365.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.897768831253051,
|
|
"epoch": 0.37261079605124975,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990606245616537,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.14310891702771186,
|
|
"num_tokens": 8172614.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.942156267166138,
|
|
"epoch": 0.37303087586641465,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990578889683579,
|
|
"loss": 5.8804,
|
|
"mean_token_accuracy": 0.1399701401591301,
|
|
"num_tokens": 8182445.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.876403188705444,
|
|
"epoch": 0.3734509556815795,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990551494059921,
|
|
"loss": 5.759,
|
|
"mean_token_accuracy": 0.14562231674790382,
|
|
"num_tokens": 8191871.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.910711050033569,
|
|
"epoch": 0.3738710354967444,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990524058746047,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.14722812101244925,
|
|
"num_tokens": 8200658.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.870158910751343,
|
|
"epoch": 0.3742911153119093,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990496583742443,
|
|
"loss": 5.828,
|
|
"mean_token_accuracy": 0.13948734179139138,
|
|
"num_tokens": 8209776.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.8510631084442135,
|
|
"epoch": 0.3747111951270741,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004990469069049596,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.14834618717432022,
|
|
"num_tokens": 8219401.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.841431474685669,
|
|
"epoch": 0.375131274942239,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990441514667993,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.14826851561665536,
|
|
"num_tokens": 8228762.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.943975448608398,
|
|
"epoch": 0.3755513547574039,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990413920598121,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.1469542607665062,
|
|
"num_tokens": 8236612.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.879862689971924,
|
|
"epoch": 0.37597143457256876,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004990386286840471,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.14322375506162643,
|
|
"num_tokens": 8245043.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.000154876708985,
|
|
"epoch": 0.37639151438773366,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990358613395532,
|
|
"loss": 5.9178,
|
|
"mean_token_accuracy": 0.14013071805238725,
|
|
"num_tokens": 8255270.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.975326061248779,
|
|
"epoch": 0.37681159420289856,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004990330900263792,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.13827874809503554,
|
|
"num_tokens": 8264761.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.914210987091065,
|
|
"epoch": 0.37723167401806346,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990303147445745,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.14292607977986335,
|
|
"num_tokens": 8274308.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.824473428726196,
|
|
"epoch": 0.3776517538332283,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990275354941881,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.15530410706996917,
|
|
"num_tokens": 8283323.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.8834668636322025,
|
|
"epoch": 0.3780718336483932,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990247522752694,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.12988803088665007,
|
|
"num_tokens": 8293452.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.955636644363404,
|
|
"epoch": 0.3784919134635581,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990219650878674,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.15242000669240952,
|
|
"num_tokens": 8302941.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.847525358200073,
|
|
"epoch": 0.37891199327872294,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004990191739320318,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.1486208386719227,
|
|
"num_tokens": 8311811.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.740224170684814,
|
|
"epoch": 0.37933207309388783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004990163788078117,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15186312943696975,
|
|
"num_tokens": 8321130.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.8464127540588375,
|
|
"epoch": 0.37975215290905273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004990135797152569,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.1421021416783333,
|
|
"num_tokens": 8330233.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.841711711883545,
|
|
"epoch": 0.3801722327242176,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990107766544169,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.14685214608907698,
|
|
"num_tokens": 8338585.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.820804738998413,
|
|
"epoch": 0.38059231253938247,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004990079696253413,
|
|
"loss": 5.7772,
|
|
"mean_token_accuracy": 0.15359208285808562,
|
|
"num_tokens": 8346618.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.856412267684936,
|
|
"epoch": 0.38101239235454737,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004990051586280799,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.14895081669092178,
|
|
"num_tokens": 8356273.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.84465913772583,
|
|
"epoch": 0.38143247216971227,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990023436626824,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.15021177157759666,
|
|
"num_tokens": 8366668.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.9355755805969235,
|
|
"epoch": 0.3818525519848771,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004989995247291988,
|
|
"loss": 5.8869,
|
|
"mean_token_accuracy": 0.14657219648361205,
|
|
"num_tokens": 8375610.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.892274522781372,
|
|
"epoch": 0.382272631800042,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989967018276789,
|
|
"loss": 5.7508,
|
|
"mean_token_accuracy": 0.14968783855438234,
|
|
"num_tokens": 8384455.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.7833092212677,
|
|
"epoch": 0.3826927116152069,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989938749581727,
|
|
"loss": 5.7971,
|
|
"mean_token_accuracy": 0.14261699542403222,
|
|
"num_tokens": 8393868.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.87280683517456,
|
|
"epoch": 0.38311279143037175,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989910441207305,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.142460335791111,
|
|
"num_tokens": 8402916.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.866139030456543,
|
|
"epoch": 0.38353287124553664,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004989882093154023,
|
|
"loss": 5.7386,
|
|
"mean_token_accuracy": 0.14703422486782075,
|
|
"num_tokens": 8411649.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.867181587219238,
|
|
"epoch": 0.38395295106070154,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989853705422381,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.14120551571249962,
|
|
"num_tokens": 8420393.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.828695583343506,
|
|
"epoch": 0.38437303087586644,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004989825278012886,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.14682712703943251,
|
|
"num_tokens": 8429404.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.838935279846192,
|
|
"epoch": 0.3847931106910313,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000498979681092604,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.1419872298836708,
|
|
"num_tokens": 8438299.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.8123194694519045,
|
|
"epoch": 0.3852131905061962,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004989768304162345,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.14794419556856156,
|
|
"num_tokens": 8447392.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.904961681365966,
|
|
"epoch": 0.3856332703213611,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989739757722308,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.14383739084005356,
|
|
"num_tokens": 8456361.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.8575108528137205,
|
|
"epoch": 0.3860533501365259,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004989711171606436,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.14821998178958892,
|
|
"num_tokens": 8465548.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.868388605117798,
|
|
"epoch": 0.3864734299516908,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989682545815232,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.1475853756070137,
|
|
"num_tokens": 8474454.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.851971101760864,
|
|
"epoch": 0.3868935097668557,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989653880349207,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.14926233142614365,
|
|
"num_tokens": 8482694.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.900271463394165,
|
|
"epoch": 0.38731358958202056,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989625175208864,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.1423931635916233,
|
|
"num_tokens": 8491162.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.7257490158081055,
|
|
"epoch": 0.38773366939718545,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989596430394717,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.15937959849834443,
|
|
"num_tokens": 8500716.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.808234357833863,
|
|
"epoch": 0.38815374921235035,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000498956764590727,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.14701972305774688,
|
|
"num_tokens": 8508871.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.95609483718872,
|
|
"epoch": 0.38857382902751525,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004989538821747037,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.14093246757984162,
|
|
"num_tokens": 8518450.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.905833387374878,
|
|
"epoch": 0.3889939088426801,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989509957914527,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.13851853534579278,
|
|
"num_tokens": 8528238.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.809105253219604,
|
|
"epoch": 0.389413988657845,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989481054410251,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.14374718815088272,
|
|
"num_tokens": 8537587.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.856853580474853,
|
|
"epoch": 0.3898340684730099,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004989452111234721,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.14598365053534507,
|
|
"num_tokens": 8547703.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.896316909790039,
|
|
"epoch": 0.39025414828817473,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000498942312838845,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.14673489332199097,
|
|
"num_tokens": 8557001.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.753481054306031,
|
|
"epoch": 0.3906742281033396,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989394105871952,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.15356985479593277,
|
|
"num_tokens": 8565638.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.9358145236969,
|
|
"epoch": 0.3910943079185045,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498936504368574,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.14542939141392708,
|
|
"num_tokens": 8574428.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.850586032867431,
|
|
"epoch": 0.3915143877336694,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004989335941830329,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.14559997841715813,
|
|
"num_tokens": 8583157.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.788503217697143,
|
|
"epoch": 0.39193446754883426,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989306800306236,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.14149378091096879,
|
|
"num_tokens": 8592382.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.7819007396697994,
|
|
"epoch": 0.39235454736399916,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004989277619113975,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.15354567617177964,
|
|
"num_tokens": 8601058.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.888355016708374,
|
|
"epoch": 0.39277462717916406,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989248398254065,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.1449069932103157,
|
|
"num_tokens": 8609479.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.876518249511719,
|
|
"epoch": 0.3931947069943289,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989219137727021,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.14826752841472626,
|
|
"num_tokens": 8618860.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.84470911026001,
|
|
"epoch": 0.3936147868094938,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004989189837533365,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.14821926057338713,
|
|
"num_tokens": 8627462.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.9267487049102785,
|
|
"epoch": 0.3940348666246587,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989160497673613,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.14269359409809113,
|
|
"num_tokens": 8637569.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.871499490737915,
|
|
"epoch": 0.39445494643982354,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004989131118148286,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.14633206725120546,
|
|
"num_tokens": 8645440.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.8017088890075685,
|
|
"epoch": 0.39487502625498844,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004989101698957904,
|
|
"loss": 5.8682,
|
|
"mean_token_accuracy": 0.14381342753767967,
|
|
"num_tokens": 8655077.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.897370004653931,
|
|
"epoch": 0.39529510607015333,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004989072240102988,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.14655678868293762,
|
|
"num_tokens": 8663126.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.9488218307495115,
|
|
"epoch": 0.39571518588531823,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004989042741584061,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.14519642665982246,
|
|
"num_tokens": 8672386.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.720374536514282,
|
|
"epoch": 0.3961352657004831,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989013203401645,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.14469049870967865,
|
|
"num_tokens": 8681930.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.841011619567871,
|
|
"epoch": 0.396555345515648,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988983625556264,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.14254847168922424,
|
|
"num_tokens": 8690993.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.822189235687256,
|
|
"epoch": 0.39697542533081287,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004988954008048438,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.1459605447947979,
|
|
"num_tokens": 8699497.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.995753383636474,
|
|
"epoch": 0.3973955051459777,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988924350878697,
|
|
"loss": 5.9601,
|
|
"mean_token_accuracy": 0.13361823558807373,
|
|
"num_tokens": 8709274.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.916924142837525,
|
|
"epoch": 0.3978155849611426,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988894654047563,
|
|
"loss": 5.8045,
|
|
"mean_token_accuracy": 0.14044342935085297,
|
|
"num_tokens": 8718158.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.780064105987549,
|
|
"epoch": 0.3982356647763075,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004988864917555562,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.147587950527668,
|
|
"num_tokens": 8727459.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.872677993774414,
|
|
"epoch": 0.3986557445914724,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988835141403224,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.15111552625894548,
|
|
"num_tokens": 8737614.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.793733787536621,
|
|
"epoch": 0.39907582440663725,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988805325591073,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.14995396584272386,
|
|
"num_tokens": 8746799.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.854796743392944,
|
|
"epoch": 0.39949590422180214,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988775470119639,
|
|
"loss": 5.8437,
|
|
"mean_token_accuracy": 0.14196141958236694,
|
|
"num_tokens": 8756555.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.811031866073608,
|
|
"epoch": 0.39991598403696704,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988745574989451,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.14688000455498695,
|
|
"num_tokens": 8765849.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.97343111038208,
|
|
"epoch": 0.4003360638521319,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004988715640201036,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.14007072225213052,
|
|
"num_tokens": 8775713.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.833617496490478,
|
|
"epoch": 0.4007561436672968,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988685665754928,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.14587045535445214,
|
|
"num_tokens": 8784717.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.850550556182862,
|
|
"epoch": 0.4011762234824617,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004988655651651656,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.14603159129619597,
|
|
"num_tokens": 8794388.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.799873685836792,
|
|
"epoch": 0.4015963032976265,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988625597891751,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.1439102217555046,
|
|
"num_tokens": 8802436.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.901528596878052,
|
|
"epoch": 0.4020163831127914,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004988595504475746,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.14495839625597,
|
|
"num_tokens": 8811184.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.891771650314331,
|
|
"epoch": 0.4024364629279563,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988565371404175,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.14259228706359864,
|
|
"num_tokens": 8820525.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.840786600112915,
|
|
"epoch": 0.4028565427431212,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988535198677571,
|
|
"loss": 5.6717,
|
|
"mean_token_accuracy": 0.15582364946603774,
|
|
"num_tokens": 8828928.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.857646703720093,
|
|
"epoch": 0.40327662255828606,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988504986296469,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.1377402052283287,
|
|
"num_tokens": 8838615.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.874919462203979,
|
|
"epoch": 0.40369670237345096,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988474734261404,
|
|
"loss": 5.8723,
|
|
"mean_token_accuracy": 0.1379916787147522,
|
|
"num_tokens": 8848709.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.955801677703858,
|
|
"epoch": 0.40411678218861585,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988444442572911,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.1377601645886898,
|
|
"num_tokens": 8858277.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.8524405002594,
|
|
"epoch": 0.4045368620037807,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004988414111231528,
|
|
"loss": 5.7865,
|
|
"mean_token_accuracy": 0.146932952105999,
|
|
"num_tokens": 8868436.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.81365385055542,
|
|
"epoch": 0.4049569418189456,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498838374023779,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.1458624616265297,
|
|
"num_tokens": 8877740.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.897781801223755,
|
|
"epoch": 0.4053770216341105,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004988353329592239,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.1458469048142433,
|
|
"num_tokens": 8887408.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.865758180618286,
|
|
"epoch": 0.4057971014492754,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004988322879295409,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.13947931975126265,
|
|
"num_tokens": 8897141.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.81132230758667,
|
|
"epoch": 0.40621718126444023,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988292389347844,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.153226038813591,
|
|
"num_tokens": 8905747.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.9674177169799805,
|
|
"epoch": 0.40663726107960513,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498826185975008,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.14231978505849838,
|
|
"num_tokens": 8914926.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.819942045211792,
|
|
"epoch": 0.40705734089477,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004988231290502662,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.14279644340276718,
|
|
"num_tokens": 8923956.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.920290994644165,
|
|
"epoch": 0.40747742070993487,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988200681606127,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.1409930519759655,
|
|
"num_tokens": 8932654.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.8871392726898195,
|
|
"epoch": 0.40789750052509977,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000498817003306102,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15066221207380295,
|
|
"num_tokens": 8941716.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.792912864685059,
|
|
"epoch": 0.40831758034026466,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004988139344867884,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.14440437257289887,
|
|
"num_tokens": 8950377.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.823495244979858,
|
|
"epoch": 0.4087376601554295,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004988108617027261,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.1429793991148472,
|
|
"num_tokens": 8959857.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.811827516555786,
|
|
"epoch": 0.4091577399705944,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004988077849539698,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.14948356971144677,
|
|
"num_tokens": 8968272.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.826247787475586,
|
|
"epoch": 0.4095778197857593,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988047042405736,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.1494896613061428,
|
|
"num_tokens": 8977445.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.932396030426025,
|
|
"epoch": 0.4099978996009242,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004988016195625924,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.13975587710738183,
|
|
"num_tokens": 8987315.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.874420547485352,
|
|
"epoch": 0.41041797941608904,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987985309200807,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.14247876554727554,
|
|
"num_tokens": 8998119.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.734928989410401,
|
|
"epoch": 0.41083805923125394,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987954383130934,
|
|
"loss": 5.7211,
|
|
"mean_token_accuracy": 0.15389348119497298,
|
|
"num_tokens": 9007167.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.831616592407227,
|
|
"epoch": 0.41125813904641884,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498792341741685,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.14183046370744706,
|
|
"num_tokens": 9016690.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.9142228126525875,
|
|
"epoch": 0.4116782188615837,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004987892412059106,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.14799081161618233,
|
|
"num_tokens": 9026117.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.786413145065308,
|
|
"epoch": 0.4120982986767486,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004987861367058251,
|
|
"loss": 5.7333,
|
|
"mean_token_accuracy": 0.14700580313801764,
|
|
"num_tokens": 9035754.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.831767606735229,
|
|
"epoch": 0.4125183784919135,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004987830282414833,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.1511758364737034,
|
|
"num_tokens": 9045453.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.920518159866333,
|
|
"epoch": 0.41293845830707837,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987799158129404,
|
|
"loss": 5.866,
|
|
"mean_token_accuracy": 0.14217546358704566,
|
|
"num_tokens": 9056045.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.811709785461426,
|
|
"epoch": 0.4133585381222432,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004987767994202516,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.14320328831672668,
|
|
"num_tokens": 9065728.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.832678318023682,
|
|
"epoch": 0.4137786179374081,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004987736790634719,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.14474476575851442,
|
|
"num_tokens": 9075522.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.789442873001098,
|
|
"epoch": 0.414198697752573,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987705547426568,
|
|
"loss": 5.7403,
|
|
"mean_token_accuracy": 0.141367207467556,
|
|
"num_tokens": 9084412.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.866390943527222,
|
|
"epoch": 0.41461877756773785,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987674264578615,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.13946182429790496,
|
|
"num_tokens": 9094289.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.853621578216552,
|
|
"epoch": 0.41503885738290275,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987642942091414,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1456735163927078,
|
|
"num_tokens": 9103124.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.831802606582642,
|
|
"epoch": 0.41545893719806765,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987611579965523,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.14086953178048134,
|
|
"num_tokens": 9112794.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.873828983306884,
|
|
"epoch": 0.4158790170132325,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987580178201492,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.1499299481511116,
|
|
"num_tokens": 9122718.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.850664281845093,
|
|
"epoch": 0.4162990968283974,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004987548736799882,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.14340481981635095,
|
|
"num_tokens": 9131855.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.820421504974365,
|
|
"epoch": 0.4167191766435623,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987517255761248,
|
|
"loss": 5.6959,
|
|
"mean_token_accuracy": 0.15145303905010224,
|
|
"num_tokens": 9141102.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.806706857681275,
|
|
"epoch": 0.4171392564587272,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004987485735086148,
|
|
"loss": 5.7767,
|
|
"mean_token_accuracy": 0.14581410586833954,
|
|
"num_tokens": 9150552.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.901687812805176,
|
|
"epoch": 0.417559336273892,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498745417477514,
|
|
"loss": 5.7678,
|
|
"mean_token_accuracy": 0.1465201199054718,
|
|
"num_tokens": 9160105.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.833481121063232,
|
|
"epoch": 0.4179794160890569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987422574828784,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.14697531685233117,
|
|
"num_tokens": 9169367.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.801551008224488,
|
|
"epoch": 0.4183994959042218,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004987390935247639,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.1524960733950138,
|
|
"num_tokens": 9177872.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.88420295715332,
|
|
"epoch": 0.41881957571938666,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987359256032265,
|
|
"loss": 5.842,
|
|
"mean_token_accuracy": 0.13641551584005357,
|
|
"num_tokens": 9187879.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.839552402496338,
|
|
"epoch": 0.41923965553455156,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004987327537183225,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.14583497866988182,
|
|
"num_tokens": 9198281.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.830025053024292,
|
|
"epoch": 0.41965973534971646,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987295778701078,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.1472972884774208,
|
|
"num_tokens": 9207670.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.890192222595215,
|
|
"epoch": 0.42007981516488135,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498726398058639,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.1478295773267746,
|
|
"num_tokens": 9216995.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.86348524093628,
|
|
"epoch": 0.4204998949800462,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987232142839723,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.14336878657341004,
|
|
"num_tokens": 9227330.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.881588125228882,
|
|
"epoch": 0.4209199747952111,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987200265461638,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.15374772921204566,
|
|
"num_tokens": 9236666.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.874930953979492,
|
|
"epoch": 0.421340054610376,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004987168348452705,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.14532062411308289,
|
|
"num_tokens": 9246388.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.783464574813843,
|
|
"epoch": 0.42176013442554083,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987136391813485,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.15355198979377746,
|
|
"num_tokens": 9255239.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.740076160430908,
|
|
"epoch": 0.42218021424070573,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004987104395544547,
|
|
"loss": 5.7036,
|
|
"mean_token_accuracy": 0.14613911658525466,
|
|
"num_tokens": 9264468.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.791272926330566,
|
|
"epoch": 0.42260029405587063,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987072359646455,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.15074100941419602,
|
|
"num_tokens": 9274140.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.844473838806152,
|
|
"epoch": 0.42302037387103547,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004987040284119778,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.14496962279081343,
|
|
"num_tokens": 9283539.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.793737411499023,
|
|
"epoch": 0.42344045368620037,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004987008168965087,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.1446337193250656,
|
|
"num_tokens": 9292664.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.882410097122192,
|
|
"epoch": 0.42386053350136527,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986976014182946,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.14475177749991416,
|
|
"num_tokens": 9302814.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.91447172164917,
|
|
"epoch": 0.42428061331653016,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004986943819773927,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.13993989303708076,
|
|
"num_tokens": 9312654.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.944200277328491,
|
|
"epoch": 0.424700693131695,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00049869115857386,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.13871566727757453,
|
|
"num_tokens": 9322271.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.914797401428222,
|
|
"epoch": 0.4251207729468599,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004986879312077536,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.14315683469176294,
|
|
"num_tokens": 9331341.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.854491138458252,
|
|
"epoch": 0.4255408527620248,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986846998791308,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.1450161539018154,
|
|
"num_tokens": 9339863.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.760708379745483,
|
|
"epoch": 0.42596093257718964,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986814645880485,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.14831122979521752,
|
|
"num_tokens": 9349488.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.763440895080566,
|
|
"epoch": 0.42638101239235454,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986782253345645,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.1446495160460472,
|
|
"num_tokens": 9357977.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.873974847793579,
|
|
"epoch": 0.42680109220751944,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986749821187358,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14651158899068834,
|
|
"num_tokens": 9367449.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.939826440811157,
|
|
"epoch": 0.42722117202268434,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00049867173494062,
|
|
"loss": 5.8443,
|
|
"mean_token_accuracy": 0.14635560363531114,
|
|
"num_tokens": 9377070.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.814030504226684,
|
|
"epoch": 0.4276412518378492,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004986684838002744,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.14356765672564506,
|
|
"num_tokens": 9385881.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.812148237228394,
|
|
"epoch": 0.4280613316530141,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004986652286977569,
|
|
"loss": 5.7935,
|
|
"mean_token_accuracy": 0.14297776967287062,
|
|
"num_tokens": 9395159.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.8577290058135985,
|
|
"epoch": 0.428481411468179,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004986619696331252,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.14707281142473222,
|
|
"num_tokens": 9404590.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.849812984466553,
|
|
"epoch": 0.4289014912833438,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986587066064367,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.15095358043909074,
|
|
"num_tokens": 9414452.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.895452976226807,
|
|
"epoch": 0.4293215710985087,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004986554396177494,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.136289519071579,
|
|
"num_tokens": 9424004.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.892696142196655,
|
|
"epoch": 0.4297416509136736,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004986521686671212,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.1541634440422058,
|
|
"num_tokens": 9433487.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.878170013427734,
|
|
"epoch": 0.43016173072883845,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00049864889375461,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14046706035733222,
|
|
"num_tokens": 9442742.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.880551862716675,
|
|
"epoch": 0.43058181054400335,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986456148802738,
|
|
"loss": 5.8803,
|
|
"mean_token_accuracy": 0.1430477738380432,
|
|
"num_tokens": 9452550.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.947691774368286,
|
|
"epoch": 0.43100189035916825,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004986423320441707,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.13825444877147675,
|
|
"num_tokens": 9461920.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.91607780456543,
|
|
"epoch": 0.43142197017433315,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986390452463588,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.1430374413728714,
|
|
"num_tokens": 9470817.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.730179119110107,
|
|
"epoch": 0.431842049989498,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004986357544868964,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.15054248571395873,
|
|
"num_tokens": 9479936.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.873006772994995,
|
|
"epoch": 0.4322621298046629,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986324597658418,
|
|
"loss": 5.7327,
|
|
"mean_token_accuracy": 0.15253930985927583,
|
|
"num_tokens": 9489818.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.753958749771118,
|
|
"epoch": 0.4326822096198278,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986291610832533,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.1437373712658882,
|
|
"num_tokens": 9499688.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.927468347549438,
|
|
"epoch": 0.4331022894349926,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986258584391892,
|
|
"loss": 5.8034,
|
|
"mean_token_accuracy": 0.14375736117362975,
|
|
"num_tokens": 9509581.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.965673732757568,
|
|
"epoch": 0.4335223692501575,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986225518337084,
|
|
"loss": 5.8699,
|
|
"mean_token_accuracy": 0.14116424545645714,
|
|
"num_tokens": 9518556.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.785204839706421,
|
|
"epoch": 0.4339424490653224,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004986192412668692,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.14554062783718108,
|
|
"num_tokens": 9527612.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.780537843704224,
|
|
"epoch": 0.4343625288804873,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004986159267387302,
|
|
"loss": 5.6635,
|
|
"mean_token_accuracy": 0.15324972867965697,
|
|
"num_tokens": 9535882.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.812596940994263,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004986126082493502,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.15061265081167222,
|
|
"num_tokens": 9544799.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.831722640991211,
|
|
"epoch": 0.43520268851081706,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986092857987881,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.14822531789541243,
|
|
"num_tokens": 9553805.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.813159799575805,
|
|
"epoch": 0.43562276832598196,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004986059593871026,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.14472756162285805,
|
|
"num_tokens": 9563493.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.843486309051514,
|
|
"epoch": 0.4360428481411468,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004986026290143527,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.1416473552584648,
|
|
"num_tokens": 9572297.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.981090354919433,
|
|
"epoch": 0.4364629279563117,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004985992946805973,
|
|
"loss": 5.944,
|
|
"mean_token_accuracy": 0.13955255076289177,
|
|
"num_tokens": 9581967.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.916019868850708,
|
|
"epoch": 0.4368830077714766,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985959563858955,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.14462848305702208,
|
|
"num_tokens": 9590885.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.895185899734497,
|
|
"epoch": 0.43730308758664144,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985926141303066,
|
|
"loss": 5.7664,
|
|
"mean_token_accuracy": 0.14494283646345138,
|
|
"num_tokens": 9599247.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.799692010879516,
|
|
"epoch": 0.43772316740180633,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004985892679138896,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.15228856280446051,
|
|
"num_tokens": 9608296.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.7856512546539305,
|
|
"epoch": 0.43814324721697123,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004985859177367038,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.14503268152475357,
|
|
"num_tokens": 9616734.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.923814201354981,
|
|
"epoch": 0.43856332703213613,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004985825635988087,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.14173559248447418,
|
|
"num_tokens": 9626246.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.93772325515747,
|
|
"epoch": 0.43898340684730097,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004985792055002635,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.14719630777835846,
|
|
"num_tokens": 9634963.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.874487066268921,
|
|
"epoch": 0.43940348666246587,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004985758434411278,
|
|
"loss": 5.7792,
|
|
"mean_token_accuracy": 0.1490402415394783,
|
|
"num_tokens": 9643615.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.830899858474732,
|
|
"epoch": 0.43982356647763077,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004985724774214613,
|
|
"loss": 5.7618,
|
|
"mean_token_accuracy": 0.14308954402804375,
|
|
"num_tokens": 9653306.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.849113464355469,
|
|
"epoch": 0.4402436462927956,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004985691074413233,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.14236897826194764,
|
|
"num_tokens": 9662389.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.755652236938476,
|
|
"epoch": 0.4406637261079605,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985657335007739,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.1460557647049427,
|
|
"num_tokens": 9671183.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.91265082359314,
|
|
"epoch": 0.4410838059231254,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004985623555998725,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.15076574087142944,
|
|
"num_tokens": 9680544.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.915414428710937,
|
|
"epoch": 0.4415038857382903,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004985589737386791,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.14628923386335374,
|
|
"num_tokens": 9690137.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.76580057144165,
|
|
"epoch": 0.44192396555345514,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985555879172535,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.14928821474313736,
|
|
"num_tokens": 9699149.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.85457215309143,
|
|
"epoch": 0.44234404536862004,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498552198135656,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.1479725457727909,
|
|
"num_tokens": 9709308.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.86218228340149,
|
|
"epoch": 0.44276412518378494,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985488043939462,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.14763879179954528,
|
|
"num_tokens": 9718462.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.848517847061157,
|
|
"epoch": 0.4431842049989498,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985454066921846,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.15294953137636186,
|
|
"num_tokens": 9727626.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.697809362411499,
|
|
"epoch": 0.4436042848141147,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985420050304312,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.14653837010264398,
|
|
"num_tokens": 9737091.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.776859283447266,
|
|
"epoch": 0.4440243646292796,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004985385994087462,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.14408197328448297,
|
|
"num_tokens": 9746135.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.90691499710083,
|
|
"epoch": 0.4444444444444444,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985351898271901,
|
|
"loss": 5.6909,
|
|
"mean_token_accuracy": 0.14973507225513458,
|
|
"num_tokens": 9754549.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.90071930885315,
|
|
"epoch": 0.4448645242596093,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004985317762858231,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.1393520101904869,
|
|
"num_tokens": 9764219.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.850748586654663,
|
|
"epoch": 0.4452846040747742,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000498528358784706,
|
|
"loss": 5.6867,
|
|
"mean_token_accuracy": 0.15024393796920776,
|
|
"num_tokens": 9772234.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.805743646621704,
|
|
"epoch": 0.4457046838899391,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000498524937323899,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.1513320118188858,
|
|
"num_tokens": 9781417.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.939965295791626,
|
|
"epoch": 0.44612476370510395,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985215119034628,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.14016103446483613,
|
|
"num_tokens": 9791286.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.8461981296539305,
|
|
"epoch": 0.44654484352026885,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004985180825234582,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.14801667556166648,
|
|
"num_tokens": 9802157.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.973970174789429,
|
|
"epoch": 0.44696492333543375,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985146491839459,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.1345731109380722,
|
|
"num_tokens": 9812646.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.948847103118896,
|
|
"epoch": 0.4473850031505986,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004985112118849865,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.13398924767971038,
|
|
"num_tokens": 9822274.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.782685327529907,
|
|
"epoch": 0.4478050829657635,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985077706266412,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.14450234919786453,
|
|
"num_tokens": 9831337.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.838633728027344,
|
|
"epoch": 0.4482251627809284,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004985043254089708,
|
|
"loss": 5.7708,
|
|
"mean_token_accuracy": 0.1397250510752201,
|
|
"num_tokens": 9840798.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.778713369369507,
|
|
"epoch": 0.44864524259609323,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985008762320364,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.14193158969283104,
|
|
"num_tokens": 9850117.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.850035953521728,
|
|
"epoch": 0.4490653224112581,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498497423095899,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.1520538941025734,
|
|
"num_tokens": 9858227.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.814627599716187,
|
|
"epoch": 0.449485402226423,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984939660006199,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.14539863988757135,
|
|
"num_tokens": 9867157.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.7682719230651855,
|
|
"epoch": 0.4499054820415879,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984905049462602,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.14406744837760926,
|
|
"num_tokens": 9877045.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.952353000640869,
|
|
"epoch": 0.45032556185675277,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984870399328814,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.14134326651692392,
|
|
"num_tokens": 9886637.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.7878330707550045,
|
|
"epoch": 0.45074564167191766,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004984835709605446,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.15287383496761323,
|
|
"num_tokens": 9895601.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.821693420410156,
|
|
"epoch": 0.45116572148708256,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984800980293116,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.14498891532421113,
|
|
"num_tokens": 9904775.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.841092920303344,
|
|
"epoch": 0.4515858013022474,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984766211392435,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.14115200862288474,
|
|
"num_tokens": 9913795.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.857733345031738,
|
|
"epoch": 0.4520058811174123,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004984731402904024,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.15439519211649894,
|
|
"num_tokens": 9922576.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.776189756393433,
|
|
"epoch": 0.4524259609325772,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984696554828496,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.1497255176305771,
|
|
"num_tokens": 9930971.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.789079189300537,
|
|
"epoch": 0.4528460407477421,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984661667166468,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.15051774978637694,
|
|
"num_tokens": 9939628.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.814688301086425,
|
|
"epoch": 0.45326612056290694,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984626739918561,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.15411069244146347,
|
|
"num_tokens": 9948397.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.903667163848877,
|
|
"epoch": 0.45368620037807184,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984591773085391,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.14472548216581343,
|
|
"num_tokens": 9957683.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.878373336791992,
|
|
"epoch": 0.45410628019323673,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004984556766667578,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.14814501702785493,
|
|
"num_tokens": 9966756.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.782114458084107,
|
|
"epoch": 0.4545263600084016,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004984521720665743,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.14963518232107162,
|
|
"num_tokens": 9976000.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.890175533294678,
|
|
"epoch": 0.4549464398235665,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004984486635080507,
|
|
"loss": 5.7788,
|
|
"mean_token_accuracy": 0.14989694356918334,
|
|
"num_tokens": 9985509.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.741406440734863,
|
|
"epoch": 0.45536651963873137,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004984451509912489,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.14937452524900435,
|
|
"num_tokens": 9994342.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.76695761680603,
|
|
"epoch": 0.4557865994538962,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004984416345162315,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.14712392613291742,
|
|
"num_tokens": 10004249.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.824491500854492,
|
|
"epoch": 0.4562066792690611,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984381140830605,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.14771454110741616,
|
|
"num_tokens": 10012430.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.907290077209472,
|
|
"epoch": 0.456626759084226,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984345896917984,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.14652188569307328,
|
|
"num_tokens": 10021434.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.826172637939453,
|
|
"epoch": 0.4570468388993909,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984310613425076,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.1499892771244049,
|
|
"num_tokens": 10030473.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.826717472076416,
|
|
"epoch": 0.45746691871455575,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004984275290352506,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.15438036620616913,
|
|
"num_tokens": 10039057.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.879296159744262,
|
|
"epoch": 0.45788699852972065,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984239927700899,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.14881263822317123,
|
|
"num_tokens": 10047998.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.906938457489014,
|
|
"epoch": 0.45830707834488554,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004984204525470883,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.14349722415208815,
|
|
"num_tokens": 10057479.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.797386360168457,
|
|
"epoch": 0.4587271581600504,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004984169083663084,
|
|
"loss": 5.7284,
|
|
"mean_token_accuracy": 0.14215826913714408,
|
|
"num_tokens": 10067754.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.769140672683716,
|
|
"epoch": 0.4591472379752153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984133602278129,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.14632865488529206,
|
|
"num_tokens": 10076815.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.929787874221802,
|
|
"epoch": 0.4595673177903802,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000498409808131665,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.14295997619628906,
|
|
"num_tokens": 10086300.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.820594406127929,
|
|
"epoch": 0.4599873976055451,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004984062520779272,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.15191168189048768,
|
|
"num_tokens": 10095383.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.724618530273437,
|
|
"epoch": 0.4604074774207099,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984026920666628,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.14800985455513,
|
|
"num_tokens": 10103971.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.801212739944458,
|
|
"epoch": 0.4608275572358748,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983991280979347,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.15083771497011184,
|
|
"num_tokens": 10113028.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.8347760200500485,
|
|
"epoch": 0.4612476370510397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983955601718061,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.14897917956113815,
|
|
"num_tokens": 10121890.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.866452312469482,
|
|
"epoch": 0.46166771686620456,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983919882883401,
|
|
"loss": 5.792,
|
|
"mean_token_accuracy": 0.14483870565891266,
|
|
"num_tokens": 10131655.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.878374290466309,
|
|
"epoch": 0.46208779668136946,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983884124476,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.1475811406970024,
|
|
"num_tokens": 10140778.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.852365493774414,
|
|
"epoch": 0.46250787649653435,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004983848326496494,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.14311327114701272,
|
|
"num_tokens": 10150229.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.915929079055786,
|
|
"epoch": 0.4629279563116992,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983812488945513,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.1459451988339424,
|
|
"num_tokens": 10158939.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.816072797775268,
|
|
"epoch": 0.4633480361268641,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983776611823696,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.1463111788034439,
|
|
"num_tokens": 10168383.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.759098815917969,
|
|
"epoch": 0.463768115942029,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004983740695131676,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.14871828705072404,
|
|
"num_tokens": 10178678.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.8468421459197994,
|
|
"epoch": 0.4641881957571939,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498370473887009,
|
|
"loss": 5.7383,
|
|
"mean_token_accuracy": 0.14837254881858825,
|
|
"num_tokens": 10188964.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.893353366851807,
|
|
"epoch": 0.46460827557235873,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983668743039573,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.15488529577851295,
|
|
"num_tokens": 10198333.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.760245847702026,
|
|
"epoch": 0.46502835538752363,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004983632707640766,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.14777156189084054,
|
|
"num_tokens": 10207876.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.78720121383667,
|
|
"epoch": 0.4654484352026885,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983596632674306,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.15150602906942368,
|
|
"num_tokens": 10216822.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.902374649047852,
|
|
"epoch": 0.46586851501785337,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983560518140831,
|
|
"loss": 5.8282,
|
|
"mean_token_accuracy": 0.13706823736429213,
|
|
"num_tokens": 10226887.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.864826297760009,
|
|
"epoch": 0.46628859483301827,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983524364040982,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.1513754189014435,
|
|
"num_tokens": 10235935.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.801887845993042,
|
|
"epoch": 0.46670867464818316,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983488170375399,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.1499588668346405,
|
|
"num_tokens": 10245590.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.719043874740601,
|
|
"epoch": 0.46712875446334806,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983451937144723,
|
|
"loss": 5.7005,
|
|
"mean_token_accuracy": 0.14591586142778395,
|
|
"num_tokens": 10255104.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.659116125106811,
|
|
"epoch": 0.4675488342785129,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983415664349595,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.15797292441129684,
|
|
"num_tokens": 10264236.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.817941188812256,
|
|
"epoch": 0.4679689140936778,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983379351990659,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.1529952183365822,
|
|
"num_tokens": 10273335.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.723038148880005,
|
|
"epoch": 0.4683889939088427,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983343000068559,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.1551787719130516,
|
|
"num_tokens": 10282206.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.658549833297729,
|
|
"epoch": 0.46880907372400754,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983306608583937,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.1606610283255577,
|
|
"num_tokens": 10290056.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.765953302383423,
|
|
"epoch": 0.46922915353917244,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004983270177537438,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.14721163958311081,
|
|
"num_tokens": 10299726.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.791565895080566,
|
|
"epoch": 0.46964923335433734,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983233706929708,
|
|
"loss": 5.7499,
|
|
"mean_token_accuracy": 0.14841315150260925,
|
|
"num_tokens": 10308696.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.832704639434814,
|
|
"epoch": 0.4700693131695022,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983197196761392,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.14296030402183532,
|
|
"num_tokens": 10317845.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.783017778396607,
|
|
"epoch": 0.4704893929846671,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983160647033139,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1538068726658821,
|
|
"num_tokens": 10326563.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.82874116897583,
|
|
"epoch": 0.470909472799832,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983124057745595,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.14498351216316224,
|
|
"num_tokens": 10335931.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.721787977218628,
|
|
"epoch": 0.47132955261499687,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983087428899408,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.1419524259865284,
|
|
"num_tokens": 10344984.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.79919285774231,
|
|
"epoch": 0.4717496324301617,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004983050760495227,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.1474568262696266,
|
|
"num_tokens": 10353522.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.907325601577758,
|
|
"epoch": 0.4721697122453266,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004983014052533702,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.15104926228523255,
|
|
"num_tokens": 10363527.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.760684251785278,
|
|
"epoch": 0.4725897920604915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982977305015481,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.14723679050803185,
|
|
"num_tokens": 10372040.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.758435773849487,
|
|
"epoch": 0.47300987187565635,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982940517941219,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.14704783335328103,
|
|
"num_tokens": 10381279.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.856901502609253,
|
|
"epoch": 0.47342995169082125,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982903691311564,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.14307899996638299,
|
|
"num_tokens": 10390608.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.73579969406128,
|
|
"epoch": 0.47385003150598615,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982866825127172,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.1558460235595703,
|
|
"num_tokens": 10399851.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.866163825988769,
|
|
"epoch": 0.47427011132115104,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982829919388692,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.1417351670563221,
|
|
"num_tokens": 10410425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.8129795551300045,
|
|
"epoch": 0.4746901911363159,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982792974096781,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.15132275298237802,
|
|
"num_tokens": 10418783.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.84749026298523,
|
|
"epoch": 0.4751102709514808,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498275598925209,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.14057652279734612,
|
|
"num_tokens": 10427360.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.890136814117431,
|
|
"epoch": 0.4755303507666457,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982718964855277,
|
|
"loss": 5.7924,
|
|
"mean_token_accuracy": 0.1445530578494072,
|
|
"num_tokens": 10436613.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.866897964477539,
|
|
"epoch": 0.4759504305818105,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004982681900907,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.14708172976970674,
|
|
"num_tokens": 10445055.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.747807741165161,
|
|
"epoch": 0.4763705103969754,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498264479740791,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.15550965517759324,
|
|
"num_tokens": 10454516.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.870613145828247,
|
|
"epoch": 0.4767905902121403,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982607654358668,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.15260702520608901,
|
|
"num_tokens": 10463771.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.8192380428314205,
|
|
"epoch": 0.47721067002730516,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000498257047175993,
|
|
"loss": 5.7218,
|
|
"mean_token_accuracy": 0.1428370013833046,
|
|
"num_tokens": 10473783.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.814655399322509,
|
|
"epoch": 0.47763074984247006,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004982533249612357,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.14914624020457268,
|
|
"num_tokens": 10483424.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.733596324920654,
|
|
"epoch": 0.47805082965763496,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004982495987916607,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.15583412498235702,
|
|
"num_tokens": 10492536.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.762752342224121,
|
|
"epoch": 0.47847090947279985,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982458686673339,
|
|
"loss": 5.7437,
|
|
"mean_token_accuracy": 0.14716439545154572,
|
|
"num_tokens": 10501616.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.899823999404907,
|
|
"epoch": 0.4788909892879647,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982421345883217,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.14301676750183107,
|
|
"num_tokens": 10511190.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.779811668395996,
|
|
"epoch": 0.4793110691031296,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004982383965546898,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.14420118555426598,
|
|
"num_tokens": 10520310.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.831453895568847,
|
|
"epoch": 0.4797311489182945,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982346545665048,
|
|
"loss": 5.6901,
|
|
"mean_token_accuracy": 0.15481160432100297,
|
|
"num_tokens": 10528711.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.8021493434906,
|
|
"epoch": 0.48015122873345933,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982309086238328,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.1420671336352825,
|
|
"num_tokens": 10538484.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.836937665939331,
|
|
"epoch": 0.48057130854862423,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982271587267403,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.1457110583782196,
|
|
"num_tokens": 10547623.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.850609970092774,
|
|
"epoch": 0.48099138836378913,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004982234048752935,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.14635915756225587,
|
|
"num_tokens": 10556234.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.8946315288543705,
|
|
"epoch": 0.481411468178954,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498219647069559,
|
|
"loss": 5.8951,
|
|
"mean_token_accuracy": 0.13762107565999032,
|
|
"num_tokens": 10566308.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.863095760345459,
|
|
"epoch": 0.48183154799411887,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004982158853096035,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.13780406042933463,
|
|
"num_tokens": 10575212.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.846006250381469,
|
|
"epoch": 0.48225162780928377,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982121195954935,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.1565147191286087,
|
|
"num_tokens": 10584590.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.7412327289581295,
|
|
"epoch": 0.48267170762444866,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004982083499272957,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.14907400235533713,
|
|
"num_tokens": 10593997.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.807267189025879,
|
|
"epoch": 0.4830917874396135,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982045763050768,
|
|
"loss": 5.8041,
|
|
"mean_token_accuracy": 0.1457974396646023,
|
|
"num_tokens": 10603299.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.819139719009399,
|
|
"epoch": 0.4835118672547784,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004982007987289041,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.14838966429233552,
|
|
"num_tokens": 10613546.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.766327381134033,
|
|
"epoch": 0.4839319470699433,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004981970171988439,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.15573283806443214,
|
|
"num_tokens": 10622966.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.8138025283813475,
|
|
"epoch": 0.48435202688510814,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004981932317149636,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.14435389563441275,
|
|
"num_tokens": 10633441.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.843524694442749,
|
|
"epoch": 0.48477210670027304,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00049818944227733,
|
|
"loss": 5.7587,
|
|
"mean_token_accuracy": 0.14196690768003464,
|
|
"num_tokens": 10643124.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.8232954978942875,
|
|
"epoch": 0.48519218651543794,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004981856488860105,
|
|
"loss": 5.7342,
|
|
"mean_token_accuracy": 0.14407299906015397,
|
|
"num_tokens": 10652517.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.807135486602784,
|
|
"epoch": 0.48561226633060284,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981818515410721,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.1420580416917801,
|
|
"num_tokens": 10663352.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.849091625213623,
|
|
"epoch": 0.4860323461457677,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004981780502425821,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.14775322377681732,
|
|
"num_tokens": 10672430.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.835392618179322,
|
|
"epoch": 0.4864524259609326,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004981742449906079,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.1527121603488922,
|
|
"num_tokens": 10681908.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.863359975814819,
|
|
"epoch": 0.4868725057760975,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981704357852168,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.14731571227312087,
|
|
"num_tokens": 10691259.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.765371608734131,
|
|
"epoch": 0.4872925855912623,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981666226264764,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.14454422146081924,
|
|
"num_tokens": 10699668.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.800967359542847,
|
|
"epoch": 0.4877126654064272,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981628055144542,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.15341386646032334,
|
|
"num_tokens": 10709146.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.810514068603515,
|
|
"epoch": 0.4881327452215921,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004981589844492177,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.14522838592529297,
|
|
"num_tokens": 10718724.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.761872911453247,
|
|
"epoch": 0.488552825036757,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004981551594308349,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.147171813249588,
|
|
"num_tokens": 10728101.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.862204074859619,
|
|
"epoch": 0.48897290485192185,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981513304593733,
|
|
"loss": 5.7442,
|
|
"mean_token_accuracy": 0.15811584144830704,
|
|
"num_tokens": 10736750.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.867376232147217,
|
|
"epoch": 0.48939298466708675,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004981474975349006,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.1416974514722824,
|
|
"num_tokens": 10746914.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.859874296188354,
|
|
"epoch": 0.48981306448225165,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000498143660657485,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.1483662724494934,
|
|
"num_tokens": 10755786.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.708901691436767,
|
|
"epoch": 0.4902331442974165,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981398198271944,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.15774477571249007,
|
|
"num_tokens": 10764821.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.774704790115356,
|
|
"epoch": 0.4906532241125814,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004981359750440968,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.1461211383342743,
|
|
"num_tokens": 10773569.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.725243186950683,
|
|
"epoch": 0.4910733039277463,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004981321263082603,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.1431654214859009,
|
|
"num_tokens": 10782298.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.738628387451172,
|
|
"epoch": 0.4914933837429111,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498128273619753,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.14975926280021667,
|
|
"num_tokens": 10792087.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.819939708709716,
|
|
"epoch": 0.491913463558076,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004981244169786433,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.14303557947278023,
|
|
"num_tokens": 10801641.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.9354065418243405,
|
|
"epoch": 0.4923335433732409,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981205563849994,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.14316534698009492,
|
|
"num_tokens": 10811612.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.813403034210205,
|
|
"epoch": 0.4927536231884058,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004981166918388897,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.15225751399993898,
|
|
"num_tokens": 10821608.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.730116319656372,
|
|
"epoch": 0.49317370300357066,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004981128233403828,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.15562243461608888,
|
|
"num_tokens": 10830679.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.774923992156983,
|
|
"epoch": 0.49359378281873556,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000498108950889547,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.14943243488669394,
|
|
"num_tokens": 10839669.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.790045118331909,
|
|
"epoch": 0.49401386263390046,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981050744864512,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.14829235821962355,
|
|
"num_tokens": 10849666.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.747752380371094,
|
|
"epoch": 0.4944339424490653,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004981011941311638,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.15378802865743638,
|
|
"num_tokens": 10858225.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.754449367523193,
|
|
"epoch": 0.4948540222642302,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980973098237535,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.14568711966276168,
|
|
"num_tokens": 10867466.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.807771825790406,
|
|
"epoch": 0.4952741020793951,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004980934215642894,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.15061958581209184,
|
|
"num_tokens": 10875850.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.799838733673096,
|
|
"epoch": 0.49569418189456,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049808952935284,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.15344742313027382,
|
|
"num_tokens": 10885154.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.781932210922241,
|
|
"epoch": 0.49611426170972484,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004980856331894747,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.1433933824300766,
|
|
"num_tokens": 10894080.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.767203950881958,
|
|
"epoch": 0.49653434152488973,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004980817330742621,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.14163193702697754,
|
|
"num_tokens": 10903248.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.848739862442017,
|
|
"epoch": 0.49695442134005463,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004980778290072716,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.14693543910980225,
|
|
"num_tokens": 10912939.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.852625370025635,
|
|
"epoch": 0.4973745011552195,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004980739209885722,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.15410863906145095,
|
|
"num_tokens": 10921505.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.887701892852784,
|
|
"epoch": 0.49779458097038437,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980700090182331,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.15374419540166856,
|
|
"num_tokens": 10931861.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.864461851119995,
|
|
"epoch": 0.49821466078554927,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004980660930963238,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.14706841260194778,
|
|
"num_tokens": 10940810.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.740756177902222,
|
|
"epoch": 0.4986347406007141,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004980621732229133,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.15016069263219833,
|
|
"num_tokens": 10949514.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.8102155208587645,
|
|
"epoch": 0.499054820415879,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004980582493980714,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.14151460081338882,
|
|
"num_tokens": 10959161.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.781671619415283,
|
|
"epoch": 0.4994749002310439,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004980543216218674,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.15644685178995132,
|
|
"num_tokens": 10968983.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.819313478469849,
|
|
"epoch": 0.4998949800462088,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980503898943711,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.14870925694704057,
|
|
"num_tokens": 10978044.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.8994536876678465,
|
|
"epoch": 0.5003150598613737,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980464542156519,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.15195106863975524,
|
|
"num_tokens": 10986980.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.804496479034424,
|
|
"epoch": 0.5007351396765385,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004980425145857796,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.16026414483785628,
|
|
"num_tokens": 10995163.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.705014753341675,
|
|
"epoch": 0.5011552194917034,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000498038571004824,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.15652424693107606,
|
|
"num_tokens": 11003722.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.725177145004272,
|
|
"epoch": 0.5015752993068683,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980346234728549,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1604843556880951,
|
|
"num_tokens": 11013176.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.815953350067138,
|
|
"epoch": 0.5019953791220332,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004980306719899424,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.14801866561174393,
|
|
"num_tokens": 11022636.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.758071231842041,
|
|
"epoch": 0.5024154589371981,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004980267165561564,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.1525172308087349,
|
|
"num_tokens": 11031896.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.801525115966797,
|
|
"epoch": 0.502835538752363,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004980227571715669,
|
|
"loss": 5.7359,
|
|
"mean_token_accuracy": 0.14860138446092605,
|
|
"num_tokens": 11040802.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.774550342559815,
|
|
"epoch": 0.5032556185675279,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004980187938362441,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.14492484778165818,
|
|
"num_tokens": 11049701.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.841704797744751,
|
|
"epoch": 0.5036756983826927,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004980148265502581,
|
|
"loss": 5.831,
|
|
"mean_token_accuracy": 0.14276057258248329,
|
|
"num_tokens": 11059555.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.823680114746094,
|
|
"epoch": 0.5040957781978576,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004980108553136795,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.14943215250968933,
|
|
"num_tokens": 11068940.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5040957781978576,
|
|
"eval_entropy": 5.697147493315468,
|
|
"eval_loss": 5.740706920623779,
|
|
"eval_mean_token_accuracy": 0.15491213997795275,
|
|
"eval_num_tokens": 11068940.0,
|
|
"eval_runtime": 27.2377,
|
|
"eval_samples_per_second": 1371.85,
|
|
"eval_steps_per_second": 171.49,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119020,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.6177520553984e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|