8ed496b588
Model: fpadovani/swe-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.2520478890989288,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"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": 8117673873408000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|