da2c0feb09
Model: fpadovani/heb-hebr-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3210444646583552,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.722395038604736,
|
|
"epoch": 0.0005350741077639254,
|
|
"grad_norm": 19.75,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.1573,
|
|
"mean_token_accuracy": 0.0019991567474789917,
|
|
"num_tokens": 10038.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.733135223388672,
|
|
"epoch": 0.0010701482155278507,
|
|
"grad_norm": 22.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.1399,
|
|
"mean_token_accuracy": 0.002229393390007317,
|
|
"num_tokens": 21916.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.8563759326934814,
|
|
"epoch": 0.0016052223232917758,
|
|
"grad_norm": 30.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 13.8613,
|
|
"mean_token_accuracy": 0.0014959125372115522,
|
|
"num_tokens": 33434.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.691608190536499,
|
|
"epoch": 0.0021402964310557014,
|
|
"grad_norm": 39.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 12.8416,
|
|
"mean_token_accuracy": 0.0012791280925739557,
|
|
"num_tokens": 44216.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 9.404048442840576,
|
|
"epoch": 0.0026753705388196263,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.1148,
|
|
"mean_token_accuracy": 0.0004811433027498424,
|
|
"num_tokens": 54874.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.681069660186768,
|
|
"epoch": 0.0032104446465835517,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.7614,
|
|
"mean_token_accuracy": 0.004937578848330304,
|
|
"num_tokens": 65085.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.695120239257813,
|
|
"epoch": 0.003745518754347477,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.4993,
|
|
"mean_token_accuracy": 0.02851757351309061,
|
|
"num_tokens": 75601.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.643773174285888,
|
|
"epoch": 0.004280592862111403,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2473,
|
|
"mean_token_accuracy": 0.029688681289553643,
|
|
"num_tokens": 86193.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.502691459655761,
|
|
"epoch": 0.004815666969875327,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0423,
|
|
"mean_token_accuracy": 0.045137681812047956,
|
|
"num_tokens": 96957.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.450238704681396,
|
|
"epoch": 0.005350741077639253,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9263,
|
|
"mean_token_accuracy": 0.04649358205497265,
|
|
"num_tokens": 108408.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.498290061950684,
|
|
"epoch": 0.005885815185403178,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.8446,
|
|
"mean_token_accuracy": 0.04394957646727562,
|
|
"num_tokens": 119273.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.508341979980468,
|
|
"epoch": 0.006420889293167103,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.7839,
|
|
"mean_token_accuracy": 0.04651816934347153,
|
|
"num_tokens": 130817.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.453034210205079,
|
|
"epoch": 0.006955963400931029,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7212,
|
|
"mean_token_accuracy": 0.04715100526809692,
|
|
"num_tokens": 142599.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.463440990447998,
|
|
"epoch": 0.007491037508694954,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.6449,
|
|
"mean_token_accuracy": 0.04722196869552135,
|
|
"num_tokens": 153617.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.457964038848877,
|
|
"epoch": 0.00802611161645888,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.6007,
|
|
"mean_token_accuracy": 0.053398077934980394,
|
|
"num_tokens": 165280.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.41784963607788,
|
|
"epoch": 0.008561185724222806,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.5362,
|
|
"mean_token_accuracy": 0.053571393340826036,
|
|
"num_tokens": 176896.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.401211261749268,
|
|
"epoch": 0.00909625983198673,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.4668,
|
|
"mean_token_accuracy": 0.05559399500489235,
|
|
"num_tokens": 188000.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.360631847381592,
|
|
"epoch": 0.009631333939750655,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4151,
|
|
"mean_token_accuracy": 0.055846284702420236,
|
|
"num_tokens": 199360.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.300343799591065,
|
|
"epoch": 0.01016640804751458,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3631,
|
|
"mean_token_accuracy": 0.05220822170376778,
|
|
"num_tokens": 210214.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.266947269439697,
|
|
"epoch": 0.010701482155278505,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2166,
|
|
"mean_token_accuracy": 0.05733812190592289,
|
|
"num_tokens": 220567.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.19696626663208,
|
|
"epoch": 0.011236556263042432,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1178,
|
|
"mean_token_accuracy": 0.05813850089907646,
|
|
"num_tokens": 230585.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.136646366119384,
|
|
"epoch": 0.011771630370806356,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0634,
|
|
"mean_token_accuracy": 0.06136388815939427,
|
|
"num_tokens": 241996.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.102339267730713,
|
|
"epoch": 0.012306704478570282,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0193,
|
|
"mean_token_accuracy": 0.0571962833404541,
|
|
"num_tokens": 253348.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.066826057434081,
|
|
"epoch": 0.012841778586334207,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9111,
|
|
"mean_token_accuracy": 0.055212068185210225,
|
|
"num_tokens": 264239.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.894806575775146,
|
|
"epoch": 0.013376852694098133,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8161,
|
|
"mean_token_accuracy": 0.05635458119213581,
|
|
"num_tokens": 274522.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.833152961730956,
|
|
"epoch": 0.013911926801862057,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.7223,
|
|
"mean_token_accuracy": 0.0572861559689045,
|
|
"num_tokens": 284492.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.669886493682862,
|
|
"epoch": 0.014447000909625984,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6657,
|
|
"mean_token_accuracy": 0.05727625191211701,
|
|
"num_tokens": 294796.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.54542293548584,
|
|
"epoch": 0.014982075017389908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.6381,
|
|
"mean_token_accuracy": 0.055407172068953514,
|
|
"num_tokens": 305252.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.40982427597046,
|
|
"epoch": 0.015517149125153834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.541,
|
|
"mean_token_accuracy": 0.0527797307819128,
|
|
"num_tokens": 315505.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.249729537963868,
|
|
"epoch": 0.01605222323291776,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.5348,
|
|
"mean_token_accuracy": 0.05866497568786144,
|
|
"num_tokens": 326997.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.123694038391113,
|
|
"epoch": 0.016587297340681685,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.4691,
|
|
"mean_token_accuracy": 0.05534619092941284,
|
|
"num_tokens": 338089.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.934013175964356,
|
|
"epoch": 0.01712237144844561,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.4569,
|
|
"mean_token_accuracy": 0.055205514281988145,
|
|
"num_tokens": 348536.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.928122615814209,
|
|
"epoch": 0.017657445556209534,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.472,
|
|
"mean_token_accuracy": 0.05698439441621304,
|
|
"num_tokens": 359776.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.888623428344726,
|
|
"epoch": 0.01819251966397346,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.4013,
|
|
"mean_token_accuracy": 0.05928085558116436,
|
|
"num_tokens": 370810.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.746195697784424,
|
|
"epoch": 0.018727593771737387,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.4049,
|
|
"mean_token_accuracy": 0.05481472611427307,
|
|
"num_tokens": 381788.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.743162918090821,
|
|
"epoch": 0.01926266787950131,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.3926,
|
|
"mean_token_accuracy": 0.055552761256694796,
|
|
"num_tokens": 391984.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.635337162017823,
|
|
"epoch": 0.019797741987265235,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.3947,
|
|
"mean_token_accuracy": 0.05619353819638491,
|
|
"num_tokens": 403430.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.695697593688966,
|
|
"epoch": 0.02033281609502916,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.3824,
|
|
"mean_token_accuracy": 0.0553983062505722,
|
|
"num_tokens": 414467.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.570184803009033,
|
|
"epoch": 0.020867890202793088,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.3479,
|
|
"mean_token_accuracy": 0.05803927257657051,
|
|
"num_tokens": 425752.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.64119758605957,
|
|
"epoch": 0.02140296431055701,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.3272,
|
|
"mean_token_accuracy": 0.05978759676218033,
|
|
"num_tokens": 435908.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.563984680175782,
|
|
"epoch": 0.021938038418320937,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.3718,
|
|
"mean_token_accuracy": 0.05641747824847698,
|
|
"num_tokens": 446424.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.567623805999755,
|
|
"epoch": 0.022473112526084863,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.3392,
|
|
"mean_token_accuracy": 0.06241393908858299,
|
|
"num_tokens": 456854.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.583000755310058,
|
|
"epoch": 0.02300818663384879,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.3556,
|
|
"mean_token_accuracy": 0.06351997442543507,
|
|
"num_tokens": 467899.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.510110855102539,
|
|
"epoch": 0.023543260741612712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.3013,
|
|
"mean_token_accuracy": 0.061149004846811295,
|
|
"num_tokens": 478683.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.565245342254638,
|
|
"epoch": 0.02407833484937664,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.3457,
|
|
"mean_token_accuracy": 0.05644676610827446,
|
|
"num_tokens": 488745.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.513838863372802,
|
|
"epoch": 0.024613408957140565,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4193,
|
|
"mean_token_accuracy": 0.055473582446575166,
|
|
"num_tokens": 499448.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.656694984436035,
|
|
"epoch": 0.02514848306490449,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.3499,
|
|
"mean_token_accuracy": 0.05867874249815941,
|
|
"num_tokens": 510148.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.570264339447021,
|
|
"epoch": 0.025683557172668414,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.2806,
|
|
"mean_token_accuracy": 0.0545498002320528,
|
|
"num_tokens": 522093.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.575170516967773,
|
|
"epoch": 0.02621863128043234,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.3034,
|
|
"mean_token_accuracy": 0.06172005347907543,
|
|
"num_tokens": 532598.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.435428237915039,
|
|
"epoch": 0.026753705388196266,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.2791,
|
|
"mean_token_accuracy": 0.06071905605494976,
|
|
"num_tokens": 542652.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.516559886932374,
|
|
"epoch": 0.027288779495960192,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.3286,
|
|
"mean_token_accuracy": 0.062316672131419185,
|
|
"num_tokens": 552526.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.463175582885743,
|
|
"epoch": 0.027823853603724115,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.3292,
|
|
"mean_token_accuracy": 0.059035299345850945,
|
|
"num_tokens": 563143.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.509436798095702,
|
|
"epoch": 0.02835892771148804,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.3044,
|
|
"mean_token_accuracy": 0.05978103019297123,
|
|
"num_tokens": 573814.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.468083572387695,
|
|
"epoch": 0.028894001819251967,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.2633,
|
|
"mean_token_accuracy": 0.06531455405056477,
|
|
"num_tokens": 585367.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.460441875457764,
|
|
"epoch": 0.02942907592701589,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.3529,
|
|
"mean_token_accuracy": 0.061703698709607124,
|
|
"num_tokens": 595902.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.537551498413086,
|
|
"epoch": 0.029964150034779816,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.2341,
|
|
"mean_token_accuracy": 0.05600880384445191,
|
|
"num_tokens": 607178.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.52383508682251,
|
|
"epoch": 0.030499224142543743,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.2256,
|
|
"mean_token_accuracy": 0.061789267137646674,
|
|
"num_tokens": 618604.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.46062650680542,
|
|
"epoch": 0.03103429825030767,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.2826,
|
|
"mean_token_accuracy": 0.06835589855909348,
|
|
"num_tokens": 628111.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.490731143951416,
|
|
"epoch": 0.03156937235807159,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3204,
|
|
"mean_token_accuracy": 0.06516639403998851,
|
|
"num_tokens": 639358.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.466291427612305,
|
|
"epoch": 0.03210444646583552,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.201,
|
|
"mean_token_accuracy": 0.0651388991624117,
|
|
"num_tokens": 649504.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.41495246887207,
|
|
"epoch": 0.032639520573599444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.2145,
|
|
"mean_token_accuracy": 0.06336927972733974,
|
|
"num_tokens": 659924.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.46861686706543,
|
|
"epoch": 0.03317459468136337,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.2479,
|
|
"mean_token_accuracy": 0.05956652238965034,
|
|
"num_tokens": 671120.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.482641410827636,
|
|
"epoch": 0.033709668789127296,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.2983,
|
|
"mean_token_accuracy": 0.06287384144961834,
|
|
"num_tokens": 681956.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.419728565216065,
|
|
"epoch": 0.03424474289689122,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.2718,
|
|
"mean_token_accuracy": 0.06350533962249756,
|
|
"num_tokens": 693226.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.438337421417236,
|
|
"epoch": 0.03477981700465514,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.2865,
|
|
"mean_token_accuracy": 0.0667075652629137,
|
|
"num_tokens": 704691.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.398693466186524,
|
|
"epoch": 0.03531489111241907,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.2436,
|
|
"mean_token_accuracy": 0.05939121432602405,
|
|
"num_tokens": 716000.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.420809078216553,
|
|
"epoch": 0.035849965220182994,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.1626,
|
|
"mean_token_accuracy": 0.06278250962495804,
|
|
"num_tokens": 726723.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.330788707733154,
|
|
"epoch": 0.03638503932794692,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.174,
|
|
"mean_token_accuracy": 0.06592709310352803,
|
|
"num_tokens": 736740.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.379256629943848,
|
|
"epoch": 0.03692011343571085,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.2427,
|
|
"mean_token_accuracy": 0.06097902096807957,
|
|
"num_tokens": 747567.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.421171760559082,
|
|
"epoch": 0.03745518754347477,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.1672,
|
|
"mean_token_accuracy": 0.06565289981663228,
|
|
"num_tokens": 757937.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.351040077209472,
|
|
"epoch": 0.0379902616512387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.1967,
|
|
"mean_token_accuracy": 0.06799040511250495,
|
|
"num_tokens": 768003.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.385930728912353,
|
|
"epoch": 0.03852533575900262,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.2486,
|
|
"mean_token_accuracy": 0.06156148537993431,
|
|
"num_tokens": 779098.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.474120998382569,
|
|
"epoch": 0.039060409866766545,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.216,
|
|
"mean_token_accuracy": 0.06129729710519314,
|
|
"num_tokens": 790002.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.336334323883056,
|
|
"epoch": 0.03959548397453047,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.1953,
|
|
"mean_token_accuracy": 0.062206690385937694,
|
|
"num_tokens": 800444.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.424775123596191,
|
|
"epoch": 0.0401305580822944,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.1423,
|
|
"mean_token_accuracy": 0.06721410900354385,
|
|
"num_tokens": 810912.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.392704105377197,
|
|
"epoch": 0.04066563219005832,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.2261,
|
|
"mean_token_accuracy": 0.05968447625637054,
|
|
"num_tokens": 822809.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.346403789520263,
|
|
"epoch": 0.04120070629782225,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.1395,
|
|
"mean_token_accuracy": 0.06515709534287453,
|
|
"num_tokens": 833362.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.385848045349121,
|
|
"epoch": 0.041735780405586176,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.1498,
|
|
"mean_token_accuracy": 0.06862472333014011,
|
|
"num_tokens": 844239.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.250670433044434,
|
|
"epoch": 0.0422708545133501,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.1561,
|
|
"mean_token_accuracy": 0.060210096463561055,
|
|
"num_tokens": 855178.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.319873905181884,
|
|
"epoch": 0.04280592862111402,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.1566,
|
|
"mean_token_accuracy": 0.06562219709157943,
|
|
"num_tokens": 866120.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.30604248046875,
|
|
"epoch": 0.04334100272887795,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.1382,
|
|
"mean_token_accuracy": 0.0657996479421854,
|
|
"num_tokens": 876569.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.446116733551026,
|
|
"epoch": 0.043876076836641874,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.2014,
|
|
"mean_token_accuracy": 0.0606235396116972,
|
|
"num_tokens": 887580.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.289253234863281,
|
|
"epoch": 0.0444111509444058,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.1351,
|
|
"mean_token_accuracy": 0.06126284152269364,
|
|
"num_tokens": 897922.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.343159866333007,
|
|
"epoch": 0.044946225052169726,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.0903,
|
|
"mean_token_accuracy": 0.06723331548273563,
|
|
"num_tokens": 908522.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.330431842803955,
|
|
"epoch": 0.04548129915993365,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.1108,
|
|
"mean_token_accuracy": 0.06402806043624878,
|
|
"num_tokens": 918253.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.292218208312988,
|
|
"epoch": 0.04601637326769758,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.106,
|
|
"mean_token_accuracy": 0.06909515634179116,
|
|
"num_tokens": 929150.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.331517314910888,
|
|
"epoch": 0.0465514473754615,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.1406,
|
|
"mean_token_accuracy": 0.06766720302402973,
|
|
"num_tokens": 941041.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.226575946807861,
|
|
"epoch": 0.047086521483225424,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.0896,
|
|
"mean_token_accuracy": 0.07020636461675167,
|
|
"num_tokens": 952714.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.243675708770752,
|
|
"epoch": 0.04762159559098935,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.1592,
|
|
"mean_token_accuracy": 0.060818764939904214,
|
|
"num_tokens": 964330.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.260573291778565,
|
|
"epoch": 0.04815666969875328,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.0846,
|
|
"mean_token_accuracy": 0.0660694733262062,
|
|
"num_tokens": 975257.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.280968284606933,
|
|
"epoch": 0.0486917438065172,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.11,
|
|
"mean_token_accuracy": 0.06583500131964684,
|
|
"num_tokens": 986335.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.23782262802124,
|
|
"epoch": 0.04922681791428113,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.9957,
|
|
"mean_token_accuracy": 0.07163017019629478,
|
|
"num_tokens": 997521.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.19036931991577,
|
|
"epoch": 0.049761892022045055,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.0475,
|
|
"mean_token_accuracy": 0.06431003175675869,
|
|
"num_tokens": 1008383.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.257700347900391,
|
|
"epoch": 0.05029696612980898,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.1057,
|
|
"mean_token_accuracy": 0.06629102565348148,
|
|
"num_tokens": 1020552.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.202971076965332,
|
|
"epoch": 0.0508320402375729,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.0756,
|
|
"mean_token_accuracy": 0.06509139761328697,
|
|
"num_tokens": 1031127.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.153694152832031,
|
|
"epoch": 0.05136711434533683,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.9914,
|
|
"mean_token_accuracy": 0.07003656215965748,
|
|
"num_tokens": 1043209.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.294580459594727,
|
|
"epoch": 0.05190218845310075,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.1227,
|
|
"mean_token_accuracy": 0.06236105561256409,
|
|
"num_tokens": 1054032.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.169051265716552,
|
|
"epoch": 0.05243726256086468,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.9544,
|
|
"mean_token_accuracy": 0.07054617665708066,
|
|
"num_tokens": 1064565.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.221727657318116,
|
|
"epoch": 0.052972336668628606,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 8.096,
|
|
"mean_token_accuracy": 0.07002902217209339,
|
|
"num_tokens": 1076352.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.255829620361329,
|
|
"epoch": 0.05350741077639253,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0241,
|
|
"mean_token_accuracy": 0.07085983417928218,
|
|
"num_tokens": 1087697.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.139251327514648,
|
|
"epoch": 0.05404248488415646,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.9711,
|
|
"mean_token_accuracy": 0.07000853382050991,
|
|
"num_tokens": 1098056.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.11564884185791,
|
|
"epoch": 0.054577558991920384,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.9527,
|
|
"mean_token_accuracy": 0.07442603223025798,
|
|
"num_tokens": 1109219.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.148744678497314,
|
|
"epoch": 0.055112633099684304,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.0254,
|
|
"mean_token_accuracy": 0.0679584439843893,
|
|
"num_tokens": 1120248.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.103824901580811,
|
|
"epoch": 0.05564770720744823,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.035,
|
|
"mean_token_accuracy": 0.06900341361761093,
|
|
"num_tokens": 1131278.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.184957122802734,
|
|
"epoch": 0.056182781315212156,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.053,
|
|
"mean_token_accuracy": 0.06036060117185116,
|
|
"num_tokens": 1143147.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.217153358459473,
|
|
"epoch": 0.05671785542297608,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.9545,
|
|
"mean_token_accuracy": 0.06593920513987542,
|
|
"num_tokens": 1154316.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.083821010589599,
|
|
"epoch": 0.05725292953074001,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.0045,
|
|
"mean_token_accuracy": 0.06556588783860207,
|
|
"num_tokens": 1164696.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.10741205215454,
|
|
"epoch": 0.057788003638503935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.9876,
|
|
"mean_token_accuracy": 0.07419452145695686,
|
|
"num_tokens": 1176129.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.21908884048462,
|
|
"epoch": 0.05832307774626786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9966,
|
|
"mean_token_accuracy": 0.06897441558539867,
|
|
"num_tokens": 1186499.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.077346086502075,
|
|
"epoch": 0.05885815185403178,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.9598,
|
|
"mean_token_accuracy": 0.06709535419940948,
|
|
"num_tokens": 1196841.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.092563199996949,
|
|
"epoch": 0.059393225961795706,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.9145,
|
|
"mean_token_accuracy": 0.07183470316231251,
|
|
"num_tokens": 1207647.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.107578134536743,
|
|
"epoch": 0.05992830006955963,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.9071,
|
|
"mean_token_accuracy": 0.07336057722568512,
|
|
"num_tokens": 1217072.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.063977479934692,
|
|
"epoch": 0.06046337417732356,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 8.0262,
|
|
"mean_token_accuracy": 0.06556856445968151,
|
|
"num_tokens": 1228564.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.046744298934936,
|
|
"epoch": 0.060998448285087485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.952,
|
|
"mean_token_accuracy": 0.07086653858423234,
|
|
"num_tokens": 1238755.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.117069578170776,
|
|
"epoch": 0.06153352239285141,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.9119,
|
|
"mean_token_accuracy": 0.0674261998385191,
|
|
"num_tokens": 1248968.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.066808080673217,
|
|
"epoch": 0.06206859650061534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.8725,
|
|
"mean_token_accuracy": 0.06969248615205288,
|
|
"num_tokens": 1259256.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.942452716827392,
|
|
"epoch": 0.06260367060837926,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.9218,
|
|
"mean_token_accuracy": 0.07239063829183578,
|
|
"num_tokens": 1270469.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.091417694091797,
|
|
"epoch": 0.06313874471614318,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.8805,
|
|
"mean_token_accuracy": 0.06797636225819588,
|
|
"num_tokens": 1280558.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.002246284484864,
|
|
"epoch": 0.06367381882390712,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.9341,
|
|
"mean_token_accuracy": 0.06753262616693974,
|
|
"num_tokens": 1291372.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.119279384613037,
|
|
"epoch": 0.06420889293167104,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 8.0125,
|
|
"mean_token_accuracy": 0.0642974954098463,
|
|
"num_tokens": 1302521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.015694999694825,
|
|
"epoch": 0.06474396703943497,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.8392,
|
|
"mean_token_accuracy": 0.06977246440947056,
|
|
"num_tokens": 1313632.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.086053228378296,
|
|
"epoch": 0.06527904114719889,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.9187,
|
|
"mean_token_accuracy": 0.07155244462192059,
|
|
"num_tokens": 1325247.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.980141305923462,
|
|
"epoch": 0.06581411525496281,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.8969,
|
|
"mean_token_accuracy": 0.07443655468523502,
|
|
"num_tokens": 1336026.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.025841999053956,
|
|
"epoch": 0.06634918936272674,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.8245,
|
|
"mean_token_accuracy": 0.07328929230570794,
|
|
"num_tokens": 1346920.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.913932514190674,
|
|
"epoch": 0.06688426347049066,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.9712,
|
|
"mean_token_accuracy": 0.07009200640022754,
|
|
"num_tokens": 1359752.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.165118312835693,
|
|
"epoch": 0.06741933757825459,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.964,
|
|
"mean_token_accuracy": 0.06890517212450505,
|
|
"num_tokens": 1370874.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.918849992752075,
|
|
"epoch": 0.06795441168601851,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.8755,
|
|
"mean_token_accuracy": 0.07662892192602158,
|
|
"num_tokens": 1382316.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.990935611724853,
|
|
"epoch": 0.06848948579378245,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.8866,
|
|
"mean_token_accuracy": 0.06935312673449516,
|
|
"num_tokens": 1394656.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.928519058227539,
|
|
"epoch": 0.06902455990154636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.8415,
|
|
"mean_token_accuracy": 0.07609727829694748,
|
|
"num_tokens": 1405061.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.969374084472657,
|
|
"epoch": 0.06955963400931028,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8124,
|
|
"mean_token_accuracy": 0.07858087830245494,
|
|
"num_tokens": 1415573.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.936450529098511,
|
|
"epoch": 0.07009470811707422,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.837,
|
|
"mean_token_accuracy": 0.07200551256537438,
|
|
"num_tokens": 1426103.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.920168352127075,
|
|
"epoch": 0.07062978222483814,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.867,
|
|
"mean_token_accuracy": 0.06607943587005138,
|
|
"num_tokens": 1437256.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.067060947418213,
|
|
"epoch": 0.07116485633260207,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.8179,
|
|
"mean_token_accuracy": 0.07232290767133236,
|
|
"num_tokens": 1446975.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.911382961273193,
|
|
"epoch": 0.07169993044036599,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.8317,
|
|
"mean_token_accuracy": 0.07128445580601692,
|
|
"num_tokens": 1457751.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.850908708572388,
|
|
"epoch": 0.07223500454812992,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.807,
|
|
"mean_token_accuracy": 0.07180027030408383,
|
|
"num_tokens": 1468186.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.946501731872559,
|
|
"epoch": 0.07277007865589384,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.8495,
|
|
"mean_token_accuracy": 0.0691140852868557,
|
|
"num_tokens": 1479780.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.927443170547486,
|
|
"epoch": 0.07330515276365776,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.7733,
|
|
"mean_token_accuracy": 0.07666020393371582,
|
|
"num_tokens": 1490565.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.999663305282593,
|
|
"epoch": 0.0738402268714217,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.8189,
|
|
"mean_token_accuracy": 0.07104030475020409,
|
|
"num_tokens": 1501552.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.861136484146118,
|
|
"epoch": 0.07437530097918561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.8092,
|
|
"mean_token_accuracy": 0.0690252747386694,
|
|
"num_tokens": 1513311.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.929182291030884,
|
|
"epoch": 0.07491037508694955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.8493,
|
|
"mean_token_accuracy": 0.07585305124521255,
|
|
"num_tokens": 1524142.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.9166868209838865,
|
|
"epoch": 0.07544544919471347,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.8032,
|
|
"mean_token_accuracy": 0.07204971313476563,
|
|
"num_tokens": 1535571.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.963001823425293,
|
|
"epoch": 0.0759805233024774,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8184,
|
|
"mean_token_accuracy": 0.07111813239753247,
|
|
"num_tokens": 1546528.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.771885633468628,
|
|
"epoch": 0.07651559741024132,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.8303,
|
|
"mean_token_accuracy": 0.06822719126939773,
|
|
"num_tokens": 1557264.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.922857713699341,
|
|
"epoch": 0.07705067151800524,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.7899,
|
|
"mean_token_accuracy": 0.0768304031342268,
|
|
"num_tokens": 1566773.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.871666193008423,
|
|
"epoch": 0.07758574562576917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.7434,
|
|
"mean_token_accuracy": 0.07752364575862884,
|
|
"num_tokens": 1578173.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.79464282989502,
|
|
"epoch": 0.07812081973353309,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.7138,
|
|
"mean_token_accuracy": 0.07739724665880203,
|
|
"num_tokens": 1588537.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.797579956054688,
|
|
"epoch": 0.07865589384129702,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.7126,
|
|
"mean_token_accuracy": 0.08267080709338188,
|
|
"num_tokens": 1599159.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.877125597000122,
|
|
"epoch": 0.07919096794906094,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7908,
|
|
"mean_token_accuracy": 0.07560665309429168,
|
|
"num_tokens": 1610378.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.83719277381897,
|
|
"epoch": 0.07972604205682488,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.8064,
|
|
"mean_token_accuracy": 0.07094332799315453,
|
|
"num_tokens": 1621215.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.8825953006744385,
|
|
"epoch": 0.0802611161645888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.7372,
|
|
"mean_token_accuracy": 0.07185808084905147,
|
|
"num_tokens": 1631170.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.881593084335327,
|
|
"epoch": 0.08079619027235273,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.7573,
|
|
"mean_token_accuracy": 0.07288290858268738,
|
|
"num_tokens": 1641897.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.814771223068237,
|
|
"epoch": 0.08133126438011665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.8249,
|
|
"mean_token_accuracy": 0.07262703813612462,
|
|
"num_tokens": 1653592.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.764955615997314,
|
|
"epoch": 0.08186633848788057,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.7359,
|
|
"mean_token_accuracy": 0.07105322629213333,
|
|
"num_tokens": 1665760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.860084962844849,
|
|
"epoch": 0.0824014125956445,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7313,
|
|
"mean_token_accuracy": 0.07819439396262169,
|
|
"num_tokens": 1676211.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.864154577255249,
|
|
"epoch": 0.08293648670340842,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.7604,
|
|
"mean_token_accuracy": 0.07544596865773201,
|
|
"num_tokens": 1686405.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.842417526245117,
|
|
"epoch": 0.08347156081117235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.7456,
|
|
"mean_token_accuracy": 0.07263315543532371,
|
|
"num_tokens": 1697340.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.7913618087768555,
|
|
"epoch": 0.08400663491893627,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.6556,
|
|
"mean_token_accuracy": 0.0825340673327446,
|
|
"num_tokens": 1707250.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.6649213314056395,
|
|
"epoch": 0.0845417090267002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.6374,
|
|
"mean_token_accuracy": 0.07561526447534561,
|
|
"num_tokens": 1718333.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.79561710357666,
|
|
"epoch": 0.08507678313446412,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.737,
|
|
"mean_token_accuracy": 0.06993279084563256,
|
|
"num_tokens": 1730520.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.776207351684571,
|
|
"epoch": 0.08561185724222804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.7826,
|
|
"mean_token_accuracy": 0.07513744048774243,
|
|
"num_tokens": 1741898.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.806885290145874,
|
|
"epoch": 0.08614693134999198,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7283,
|
|
"mean_token_accuracy": 0.07864765003323555,
|
|
"num_tokens": 1751671.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.722856760025024,
|
|
"epoch": 0.0866820054577559,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7421,
|
|
"mean_token_accuracy": 0.07978087440133094,
|
|
"num_tokens": 1762076.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.788973808288574,
|
|
"epoch": 0.08721707956551983,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.7164,
|
|
"mean_token_accuracy": 0.07577739097177982,
|
|
"num_tokens": 1772666.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.822106456756591,
|
|
"epoch": 0.08775215367328375,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.7369,
|
|
"mean_token_accuracy": 0.07942529432475567,
|
|
"num_tokens": 1783621.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.778071069717408,
|
|
"epoch": 0.08828722778104768,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.8027,
|
|
"mean_token_accuracy": 0.0739357691258192,
|
|
"num_tokens": 1794654.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.724924182891845,
|
|
"epoch": 0.0888223018888116,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.6881,
|
|
"mean_token_accuracy": 0.08523635193705559,
|
|
"num_tokens": 1805853.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.641312026977539,
|
|
"epoch": 0.08935737599657552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6675,
|
|
"mean_token_accuracy": 0.07578803896903992,
|
|
"num_tokens": 1817006.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.8067771911621096,
|
|
"epoch": 0.08989245010433945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.662,
|
|
"mean_token_accuracy": 0.07342330142855644,
|
|
"num_tokens": 1827166.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.841296720504761,
|
|
"epoch": 0.09042752421210337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.7485,
|
|
"mean_token_accuracy": 0.07532198280096054,
|
|
"num_tokens": 1837182.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.612701177597046,
|
|
"epoch": 0.0909625983198673,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.6955,
|
|
"mean_token_accuracy": 0.07896317429840564,
|
|
"num_tokens": 1849034.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.698033094406128,
|
|
"epoch": 0.09149767242763122,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5761,
|
|
"mean_token_accuracy": 0.08696590065956115,
|
|
"num_tokens": 1859033.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.688354253768921,
|
|
"epoch": 0.09203274653539516,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6849,
|
|
"mean_token_accuracy": 0.07928116545081139,
|
|
"num_tokens": 1870274.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.66806640625,
|
|
"epoch": 0.09256782064315908,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.6252,
|
|
"mean_token_accuracy": 0.08459196016192436,
|
|
"num_tokens": 1881306.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.665304851531983,
|
|
"epoch": 0.093102894750923,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.6184,
|
|
"mean_token_accuracy": 0.07928042747080326,
|
|
"num_tokens": 1892464.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.751847410202027,
|
|
"epoch": 0.09363796885868693,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6891,
|
|
"mean_token_accuracy": 0.07430651262402535,
|
|
"num_tokens": 1903743.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.656659269332886,
|
|
"epoch": 0.09417304296645085,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.6452,
|
|
"mean_token_accuracy": 0.08042613193392753,
|
|
"num_tokens": 1915253.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.739474582672119,
|
|
"epoch": 0.09470811707421478,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.6105,
|
|
"mean_token_accuracy": 0.07811787836253643,
|
|
"num_tokens": 1926113.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.660387325286865,
|
|
"epoch": 0.0952431911819787,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.709,
|
|
"mean_token_accuracy": 0.07902690842747688,
|
|
"num_tokens": 1937718.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.725072240829467,
|
|
"epoch": 0.09577826528974263,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6993,
|
|
"mean_token_accuracy": 0.07840467914938927,
|
|
"num_tokens": 1948307.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.573423147201538,
|
|
"epoch": 0.09631333939750655,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.5078,
|
|
"mean_token_accuracy": 0.0859848216176033,
|
|
"num_tokens": 1957861.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.603833866119385,
|
|
"epoch": 0.09684841350527049,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.5528,
|
|
"mean_token_accuracy": 0.08676589056849479,
|
|
"num_tokens": 1967984.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.597575378417969,
|
|
"epoch": 0.0973834876130344,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.5639,
|
|
"mean_token_accuracy": 0.08211242109537124,
|
|
"num_tokens": 1978608.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.650602197647094,
|
|
"epoch": 0.09791856172079832,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6146,
|
|
"mean_token_accuracy": 0.08076006174087524,
|
|
"num_tokens": 1989355.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.582733201980591,
|
|
"epoch": 0.09845363582856226,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6068,
|
|
"mean_token_accuracy": 0.08393601626157761,
|
|
"num_tokens": 1999754.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.575737714767456,
|
|
"epoch": 0.09898870993632618,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5896,
|
|
"mean_token_accuracy": 0.0805906105786562,
|
|
"num_tokens": 2010877.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.744453620910645,
|
|
"epoch": 0.09952378404409011,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.6979,
|
|
"mean_token_accuracy": 0.07580301314592361,
|
|
"num_tokens": 2022301.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.62055778503418,
|
|
"epoch": 0.10005885815185403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5905,
|
|
"mean_token_accuracy": 0.07995235547423363,
|
|
"num_tokens": 2033537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.555106735229492,
|
|
"epoch": 0.10059393225961796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.5269,
|
|
"mean_token_accuracy": 0.0813826397061348,
|
|
"num_tokens": 2044360.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.654840993881225,
|
|
"epoch": 0.10112900636738188,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.6073,
|
|
"mean_token_accuracy": 0.08286485522985458,
|
|
"num_tokens": 2055000.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.554987287521362,
|
|
"epoch": 0.1016640804751458,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6055,
|
|
"mean_token_accuracy": 0.08866458013653755,
|
|
"num_tokens": 2064807.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.591622447967529,
|
|
"epoch": 0.10219915458290973,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.5605,
|
|
"mean_token_accuracy": 0.07844374999403954,
|
|
"num_tokens": 2075618.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.59330415725708,
|
|
"epoch": 0.10273422869067365,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.5705,
|
|
"mean_token_accuracy": 0.07968904972076415,
|
|
"num_tokens": 2086226.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.618208169937134,
|
|
"epoch": 0.10326930279843759,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5604,
|
|
"mean_token_accuracy": 0.07846201322972775,
|
|
"num_tokens": 2097222.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.5985006332397464,
|
|
"epoch": 0.1038043769062015,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.6154,
|
|
"mean_token_accuracy": 0.080904171615839,
|
|
"num_tokens": 2108919.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.526676940917969,
|
|
"epoch": 0.10433945101396544,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5506,
|
|
"mean_token_accuracy": 0.08453056961297989,
|
|
"num_tokens": 2120215.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.601911354064941,
|
|
"epoch": 0.10487452512172936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.5917,
|
|
"mean_token_accuracy": 0.07946700900793076,
|
|
"num_tokens": 2131503.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.553497743606568,
|
|
"epoch": 0.10540959922949328,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.536,
|
|
"mean_token_accuracy": 0.08508892878890037,
|
|
"num_tokens": 2141551.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.530622768402099,
|
|
"epoch": 0.10594467333725721,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.5234,
|
|
"mean_token_accuracy": 0.08779416754841804,
|
|
"num_tokens": 2151821.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.575374460220337,
|
|
"epoch": 0.10647974744502113,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.569,
|
|
"mean_token_accuracy": 0.08431452587246895,
|
|
"num_tokens": 2162474.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.60914421081543,
|
|
"epoch": 0.10701482155278506,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.6061,
|
|
"mean_token_accuracy": 0.0851107444614172,
|
|
"num_tokens": 2173985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.586228322982788,
|
|
"epoch": 0.10754989566054898,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999999979210101,
|
|
"loss": 7.6445,
|
|
"mean_token_accuracy": 0.0784386482089758,
|
|
"num_tokens": 2186432.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.589601135253906,
|
|
"epoch": 0.10808496976831292,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999999894751138,
|
|
"loss": 7.4898,
|
|
"mean_token_accuracy": 0.08204622492194176,
|
|
"num_tokens": 2197085.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.4365442276000975,
|
|
"epoch": 0.10862004387607684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999745323744,
|
|
"loss": 7.4981,
|
|
"mean_token_accuracy": 0.08734163418412208,
|
|
"num_tokens": 2207162.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.579596948623657,
|
|
"epoch": 0.10915511798384077,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999999530927923,
|
|
"loss": 7.6013,
|
|
"mean_token_accuracy": 0.07841602377593518,
|
|
"num_tokens": 2218714.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.562452411651611,
|
|
"epoch": 0.10969019209160469,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999999251563682,
|
|
"loss": 7.5478,
|
|
"mean_token_accuracy": 0.08398598507046699,
|
|
"num_tokens": 2229711.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.566829061508178,
|
|
"epoch": 0.11022526619936861,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999998907231029,
|
|
"loss": 7.5443,
|
|
"mean_token_accuracy": 0.08293986842036247,
|
|
"num_tokens": 2239885.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.510043811798096,
|
|
"epoch": 0.11076034030713254,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999998497929974,
|
|
"loss": 7.5413,
|
|
"mean_token_accuracy": 0.08550122715532779,
|
|
"num_tokens": 2250221.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.535279560089111,
|
|
"epoch": 0.11129541441489646,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999998023660527,
|
|
"loss": 7.6213,
|
|
"mean_token_accuracy": 0.07655972242355347,
|
|
"num_tokens": 2261059.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.53675012588501,
|
|
"epoch": 0.11183048852266039,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999997484422705,
|
|
"loss": 7.4938,
|
|
"mean_token_accuracy": 0.08518914058804512,
|
|
"num_tokens": 2271174.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.458289527893067,
|
|
"epoch": 0.11236556263042431,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996880216521,
|
|
"loss": 7.5496,
|
|
"mean_token_accuracy": 0.08104559034109116,
|
|
"num_tokens": 2282431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.545944452285767,
|
|
"epoch": 0.11290063673818825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999996211041994,
|
|
"loss": 7.5439,
|
|
"mean_token_accuracy": 0.08365396112203598,
|
|
"num_tokens": 2292891.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.627215766906739,
|
|
"epoch": 0.11343571084595216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999995476899141,
|
|
"loss": 7.5633,
|
|
"mean_token_accuracy": 0.08242802582681179,
|
|
"num_tokens": 2303764.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.38291015625,
|
|
"epoch": 0.11397078495371608,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999994677787987,
|
|
"loss": 7.4539,
|
|
"mean_token_accuracy": 0.08884900882840156,
|
|
"num_tokens": 2314172.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.587633895874023,
|
|
"epoch": 0.11450585906148002,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999993813708551,
|
|
"loss": 7.4497,
|
|
"mean_token_accuracy": 0.09005523398518563,
|
|
"num_tokens": 2324848.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.366536426544189,
|
|
"epoch": 0.11504093316924394,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499999288466086,
|
|
"loss": 7.4785,
|
|
"mean_token_accuracy": 0.08457461893558502,
|
|
"num_tokens": 2336601.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.547029972076416,
|
|
"epoch": 0.11557600727700787,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999991890644941,
|
|
"loss": 7.4505,
|
|
"mean_token_accuracy": 0.08462237492203713,
|
|
"num_tokens": 2347281.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.441406202316284,
|
|
"epoch": 0.11611108138477179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999990831660822,
|
|
"loss": 7.4898,
|
|
"mean_token_accuracy": 0.09125454500317573,
|
|
"num_tokens": 2358199.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.519572830200195,
|
|
"epoch": 0.11664615549253572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999989707708534,
|
|
"loss": 7.5368,
|
|
"mean_token_accuracy": 0.08167605474591255,
|
|
"num_tokens": 2369092.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.438222408294678,
|
|
"epoch": 0.11718122960029964,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999988518788111,
|
|
"loss": 7.5142,
|
|
"mean_token_accuracy": 0.08107429631054401,
|
|
"num_tokens": 2378849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.512506532669067,
|
|
"epoch": 0.11771630370806356,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999987264899583,
|
|
"loss": 7.5032,
|
|
"mean_token_accuracy": 0.08989172950387,
|
|
"num_tokens": 2389587.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.559766674041748,
|
|
"epoch": 0.1182513778158275,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499998594604299,
|
|
"loss": 7.4806,
|
|
"mean_token_accuracy": 0.0849291667342186,
|
|
"num_tokens": 2400442.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.420989179611206,
|
|
"epoch": 0.11878645192359141,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499998456221837,
|
|
"loss": 7.4684,
|
|
"mean_token_accuracy": 0.08736843839287758,
|
|
"num_tokens": 2410771.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.410952568054199,
|
|
"epoch": 0.11932152603135535,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999983113425762,
|
|
"loss": 7.4693,
|
|
"mean_token_accuracy": 0.09239947721362114,
|
|
"num_tokens": 2421112.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.545989656448365,
|
|
"epoch": 0.11985660013911927,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999981599665207,
|
|
"loss": 7.4512,
|
|
"mean_token_accuracy": 0.08613410592079163,
|
|
"num_tokens": 2431891.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.4298975467681885,
|
|
"epoch": 0.1203916742468832,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999980020936748,
|
|
"loss": 7.4131,
|
|
"mean_token_accuracy": 0.08798880130052567,
|
|
"num_tokens": 2442987.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.39614634513855,
|
|
"epoch": 0.12092674835464712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999978377240434,
|
|
"loss": 7.4519,
|
|
"mean_token_accuracy": 0.08737303614616394,
|
|
"num_tokens": 2452703.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.4548506259918215,
|
|
"epoch": 0.12146182246241104,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499997666857631,
|
|
"loss": 7.5001,
|
|
"mean_token_accuracy": 0.08815332502126694,
|
|
"num_tokens": 2462975.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.4424488067626955,
|
|
"epoch": 0.12199689657017497,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999974894944426,
|
|
"loss": 7.4515,
|
|
"mean_token_accuracy": 0.084615208953619,
|
|
"num_tokens": 2473853.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.427521181106568,
|
|
"epoch": 0.12253197067793889,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999973056344832,
|
|
"loss": 7.4324,
|
|
"mean_token_accuracy": 0.08493943735957146,
|
|
"num_tokens": 2485633.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.469012641906739,
|
|
"epoch": 0.12306704478570282,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999971152777583,
|
|
"loss": 7.3906,
|
|
"mean_token_accuracy": 0.08597971722483636,
|
|
"num_tokens": 2496922.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.443756341934204,
|
|
"epoch": 0.12360211889346674,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999969184242733,
|
|
"loss": 7.4573,
|
|
"mean_token_accuracy": 0.08639369383454323,
|
|
"num_tokens": 2507890.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.414251852035522,
|
|
"epoch": 0.12413719300123068,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499996715074034,
|
|
"loss": 7.4679,
|
|
"mean_token_accuracy": 0.08895903378725052,
|
|
"num_tokens": 2519749.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.369732522964478,
|
|
"epoch": 0.1246722671089946,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999965052270461,
|
|
"loss": 7.4587,
|
|
"mean_token_accuracy": 0.08741387501358985,
|
|
"num_tokens": 2530666.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.455218648910522,
|
|
"epoch": 0.12520734121675853,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999962888833157,
|
|
"loss": 7.4517,
|
|
"mean_token_accuracy": 0.087038604170084,
|
|
"num_tokens": 2541594.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.468952941894531,
|
|
"epoch": 0.12574241532452243,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999960660428491,
|
|
"loss": 7.4548,
|
|
"mean_token_accuracy": 0.08958195969462394,
|
|
"num_tokens": 2552330.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.457394981384278,
|
|
"epoch": 0.12627748943228637,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999958367056526,
|
|
"loss": 7.5094,
|
|
"mean_token_accuracy": 0.0814846083521843,
|
|
"num_tokens": 2564601.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.5275298118591305,
|
|
"epoch": 0.1268125635400503,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499995600871733,
|
|
"loss": 7.4705,
|
|
"mean_token_accuracy": 0.08419692143797874,
|
|
"num_tokens": 2575539.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.352044630050659,
|
|
"epoch": 0.12734763764781423,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999953585410971,
|
|
"loss": 7.3968,
|
|
"mean_token_accuracy": 0.08637173548340797,
|
|
"num_tokens": 2586635.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.49582724571228,
|
|
"epoch": 0.12788271175557814,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999951097137518,
|
|
"loss": 7.4108,
|
|
"mean_token_accuracy": 0.09154140949249268,
|
|
"num_tokens": 2596814.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.325179576873779,
|
|
"epoch": 0.12841778586334207,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999948543897044,
|
|
"loss": 7.4522,
|
|
"mean_token_accuracy": 0.08449748009443284,
|
|
"num_tokens": 2608087.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.586294317245484,
|
|
"epoch": 0.128952859971106,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999945925689621,
|
|
"loss": 7.4593,
|
|
"mean_token_accuracy": 0.08878617733716965,
|
|
"num_tokens": 2619377.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.303364086151123,
|
|
"epoch": 0.12948793407886994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999943242515325,
|
|
"loss": 7.3505,
|
|
"mean_token_accuracy": 0.09070543050765992,
|
|
"num_tokens": 2629089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.450505971908569,
|
|
"epoch": 0.13002300818663384,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999940494374236,
|
|
"loss": 7.4299,
|
|
"mean_token_accuracy": 0.08928245157003403,
|
|
"num_tokens": 2639743.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.489728927612305,
|
|
"epoch": 0.13055808229439778,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499993768126643,
|
|
"loss": 7.4676,
|
|
"mean_token_accuracy": 0.08282669633626938,
|
|
"num_tokens": 2650631.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.376281833648681,
|
|
"epoch": 0.1310931564021617,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499993480319199,
|
|
"loss": 7.4305,
|
|
"mean_token_accuracy": 0.08671566098928452,
|
|
"num_tokens": 2660197.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.40994963645935,
|
|
"epoch": 0.13162823050992561,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999931860150999,
|
|
"loss": 7.3856,
|
|
"mean_token_accuracy": 0.08833521455526352,
|
|
"num_tokens": 2670162.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.446912240982056,
|
|
"epoch": 0.13216330461768955,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999928852143541,
|
|
"loss": 7.3825,
|
|
"mean_token_accuracy": 0.0878111682832241,
|
|
"num_tokens": 2681233.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.31794056892395,
|
|
"epoch": 0.13269837872545348,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999925779169703,
|
|
"loss": 7.3545,
|
|
"mean_token_accuracy": 0.08922291100025177,
|
|
"num_tokens": 2692145.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.363669300079346,
|
|
"epoch": 0.13323345283321741,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999922641229575,
|
|
"loss": 7.3874,
|
|
"mean_token_accuracy": 0.09013602733612061,
|
|
"num_tokens": 2703192.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.490590524673462,
|
|
"epoch": 0.13376852694098132,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999919438323248,
|
|
"loss": 7.4102,
|
|
"mean_token_accuracy": 0.08662581890821457,
|
|
"num_tokens": 2714804.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.302708768844605,
|
|
"epoch": 0.13430360104874525,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999916170450812,
|
|
"loss": 7.3626,
|
|
"mean_token_accuracy": 0.09281876906752587,
|
|
"num_tokens": 2724340.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.357819366455078,
|
|
"epoch": 0.13483867515650919,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999912837612364,
|
|
"loss": 7.3677,
|
|
"mean_token_accuracy": 0.0910140611231327,
|
|
"num_tokens": 2735767.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.488349437713623,
|
|
"epoch": 0.1353737492642731,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999909439807997,
|
|
"loss": 7.4274,
|
|
"mean_token_accuracy": 0.08374015688896179,
|
|
"num_tokens": 2747658.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.304438734054566,
|
|
"epoch": 0.13590882337203702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999905977037813,
|
|
"loss": 7.2895,
|
|
"mean_token_accuracy": 0.09504042863845825,
|
|
"num_tokens": 2757901.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.333110237121582,
|
|
"epoch": 0.13644389747980096,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999902449301909,
|
|
"loss": 7.3426,
|
|
"mean_token_accuracy": 0.08784788250923156,
|
|
"num_tokens": 2768945.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.313035011291504,
|
|
"epoch": 0.1369789715875649,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999898856600387,
|
|
"loss": 7.3162,
|
|
"mean_token_accuracy": 0.10365832224488258,
|
|
"num_tokens": 2780276.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.380517864227295,
|
|
"epoch": 0.1375140456953288,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999895198933354,
|
|
"loss": 7.3902,
|
|
"mean_token_accuracy": 0.09485040828585625,
|
|
"num_tokens": 2791183.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.4089750289917,
|
|
"epoch": 0.13804911980309273,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999891476300911,
|
|
"loss": 7.3059,
|
|
"mean_token_accuracy": 0.08951659351587296,
|
|
"num_tokens": 2801928.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.355879497528076,
|
|
"epoch": 0.13858419391085666,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499988768870317,
|
|
"loss": 7.3872,
|
|
"mean_token_accuracy": 0.08165468871593476,
|
|
"num_tokens": 2813415.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.355454301834106,
|
|
"epoch": 0.13911926801862057,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999883836140236,
|
|
"loss": 7.3923,
|
|
"mean_token_accuracy": 0.08718730732798577,
|
|
"num_tokens": 2825288.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.375982999801636,
|
|
"epoch": 0.1396543421263845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999879918612224,
|
|
"loss": 7.3466,
|
|
"mean_token_accuracy": 0.09210592210292816,
|
|
"num_tokens": 2836298.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.382136964797974,
|
|
"epoch": 0.14018941623414843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999875936119245,
|
|
"loss": 7.325,
|
|
"mean_token_accuracy": 0.09450321719050407,
|
|
"num_tokens": 2846367.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.285005521774292,
|
|
"epoch": 0.14072449034191237,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999871888661415,
|
|
"loss": 7.3419,
|
|
"mean_token_accuracy": 0.08686081692576408,
|
|
"num_tokens": 2856832.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.406700801849365,
|
|
"epoch": 0.14125956444967627,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499986777623885,
|
|
"loss": 7.3557,
|
|
"mean_token_accuracy": 0.08402335196733475,
|
|
"num_tokens": 2867954.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.433336400985718,
|
|
"epoch": 0.1417946385574402,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999863598851669,
|
|
"loss": 7.4023,
|
|
"mean_token_accuracy": 0.0905662328004837,
|
|
"num_tokens": 2878714.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.216334629058838,
|
|
"epoch": 0.14232971266520414,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999859356499992,
|
|
"loss": 7.3287,
|
|
"mean_token_accuracy": 0.09552604258060456,
|
|
"num_tokens": 2890697.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.416978931427002,
|
|
"epoch": 0.14286478677296804,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999855049183943,
|
|
"loss": 7.3428,
|
|
"mean_token_accuracy": 0.08655953332781792,
|
|
"num_tokens": 2901468.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.319197273254394,
|
|
"epoch": 0.14339986088073198,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999850676903646,
|
|
"loss": 7.3074,
|
|
"mean_token_accuracy": 0.0925314411520958,
|
|
"num_tokens": 2913466.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.3042479991912845,
|
|
"epoch": 0.1439349349884959,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999846239659226,
|
|
"loss": 7.2803,
|
|
"mean_token_accuracy": 0.09751186668872833,
|
|
"num_tokens": 2923638.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.315991830825806,
|
|
"epoch": 0.14447000909625984,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999841737450812,
|
|
"loss": 7.3706,
|
|
"mean_token_accuracy": 0.09228342920541763,
|
|
"num_tokens": 2934790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.371410799026489,
|
|
"epoch": 0.14500508320402375,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999837170278535,
|
|
"loss": 7.3076,
|
|
"mean_token_accuracy": 0.08736552372574806,
|
|
"num_tokens": 2946320.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.350737285614014,
|
|
"epoch": 0.14554015731178768,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999832538142526,
|
|
"loss": 7.2741,
|
|
"mean_token_accuracy": 0.09060471281409263,
|
|
"num_tokens": 2957077.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.227811241149903,
|
|
"epoch": 0.14607523141955162,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999827841042917,
|
|
"loss": 7.2953,
|
|
"mean_token_accuracy": 0.08847967609763145,
|
|
"num_tokens": 2967286.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.3782144546508786,
|
|
"epoch": 0.14661030552731552,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999823078979846,
|
|
"loss": 7.3385,
|
|
"mean_token_accuracy": 0.09329641237854958,
|
|
"num_tokens": 2979516.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.3981129169464115,
|
|
"epoch": 0.14714537963507945,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999818251953449,
|
|
"loss": 7.4533,
|
|
"mean_token_accuracy": 0.08806639239192009,
|
|
"num_tokens": 2991594.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.355781364440918,
|
|
"epoch": 0.1476804537428434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999813359963867,
|
|
"loss": 7.3319,
|
|
"mean_token_accuracy": 0.09073294252157212,
|
|
"num_tokens": 3002487.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.387376403808593,
|
|
"epoch": 0.14821552785060732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999808403011241,
|
|
"loss": 7.3475,
|
|
"mean_token_accuracy": 0.09293655529618264,
|
|
"num_tokens": 3013197.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.207638359069824,
|
|
"epoch": 0.14875060195837123,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999803381095712,
|
|
"loss": 7.3669,
|
|
"mean_token_accuracy": 0.08983460813760757,
|
|
"num_tokens": 3024512.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.475574684143067,
|
|
"epoch": 0.14928567606613516,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999798294217428,
|
|
"loss": 7.3365,
|
|
"mean_token_accuracy": 0.08949591889977455,
|
|
"num_tokens": 3035621.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.273073291778564,
|
|
"epoch": 0.1498207501738991,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999793142376533,
|
|
"loss": 7.328,
|
|
"mean_token_accuracy": 0.09089694023132325,
|
|
"num_tokens": 3046492.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.384609603881836,
|
|
"epoch": 0.150355824281663,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999787925573177,
|
|
"loss": 7.3486,
|
|
"mean_token_accuracy": 0.09108722358942031,
|
|
"num_tokens": 3057715.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.4058764457702635,
|
|
"epoch": 0.15089089838942693,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999782643807513,
|
|
"loss": 7.2967,
|
|
"mean_token_accuracy": 0.08750828057527542,
|
|
"num_tokens": 3068344.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.250711297988891,
|
|
"epoch": 0.15142597249719086,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999777297079689,
|
|
"loss": 7.2772,
|
|
"mean_token_accuracy": 0.08728645220398903,
|
|
"num_tokens": 3079576.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.336335229873657,
|
|
"epoch": 0.1519610466049548,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999771885389863,
|
|
"loss": 7.2531,
|
|
"mean_token_accuracy": 0.0913350023329258,
|
|
"num_tokens": 3090201.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.224132394790649,
|
|
"epoch": 0.1524961207127187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999766408738189,
|
|
"loss": 7.2227,
|
|
"mean_token_accuracy": 0.09826805666089058,
|
|
"num_tokens": 3099824.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.277629327774048,
|
|
"epoch": 0.15303119482048264,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999760867124827,
|
|
"loss": 7.3072,
|
|
"mean_token_accuracy": 0.08773592785000801,
|
|
"num_tokens": 3109948.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.388230419158935,
|
|
"epoch": 0.15356626892824657,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999755260549937,
|
|
"loss": 7.2946,
|
|
"mean_token_accuracy": 0.09707588031888008,
|
|
"num_tokens": 3121492.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.204993820190429,
|
|
"epoch": 0.15410134303601047,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004999749589013677,
|
|
"loss": 7.0761,
|
|
"mean_token_accuracy": 0.11195724084973335,
|
|
"num_tokens": 3131990.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.1843321323394775,
|
|
"epoch": 0.1546364171437744,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999743852516217,
|
|
"loss": 7.2552,
|
|
"mean_token_accuracy": 0.09591018855571747,
|
|
"num_tokens": 3142567.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.3704992771148685,
|
|
"epoch": 0.15517149125153834,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004999738051057717,
|
|
"loss": 7.2903,
|
|
"mean_token_accuracy": 0.09068220183253288,
|
|
"num_tokens": 3153083.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.274682903289795,
|
|
"epoch": 0.15570656535930227,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999732184638347,
|
|
"loss": 7.2761,
|
|
"mean_token_accuracy": 0.09170850291848183,
|
|
"num_tokens": 3163985.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.231216716766357,
|
|
"epoch": 0.15624163946706618,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999726253258278,
|
|
"loss": 7.2721,
|
|
"mean_token_accuracy": 0.09016884565353393,
|
|
"num_tokens": 3175259.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.324146890640259,
|
|
"epoch": 0.1567767135748301,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999720256917678,
|
|
"loss": 7.2402,
|
|
"mean_token_accuracy": 0.09691082388162613,
|
|
"num_tokens": 3185487.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.17336688041687,
|
|
"epoch": 0.15731178768259405,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999714195616723,
|
|
"loss": 7.226,
|
|
"mean_token_accuracy": 0.0957397349178791,
|
|
"num_tokens": 3196200.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.437542724609375,
|
|
"epoch": 0.15784686179035795,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999708069355586,
|
|
"loss": 7.3376,
|
|
"mean_token_accuracy": 0.08450718447566033,
|
|
"num_tokens": 3207675.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.145585060119629,
|
|
"epoch": 0.15838193589812188,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999701878134445,
|
|
"loss": 7.2091,
|
|
"mean_token_accuracy": 0.09381906762719154,
|
|
"num_tokens": 3218117.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.420627593994141,
|
|
"epoch": 0.15891701000588582,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999695621953477,
|
|
"loss": 7.2853,
|
|
"mean_token_accuracy": 0.10199789702892303,
|
|
"num_tokens": 3229208.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.2098907947540285,
|
|
"epoch": 0.15945208411364975,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999689300812866,
|
|
"loss": 7.184,
|
|
"mean_token_accuracy": 0.09962581098079681,
|
|
"num_tokens": 3239586.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.2988934993743895,
|
|
"epoch": 0.15998715822141366,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999682914712791,
|
|
"loss": 7.2533,
|
|
"mean_token_accuracy": 0.09887138307094574,
|
|
"num_tokens": 3250103.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.312133359909057,
|
|
"epoch": 0.1605222323291776,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999676463653439,
|
|
"loss": 7.2385,
|
|
"mean_token_accuracy": 0.09936083406209946,
|
|
"num_tokens": 3261844.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.241543960571289,
|
|
"epoch": 0.16105730643694152,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999669947634996,
|
|
"loss": 7.1859,
|
|
"mean_token_accuracy": 0.09886201843619347,
|
|
"num_tokens": 3272073.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.265321111679077,
|
|
"epoch": 0.16159238054470546,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999663366657647,
|
|
"loss": 7.1839,
|
|
"mean_token_accuracy": 0.09600849002599716,
|
|
"num_tokens": 3281725.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.194610452651977,
|
|
"epoch": 0.16212745465246936,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999656720721586,
|
|
"loss": 7.3232,
|
|
"mean_token_accuracy": 0.09642767012119294,
|
|
"num_tokens": 3292708.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.37993426322937,
|
|
"epoch": 0.1626625287602333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999650009827004,
|
|
"loss": 7.3017,
|
|
"mean_token_accuracy": 0.0933539777994156,
|
|
"num_tokens": 3303548.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.182165908813476,
|
|
"epoch": 0.16319760286799723,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999643233974092,
|
|
"loss": 7.1686,
|
|
"mean_token_accuracy": 0.09983909949660301,
|
|
"num_tokens": 3314261.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.272876930236817,
|
|
"epoch": 0.16373267697576113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999636393163049,
|
|
"loss": 7.1939,
|
|
"mean_token_accuracy": 0.09785049334168434,
|
|
"num_tokens": 3324833.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.116202354431152,
|
|
"epoch": 0.16426775108352507,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999629487394071,
|
|
"loss": 7.0996,
|
|
"mean_token_accuracy": 0.10248475447297097,
|
|
"num_tokens": 3334790.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.299325656890869,
|
|
"epoch": 0.164802825191289,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999622516667358,
|
|
"loss": 7.229,
|
|
"mean_token_accuracy": 0.09786866381764411,
|
|
"num_tokens": 3345115.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.127289056777954,
|
|
"epoch": 0.16533789929905293,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499961548098311,
|
|
"loss": 7.1158,
|
|
"mean_token_accuracy": 0.10143255740404129,
|
|
"num_tokens": 3356187.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.1759922981262205,
|
|
"epoch": 0.16587297340681684,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999608380341533,
|
|
"loss": 7.1422,
|
|
"mean_token_accuracy": 0.10127759128808975,
|
|
"num_tokens": 3367218.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.264885663986206,
|
|
"epoch": 0.16640804751458077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999601214742829,
|
|
"loss": 7.285,
|
|
"mean_token_accuracy": 0.08926323279738427,
|
|
"num_tokens": 3377557.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.265757751464844,
|
|
"epoch": 0.1669431216223447,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999593984187206,
|
|
"loss": 7.2802,
|
|
"mean_token_accuracy": 0.09445410892367363,
|
|
"num_tokens": 3387402.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.219360876083374,
|
|
"epoch": 0.1674781957301086,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999586688674872,
|
|
"loss": 7.1539,
|
|
"mean_token_accuracy": 0.09557267501950265,
|
|
"num_tokens": 3397924.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.275343990325927,
|
|
"epoch": 0.16801326983787254,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499957932820604,
|
|
"loss": 7.2363,
|
|
"mean_token_accuracy": 0.0918659195303917,
|
|
"num_tokens": 3408622.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.273813772201538,
|
|
"epoch": 0.16854834394563648,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499957190278092,
|
|
"loss": 7.1887,
|
|
"mean_token_accuracy": 0.09335600733757018,
|
|
"num_tokens": 3419692.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.148430204391479,
|
|
"epoch": 0.1690834180534004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999564412399728,
|
|
"loss": 7.2385,
|
|
"mean_token_accuracy": 0.09515550211071969,
|
|
"num_tokens": 3430986.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.262103271484375,
|
|
"epoch": 0.1696184921611643,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499955685706268,
|
|
"loss": 7.1655,
|
|
"mean_token_accuracy": 0.09615519493818284,
|
|
"num_tokens": 3442211.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.084865522384644,
|
|
"epoch": 0.17015356626892825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999549236769993,
|
|
"loss": 7.144,
|
|
"mean_token_accuracy": 0.10298331528902054,
|
|
"num_tokens": 3453585.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.217924642562866,
|
|
"epoch": 0.17068864037669218,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999541551521888,
|
|
"loss": 7.1997,
|
|
"mean_token_accuracy": 0.09542482867836952,
|
|
"num_tokens": 3464156.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.321245956420898,
|
|
"epoch": 0.17122371448445609,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999533801318587,
|
|
"loss": 7.2598,
|
|
"mean_token_accuracy": 0.0914094440639019,
|
|
"num_tokens": 3474853.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.274269437789917,
|
|
"epoch": 0.17175878859222002,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999525986160313,
|
|
"loss": 7.2159,
|
|
"mean_token_accuracy": 0.09993736371397972,
|
|
"num_tokens": 3486841.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.151181650161743,
|
|
"epoch": 0.17229386269998395,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999518106047293,
|
|
"loss": 7.2369,
|
|
"mean_token_accuracy": 0.09555753394961357,
|
|
"num_tokens": 3498735.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.3050923347473145,
|
|
"epoch": 0.17282893680774788,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999510160979754,
|
|
"loss": 7.2628,
|
|
"mean_token_accuracy": 0.09753414988517761,
|
|
"num_tokens": 3508829.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.1783294677734375,
|
|
"epoch": 0.1733640109155118,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999502150957925,
|
|
"loss": 7.1788,
|
|
"mean_token_accuracy": 0.09674842134118081,
|
|
"num_tokens": 3519465.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.303341913223266,
|
|
"epoch": 0.17389908502327572,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999494075982037,
|
|
"loss": 7.1351,
|
|
"mean_token_accuracy": 0.10047532543540001,
|
|
"num_tokens": 3530401.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.150378227233887,
|
|
"epoch": 0.17443415913103966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999485936052324,
|
|
"loss": 7.214,
|
|
"mean_token_accuracy": 0.09674938917160034,
|
|
"num_tokens": 3541136.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.273062419891358,
|
|
"epoch": 0.17496923323880356,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499947773116902,
|
|
"loss": 7.1883,
|
|
"mean_token_accuracy": 0.09701626598834992,
|
|
"num_tokens": 3552525.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.137057590484619,
|
|
"epoch": 0.1755043073465675,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999469461332365,
|
|
"loss": 7.1541,
|
|
"mean_token_accuracy": 0.09842078015208244,
|
|
"num_tokens": 3563028.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.233504962921143,
|
|
"epoch": 0.17603938145433143,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999461126542592,
|
|
"loss": 7.108,
|
|
"mean_token_accuracy": 0.1023821361362934,
|
|
"num_tokens": 3573354.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.027111387252807,
|
|
"epoch": 0.17657445556209536,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999452726799947,
|
|
"loss": 7.1025,
|
|
"mean_token_accuracy": 0.09993429109454155,
|
|
"num_tokens": 3585576.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.312371683120728,
|
|
"epoch": 0.17710952966985927,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999444262104671,
|
|
"loss": 7.233,
|
|
"mean_token_accuracy": 0.08933234214782715,
|
|
"num_tokens": 3596478.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.192934226989746,
|
|
"epoch": 0.1776446037776232,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999435732457007,
|
|
"loss": 7.1824,
|
|
"mean_token_accuracy": 0.09323065280914307,
|
|
"num_tokens": 3608014.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.241013860702514,
|
|
"epoch": 0.17817967788538713,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999427137857203,
|
|
"loss": 7.2286,
|
|
"mean_token_accuracy": 0.09294094443321228,
|
|
"num_tokens": 3620120.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.1006693840026855,
|
|
"epoch": 0.17871475199315104,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999418478305506,
|
|
"loss": 7.1279,
|
|
"mean_token_accuracy": 0.099704759567976,
|
|
"num_tokens": 3632578.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.275180101394653,
|
|
"epoch": 0.17924982610091497,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999409753802167,
|
|
"loss": 7.1468,
|
|
"mean_token_accuracy": 0.10483805015683174,
|
|
"num_tokens": 3643245.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.124938106536865,
|
|
"epoch": 0.1797849002086789,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999400964347437,
|
|
"loss": 7.1487,
|
|
"mean_token_accuracy": 0.09849804788827896,
|
|
"num_tokens": 3655832.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.222979402542114,
|
|
"epoch": 0.18031997431644284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999392109941571,
|
|
"loss": 7.1295,
|
|
"mean_token_accuracy": 0.10116728618741036,
|
|
"num_tokens": 3666566.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.194202947616577,
|
|
"epoch": 0.18085504842420674,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999383190584822,
|
|
"loss": 7.1611,
|
|
"mean_token_accuracy": 0.10110493823885917,
|
|
"num_tokens": 3677572.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.103847599029541,
|
|
"epoch": 0.18139012253197068,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999374206277451,
|
|
"loss": 7.0891,
|
|
"mean_token_accuracy": 0.09825331270694733,
|
|
"num_tokens": 3687116.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.121718025207519,
|
|
"epoch": 0.1819251966397346,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999365157019717,
|
|
"loss": 7.176,
|
|
"mean_token_accuracy": 0.10047127306461334,
|
|
"num_tokens": 3697961.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.246279668807984,
|
|
"epoch": 0.18246027074749852,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999356042811878,
|
|
"loss": 7.1016,
|
|
"mean_token_accuracy": 0.10373674482107162,
|
|
"num_tokens": 3708834.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.094297456741333,
|
|
"epoch": 0.18299534485526245,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049993468636542,
|
|
"loss": 7.1584,
|
|
"mean_token_accuracy": 0.09685484990477562,
|
|
"num_tokens": 3719835.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.173304510116577,
|
|
"epoch": 0.18353041896302638,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999337619546948,
|
|
"loss": 7.0544,
|
|
"mean_token_accuracy": 0.10510629564523696,
|
|
"num_tokens": 3730408.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.064211463928222,
|
|
"epoch": 0.18406549307079031,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999328310490387,
|
|
"loss": 7.1446,
|
|
"mean_token_accuracy": 0.10267272144556046,
|
|
"num_tokens": 3741257.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.2027805805206295,
|
|
"epoch": 0.18460056717855422,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999318936484789,
|
|
"loss": 7.1282,
|
|
"mean_token_accuracy": 0.10227805599570275,
|
|
"num_tokens": 3752615.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.191047954559326,
|
|
"epoch": 0.18513564128631815,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999309497530422,
|
|
"loss": 7.1568,
|
|
"mean_token_accuracy": 0.0937609352171421,
|
|
"num_tokens": 3763656.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.051603937149048,
|
|
"epoch": 0.1856707153940821,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999299993627558,
|
|
"loss": 7.1315,
|
|
"mean_token_accuracy": 0.10040904507040978,
|
|
"num_tokens": 3775257.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.149741744995117,
|
|
"epoch": 0.186205789501846,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999290424776475,
|
|
"loss": 7.0984,
|
|
"mean_token_accuracy": 0.10568056777119636,
|
|
"num_tokens": 3786094.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.321368026733398,
|
|
"epoch": 0.18674086360960993,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999280790977445,
|
|
"loss": 7.1886,
|
|
"mean_token_accuracy": 0.09335805177688598,
|
|
"num_tokens": 3796672.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.137669038772583,
|
|
"epoch": 0.18727593771737386,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499927109223075,
|
|
"loss": 7.1558,
|
|
"mean_token_accuracy": 0.10123137831687927,
|
|
"num_tokens": 3807910.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.183064413070679,
|
|
"epoch": 0.1878110118251378,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999261328536667,
|
|
"loss": 7.1356,
|
|
"mean_token_accuracy": 0.09966104477643967,
|
|
"num_tokens": 3820792.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.04319133758545,
|
|
"epoch": 0.1883460859329017,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999251499895479,
|
|
"loss": 7.038,
|
|
"mean_token_accuracy": 0.10163617879152298,
|
|
"num_tokens": 3831126.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.234713125228882,
|
|
"epoch": 0.18888116004066563,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999241606307471,
|
|
"loss": 7.1611,
|
|
"mean_token_accuracy": 0.09807982221245766,
|
|
"num_tokens": 3841923.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.183645105361938,
|
|
"epoch": 0.18941623414842956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999231647772927,
|
|
"loss": 7.0516,
|
|
"mean_token_accuracy": 0.1046050101518631,
|
|
"num_tokens": 3852504.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.985522317886352,
|
|
"epoch": 0.1899513082561935,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999221624292136,
|
|
"loss": 7.0732,
|
|
"mean_token_accuracy": 0.10412966907024383,
|
|
"num_tokens": 3862761.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.208767414093018,
|
|
"epoch": 0.1904863823639574,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999211535865385,
|
|
"loss": 7.0701,
|
|
"mean_token_accuracy": 0.09672508612275124,
|
|
"num_tokens": 3873662.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.0239424228668215,
|
|
"epoch": 0.19102145647172133,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999201382492969,
|
|
"loss": 7.0227,
|
|
"mean_token_accuracy": 0.10187353417277337,
|
|
"num_tokens": 3884835.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.158309888839722,
|
|
"epoch": 0.19155653057948527,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999191164175178,
|
|
"loss": 7.1636,
|
|
"mean_token_accuracy": 0.09919204637408256,
|
|
"num_tokens": 3895073.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.206078290939331,
|
|
"epoch": 0.19209160468724917,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999180880912309,
|
|
"loss": 7.1267,
|
|
"mean_token_accuracy": 0.09839320108294487,
|
|
"num_tokens": 3905440.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.085821580886841,
|
|
"epoch": 0.1926266787950131,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999170532704657,
|
|
"loss": 7.125,
|
|
"mean_token_accuracy": 0.09741980135440827,
|
|
"num_tokens": 3917135.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.156965684890747,
|
|
"epoch": 0.19316175290277704,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999160119552523,
|
|
"loss": 7.1303,
|
|
"mean_token_accuracy": 0.10348564088344574,
|
|
"num_tokens": 3928247.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.109297609329223,
|
|
"epoch": 0.19369682701054097,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999149641456206,
|
|
"loss": 7.1139,
|
|
"mean_token_accuracy": 0.09793074429035187,
|
|
"num_tokens": 3938609.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.246528387069702,
|
|
"epoch": 0.19423190111830488,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499913909841601,
|
|
"loss": 7.098,
|
|
"mean_token_accuracy": 0.10168406963348389,
|
|
"num_tokens": 3949221.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.995891475677491,
|
|
"epoch": 0.1947669752260688,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999128490432238,
|
|
"loss": 7.0711,
|
|
"mean_token_accuracy": 0.09396483302116394,
|
|
"num_tokens": 3959475.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.154359769821167,
|
|
"epoch": 0.19530204933383274,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999117817505196,
|
|
"loss": 7.0738,
|
|
"mean_token_accuracy": 0.11302891224622727,
|
|
"num_tokens": 3969638.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.10610032081604,
|
|
"epoch": 0.19583712344159665,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999107079635194,
|
|
"loss": 7.123,
|
|
"mean_token_accuracy": 0.10322771817445756,
|
|
"num_tokens": 3980543.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.329257583618164,
|
|
"epoch": 0.19637219754936058,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499909627682254,
|
|
"loss": 7.1756,
|
|
"mean_token_accuracy": 0.08275276124477386,
|
|
"num_tokens": 3993518.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.120573711395264,
|
|
"epoch": 0.19690727165712452,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999085409067549,
|
|
"loss": 7.155,
|
|
"mean_token_accuracy": 0.10039021968841552,
|
|
"num_tokens": 4002940.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.034014892578125,
|
|
"epoch": 0.19744234576488845,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999074476370531,
|
|
"loss": 7.0947,
|
|
"mean_token_accuracy": 0.10023277997970581,
|
|
"num_tokens": 4013982.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.101888799667359,
|
|
"epoch": 0.19797741987265235,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999063478731805,
|
|
"loss": 7.0607,
|
|
"mean_token_accuracy": 0.10425660833716392,
|
|
"num_tokens": 4025607.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.142320871353149,
|
|
"epoch": 0.1985124939804163,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999052416151687,
|
|
"loss": 7.1317,
|
|
"mean_token_accuracy": 0.09948315396904946,
|
|
"num_tokens": 4037467.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.155796337127685,
|
|
"epoch": 0.19904756808818022,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999041288630496,
|
|
"loss": 7.1317,
|
|
"mean_token_accuracy": 0.10021365135908127,
|
|
"num_tokens": 4049146.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.215651226043701,
|
|
"epoch": 0.19958264219594413,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999030096168553,
|
|
"loss": 7.1688,
|
|
"mean_token_accuracy": 0.09719501882791519,
|
|
"num_tokens": 4060500.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.176360416412353,
|
|
"epoch": 0.20011771630370806,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999018838766182,
|
|
"loss": 7.121,
|
|
"mean_token_accuracy": 0.10209911167621613,
|
|
"num_tokens": 4070553.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.173916673660278,
|
|
"epoch": 0.200652790411472,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499900751642371,
|
|
"loss": 7.0344,
|
|
"mean_token_accuracy": 0.11530624777078628,
|
|
"num_tokens": 4079653.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.061277198791504,
|
|
"epoch": 0.20118786451923593,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998996129141461,
|
|
"loss": 7.135,
|
|
"mean_token_accuracy": 0.09668742194771766,
|
|
"num_tokens": 4089912.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.230644083023071,
|
|
"epoch": 0.20172293862699983,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998984676919764,
|
|
"loss": 7.0917,
|
|
"mean_token_accuracy": 0.0961770847439766,
|
|
"num_tokens": 4100577.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.1247584342956545,
|
|
"epoch": 0.20225801273476376,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998973159758952,
|
|
"loss": 7.1167,
|
|
"mean_token_accuracy": 0.10018153339624405,
|
|
"num_tokens": 4111752.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.063771104812622,
|
|
"epoch": 0.2027930868425277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998961577659355,
|
|
"loss": 7.0671,
|
|
"mean_token_accuracy": 0.10595502480864524,
|
|
"num_tokens": 4122616.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.2158653259277346,
|
|
"epoch": 0.2033281609502916,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998949930621309,
|
|
"loss": 7.1747,
|
|
"mean_token_accuracy": 0.1001809298992157,
|
|
"num_tokens": 4134275.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.102860450744629,
|
|
"epoch": 0.20386323505805554,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998938218645149,
|
|
"loss": 7.0642,
|
|
"mean_token_accuracy": 0.10334794074296952,
|
|
"num_tokens": 4146412.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.073519086837768,
|
|
"epoch": 0.20439830916581947,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998926441731215,
|
|
"loss": 7.0558,
|
|
"mean_token_accuracy": 0.10119741782546043,
|
|
"num_tokens": 4157592.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.074370908737182,
|
|
"epoch": 0.2049333832735834,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998914599879845,
|
|
"loss": 7.0511,
|
|
"mean_token_accuracy": 0.10084806829690933,
|
|
"num_tokens": 4168637.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.115645503997802,
|
|
"epoch": 0.2054684573813473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998902693091382,
|
|
"loss": 7.0857,
|
|
"mean_token_accuracy": 0.09849425479769706,
|
|
"num_tokens": 4179951.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.090283823013306,
|
|
"epoch": 0.20600353148911124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998890721366171,
|
|
"loss": 6.9867,
|
|
"mean_token_accuracy": 0.10344830304384231,
|
|
"num_tokens": 4189895.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.081069898605347,
|
|
"epoch": 0.20653860559687517,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998878684704556,
|
|
"loss": 7.0339,
|
|
"mean_token_accuracy": 0.10446125566959381,
|
|
"num_tokens": 4199796.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.079880237579346,
|
|
"epoch": 0.20707367970463908,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998866583106884,
|
|
"loss": 7.0653,
|
|
"mean_token_accuracy": 0.10093458741903305,
|
|
"num_tokens": 4210428.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.160430908203125,
|
|
"epoch": 0.207608753812403,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998854416573506,
|
|
"loss": 7.1286,
|
|
"mean_token_accuracy": 0.10443870946764947,
|
|
"num_tokens": 4221515.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.142211771011352,
|
|
"epoch": 0.20814382792016695,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998842185104772,
|
|
"loss": 7.1474,
|
|
"mean_token_accuracy": 0.0981269545853138,
|
|
"num_tokens": 4232580.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.054647779464721,
|
|
"epoch": 0.20867890202793088,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998829888701036,
|
|
"loss": 7.0565,
|
|
"mean_token_accuracy": 0.10753207132220269,
|
|
"num_tokens": 4242871.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.156534862518311,
|
|
"epoch": 0.20921397613569478,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998817527362654,
|
|
"loss": 7.0786,
|
|
"mean_token_accuracy": 0.09486880823969841,
|
|
"num_tokens": 4253419.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.098293828964233,
|
|
"epoch": 0.20974905024345872,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998805101089982,
|
|
"loss": 7.0551,
|
|
"mean_token_accuracy": 0.10472317561507224,
|
|
"num_tokens": 4264327.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.143654727935791,
|
|
"epoch": 0.21028412435122265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998792609883378,
|
|
"loss": 7.0423,
|
|
"mean_token_accuracy": 0.10480301082134247,
|
|
"num_tokens": 4274568.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.062982511520386,
|
|
"epoch": 0.21081919845898656,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998780053743203,
|
|
"loss": 7.0376,
|
|
"mean_token_accuracy": 0.10589545667171478,
|
|
"num_tokens": 4284895.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.148151302337647,
|
|
"epoch": 0.2113542725667505,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998767432669822,
|
|
"loss": 7.0787,
|
|
"mean_token_accuracy": 0.102964149415493,
|
|
"num_tokens": 4297258.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.025489664077758,
|
|
"epoch": 0.21188934667451442,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998754746663595,
|
|
"loss": 6.9864,
|
|
"mean_token_accuracy": 0.10545038804411888,
|
|
"num_tokens": 4308307.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.0815025806427006,
|
|
"epoch": 0.21242442078227836,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998741995724892,
|
|
"loss": 7.0615,
|
|
"mean_token_accuracy": 0.10010265707969665,
|
|
"num_tokens": 4318801.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.061044788360595,
|
|
"epoch": 0.21295949489004226,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998729179854079,
|
|
"loss": 7.0328,
|
|
"mean_token_accuracy": 0.1036236509680748,
|
|
"num_tokens": 4329531.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.0804825782775875,
|
|
"epoch": 0.2134945689978062,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998716299051527,
|
|
"loss": 7.0256,
|
|
"mean_token_accuracy": 0.10520645901560784,
|
|
"num_tokens": 4341203.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.035392093658447,
|
|
"epoch": 0.21402964310557013,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998703353317609,
|
|
"loss": 7.0754,
|
|
"mean_token_accuracy": 0.09851410016417503,
|
|
"num_tokens": 4352426.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.181427955627441,
|
|
"epoch": 0.21456471721333403,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998690342652697,
|
|
"loss": 7.0155,
|
|
"mean_token_accuracy": 0.10717839673161507,
|
|
"num_tokens": 4363413.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.992197751998901,
|
|
"epoch": 0.21509979132109797,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998677267057166,
|
|
"loss": 6.9503,
|
|
"mean_token_accuracy": 0.10650679394602776,
|
|
"num_tokens": 4373470.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.0062854290008545,
|
|
"epoch": 0.2156348654288619,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998664126531397,
|
|
"loss": 7.0237,
|
|
"mean_token_accuracy": 0.10450349599123002,
|
|
"num_tokens": 4384438.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.172478914260864,
|
|
"epoch": 0.21616993953662583,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998650921075766,
|
|
"loss": 6.9991,
|
|
"mean_token_accuracy": 0.10896808505058289,
|
|
"num_tokens": 4395100.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.004340648651123,
|
|
"epoch": 0.21670501364438974,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998637650690656,
|
|
"loss": 7.1196,
|
|
"mean_token_accuracy": 0.09563550055027008,
|
|
"num_tokens": 4407131.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.083667659759522,
|
|
"epoch": 0.21724008775215367,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499862431537645,
|
|
"loss": 6.9577,
|
|
"mean_token_accuracy": 0.10268971174955369,
|
|
"num_tokens": 4417701.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.023851299285889,
|
|
"epoch": 0.2177751618599176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998610915133533,
|
|
"loss": 7.0216,
|
|
"mean_token_accuracy": 0.10145122185349464,
|
|
"num_tokens": 4429309.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.0214043140411375,
|
|
"epoch": 0.21831023596768154,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998597449962292,
|
|
"loss": 7.0769,
|
|
"mean_token_accuracy": 0.10378911569714547,
|
|
"num_tokens": 4440850.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.054154539108277,
|
|
"epoch": 0.21884531007544544,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998583919863115,
|
|
"loss": 7.054,
|
|
"mean_token_accuracy": 0.09939034059643745,
|
|
"num_tokens": 4451995.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.043123245239258,
|
|
"epoch": 0.21938038418320938,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998570324836393,
|
|
"loss": 6.972,
|
|
"mean_token_accuracy": 0.10836615711450577,
|
|
"num_tokens": 4461916.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.089596509933472,
|
|
"epoch": 0.2199154582909733,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499855666488252,
|
|
"loss": 7.0501,
|
|
"mean_token_accuracy": 0.10234842598438262,
|
|
"num_tokens": 4471603.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.144379091262818,
|
|
"epoch": 0.22045053239873721,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998542940001889,
|
|
"loss": 7.0775,
|
|
"mean_token_accuracy": 0.10257849842309952,
|
|
"num_tokens": 4483166.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.052639961242676,
|
|
"epoch": 0.22098560650650115,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998529150194895,
|
|
"loss": 7.0006,
|
|
"mean_token_accuracy": 0.10316628888249398,
|
|
"num_tokens": 4493824.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.0311055183410645,
|
|
"epoch": 0.22152068061426508,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998515295461939,
|
|
"loss": 6.9058,
|
|
"mean_token_accuracy": 0.12331796064972878,
|
|
"num_tokens": 4505674.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.943395900726318,
|
|
"epoch": 0.22205575472202901,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499850137580342,
|
|
"loss": 7.0,
|
|
"mean_token_accuracy": 0.10888025835156441,
|
|
"num_tokens": 4516516.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.085627651214599,
|
|
"epoch": 0.22259082882979292,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998487391219739,
|
|
"loss": 6.9976,
|
|
"mean_token_accuracy": 0.10101775825023651,
|
|
"num_tokens": 4527811.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.010357475280761,
|
|
"epoch": 0.22312590293755685,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998473341711301,
|
|
"loss": 6.9383,
|
|
"mean_token_accuracy": 0.10195653289556503,
|
|
"num_tokens": 4538988.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.025439023971558,
|
|
"epoch": 0.22366097704532079,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998459227278512,
|
|
"loss": 6.9788,
|
|
"mean_token_accuracy": 0.10650492385029793,
|
|
"num_tokens": 4550049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.1111595153808596,
|
|
"epoch": 0.2241960511530847,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998445047921777,
|
|
"loss": 7.0758,
|
|
"mean_token_accuracy": 0.10203522294759751,
|
|
"num_tokens": 4559784.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.0501655578613285,
|
|
"epoch": 0.22473112526084862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998430803641509,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.10454667881131172,
|
|
"num_tokens": 4569982.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.932292032241821,
|
|
"epoch": 0.22526619936861256,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998416494438118,
|
|
"loss": 6.9489,
|
|
"mean_token_accuracy": 0.10733313858509064,
|
|
"num_tokens": 4581117.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.042090797424317,
|
|
"epoch": 0.2258012734763765,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998402120312014,
|
|
"loss": 7.0174,
|
|
"mean_token_accuracy": 0.10961635783314705,
|
|
"num_tokens": 4592012.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.025863790512085,
|
|
"epoch": 0.2263363475841404,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998387681263616,
|
|
"loss": 7.0634,
|
|
"mean_token_accuracy": 0.10254996567964554,
|
|
"num_tokens": 4602591.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.054075098037719,
|
|
"epoch": 0.22687142169190433,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499837317729334,
|
|
"loss": 6.9882,
|
|
"mean_token_accuracy": 0.10465681180357933,
|
|
"num_tokens": 4613418.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.957354021072388,
|
|
"epoch": 0.22740649579966826,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998358608401603,
|
|
"loss": 6.9169,
|
|
"mean_token_accuracy": 0.1147283211350441,
|
|
"num_tokens": 4625156.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.111089897155762,
|
|
"epoch": 0.22794156990743217,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499834397458883,
|
|
"loss": 6.9472,
|
|
"mean_token_accuracy": 0.10765151679515839,
|
|
"num_tokens": 4634523.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.936869287490845,
|
|
"epoch": 0.2284766440151961,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998329275855438,
|
|
"loss": 6.9341,
|
|
"mean_token_accuracy": 0.11054303497076035,
|
|
"num_tokens": 4646292.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.02635498046875,
|
|
"epoch": 0.22901171812296003,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998314512201855,
|
|
"loss": 6.9176,
|
|
"mean_token_accuracy": 0.10452343374490738,
|
|
"num_tokens": 4656417.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.944140291213989,
|
|
"epoch": 0.22954679223072397,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998299683628507,
|
|
"loss": 6.9361,
|
|
"mean_token_accuracy": 0.10723940208554268,
|
|
"num_tokens": 4666933.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.071186447143555,
|
|
"epoch": 0.23008186633848787,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998284790135821,
|
|
"loss": 7.1086,
|
|
"mean_token_accuracy": 0.09997956231236457,
|
|
"num_tokens": 4678482.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.071504402160644,
|
|
"epoch": 0.2306169404462518,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998269831724228,
|
|
"loss": 6.943,
|
|
"mean_token_accuracy": 0.1055432416498661,
|
|
"num_tokens": 4688454.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.989952278137207,
|
|
"epoch": 0.23115201455401574,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998254808394159,
|
|
"loss": 6.9886,
|
|
"mean_token_accuracy": 0.10683377385139466,
|
|
"num_tokens": 4699545.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.105897760391235,
|
|
"epoch": 0.23168708866177964,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004998239720146048,
|
|
"loss": 7.0006,
|
|
"mean_token_accuracy": 0.10335398241877555,
|
|
"num_tokens": 4711149.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.922723054885864,
|
|
"epoch": 0.23222216276954358,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998224566980332,
|
|
"loss": 6.996,
|
|
"mean_token_accuracy": 0.10218452662229538,
|
|
"num_tokens": 4722651.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.068100786209106,
|
|
"epoch": 0.2327572368773075,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998209348897447,
|
|
"loss": 6.9957,
|
|
"mean_token_accuracy": 0.09393229782581329,
|
|
"num_tokens": 4733883.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.1184226989746096,
|
|
"epoch": 0.23329231098507144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998194065897833,
|
|
"loss": 6.9513,
|
|
"mean_token_accuracy": 0.11117385998368264,
|
|
"num_tokens": 4744517.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.966147184371948,
|
|
"epoch": 0.23382738509283535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499817871798193,
|
|
"loss": 6.9746,
|
|
"mean_token_accuracy": 0.11019051298499108,
|
|
"num_tokens": 4755481.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.96983757019043,
|
|
"epoch": 0.23436245920059928,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998163305150185,
|
|
"loss": 6.9042,
|
|
"mean_token_accuracy": 0.11359247267246246,
|
|
"num_tokens": 4765535.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 7.0188885688781735,
|
|
"epoch": 0.23489753330836322,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998147827403038,
|
|
"loss": 7.0168,
|
|
"mean_token_accuracy": 0.10479639694094658,
|
|
"num_tokens": 4777045.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.045113372802734,
|
|
"epoch": 0.23543260741612712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499813228474094,
|
|
"loss": 6.9067,
|
|
"mean_token_accuracy": 0.11008131876587868,
|
|
"num_tokens": 4787958.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.917256498336792,
|
|
"epoch": 0.23596768152389105,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998116677164338,
|
|
"loss": 6.9399,
|
|
"mean_token_accuracy": 0.1049346685409546,
|
|
"num_tokens": 4798502.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.958500146865845,
|
|
"epoch": 0.236502755631655,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998101004673682,
|
|
"loss": 6.9403,
|
|
"mean_token_accuracy": 0.1110065832734108,
|
|
"num_tokens": 4809179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.1306075096130375,
|
|
"epoch": 0.23703782973941892,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998085267269426,
|
|
"loss": 7.0169,
|
|
"mean_token_accuracy": 0.09675444290041924,
|
|
"num_tokens": 4819803.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.033319044113159,
|
|
"epoch": 0.23757290384718283,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998069464952025,
|
|
"loss": 6.9958,
|
|
"mean_token_accuracy": 0.1008896566927433,
|
|
"num_tokens": 4831226.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 7.051976871490479,
|
|
"epoch": 0.23810797795494676,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998053597721932,
|
|
"loss": 7.0115,
|
|
"mean_token_accuracy": 0.10829942151904107,
|
|
"num_tokens": 4842168.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 7.034261083602905,
|
|
"epoch": 0.2386430520627107,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998037665579608,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.10675674006342888,
|
|
"num_tokens": 4852655.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.881174850463867,
|
|
"epoch": 0.2391781261704746,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998021668525513,
|
|
"loss": 6.8537,
|
|
"mean_token_accuracy": 0.11227660775184631,
|
|
"num_tokens": 4862164.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.07776198387146,
|
|
"epoch": 0.23971320027823853,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998005606560107,
|
|
"loss": 7.0126,
|
|
"mean_token_accuracy": 0.11018440797924996,
|
|
"num_tokens": 4874233.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.984408712387085,
|
|
"epoch": 0.24024827438600246,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997989479683856,
|
|
"loss": 6.9927,
|
|
"mean_token_accuracy": 0.10390212759375572,
|
|
"num_tokens": 4885948.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.981641530990601,
|
|
"epoch": 0.2407833484937664,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997973287897224,
|
|
"loss": 6.9739,
|
|
"mean_token_accuracy": 0.10715372562408447,
|
|
"num_tokens": 4897128.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.011375617980957,
|
|
"epoch": 0.2413184226015303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997957031200681,
|
|
"loss": 6.939,
|
|
"mean_token_accuracy": 0.11313669458031654,
|
|
"num_tokens": 4907699.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.93510890007019,
|
|
"epoch": 0.24185349670929424,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997940709594692,
|
|
"loss": 6.875,
|
|
"mean_token_accuracy": 0.10799874365329742,
|
|
"num_tokens": 4918772.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.044176292419434,
|
|
"epoch": 0.24238857081705817,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997924323079733,
|
|
"loss": 6.9352,
|
|
"mean_token_accuracy": 0.10844795927405357,
|
|
"num_tokens": 4930046.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.897712516784668,
|
|
"epoch": 0.24292364492482207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997907871656273,
|
|
"loss": 6.9542,
|
|
"mean_token_accuracy": 0.10848618820309638,
|
|
"num_tokens": 4940609.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.033410692214966,
|
|
"epoch": 0.243458719032586,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997891355324791,
|
|
"loss": 6.9538,
|
|
"mean_token_accuracy": 0.10902024582028388,
|
|
"num_tokens": 4951339.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.970147943496704,
|
|
"epoch": 0.24399379314034994,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997874774085761,
|
|
"loss": 6.8889,
|
|
"mean_token_accuracy": 0.10065512731671333,
|
|
"num_tokens": 4961083.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.938036298751831,
|
|
"epoch": 0.24452886724811387,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997858127939662,
|
|
"loss": 6.8926,
|
|
"mean_token_accuracy": 0.10896471291780471,
|
|
"num_tokens": 4971399.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.986947107315063,
|
|
"epoch": 0.24506394135587778,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997841416886976,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.1085882268846035,
|
|
"num_tokens": 4982429.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 7.061171579360962,
|
|
"epoch": 0.2455990154636417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997824640928186,
|
|
"loss": 7.0195,
|
|
"mean_token_accuracy": 0.10628353208303451,
|
|
"num_tokens": 4993706.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.986022043228149,
|
|
"epoch": 0.24613408957140565,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997807800063774,
|
|
"loss": 6.9109,
|
|
"mean_token_accuracy": 0.11161794662475585,
|
|
"num_tokens": 5005411.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.0011697769165036,
|
|
"epoch": 0.24666916367916958,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499779089429423,
|
|
"loss": 7.0298,
|
|
"mean_token_accuracy": 0.10325584262609482,
|
|
"num_tokens": 5016011.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.0111462593078615,
|
|
"epoch": 0.24720423778693348,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997773923620037,
|
|
"loss": 6.9998,
|
|
"mean_token_accuracy": 0.10303730890154839,
|
|
"num_tokens": 5027841.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 7.078068637847901,
|
|
"epoch": 0.24773931189469742,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997756888041689,
|
|
"loss": 6.9792,
|
|
"mean_token_accuracy": 0.09846872761845589,
|
|
"num_tokens": 5038640.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.975053834915161,
|
|
"epoch": 0.24827438600246135,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997739787559677,
|
|
"loss": 6.9227,
|
|
"mean_token_accuracy": 0.10773401260375977,
|
|
"num_tokens": 5050423.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.994720554351806,
|
|
"epoch": 0.24880946011022526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997722622174494,
|
|
"loss": 6.9495,
|
|
"mean_token_accuracy": 0.10427153035998345,
|
|
"num_tokens": 5060654.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.94322247505188,
|
|
"epoch": 0.2493445342179892,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997705391886636,
|
|
"loss": 6.8533,
|
|
"mean_token_accuracy": 0.11165059134364128,
|
|
"num_tokens": 5070165.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.8971030712127686,
|
|
"epoch": 0.24987960832575312,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997688096696601,
|
|
"loss": 6.9014,
|
|
"mean_token_accuracy": 0.10189634934067726,
|
|
"num_tokens": 5080937.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.940387964248657,
|
|
"epoch": 0.25041468243351706,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997670736604888,
|
|
"loss": 6.8601,
|
|
"mean_token_accuracy": 0.11307725235819817,
|
|
"num_tokens": 5090955.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 7.025439310073852,
|
|
"epoch": 0.250949756541281,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997653311611998,
|
|
"loss": 7.012,
|
|
"mean_token_accuracy": 0.1010633334517479,
|
|
"num_tokens": 5102201.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.99841890335083,
|
|
"epoch": 0.25148483064904487,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997635821718435,
|
|
"loss": 6.935,
|
|
"mean_token_accuracy": 0.11045385003089905,
|
|
"num_tokens": 5112235.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.925424194335937,
|
|
"epoch": 0.2520199047568088,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997618266924704,
|
|
"loss": 6.7969,
|
|
"mean_token_accuracy": 0.10532390475273132,
|
|
"num_tokens": 5122360.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.942410039901733,
|
|
"epoch": 0.25255497886457273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499760064723131,
|
|
"loss": 6.9771,
|
|
"mean_token_accuracy": 0.10276588127017021,
|
|
"num_tokens": 5133084.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.947847557067871,
|
|
"epoch": 0.25309005297233667,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997582962638764,
|
|
"loss": 6.9291,
|
|
"mean_token_accuracy": 0.10205074176192283,
|
|
"num_tokens": 5144495.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.063449239730835,
|
|
"epoch": 0.2536251270801006,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997565213147575,
|
|
"loss": 6.9216,
|
|
"mean_token_accuracy": 0.11108831390738487,
|
|
"num_tokens": 5154824.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.933940172195435,
|
|
"epoch": 0.25416020118786453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997547398758257,
|
|
"loss": 6.9012,
|
|
"mean_token_accuracy": 0.10534899979829788,
|
|
"num_tokens": 5165061.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.941448068618774,
|
|
"epoch": 0.25469527529562846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997529519471323,
|
|
"loss": 6.8652,
|
|
"mean_token_accuracy": 0.11675361394882203,
|
|
"num_tokens": 5174964.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.894770765304566,
|
|
"epoch": 0.25523034940339234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997511575287291,
|
|
"loss": 6.9139,
|
|
"mean_token_accuracy": 0.10526548847556114,
|
|
"num_tokens": 5185458.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.003988265991211,
|
|
"epoch": 0.2557654235111563,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997493566206677,
|
|
"loss": 6.8953,
|
|
"mean_token_accuracy": 0.10926351025700569,
|
|
"num_tokens": 5196193.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.910524320602417,
|
|
"epoch": 0.2563004976189202,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997475492230003,
|
|
"loss": 7.0084,
|
|
"mean_token_accuracy": 0.09937358275055885,
|
|
"num_tokens": 5208541.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 7.02528567314148,
|
|
"epoch": 0.25683557172668414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499745735335779,
|
|
"loss": 6.8456,
|
|
"mean_token_accuracy": 0.11003420725464821,
|
|
"num_tokens": 5218567.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.922707414627075,
|
|
"epoch": 0.2573706458344481,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997439149590561,
|
|
"loss": 6.9484,
|
|
"mean_token_accuracy": 0.10656592324376106,
|
|
"num_tokens": 5228293.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.966908025741577,
|
|
"epoch": 0.257905719942212,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997420880928843,
|
|
"loss": 6.8958,
|
|
"mean_token_accuracy": 0.11399568244814873,
|
|
"num_tokens": 5238880.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.962517213821411,
|
|
"epoch": 0.25844079404997594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997402547373162,
|
|
"loss": 6.9943,
|
|
"mean_token_accuracy": 0.10480297654867173,
|
|
"num_tokens": 5250104.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.100482559204101,
|
|
"epoch": 0.2589758681577399,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997384148924049,
|
|
"loss": 7.011,
|
|
"mean_token_accuracy": 0.10677094757556915,
|
|
"num_tokens": 5260355.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.962700939178466,
|
|
"epoch": 0.25951094226550375,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997365685582035,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.1068173035979271,
|
|
"num_tokens": 5272117.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.024838829040528,
|
|
"epoch": 0.2600460163732677,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997347157347651,
|
|
"loss": 7.0198,
|
|
"mean_token_accuracy": 0.09878586754202842,
|
|
"num_tokens": 5284583.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.973494672775269,
|
|
"epoch": 0.2605810904810316,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997328564221435,
|
|
"loss": 6.8048,
|
|
"mean_token_accuracy": 0.11668524593114853,
|
|
"num_tokens": 5295846.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.864496850967408,
|
|
"epoch": 0.26111616458879555,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997309906203922,
|
|
"loss": 6.9651,
|
|
"mean_token_accuracy": 0.10438142120838165,
|
|
"num_tokens": 5307802.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.095636558532715,
|
|
"epoch": 0.2616512386965595,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997291183295652,
|
|
"loss": 6.8785,
|
|
"mean_token_accuracy": 0.11019614040851593,
|
|
"num_tokens": 5318263.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.985703229904175,
|
|
"epoch": 0.2621863128043234,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997272395497164,
|
|
"loss": 6.9369,
|
|
"mean_token_accuracy": 0.10467563569545746,
|
|
"num_tokens": 5328555.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.877440309524536,
|
|
"epoch": 0.26272138691208735,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997253542809002,
|
|
"loss": 6.8952,
|
|
"mean_token_accuracy": 0.11062222197651864,
|
|
"num_tokens": 5339954.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.098154449462891,
|
|
"epoch": 0.26325646101985123,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997234625231709,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.10974880829453468,
|
|
"num_tokens": 5350919.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.838466548919678,
|
|
"epoch": 0.26379153512761516,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997215642765832,
|
|
"loss": 6.9072,
|
|
"mean_token_accuracy": 0.11278821527957916,
|
|
"num_tokens": 5361844.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.999466514587402,
|
|
"epoch": 0.2643266092353791,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499719659541192,
|
|
"loss": 6.9529,
|
|
"mean_token_accuracy": 0.10501818954944611,
|
|
"num_tokens": 5372026.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.002458000183106,
|
|
"epoch": 0.26486168334314303,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997177483170521,
|
|
"loss": 6.9913,
|
|
"mean_token_accuracy": 0.11029187738895416,
|
|
"num_tokens": 5382965.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.9821876049041744,
|
|
"epoch": 0.26539675745090696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997158306042188,
|
|
"loss": 6.9353,
|
|
"mean_token_accuracy": 0.11200979501008987,
|
|
"num_tokens": 5393738.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.932433700561523,
|
|
"epoch": 0.2659318315586709,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997139064027476,
|
|
"loss": 6.8079,
|
|
"mean_token_accuracy": 0.1185495488345623,
|
|
"num_tokens": 5404059.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.902970170974731,
|
|
"epoch": 0.26646690566643483,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997119757126938,
|
|
"loss": 6.8471,
|
|
"mean_token_accuracy": 0.10944071337580681,
|
|
"num_tokens": 5414152.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 7.007512903213501,
|
|
"epoch": 0.2670019797741987,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997100385341133,
|
|
"loss": 7.0207,
|
|
"mean_token_accuracy": 0.1047422781586647,
|
|
"num_tokens": 5425227.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.9481219291687015,
|
|
"epoch": 0.26753705388196264,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997080948670621,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.11013932898640633,
|
|
"num_tokens": 5435716.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.94979419708252,
|
|
"epoch": 0.26807212798972657,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997061447115962,
|
|
"loss": 6.9098,
|
|
"mean_token_accuracy": 0.10717173442244529,
|
|
"num_tokens": 5446519.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.94394063949585,
|
|
"epoch": 0.2686072020974905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997041880677719,
|
|
"loss": 6.9125,
|
|
"mean_token_accuracy": 0.10961175858974456,
|
|
"num_tokens": 5457496.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.833197116851807,
|
|
"epoch": 0.26914227620525444,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997022249356457,
|
|
"loss": 6.7977,
|
|
"mean_token_accuracy": 0.11055489629507065,
|
|
"num_tokens": 5469059.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.931081962585449,
|
|
"epoch": 0.26967735031301837,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997002553152745,
|
|
"loss": 6.9011,
|
|
"mean_token_accuracy": 0.10881304815411567,
|
|
"num_tokens": 5480324.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.962761163711548,
|
|
"epoch": 0.2702124244207823,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996982792067148,
|
|
"loss": 6.9194,
|
|
"mean_token_accuracy": 0.10171629562973976,
|
|
"num_tokens": 5491513.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.862958478927612,
|
|
"epoch": 0.2707474985285462,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499696296610024,
|
|
"loss": 6.8224,
|
|
"mean_token_accuracy": 0.11024987697601318,
|
|
"num_tokens": 5502414.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.903598022460938,
|
|
"epoch": 0.2712825726363101,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996943075252592,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.10326235815882683,
|
|
"num_tokens": 5512962.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.995188236236572,
|
|
"epoch": 0.27181764674407405,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996923119524777,
|
|
"loss": 6.8347,
|
|
"mean_token_accuracy": 0.10915073826909065,
|
|
"num_tokens": 5524648.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.832237482070923,
|
|
"epoch": 0.272352720851838,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996903098917375,
|
|
"loss": 6.9081,
|
|
"mean_token_accuracy": 0.10347842946648597,
|
|
"num_tokens": 5536158.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.879280519485474,
|
|
"epoch": 0.2728877949596019,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499688301343096,
|
|
"loss": 6.8113,
|
|
"mean_token_accuracy": 0.11145112216472626,
|
|
"num_tokens": 5547374.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9910749912261965,
|
|
"epoch": 0.27342286906736585,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996862863066114,
|
|
"loss": 6.9016,
|
|
"mean_token_accuracy": 0.10962290540337563,
|
|
"num_tokens": 5559212.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.935283899307251,
|
|
"epoch": 0.2739579431751298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996842647823419,
|
|
"loss": 6.862,
|
|
"mean_token_accuracy": 0.11124518364667893,
|
|
"num_tokens": 5569302.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.867130374908447,
|
|
"epoch": 0.27449301728289366,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996822367703458,
|
|
"loss": 6.8764,
|
|
"mean_token_accuracy": 0.1044128842651844,
|
|
"num_tokens": 5581688.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.930262565612793,
|
|
"epoch": 0.2750280913906576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996802022706817,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.1141422875225544,
|
|
"num_tokens": 5591376.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.87796802520752,
|
|
"epoch": 0.2755631654984215,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996781612834083,
|
|
"loss": 6.8474,
|
|
"mean_token_accuracy": 0.11154236644506454,
|
|
"num_tokens": 5601510.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.987272834777832,
|
|
"epoch": 0.27609823960618546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996761138085846,
|
|
"loss": 6.9155,
|
|
"mean_token_accuracy": 0.10548463389277458,
|
|
"num_tokens": 5611436.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.904627418518066,
|
|
"epoch": 0.2766333137139494,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996740598462697,
|
|
"loss": 6.919,
|
|
"mean_token_accuracy": 0.10808756351470947,
|
|
"num_tokens": 5620470.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.84314284324646,
|
|
"epoch": 0.2771683878217133,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996719993965229,
|
|
"loss": 6.8253,
|
|
"mean_token_accuracy": 0.11080246791243553,
|
|
"num_tokens": 5630740.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.915116310119629,
|
|
"epoch": 0.27770346192947726,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996699324594036,
|
|
"loss": 6.8227,
|
|
"mean_token_accuracy": 0.11591969728469849,
|
|
"num_tokens": 5641138.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.922396898269653,
|
|
"epoch": 0.27823853603724114,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996678590349717,
|
|
"loss": 6.9565,
|
|
"mean_token_accuracy": 0.10815248861908913,
|
|
"num_tokens": 5652474.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.979134368896484,
|
|
"epoch": 0.27877361014500507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996657791232868,
|
|
"loss": 6.8568,
|
|
"mean_token_accuracy": 0.11182226091623307,
|
|
"num_tokens": 5663178.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.886240863800049,
|
|
"epoch": 0.279308684252769,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996636927244092,
|
|
"loss": 6.8834,
|
|
"mean_token_accuracy": 0.10366401001811028,
|
|
"num_tokens": 5673565.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 7.031818151473999,
|
|
"epoch": 0.27984375836053293,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499661599838399,
|
|
"loss": 6.924,
|
|
"mean_token_accuracy": 0.10450949743390084,
|
|
"num_tokens": 5684651.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.81337537765503,
|
|
"epoch": 0.28037883246829687,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996595004653167,
|
|
"loss": 6.8068,
|
|
"mean_token_accuracy": 0.1102476328611374,
|
|
"num_tokens": 5696081.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.930059099197388,
|
|
"epoch": 0.2809139065760608,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996573946052229,
|
|
"loss": 6.8431,
|
|
"mean_token_accuracy": 0.11160285472869873,
|
|
"num_tokens": 5706830.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.902744102478027,
|
|
"epoch": 0.28144898068382473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996552822581783,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.11438541486859322,
|
|
"num_tokens": 5717261.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.92958779335022,
|
|
"epoch": 0.2819840547915886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499653163424244,
|
|
"loss": 6.8333,
|
|
"mean_token_accuracy": 0.10897459760308266,
|
|
"num_tokens": 5727280.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.897455167770386,
|
|
"epoch": 0.28251912889935255,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996510381034814,
|
|
"loss": 6.9035,
|
|
"mean_token_accuracy": 0.10450076460838317,
|
|
"num_tokens": 5737485.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.918154382705689,
|
|
"epoch": 0.2830542030071165,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996489062959515,
|
|
"loss": 6.8543,
|
|
"mean_token_accuracy": 0.10870546996593475,
|
|
"num_tokens": 5747683.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.8486976146698,
|
|
"epoch": 0.2835892771148804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996467680017159,
|
|
"loss": 6.927,
|
|
"mean_token_accuracy": 0.10556823164224624,
|
|
"num_tokens": 5758148.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.931982326507568,
|
|
"epoch": 0.28412435122264434,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996446232208365,
|
|
"loss": 6.855,
|
|
"mean_token_accuracy": 0.11552600264549255,
|
|
"num_tokens": 5769109.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.934611415863037,
|
|
"epoch": 0.2846594253304083,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996424719533753,
|
|
"loss": 6.8814,
|
|
"mean_token_accuracy": 0.10460555031895638,
|
|
"num_tokens": 5780344.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.882219982147217,
|
|
"epoch": 0.2851944994381722,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996403141993941,
|
|
"loss": 6.6908,
|
|
"mean_token_accuracy": 0.11797674894332885,
|
|
"num_tokens": 5790167.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.848588514328003,
|
|
"epoch": 0.2857295735459361,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996381499589555,
|
|
"loss": 6.8693,
|
|
"mean_token_accuracy": 0.10816706344485283,
|
|
"num_tokens": 5800076.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.981981515884399,
|
|
"epoch": 0.2862646476537,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996359792321219,
|
|
"loss": 6.806,
|
|
"mean_token_accuracy": 0.11308679804205894,
|
|
"num_tokens": 5810547.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.848021030426025,
|
|
"epoch": 0.28679972176146395,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499633802018956,
|
|
"loss": 6.8335,
|
|
"mean_token_accuracy": 0.11338982209563256,
|
|
"num_tokens": 5821210.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.866777563095093,
|
|
"epoch": 0.2873347958692279,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996316183195204,
|
|
"loss": 6.8726,
|
|
"mean_token_accuracy": 0.10846167802810669,
|
|
"num_tokens": 5832361.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.973077297210693,
|
|
"epoch": 0.2878698699769918,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996294281338786,
|
|
"loss": 6.8657,
|
|
"mean_token_accuracy": 0.10616375505924225,
|
|
"num_tokens": 5843242.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.948590850830078,
|
|
"epoch": 0.28840494408475575,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996272314620936,
|
|
"loss": 6.9116,
|
|
"mean_token_accuracy": 0.10822648853063584,
|
|
"num_tokens": 5855163.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.8517499446868895,
|
|
"epoch": 0.2889400181925197,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996250283042288,
|
|
"loss": 6.8609,
|
|
"mean_token_accuracy": 0.11147657707333565,
|
|
"num_tokens": 5866908.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.9437988758087155,
|
|
"epoch": 0.28947509230028357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499622818660348,
|
|
"loss": 6.8965,
|
|
"mean_token_accuracy": 0.10642576739192008,
|
|
"num_tokens": 5877342.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.871459531784057,
|
|
"epoch": 0.2900101664080475,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996206025305147,
|
|
"loss": 6.8371,
|
|
"mean_token_accuracy": 0.1101390264928341,
|
|
"num_tokens": 5887960.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.852532005310058,
|
|
"epoch": 0.29054524051581143,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996183799147932,
|
|
"loss": 6.8293,
|
|
"mean_token_accuracy": 0.1123297668993473,
|
|
"num_tokens": 5899887.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.906511831283569,
|
|
"epoch": 0.29108031462357536,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996161508132475,
|
|
"loss": 6.8399,
|
|
"mean_token_accuracy": 0.10181801989674569,
|
|
"num_tokens": 5911022.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.972908449172974,
|
|
"epoch": 0.2916153887313393,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499613915225942,
|
|
"loss": 6.9042,
|
|
"mean_token_accuracy": 0.11424257606267929,
|
|
"num_tokens": 5922780.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.888608407974243,
|
|
"epoch": 0.29215046283910323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996116731529412,
|
|
"loss": 6.9206,
|
|
"mean_token_accuracy": 0.10672475844621658,
|
|
"num_tokens": 5934112.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.909975528717041,
|
|
"epoch": 0.29268553694686716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049960942459431,
|
|
"loss": 6.8719,
|
|
"mean_token_accuracy": 0.1075200729072094,
|
|
"num_tokens": 5944386.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.823930931091309,
|
|
"epoch": 0.29322061105463104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996071695501132,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.11570547893643379,
|
|
"num_tokens": 5955552.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.929108047485352,
|
|
"epoch": 0.293755685162395,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996049080204159,
|
|
"loss": 6.7992,
|
|
"mean_token_accuracy": 0.11161436066031456,
|
|
"num_tokens": 5966790.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.947720003128052,
|
|
"epoch": 0.2942907592701589,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996026400052835,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.10977331325411796,
|
|
"num_tokens": 5977704.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.746592235565186,
|
|
"epoch": 0.29482583337792284,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996003655047814,
|
|
"loss": 6.8204,
|
|
"mean_token_accuracy": 0.11269323304295539,
|
|
"num_tokens": 5989221.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.8818727970123295,
|
|
"epoch": 0.2953609074856868,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995980845189753,
|
|
"loss": 6.8632,
|
|
"mean_token_accuracy": 0.10988379120826722,
|
|
"num_tokens": 6000906.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.933154582977295,
|
|
"epoch": 0.2958959815934507,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995957970479312,
|
|
"loss": 6.8819,
|
|
"mean_token_accuracy": 0.10542053505778312,
|
|
"num_tokens": 6012039.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.859393644332886,
|
|
"epoch": 0.29643105570121464,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995935030917148,
|
|
"loss": 6.7583,
|
|
"mean_token_accuracy": 0.1107563003897667,
|
|
"num_tokens": 6024383.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.944475984573364,
|
|
"epoch": 0.2969661298089785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995912026503926,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.10689945966005325,
|
|
"num_tokens": 6034904.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.822006130218506,
|
|
"epoch": 0.29750120391674245,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499588895724031,
|
|
"loss": 6.8446,
|
|
"mean_token_accuracy": 0.10969873294234275,
|
|
"num_tokens": 6044449.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.967623519897461,
|
|
"epoch": 0.2980362780245064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995865823126968,
|
|
"loss": 6.8635,
|
|
"mean_token_accuracy": 0.10977466106414795,
|
|
"num_tokens": 6054465.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.842376041412353,
|
|
"epoch": 0.2985713521322703,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995842624164564,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.11244026795029641,
|
|
"num_tokens": 6065539.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.909923028945923,
|
|
"epoch": 0.29910642624003425,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499581936035377,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.11023836135864258,
|
|
"num_tokens": 6076135.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.862402391433716,
|
|
"epoch": 0.2996415003477982,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995796031695257,
|
|
"loss": 6.8321,
|
|
"mean_token_accuracy": 0.11241180747747422,
|
|
"num_tokens": 6086604.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.898853063583374,
|
|
"epoch": 0.3001765744555621,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049957726381897,
|
|
"loss": 6.8524,
|
|
"mean_token_accuracy": 0.110887211561203,
|
|
"num_tokens": 6095672.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.832514142990112,
|
|
"epoch": 0.300711648563326,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995749179837773,
|
|
"loss": 6.7318,
|
|
"mean_token_accuracy": 0.1211558923125267,
|
|
"num_tokens": 6105652.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.821787977218628,
|
|
"epoch": 0.30124672267108993,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995725656640155,
|
|
"loss": 6.7662,
|
|
"mean_token_accuracy": 0.11450377255678176,
|
|
"num_tokens": 6116930.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.7775352001190186,
|
|
"epoch": 0.30178179677885386,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995702068597524,
|
|
"loss": 6.7879,
|
|
"mean_token_accuracy": 0.11996725052595139,
|
|
"num_tokens": 6126659.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.892369937896729,
|
|
"epoch": 0.3023168708866178,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995678415710561,
|
|
"loss": 6.8129,
|
|
"mean_token_accuracy": 0.11141618713736534,
|
|
"num_tokens": 6137227.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.947154092788696,
|
|
"epoch": 0.3028519449943817,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499565469797995,
|
|
"loss": 6.8657,
|
|
"mean_token_accuracy": 0.10855738222599029,
|
|
"num_tokens": 6147800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.7966372013092045,
|
|
"epoch": 0.30338701910214566,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995630915406374,
|
|
"loss": 6.7189,
|
|
"mean_token_accuracy": 0.12241782546043396,
|
|
"num_tokens": 6157671.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.899184989929199,
|
|
"epoch": 0.3039220932099096,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995607067990521,
|
|
"loss": 6.8556,
|
|
"mean_token_accuracy": 0.10919948741793632,
|
|
"num_tokens": 6168651.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.825665998458862,
|
|
"epoch": 0.30445716731767347,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499558315573308,
|
|
"loss": 6.8348,
|
|
"mean_token_accuracy": 0.11045416444540024,
|
|
"num_tokens": 6179925.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.824082469940185,
|
|
"epoch": 0.3049922414254374,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995559178634741,
|
|
"loss": 6.8225,
|
|
"mean_token_accuracy": 0.1148190289735794,
|
|
"num_tokens": 6190541.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.998980903625489,
|
|
"epoch": 0.30552731553320134,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995535136696196,
|
|
"loss": 6.8724,
|
|
"mean_token_accuracy": 0.10492667257785797,
|
|
"num_tokens": 6201491.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.7254845142364506,
|
|
"epoch": 0.30606238964096527,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499551102991814,
|
|
"loss": 6.6706,
|
|
"mean_token_accuracy": 0.11548433601856231,
|
|
"num_tokens": 6212443.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.859250020980835,
|
|
"epoch": 0.3065974637487292,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995486858301268,
|
|
"loss": 6.8688,
|
|
"mean_token_accuracy": 0.10495678186416627,
|
|
"num_tokens": 6222623.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.866484022140503,
|
|
"epoch": 0.30713253785649314,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995462621846279,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.11185173094272613,
|
|
"num_tokens": 6233712.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.8427448749542235,
|
|
"epoch": 0.30766761196425707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995438320553871,
|
|
"loss": 6.8319,
|
|
"mean_token_accuracy": 0.11026796624064446,
|
|
"num_tokens": 6244254.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.854343605041504,
|
|
"epoch": 0.30820268607202095,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995413954424748,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.11795990094542504,
|
|
"num_tokens": 6254202.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.881530380249023,
|
|
"epoch": 0.3087377601797849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995389523459612,
|
|
"loss": 6.7989,
|
|
"mean_token_accuracy": 0.11081418693065644,
|
|
"num_tokens": 6264496.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.803116035461426,
|
|
"epoch": 0.3092728342875488,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499536502765917,
|
|
"loss": 6.8187,
|
|
"mean_token_accuracy": 0.1121898703277111,
|
|
"num_tokens": 6275835.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.885844755172729,
|
|
"epoch": 0.30980790839531275,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995340467024128,
|
|
"loss": 6.7583,
|
|
"mean_token_accuracy": 0.11417267769575119,
|
|
"num_tokens": 6286805.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.834712362289428,
|
|
"epoch": 0.3103429825030767,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995315841555195,
|
|
"loss": 6.7758,
|
|
"mean_token_accuracy": 0.10655382797122001,
|
|
"num_tokens": 6298444.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.729912948608399,
|
|
"epoch": 0.3108780566108406,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995291151253083,
|
|
"loss": 6.7163,
|
|
"mean_token_accuracy": 0.11894652470946313,
|
|
"num_tokens": 6308259.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.859683704376221,
|
|
"epoch": 0.31141313071860455,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995266396118505,
|
|
"loss": 6.7759,
|
|
"mean_token_accuracy": 0.10650198608636856,
|
|
"num_tokens": 6320058.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.822231721878052,
|
|
"epoch": 0.3119482048263684,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995241576152174,
|
|
"loss": 6.7593,
|
|
"mean_token_accuracy": 0.11011653542518615,
|
|
"num_tokens": 6331203.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.908184051513672,
|
|
"epoch": 0.31248327893413236,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499521669135481,
|
|
"loss": 6.8635,
|
|
"mean_token_accuracy": 0.1086197093129158,
|
|
"num_tokens": 6342027.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.910853099822998,
|
|
"epoch": 0.3130183530418963,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995191741727128,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.11335675492882728,
|
|
"num_tokens": 6352580.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.797909688949585,
|
|
"epoch": 0.3135534271496602,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499516672726985,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.1125186413526535,
|
|
"num_tokens": 6363997.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.844564914703369,
|
|
"epoch": 0.31408850125742416,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995141647983699,
|
|
"loss": 6.8312,
|
|
"mean_token_accuracy": 0.11025090962648391,
|
|
"num_tokens": 6375284.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.801123428344726,
|
|
"epoch": 0.3146235753651881,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995116503869398,
|
|
"loss": 6.7135,
|
|
"mean_token_accuracy": 0.11932718157768249,
|
|
"num_tokens": 6386698.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.840458106994629,
|
|
"epoch": 0.315158649472952,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995091294927673,
|
|
"loss": 6.8021,
|
|
"mean_token_accuracy": 0.10923359990119934,
|
|
"num_tokens": 6397237.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.926814460754395,
|
|
"epoch": 0.3156937235807159,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995066021159253,
|
|
"loss": 6.9187,
|
|
"mean_token_accuracy": 0.10698705762624741,
|
|
"num_tokens": 6408266.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.794530534744263,
|
|
"epoch": 0.31622879768847983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995040682564867,
|
|
"loss": 6.8007,
|
|
"mean_token_accuracy": 0.11740597262978554,
|
|
"num_tokens": 6419563.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.8177916526794435,
|
|
"epoch": 0.31676387179624377,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995015279145247,
|
|
"loss": 6.7606,
|
|
"mean_token_accuracy": 0.11514141336083412,
|
|
"num_tokens": 6430220.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.885624027252197,
|
|
"epoch": 0.3172989459040077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994989810901126,
|
|
"loss": 6.7825,
|
|
"mean_token_accuracy": 0.10802810341119766,
|
|
"num_tokens": 6440157.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.80977611541748,
|
|
"epoch": 0.31783402001177163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994964277833239,
|
|
"loss": 6.8243,
|
|
"mean_token_accuracy": 0.1138004906475544,
|
|
"num_tokens": 6449511.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.902962112426758,
|
|
"epoch": 0.31836909411953557,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994938679942324,
|
|
"loss": 6.8115,
|
|
"mean_token_accuracy": 0.10856785252690315,
|
|
"num_tokens": 6460608.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.849463319778442,
|
|
"epoch": 0.3189041682272995,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994913017229121,
|
|
"loss": 6.8086,
|
|
"mean_token_accuracy": 0.11735697165131569,
|
|
"num_tokens": 6472737.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.767067813873291,
|
|
"epoch": 0.31943924233506343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994887289694371,
|
|
"loss": 6.6996,
|
|
"mean_token_accuracy": 0.11470640897750854,
|
|
"num_tokens": 6482993.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.941344833374023,
|
|
"epoch": 0.3199743164428273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994861497338814,
|
|
"loss": 6.9096,
|
|
"mean_token_accuracy": 0.10804323926568031,
|
|
"num_tokens": 6494530.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.845445013046264,
|
|
"epoch": 0.32050939055059124,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994835640163198,
|
|
"loss": 6.729,
|
|
"mean_token_accuracy": 0.10808207094669342,
|
|
"num_tokens": 6504691.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.832252359390258,
|
|
"epoch": 0.3210444646583552,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994809718168267,
|
|
"loss": 6.7681,
|
|
"mean_token_accuracy": 0.11426141634583473,
|
|
"num_tokens": 6514924.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3210444646583552,
|
|
"eval_entropy": 6.628516179339262,
|
|
"eval_loss": 6.879497051239014,
|
|
"eval_mean_token_accuracy": 0.1148492504127143,
|
|
"eval_num_tokens": 6514924.0,
|
|
"eval_runtime": 23.2795,
|
|
"eval_samples_per_second": 1274.897,
|
|
"eval_steps_per_second": 159.367,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 93440,
|
|
"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": 9543356688384000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|