c3e92c4ecd
Model: fpadovani/eus-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10 Source: Original Platform
5090 lines
137 KiB
JSON
5090 lines
137 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.1478298238074776,
|
|
"eval_steps": 500,
|
|
"global_step": 2500,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.318607425689697,
|
|
"epoch": 0.004297378599054577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.4191,
|
|
"mean_token_accuracy": 0.09157993644475937,
|
|
"num_tokens": 8559.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.338263130187988,
|
|
"epoch": 0.008594757198109154,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.3752,
|
|
"mean_token_accuracy": 0.09438179731369019,
|
|
"num_tokens": 18235.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.412753295898438,
|
|
"epoch": 0.01289213579716373,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.378,
|
|
"mean_token_accuracy": 0.0941568873822689,
|
|
"num_tokens": 28257.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.402242660522461,
|
|
"epoch": 0.017189514396218308,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.3608,
|
|
"mean_token_accuracy": 0.09274673461914062,
|
|
"num_tokens": 38142.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.447778749465942,
|
|
"epoch": 0.021486892995272882,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.389,
|
|
"mean_token_accuracy": 0.09097675308585167,
|
|
"num_tokens": 47363.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.516436624526977,
|
|
"epoch": 0.02578427159432746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.336,
|
|
"mean_token_accuracy": 0.10141076073050499,
|
|
"num_tokens": 57121.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.562677669525146,
|
|
"epoch": 0.030081650193382038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.3441,
|
|
"mean_token_accuracy": 0.09505503103137017,
|
|
"num_tokens": 66785.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.522300148010254,
|
|
"epoch": 0.034379028792436615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.2518,
|
|
"mean_token_accuracy": 0.1012355662882328,
|
|
"num_tokens": 76313.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.549300718307495,
|
|
"epoch": 0.03867640739149119,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.3611,
|
|
"mean_token_accuracy": 0.0938008576631546,
|
|
"num_tokens": 86151.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.5571035861969,
|
|
"epoch": 0.042973785990545764,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.3491,
|
|
"mean_token_accuracy": 0.09041639566421508,
|
|
"num_tokens": 94916.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.54373984336853,
|
|
"epoch": 0.047271164589600345,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.2944,
|
|
"mean_token_accuracy": 0.09890028536319732,
|
|
"num_tokens": 104592.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.575749158859253,
|
|
"epoch": 0.05156854318865492,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.2915,
|
|
"mean_token_accuracy": 0.10528360232710839,
|
|
"num_tokens": 113942.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.521316862106323,
|
|
"epoch": 0.055865921787709494,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.3286,
|
|
"mean_token_accuracy": 0.09918183535337448,
|
|
"num_tokens": 123190.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.60635232925415,
|
|
"epoch": 0.060163300386764075,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.5078,
|
|
"mean_token_accuracy": 0.08831268101930619,
|
|
"num_tokens": 132367.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.664913272857666,
|
|
"epoch": 0.06446067898581866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.2721,
|
|
"mean_token_accuracy": 0.10505343601107597,
|
|
"num_tokens": 141375.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.561436700820923,
|
|
"epoch": 0.06875805758487323,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.2566,
|
|
"mean_token_accuracy": 0.10234465301036835,
|
|
"num_tokens": 150791.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.493262481689453,
|
|
"epoch": 0.0730554361839278,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.3507,
|
|
"mean_token_accuracy": 0.09232475236058235,
|
|
"num_tokens": 158686.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.559574556350708,
|
|
"epoch": 0.07735281478298238,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.2842,
|
|
"mean_token_accuracy": 0.09609017446637154,
|
|
"num_tokens": 167482.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.523833465576172,
|
|
"epoch": 0.08165019338203695,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.1847,
|
|
"mean_token_accuracy": 0.10569239854812622,
|
|
"num_tokens": 176598.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.474951887130738,
|
|
"epoch": 0.08594757198109153,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.1612,
|
|
"mean_token_accuracy": 0.10713009536266327,
|
|
"num_tokens": 185883.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.453275728225708,
|
|
"epoch": 0.09024495058014612,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.2229,
|
|
"mean_token_accuracy": 0.099655120074749,
|
|
"num_tokens": 194820.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.569756937026978,
|
|
"epoch": 0.09454232917920069,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.2667,
|
|
"mean_token_accuracy": 0.09399808198213577,
|
|
"num_tokens": 203710.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.516098976135254,
|
|
"epoch": 0.09883970777825526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.2409,
|
|
"mean_token_accuracy": 0.10409615635871887,
|
|
"num_tokens": 212642.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.51554684638977,
|
|
"epoch": 0.10313708637730984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.2735,
|
|
"mean_token_accuracy": 0.09576103389263153,
|
|
"num_tokens": 221411.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.539292192459106,
|
|
"epoch": 0.10743446497636441,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.1672,
|
|
"mean_token_accuracy": 0.10191577151417733,
|
|
"num_tokens": 230454.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.474944972991944,
|
|
"epoch": 0.11173184357541899,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.2508,
|
|
"mean_token_accuracy": 0.09938024953007699,
|
|
"num_tokens": 240272.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.49649453163147,
|
|
"epoch": 0.11602922217447358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.2856,
|
|
"mean_token_accuracy": 0.10054537132382393,
|
|
"num_tokens": 249652.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.581856298446655,
|
|
"epoch": 0.12032660077352815,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.1517,
|
|
"mean_token_accuracy": 0.1040219210088253,
|
|
"num_tokens": 258359.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.510291481018067,
|
|
"epoch": 0.12462397937258272,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.1336,
|
|
"mean_token_accuracy": 0.10528543666005134,
|
|
"num_tokens": 266863.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.496348476409912,
|
|
"epoch": 0.1289213579716373,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.2272,
|
|
"mean_token_accuracy": 0.10392259955406188,
|
|
"num_tokens": 274694.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.5612743377685545,
|
|
"epoch": 0.1332187365706919,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.3341,
|
|
"mean_token_accuracy": 0.09439479187130928,
|
|
"num_tokens": 285038.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.626920127868653,
|
|
"epoch": 0.13751611516974646,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.2748,
|
|
"mean_token_accuracy": 0.09491272494196892,
|
|
"num_tokens": 293451.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.397944831848145,
|
|
"epoch": 0.14181349376880104,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.1126,
|
|
"mean_token_accuracy": 0.10942281857132911,
|
|
"num_tokens": 302184.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.540780925750733,
|
|
"epoch": 0.1461108723678556,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.2473,
|
|
"mean_token_accuracy": 0.10303145796060562,
|
|
"num_tokens": 311069.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.574706363677978,
|
|
"epoch": 0.15040825096691018,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.2454,
|
|
"mean_token_accuracy": 0.09808394089341163,
|
|
"num_tokens": 319841.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.498692369461059,
|
|
"epoch": 0.15470562956596476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.225,
|
|
"mean_token_accuracy": 0.09445683807134628,
|
|
"num_tokens": 328621.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.5258214473724365,
|
|
"epoch": 0.15900300816501933,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.204,
|
|
"mean_token_accuracy": 0.10020598471164703,
|
|
"num_tokens": 336469.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.548258686065674,
|
|
"epoch": 0.1633003867640739,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.2766,
|
|
"mean_token_accuracy": 0.09492596611380577,
|
|
"num_tokens": 344859.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.586396789550781,
|
|
"epoch": 0.16759776536312848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2416,
|
|
"mean_token_accuracy": 0.09392696470022202,
|
|
"num_tokens": 354536.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.494244813919067,
|
|
"epoch": 0.17189514396218306,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.2726,
|
|
"mean_token_accuracy": 0.10099927261471749,
|
|
"num_tokens": 363592.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.5656694889068605,
|
|
"epoch": 0.17619252256123766,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1745,
|
|
"mean_token_accuracy": 0.10011893808841706,
|
|
"num_tokens": 373278.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.549917793273925,
|
|
"epoch": 0.18048990116029223,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.2723,
|
|
"mean_token_accuracy": 0.09688640609383584,
|
|
"num_tokens": 382498.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.570077800750733,
|
|
"epoch": 0.1847872797593468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1941,
|
|
"mean_token_accuracy": 0.10630622431635857,
|
|
"num_tokens": 391273.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.451020860671997,
|
|
"epoch": 0.18908465835840138,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1551,
|
|
"mean_token_accuracy": 0.09831803515553475,
|
|
"num_tokens": 400340.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.513375282287598,
|
|
"epoch": 0.19338203695745596,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.1945,
|
|
"mean_token_accuracy": 0.1025567151606083,
|
|
"num_tokens": 409162.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.531175994873047,
|
|
"epoch": 0.19767941555651053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1772,
|
|
"mean_token_accuracy": 0.103980852663517,
|
|
"num_tokens": 417345.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.446167516708374,
|
|
"epoch": 0.2019767941555651,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1774,
|
|
"mean_token_accuracy": 0.10338029116392136,
|
|
"num_tokens": 427488.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.533880424499512,
|
|
"epoch": 0.20627417275461968,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1371,
|
|
"mean_token_accuracy": 0.1055621288716793,
|
|
"num_tokens": 435496.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.404056406021118,
|
|
"epoch": 0.21057155135367425,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.089,
|
|
"mean_token_accuracy": 0.10534645691514015,
|
|
"num_tokens": 444290.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.516732883453369,
|
|
"epoch": 0.21486892995272883,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2072,
|
|
"mean_token_accuracy": 0.1041240192949772,
|
|
"num_tokens": 452704.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.54860291481018,
|
|
"epoch": 0.2191663085517834,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1303,
|
|
"mean_token_accuracy": 0.10454478338360787,
|
|
"num_tokens": 461445.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.390961217880249,
|
|
"epoch": 0.22346368715083798,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1877,
|
|
"mean_token_accuracy": 0.10488151460886001,
|
|
"num_tokens": 470644.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.427588891983032,
|
|
"epoch": 0.22776106574989258,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.10415012761950493,
|
|
"num_tokens": 479212.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.486822843551636,
|
|
"epoch": 0.23205844434894715,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.2598,
|
|
"mean_token_accuracy": 0.09593637436628341,
|
|
"num_tokens": 489027.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.549335575103759,
|
|
"epoch": 0.23635582294800173,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.2775,
|
|
"mean_token_accuracy": 0.10373037382960319,
|
|
"num_tokens": 497548.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.466809272766113,
|
|
"epoch": 0.2406532015470563,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0831,
|
|
"mean_token_accuracy": 0.10918937921524048,
|
|
"num_tokens": 505836.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.526752281188965,
|
|
"epoch": 0.24495058014611087,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.231,
|
|
"mean_token_accuracy": 0.09891332313418388,
|
|
"num_tokens": 515463.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.458172607421875,
|
|
"epoch": 0.24924795874516545,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1369,
|
|
"mean_token_accuracy": 0.10318988189101219,
|
|
"num_tokens": 524882.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.400683259963989,
|
|
"epoch": 0.25354533734422,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1488,
|
|
"mean_token_accuracy": 0.09986984804272651,
|
|
"num_tokens": 534523.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.545065259933471,
|
|
"epoch": 0.2578427159432746,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.1232,
|
|
"mean_token_accuracy": 0.10373991057276725,
|
|
"num_tokens": 543772.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.3497340202331545,
|
|
"epoch": 0.26214009454232917,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0968,
|
|
"mean_token_accuracy": 0.1055608831346035,
|
|
"num_tokens": 552024.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.485379552841186,
|
|
"epoch": 0.2664374731413838,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1063,
|
|
"mean_token_accuracy": 0.1070250503718853,
|
|
"num_tokens": 561114.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.523478364944458,
|
|
"epoch": 0.2707348517404383,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1463,
|
|
"mean_token_accuracy": 0.10905889123678207,
|
|
"num_tokens": 569655.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.377780628204346,
|
|
"epoch": 0.2750322303394929,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1831,
|
|
"mean_token_accuracy": 0.10561417937278747,
|
|
"num_tokens": 578701.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.41802134513855,
|
|
"epoch": 0.27932960893854747,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.1493,
|
|
"mean_token_accuracy": 0.10375717356801033,
|
|
"num_tokens": 588166.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.434600496292115,
|
|
"epoch": 0.28362698753760207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.1779,
|
|
"mean_token_accuracy": 0.10254393517971039,
|
|
"num_tokens": 598862.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.429252767562867,
|
|
"epoch": 0.2879243661366566,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1318,
|
|
"mean_token_accuracy": 0.10302076190710067,
|
|
"num_tokens": 607680.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.45730152130127,
|
|
"epoch": 0.2922217447357112,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.1604,
|
|
"mean_token_accuracy": 0.09979369044303894,
|
|
"num_tokens": 617194.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.370795726776123,
|
|
"epoch": 0.29651912333476577,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1056,
|
|
"mean_token_accuracy": 0.10890763849020005,
|
|
"num_tokens": 625946.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.480315494537353,
|
|
"epoch": 0.30081650193382037,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0787,
|
|
"mean_token_accuracy": 0.10798180177807808,
|
|
"num_tokens": 634293.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.34269905090332,
|
|
"epoch": 0.30511388053287497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.0733,
|
|
"mean_token_accuracy": 0.106089236587286,
|
|
"num_tokens": 643479.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.386287689208984,
|
|
"epoch": 0.3094112591319295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1175,
|
|
"mean_token_accuracy": 0.1021731823682785,
|
|
"num_tokens": 653599.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.3755628108978275,
|
|
"epoch": 0.3137086377309841,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0971,
|
|
"mean_token_accuracy": 0.10849021822214126,
|
|
"num_tokens": 663042.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.371647834777832,
|
|
"epoch": 0.31800601633003867,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.036,
|
|
"mean_token_accuracy": 0.10965228900313377,
|
|
"num_tokens": 672254.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.470899868011474,
|
|
"epoch": 0.32230339492909327,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0761,
|
|
"mean_token_accuracy": 0.10654274672269821,
|
|
"num_tokens": 681648.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.253026962280273,
|
|
"epoch": 0.3266007735281478,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0529,
|
|
"mean_token_accuracy": 0.11080088913440704,
|
|
"num_tokens": 691080.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.3884796619415285,
|
|
"epoch": 0.3308981521272024,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.1391,
|
|
"mean_token_accuracy": 0.10383651852607727,
|
|
"num_tokens": 700549.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.5841371536254885,
|
|
"epoch": 0.33519553072625696,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1858,
|
|
"mean_token_accuracy": 0.10275669917464256,
|
|
"num_tokens": 710623.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.3249256134033205,
|
|
"epoch": 0.33949290932531156,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.1082,
|
|
"mean_token_accuracy": 0.10990465432405472,
|
|
"num_tokens": 719695.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.283933448791504,
|
|
"epoch": 0.3437902879243661,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.088,
|
|
"mean_token_accuracy": 0.10904877632856369,
|
|
"num_tokens": 728998.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.4869218349456785,
|
|
"epoch": 0.3480876665234207,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.1604,
|
|
"mean_token_accuracy": 0.10160251557826996,
|
|
"num_tokens": 738537.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.35856614112854,
|
|
"epoch": 0.3523850451224753,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.0856,
|
|
"mean_token_accuracy": 0.10455845221877098,
|
|
"num_tokens": 747555.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.3205808162689205,
|
|
"epoch": 0.35668242372152986,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0854,
|
|
"mean_token_accuracy": 0.10954482555389404,
|
|
"num_tokens": 756857.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.390940237045288,
|
|
"epoch": 0.36097980232058446,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.0953,
|
|
"mean_token_accuracy": 0.11360994949936867,
|
|
"num_tokens": 766181.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.433085155487061,
|
|
"epoch": 0.365277180919639,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.1085,
|
|
"mean_token_accuracy": 0.10497047677636147,
|
|
"num_tokens": 774894.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.305972146987915,
|
|
"epoch": 0.3695745595186936,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1319,
|
|
"mean_token_accuracy": 0.1049921877682209,
|
|
"num_tokens": 784601.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.370691442489624,
|
|
"epoch": 0.37387193811774816,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1739,
|
|
"mean_token_accuracy": 0.10319070667028427,
|
|
"num_tokens": 794373.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.330904865264893,
|
|
"epoch": 0.37816931671680276,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.0547,
|
|
"mean_token_accuracy": 0.10838651731610298,
|
|
"num_tokens": 803608.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.375745105743408,
|
|
"epoch": 0.3824666953158573,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0837,
|
|
"mean_token_accuracy": 0.10409105122089386,
|
|
"num_tokens": 812287.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.335326385498047,
|
|
"epoch": 0.3867640739149119,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0273,
|
|
"mean_token_accuracy": 0.10988899692893028,
|
|
"num_tokens": 821049.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.3366615772247314,
|
|
"epoch": 0.39106145251396646,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.037,
|
|
"mean_token_accuracy": 0.10783056244254112,
|
|
"num_tokens": 829148.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.3818999290466305,
|
|
"epoch": 0.39535883111302106,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.0454,
|
|
"mean_token_accuracy": 0.10884898602962494,
|
|
"num_tokens": 838228.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.300606727600098,
|
|
"epoch": 0.39965620971207566,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0491,
|
|
"mean_token_accuracy": 0.10492841824889183,
|
|
"num_tokens": 846059.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.4146685123443605,
|
|
"epoch": 0.4039535883111302,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.1786,
|
|
"mean_token_accuracy": 0.10016006529331208,
|
|
"num_tokens": 856309.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.28831844329834,
|
|
"epoch": 0.4082509669101848,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.0303,
|
|
"mean_token_accuracy": 0.11658978387713433,
|
|
"num_tokens": 865921.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.264179229736328,
|
|
"epoch": 0.41254834550923936,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.031,
|
|
"mean_token_accuracy": 0.11011900380253792,
|
|
"num_tokens": 875076.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.346679544448852,
|
|
"epoch": 0.41684572410829396,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.0691,
|
|
"mean_token_accuracy": 0.10555051863193513,
|
|
"num_tokens": 884586.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.398708009719849,
|
|
"epoch": 0.4211431027073485,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.1919,
|
|
"mean_token_accuracy": 0.10402772873640061,
|
|
"num_tokens": 894192.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.372455215454101,
|
|
"epoch": 0.4254404813064031,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.083,
|
|
"mean_token_accuracy": 0.10693729296326637,
|
|
"num_tokens": 903542.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.1894408702850345,
|
|
"epoch": 0.42973785990545765,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9916,
|
|
"mean_token_accuracy": 0.11179914698004723,
|
|
"num_tokens": 912625.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.42973785990545765,
|
|
"eval_entropy": 7.3068524684991925,
|
|
"eval_loss": 7.0247063636779785,
|
|
"eval_mean_token_accuracy": 0.11340155569953961,
|
|
"eval_num_tokens": 912625.0,
|
|
"eval_runtime": 2.6673,
|
|
"eval_samples_per_second": 1330.579,
|
|
"eval_steps_per_second": 166.463,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.301834917068481,
|
|
"epoch": 0.43403523850451226,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9753,
|
|
"mean_token_accuracy": 0.11066327542066574,
|
|
"num_tokens": 921438.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.299079513549804,
|
|
"epoch": 0.4383326171035668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.9705,
|
|
"mean_token_accuracy": 0.11115480959415436,
|
|
"num_tokens": 931097.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.25611834526062,
|
|
"epoch": 0.4426299957026214,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.9377,
|
|
"mean_token_accuracy": 0.1125190131366253,
|
|
"num_tokens": 939375.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.2075482368469235,
|
|
"epoch": 0.44692737430167595,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9692,
|
|
"mean_token_accuracy": 0.11348672360181808,
|
|
"num_tokens": 948223.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.267970848083496,
|
|
"epoch": 0.45122475290073055,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.10696823000907899,
|
|
"num_tokens": 956243.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.269130039215088,
|
|
"epoch": 0.45552213149978515,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.9888,
|
|
"mean_token_accuracy": 0.11132953837513923,
|
|
"num_tokens": 964506.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.2140302658081055,
|
|
"epoch": 0.4598195100988397,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.0261,
|
|
"mean_token_accuracy": 0.11418202742934228,
|
|
"num_tokens": 973617.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.263705730438232,
|
|
"epoch": 0.4641168886978943,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9285,
|
|
"mean_token_accuracy": 0.11379739046096801,
|
|
"num_tokens": 981796.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.2532874584198,
|
|
"epoch": 0.46841426729694885,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.9974,
|
|
"mean_token_accuracy": 0.11635445952415466,
|
|
"num_tokens": 990677.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.17174711227417,
|
|
"epoch": 0.47271164589600345,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9292,
|
|
"mean_token_accuracy": 0.11551985442638397,
|
|
"num_tokens": 1001131.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.255539464950561,
|
|
"epoch": 0.477009024495058,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.0782,
|
|
"mean_token_accuracy": 0.1087973214685917,
|
|
"num_tokens": 1009925.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.204084014892578,
|
|
"epoch": 0.4813064030941126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.9989,
|
|
"mean_token_accuracy": 0.11738647520542145,
|
|
"num_tokens": 1018998.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.313282203674317,
|
|
"epoch": 0.48560378169316715,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.9487,
|
|
"mean_token_accuracy": 0.11487800031900405,
|
|
"num_tokens": 1027496.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.188301038742066,
|
|
"epoch": 0.48990116029222175,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9178,
|
|
"mean_token_accuracy": 0.1234424039721489,
|
|
"num_tokens": 1035669.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.197154760360718,
|
|
"epoch": 0.4941985388912763,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9966,
|
|
"mean_token_accuracy": 0.11247355863451958,
|
|
"num_tokens": 1044416.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.310844898223877,
|
|
"epoch": 0.4984959174903309,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.0271,
|
|
"mean_token_accuracy": 0.11254049837589264,
|
|
"num_tokens": 1053500.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.146087980270385,
|
|
"epoch": 0.5027932960893855,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.11227174699306489,
|
|
"num_tokens": 1061758.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.159999990463257,
|
|
"epoch": 0.50709067468844,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.9957,
|
|
"mean_token_accuracy": 0.11408972144126892,
|
|
"num_tokens": 1070570.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.258799076080322,
|
|
"epoch": 0.5113880532874946,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.9414,
|
|
"mean_token_accuracy": 0.11279132589697838,
|
|
"num_tokens": 1080640.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.13523416519165,
|
|
"epoch": 0.5156854318865493,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9924,
|
|
"mean_token_accuracy": 0.11432184651494026,
|
|
"num_tokens": 1090680.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.3078405380249025,
|
|
"epoch": 0.5199828104856038,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.10550333335995674,
|
|
"num_tokens": 1100453.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.091824913024903,
|
|
"epoch": 0.5242801890846583,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8893,
|
|
"mean_token_accuracy": 0.11649776622653008,
|
|
"num_tokens": 1109085.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.119379043579102,
|
|
"epoch": 0.5285775676837129,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.11886096745729446,
|
|
"num_tokens": 1118333.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.0497113227844235,
|
|
"epoch": 0.5328749462827675,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8463,
|
|
"mean_token_accuracy": 0.12016497254371643,
|
|
"num_tokens": 1127459.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.180634450912476,
|
|
"epoch": 0.5371723248818221,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.994,
|
|
"mean_token_accuracy": 0.11278382316231728,
|
|
"num_tokens": 1137071.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.2187317371368405,
|
|
"epoch": 0.5414697034808766,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.9744,
|
|
"mean_token_accuracy": 0.10984951481223107,
|
|
"num_tokens": 1146856.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.1333935260772705,
|
|
"epoch": 0.5457670820799312,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.0027,
|
|
"mean_token_accuracy": 0.11289475411176682,
|
|
"num_tokens": 1155847.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.205038070678711,
|
|
"epoch": 0.5500644606789858,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9754,
|
|
"mean_token_accuracy": 0.11328396424651146,
|
|
"num_tokens": 1164922.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.175393056869507,
|
|
"epoch": 0.5543618392780404,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.9435,
|
|
"mean_token_accuracy": 0.11000620648264885,
|
|
"num_tokens": 1174389.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.118865060806274,
|
|
"epoch": 0.5586592178770949,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.8989,
|
|
"mean_token_accuracy": 0.11063683554530143,
|
|
"num_tokens": 1182959.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.158196449279785,
|
|
"epoch": 0.5629565964761496,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.9443,
|
|
"mean_token_accuracy": 0.11405061110854149,
|
|
"num_tokens": 1191777.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.121678113937378,
|
|
"epoch": 0.5672539750752041,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8375,
|
|
"mean_token_accuracy": 0.12199422866106033,
|
|
"num_tokens": 1200658.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.01548957824707,
|
|
"epoch": 0.5715513536742587,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8453,
|
|
"mean_token_accuracy": 0.12067256942391395,
|
|
"num_tokens": 1209607.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.2269895553588865,
|
|
"epoch": 0.5758487322733132,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.974,
|
|
"mean_token_accuracy": 0.10879514962434769,
|
|
"num_tokens": 1218146.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.988537359237671,
|
|
"epoch": 0.5801461108723679,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.11418939754366875,
|
|
"num_tokens": 1226886.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.105102682113648,
|
|
"epoch": 0.5844434894714224,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8729,
|
|
"mean_token_accuracy": 0.1209171898663044,
|
|
"num_tokens": 1235408.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.0300126552581785,
|
|
"epoch": 0.588740868070477,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8501,
|
|
"mean_token_accuracy": 0.12092051953077317,
|
|
"num_tokens": 1244643.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.138811111450195,
|
|
"epoch": 0.5930382466695315,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.9133,
|
|
"mean_token_accuracy": 0.11425379812717437,
|
|
"num_tokens": 1254145.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.102302742004395,
|
|
"epoch": 0.5973356252685862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.9522,
|
|
"mean_token_accuracy": 0.11475471332669258,
|
|
"num_tokens": 1263395.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.116247606277466,
|
|
"epoch": 0.6016330038676407,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8717,
|
|
"mean_token_accuracy": 0.12142749726772309,
|
|
"num_tokens": 1272942.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.9945995807647705,
|
|
"epoch": 0.6059303824666953,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.8167,
|
|
"mean_token_accuracy": 0.12329712808132172,
|
|
"num_tokens": 1281481.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.154071187973022,
|
|
"epoch": 0.6102277610657499,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.9737,
|
|
"mean_token_accuracy": 0.1102140225470066,
|
|
"num_tokens": 1290455.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.065611410140991,
|
|
"epoch": 0.6145251396648045,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.8602,
|
|
"mean_token_accuracy": 0.11892874240875244,
|
|
"num_tokens": 1299241.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.104707860946656,
|
|
"epoch": 0.618822518263859,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.9291,
|
|
"mean_token_accuracy": 0.1116059735417366,
|
|
"num_tokens": 1308658.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.139448833465576,
|
|
"epoch": 0.6231198968629136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.11212217062711716,
|
|
"num_tokens": 1316987.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.924467325210571,
|
|
"epoch": 0.6274172754619682,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8228,
|
|
"mean_token_accuracy": 0.12177187651395797,
|
|
"num_tokens": 1325500.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.004321479797364,
|
|
"epoch": 0.6317146540610228,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.9595,
|
|
"mean_token_accuracy": 0.11682300940155983,
|
|
"num_tokens": 1335048.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.079775619506836,
|
|
"epoch": 0.6360120326600773,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.8921,
|
|
"mean_token_accuracy": 0.11796021088957787,
|
|
"num_tokens": 1343879.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.036481952667236,
|
|
"epoch": 0.6403094112591319,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8026,
|
|
"mean_token_accuracy": 0.1175395205616951,
|
|
"num_tokens": 1353169.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.024873685836792,
|
|
"epoch": 0.6446067898581865,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.9047,
|
|
"mean_token_accuracy": 0.11657271012663842,
|
|
"num_tokens": 1362912.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.031742286682129,
|
|
"epoch": 0.6489041684572411,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.9109,
|
|
"mean_token_accuracy": 0.1104318842291832,
|
|
"num_tokens": 1372331.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.986195516586304,
|
|
"epoch": 0.6532015470562956,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7911,
|
|
"mean_token_accuracy": 0.12072895392775536,
|
|
"num_tokens": 1381060.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.975994014739991,
|
|
"epoch": 0.6574989256553503,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7951,
|
|
"mean_token_accuracy": 0.13102718442678452,
|
|
"num_tokens": 1388749.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.983586311340332,
|
|
"epoch": 0.6617963042544048,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.11960498094558716,
|
|
"num_tokens": 1398456.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.966071653366089,
|
|
"epoch": 0.6660936828534594,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7798,
|
|
"mean_token_accuracy": 0.12140673324465752,
|
|
"num_tokens": 1407430.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.90265302658081,
|
|
"epoch": 0.6703910614525139,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.8787,
|
|
"mean_token_accuracy": 0.11302192658185958,
|
|
"num_tokens": 1416631.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.030915307998657,
|
|
"epoch": 0.6746884400515686,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.8116,
|
|
"mean_token_accuracy": 0.11736064329743386,
|
|
"num_tokens": 1426124.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.964035367965698,
|
|
"epoch": 0.6789858186506231,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.9457,
|
|
"mean_token_accuracy": 0.11582199558615684,
|
|
"num_tokens": 1436510.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.125880765914917,
|
|
"epoch": 0.6832831972496777,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.8824,
|
|
"mean_token_accuracy": 0.1163998268544674,
|
|
"num_tokens": 1445954.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.923286104202271,
|
|
"epoch": 0.6875805758487322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.8985,
|
|
"mean_token_accuracy": 0.10873348712921142,
|
|
"num_tokens": 1454981.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.04893126487732,
|
|
"epoch": 0.6918779544477869,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.11823213398456574,
|
|
"num_tokens": 1464904.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.886806869506836,
|
|
"epoch": 0.6961753330468414,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.12331509366631507,
|
|
"num_tokens": 1473605.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.912139225006103,
|
|
"epoch": 0.700472711645896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.759,
|
|
"mean_token_accuracy": 0.1245518982410431,
|
|
"num_tokens": 1482989.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.9620767593383786,
|
|
"epoch": 0.7047700902449506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.8448,
|
|
"mean_token_accuracy": 0.11647504344582557,
|
|
"num_tokens": 1492514.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.943895387649536,
|
|
"epoch": 0.7090674688440052,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.8546,
|
|
"mean_token_accuracy": 0.12430108189582825,
|
|
"num_tokens": 1501127.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.962851333618164,
|
|
"epoch": 0.7133648474430597,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.8742,
|
|
"mean_token_accuracy": 0.11583281457424163,
|
|
"num_tokens": 1509698.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.987609577178955,
|
|
"epoch": 0.7176622260421143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.8135,
|
|
"mean_token_accuracy": 0.12093358635902404,
|
|
"num_tokens": 1518224.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.959578323364258,
|
|
"epoch": 0.7219596046411689,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.8131,
|
|
"mean_token_accuracy": 0.12489956095814705,
|
|
"num_tokens": 1527163.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.942628192901611,
|
|
"epoch": 0.7262569832402235,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.8483,
|
|
"mean_token_accuracy": 0.11925563141703606,
|
|
"num_tokens": 1536980.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.907382965087891,
|
|
"epoch": 0.730554361839278,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.12201033234596252,
|
|
"num_tokens": 1546388.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.943301010131836,
|
|
"epoch": 0.7348517404383326,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.8442,
|
|
"mean_token_accuracy": 0.11446970775723457,
|
|
"num_tokens": 1555618.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.032028865814209,
|
|
"epoch": 0.7391491190373872,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.9204,
|
|
"mean_token_accuracy": 0.11842655092477798,
|
|
"num_tokens": 1565398.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.910132169723511,
|
|
"epoch": 0.7434464976364418,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.78,
|
|
"mean_token_accuracy": 0.1209449052810669,
|
|
"num_tokens": 1574052.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.863509893417358,
|
|
"epoch": 0.7477438762354963,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.7197,
|
|
"mean_token_accuracy": 0.12694448828697205,
|
|
"num_tokens": 1582930.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.87777304649353,
|
|
"epoch": 0.752041254834551,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.8381,
|
|
"mean_token_accuracy": 0.11370284855365753,
|
|
"num_tokens": 1592007.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.8960123538970945,
|
|
"epoch": 0.7563386334336055,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6681,
|
|
"mean_token_accuracy": 0.13288158252835275,
|
|
"num_tokens": 1600532.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.847743368148803,
|
|
"epoch": 0.7606360120326601,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.8122,
|
|
"mean_token_accuracy": 0.11822389364242554,
|
|
"num_tokens": 1610319.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.883726263046265,
|
|
"epoch": 0.7649333906317146,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6769,
|
|
"mean_token_accuracy": 0.12348684296011925,
|
|
"num_tokens": 1618161.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.87597885131836,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.7947,
|
|
"mean_token_accuracy": 0.12304572686553002,
|
|
"num_tokens": 1627676.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.900651979446411,
|
|
"epoch": 0.7735281478298238,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.7425,
|
|
"mean_token_accuracy": 0.11917232349514961,
|
|
"num_tokens": 1636693.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.785532140731812,
|
|
"epoch": 0.7778255264288784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.7689,
|
|
"mean_token_accuracy": 0.11988367959856987,
|
|
"num_tokens": 1645577.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.942232894897461,
|
|
"epoch": 0.7821229050279329,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.7411,
|
|
"mean_token_accuracy": 0.11902217343449592,
|
|
"num_tokens": 1654239.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.833974695205688,
|
|
"epoch": 0.7864202836269876,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7464,
|
|
"mean_token_accuracy": 0.12057677283883095,
|
|
"num_tokens": 1663085.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.830857181549073,
|
|
"epoch": 0.7907176622260421,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.7733,
|
|
"mean_token_accuracy": 0.12257009446620941,
|
|
"num_tokens": 1671621.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.914818286895752,
|
|
"epoch": 0.7950150408250967,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.7718,
|
|
"mean_token_accuracy": 0.12270039841532707,
|
|
"num_tokens": 1680912.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.676487874984741,
|
|
"epoch": 0.7993124194241513,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.129410083591938,
|
|
"num_tokens": 1689772.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.942879056930542,
|
|
"epoch": 0.8036097980232059,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8636,
|
|
"mean_token_accuracy": 0.11327557042241096,
|
|
"num_tokens": 1698985.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.8534533977508545,
|
|
"epoch": 0.8079071766222604,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.7291,
|
|
"mean_token_accuracy": 0.12363906055688859,
|
|
"num_tokens": 1707365.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.760773754119873,
|
|
"epoch": 0.812204555221315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.1252680540084839,
|
|
"num_tokens": 1715858.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.933451700210571,
|
|
"epoch": 0.8165019338203696,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.7832,
|
|
"mean_token_accuracy": 0.11664097607135773,
|
|
"num_tokens": 1724721.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.852610778808594,
|
|
"epoch": 0.8207993124194242,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.7964,
|
|
"mean_token_accuracy": 0.12085579261183739,
|
|
"num_tokens": 1733700.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.8043561458587645,
|
|
"epoch": 0.8250966910184787,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.11831567585468292,
|
|
"num_tokens": 1742167.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.86628828048706,
|
|
"epoch": 0.8293940696175333,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.12031449228525162,
|
|
"num_tokens": 1752087.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.81239686012268,
|
|
"epoch": 0.8336914482165879,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.1284126915037632,
|
|
"num_tokens": 1760749.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.679265117645263,
|
|
"epoch": 0.8379888268156425,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.7459,
|
|
"mean_token_accuracy": 0.11835021451115608,
|
|
"num_tokens": 1770923.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.882328510284424,
|
|
"epoch": 0.842286205414697,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.12391256019473076,
|
|
"num_tokens": 1779233.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.815756559371948,
|
|
"epoch": 0.8465835840137517,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.7245,
|
|
"mean_token_accuracy": 0.1235703021287918,
|
|
"num_tokens": 1787593.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.834695529937744,
|
|
"epoch": 0.8508809626128062,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.773,
|
|
"mean_token_accuracy": 0.11845792606472969,
|
|
"num_tokens": 1796655.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.734475326538086,
|
|
"epoch": 0.8551783412118608,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.701,
|
|
"mean_token_accuracy": 0.12803028374910355,
|
|
"num_tokens": 1805790.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.814859628677368,
|
|
"epoch": 0.8594757198109153,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.683,
|
|
"mean_token_accuracy": 0.11991076469421387,
|
|
"num_tokens": 1813776.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.8594757198109153,
|
|
"eval_entropy": 6.726756938942918,
|
|
"eval_loss": 6.731381416320801,
|
|
"eval_mean_token_accuracy": 0.12728899561271473,
|
|
"eval_num_tokens": 1813776.0,
|
|
"eval_runtime": 2.8327,
|
|
"eval_samples_per_second": 1252.854,
|
|
"eval_steps_per_second": 156.739,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.696360111236572,
|
|
"epoch": 0.86377309840997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999998427807679,
|
|
"loss": 6.6901,
|
|
"mean_token_accuracy": 0.12232941612601281,
|
|
"num_tokens": 1823034.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.810961771011352,
|
|
"epoch": 0.8680704770090245,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999992040780138,
|
|
"loss": 6.7822,
|
|
"mean_token_accuracy": 0.11861197948455811,
|
|
"num_tokens": 1832320.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.716808557510376,
|
|
"epoch": 0.8723678556080791,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999980740669294,
|
|
"loss": 6.6632,
|
|
"mean_token_accuracy": 0.12679338902235032,
|
|
"num_tokens": 1841165.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.7952981948852536,
|
|
"epoch": 0.8766652342071336,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999964527499823,
|
|
"loss": 6.7338,
|
|
"mean_token_accuracy": 0.12241052910685539,
|
|
"num_tokens": 1850440.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.801466560363769,
|
|
"epoch": 0.8809626128061883,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004999943401307127,
|
|
"loss": 6.7461,
|
|
"mean_token_accuracy": 0.12134231030941009,
|
|
"num_tokens": 1859304.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.778349208831787,
|
|
"epoch": 0.8852599914052428,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999917362137337,
|
|
"loss": 6.6069,
|
|
"mean_token_accuracy": 0.13296075016260148,
|
|
"num_tokens": 1867560.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.69033408164978,
|
|
"epoch": 0.8895573700042974,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999886410047312,
|
|
"loss": 6.6847,
|
|
"mean_token_accuracy": 0.1256091572344303,
|
|
"num_tokens": 1876742.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.799950695037841,
|
|
"epoch": 0.8938547486033519,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999850545104638,
|
|
"loss": 6.6921,
|
|
"mean_token_accuracy": 0.12495070844888687,
|
|
"num_tokens": 1885738.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.801503467559814,
|
|
"epoch": 0.8981521272024066,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999809767387633,
|
|
"loss": 6.7228,
|
|
"mean_token_accuracy": 0.11731479540467263,
|
|
"num_tokens": 1894688.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.757845163345337,
|
|
"epoch": 0.9024495058014611,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999764076985337,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.12538044303655624,
|
|
"num_tokens": 1903809.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.814986515045166,
|
|
"epoch": 0.9067468844005157,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999713473997519,
|
|
"loss": 6.747,
|
|
"mean_token_accuracy": 0.12134177088737488,
|
|
"num_tokens": 1913558.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.723377370834351,
|
|
"epoch": 0.9110442629995703,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999657958534677,
|
|
"loss": 6.7283,
|
|
"mean_token_accuracy": 0.11966701298952102,
|
|
"num_tokens": 1923324.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.708611631393433,
|
|
"epoch": 0.9153416415986249,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999597530718034,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.12495688870549201,
|
|
"num_tokens": 1932849.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.832595348358154,
|
|
"epoch": 0.9196390201976794,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499953219067954,
|
|
"loss": 6.8184,
|
|
"mean_token_accuracy": 0.12064682915806771,
|
|
"num_tokens": 1942678.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.740026760101318,
|
|
"epoch": 0.923936398796734,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999461938561873,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.11836395263671876,
|
|
"num_tokens": 1951670.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.813496685028076,
|
|
"epoch": 0.9282337773957886,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999386774518432,
|
|
"loss": 6.7849,
|
|
"mean_token_accuracy": 0.12696564868092536,
|
|
"num_tokens": 1961060.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.821066284179688,
|
|
"epoch": 0.9325311559948432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999306698713349,
|
|
"loss": 6.7251,
|
|
"mean_token_accuracy": 0.12872326821088792,
|
|
"num_tokens": 1970790.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.802606868743896,
|
|
"epoch": 0.9368285345938977,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999221711321477,
|
|
"loss": 6.7599,
|
|
"mean_token_accuracy": 0.12338658943772315,
|
|
"num_tokens": 1980016.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.666169691085815,
|
|
"epoch": 0.9411259131929522,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999131812528393,
|
|
"loss": 6.7137,
|
|
"mean_token_accuracy": 0.12647809982299804,
|
|
"num_tokens": 1989542.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.856275272369385,
|
|
"epoch": 0.9454232917920069,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049990370025304,
|
|
"loss": 6.6789,
|
|
"mean_token_accuracy": 0.1320645920932293,
|
|
"num_tokens": 1999212.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.65680422782898,
|
|
"epoch": 0.9497206703910615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998937281534526,
|
|
"loss": 6.6665,
|
|
"mean_token_accuracy": 0.12952047884464263,
|
|
"num_tokens": 2008378.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.683283519744873,
|
|
"epoch": 0.954018048990116,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004998832649758521,
|
|
"loss": 6.7497,
|
|
"mean_token_accuracy": 0.11866686791181565,
|
|
"num_tokens": 2018985.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.716252756118775,
|
|
"epoch": 0.9583154275891707,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998723107430862,
|
|
"loss": 6.6294,
|
|
"mean_token_accuracy": 0.12505461126565934,
|
|
"num_tokens": 2027274.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.733844661712647,
|
|
"epoch": 0.9626128061882252,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998608654790741,
|
|
"loss": 6.7276,
|
|
"mean_token_accuracy": 0.12319627404212952,
|
|
"num_tokens": 2036892.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.80896143913269,
|
|
"epoch": 0.9669101847872797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499848929208808,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.1196390450000763,
|
|
"num_tokens": 2046042.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.681768321990967,
|
|
"epoch": 0.9712075633863343,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998365019583519,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.1205221801996231,
|
|
"num_tokens": 2054576.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.673296976089477,
|
|
"epoch": 0.975504941985389,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998235837548417,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.13002716973423958,
|
|
"num_tokens": 2063552.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.650518178939819,
|
|
"epoch": 0.9798023205844435,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499810174626486,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.1278505653142929,
|
|
"num_tokens": 2072965.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.689944839477539,
|
|
"epoch": 0.984099699183498,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004997962746025646,
|
|
"loss": 6.6977,
|
|
"mean_token_accuracy": 0.12715715765953065,
|
|
"num_tokens": 2082461.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.717270183563232,
|
|
"epoch": 0.9883970777825526,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997818837134298,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.12612896114587785,
|
|
"num_tokens": 2091022.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.634740400314331,
|
|
"epoch": 0.9926944563816072,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997670019905057,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.13522578105330468,
|
|
"num_tokens": 2099896.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.714453172683716,
|
|
"epoch": 0.9969918349806618,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997516294662876,
|
|
"loss": 6.671,
|
|
"mean_token_accuracy": 0.12892441749572753,
|
|
"num_tokens": 2109122.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.7551817364162865,
|
|
"epoch": 1.0008594757198108,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997357661743433,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.12951675057411194,
|
|
"num_tokens": 2117879.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.554825782775879,
|
|
"epoch": 1.0051568543188656,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997194121493118,
|
|
"loss": 6.3746,
|
|
"mean_token_accuracy": 0.13388435691595077,
|
|
"num_tokens": 2127552.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.640289449691773,
|
|
"epoch": 1.0094542329179201,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997025674269037,
|
|
"loss": 6.3859,
|
|
"mean_token_accuracy": 0.13642154037952423,
|
|
"num_tokens": 2136648.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.596437311172485,
|
|
"epoch": 1.0137516115169747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996852320439013,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.13524584099650383,
|
|
"num_tokens": 2144852.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.616053581237793,
|
|
"epoch": 1.0180489901160292,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996674060381578,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.1324625827372074,
|
|
"num_tokens": 2154567.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.667360925674439,
|
|
"epoch": 1.0223463687150838,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996490894485985,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.1303381770849228,
|
|
"num_tokens": 2164260.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.516767692565918,
|
|
"epoch": 1.0266437473141383,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996302823152193,
|
|
"loss": 6.4128,
|
|
"mean_token_accuracy": 0.14060178995132447,
|
|
"num_tokens": 2173247.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.566610860824585,
|
|
"epoch": 1.0309411259131929,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996109846790873,
|
|
"loss": 6.4723,
|
|
"mean_token_accuracy": 0.12932706177234649,
|
|
"num_tokens": 2181595.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.6948295593261715,
|
|
"epoch": 1.0352385045122476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995911965823412,
|
|
"loss": 6.3895,
|
|
"mean_token_accuracy": 0.1299505650997162,
|
|
"num_tokens": 2190608.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.462952327728272,
|
|
"epoch": 1.0395358831113022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995709180681899,
|
|
"loss": 6.3982,
|
|
"mean_token_accuracy": 0.13950304985046386,
|
|
"num_tokens": 2199131.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.655004644393921,
|
|
"epoch": 1.0438332617103567,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499550149180914,
|
|
"loss": 6.5499,
|
|
"mean_token_accuracy": 0.1290518805384636,
|
|
"num_tokens": 2208365.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.545926237106324,
|
|
"epoch": 1.0481306403094113,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995288899658641,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.13622732385993003,
|
|
"num_tokens": 2216851.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.64662799835205,
|
|
"epoch": 1.0524280189084658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995071404694619,
|
|
"loss": 6.4725,
|
|
"mean_token_accuracy": 0.12700082510709762,
|
|
"num_tokens": 2225309.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.5808178901672365,
|
|
"epoch": 1.0567253975075204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994849007391996,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.13448652923107146,
|
|
"num_tokens": 2235036.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.624714040756226,
|
|
"epoch": 1.061022776106575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994621708236401,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.13216220885515212,
|
|
"num_tokens": 2244038.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.5215829372406,
|
|
"epoch": 1.0653201547056295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499438950772416,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.13749199584126473,
|
|
"num_tokens": 2252828.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.589654731750488,
|
|
"epoch": 1.0696175333046842,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994152406362311,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.13534352406859398,
|
|
"num_tokens": 2261709.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.544873857498169,
|
|
"epoch": 1.0739149119037388,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993910404668586,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.13456418067216874,
|
|
"num_tokens": 2269801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.497649669647217,
|
|
"epoch": 1.0782122905027933,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499366350317142,
|
|
"loss": 6.3616,
|
|
"mean_token_accuracy": 0.13916796073317528,
|
|
"num_tokens": 2280587.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.4322058200836185,
|
|
"epoch": 1.0825096691018479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993411702409948,
|
|
"loss": 6.3588,
|
|
"mean_token_accuracy": 0.1342848613858223,
|
|
"num_tokens": 2289783.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.5220903873443605,
|
|
"epoch": 1.0868070477009024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993155002934002,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.1303260490298271,
|
|
"num_tokens": 2298785.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.592111110687256,
|
|
"epoch": 1.091104426299957,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992893405304111,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.1299525059759617,
|
|
"num_tokens": 2308400.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.564047622680664,
|
|
"epoch": 1.0954018048990115,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049926269100915,
|
|
"loss": 6.3635,
|
|
"mean_token_accuracy": 0.14365571066737176,
|
|
"num_tokens": 2317440.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.465882968902588,
|
|
"epoch": 1.0996991834980663,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992355517878087,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.13191932812333107,
|
|
"num_tokens": 2326730.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.493737697601318,
|
|
"epoch": 1.1039965620971208,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992079229256484,
|
|
"loss": 6.3817,
|
|
"mean_token_accuracy": 0.14110777899622917,
|
|
"num_tokens": 2336126.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.5359251499176025,
|
|
"epoch": 1.1082939406961754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991798044829996,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.13598520383238794,
|
|
"num_tokens": 2345144.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.489447927474975,
|
|
"epoch": 1.11259131929523,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991511965212618,
|
|
"loss": 6.3612,
|
|
"mean_token_accuracy": 0.14140836670994758,
|
|
"num_tokens": 2353851.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.433896398544311,
|
|
"epoch": 1.1168886978942845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991220991029032,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.14358441829681395,
|
|
"num_tokens": 2362316.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.580701875686645,
|
|
"epoch": 1.121186076493339,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499092512291461,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.13336558341979982,
|
|
"num_tokens": 2373350.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.581955623626709,
|
|
"epoch": 1.1254834550923936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499062436151541,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.13979026824235916,
|
|
"num_tokens": 2381753.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.408409786224365,
|
|
"epoch": 1.129780833691448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990318707488173,
|
|
"loss": 6.4101,
|
|
"mean_token_accuracy": 0.13570450320839883,
|
|
"num_tokens": 2390093.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.653066492080688,
|
|
"epoch": 1.1340782122905029,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990008161500327,
|
|
"loss": 6.4404,
|
|
"mean_token_accuracy": 0.13621403872966767,
|
|
"num_tokens": 2399103.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.472879123687744,
|
|
"epoch": 1.1383755908895574,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498969272422998,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.1384277917444706,
|
|
"num_tokens": 2407530.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.486513137817383,
|
|
"epoch": 1.142672969488612,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989372396365921,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.14020788073539733,
|
|
"num_tokens": 2416264.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.486220169067383,
|
|
"epoch": 1.1469703480876665,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989047178607618,
|
|
"loss": 6.4839,
|
|
"mean_token_accuracy": 0.13277149870991706,
|
|
"num_tokens": 2425256.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.470200538635254,
|
|
"epoch": 1.151267726686721,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988717071665215,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.13158162906765938,
|
|
"num_tokens": 2434343.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.559522008895874,
|
|
"epoch": 1.1555651052857756,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004988382076259537,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.14069283604621888,
|
|
"num_tokens": 2442864.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.418056011199951,
|
|
"epoch": 1.1598624838848304,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004988042193122077,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.13773582503199577,
|
|
"num_tokens": 2451701.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.470896196365357,
|
|
"epoch": 1.164159862483885,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987697422995005,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.13572183027863502,
|
|
"num_tokens": 2460943.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.459086990356445,
|
|
"epoch": 1.1684572410829395,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987347766631161,
|
|
"loss": 6.4124,
|
|
"mean_token_accuracy": 0.1375699020922184,
|
|
"num_tokens": 2470294.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.532469606399536,
|
|
"epoch": 1.172754619681994,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004986993224794055,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.12745001912117004,
|
|
"num_tokens": 2479530.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.472117757797241,
|
|
"epoch": 1.1770519982810486,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986633798257865,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.14262767881155014,
|
|
"num_tokens": 2488511.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.497004985809326,
|
|
"epoch": 1.181349376880103,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986269487807434,
|
|
"loss": 6.4471,
|
|
"mean_token_accuracy": 0.13357599899172784,
|
|
"num_tokens": 2497868.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.477199649810791,
|
|
"epoch": 1.1856467554791577,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498590029423827,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.13786919862031938,
|
|
"num_tokens": 2506873.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.5761964321136475,
|
|
"epoch": 1.1899441340782122,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985526218356546,
|
|
"loss": 6.5068,
|
|
"mean_token_accuracy": 0.13015856072306634,
|
|
"num_tokens": 2517317.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.4771264553070065,
|
|
"epoch": 1.1942415126772667,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985147260979093,
|
|
"loss": 6.4256,
|
|
"mean_token_accuracy": 0.14017087668180467,
|
|
"num_tokens": 2527348.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.5237367153167725,
|
|
"epoch": 1.1985388912763215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984763422933402,
|
|
"loss": 6.3999,
|
|
"mean_token_accuracy": 0.1334431551396847,
|
|
"num_tokens": 2536277.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.4698676586151125,
|
|
"epoch": 1.202836269875376,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984374705057623,
|
|
"loss": 6.4717,
|
|
"mean_token_accuracy": 0.12729324474930764,
|
|
"num_tokens": 2545638.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.3455939292907715,
|
|
"epoch": 1.2071336484744306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983981108200561,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.14563890397548676,
|
|
"num_tokens": 2555694.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.531454277038574,
|
|
"epoch": 1.2114310270734852,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983582633221672,
|
|
"loss": 6.3456,
|
|
"mean_token_accuracy": 0.13223223984241486,
|
|
"num_tokens": 2564344.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.432409477233887,
|
|
"epoch": 1.2157284056725397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983179280991068,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.13943792656064033,
|
|
"num_tokens": 2573726.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.452390909194946,
|
|
"epoch": 1.2200257842715942,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982771052389508,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.13722645938396455,
|
|
"num_tokens": 2582845.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.4626904964447025,
|
|
"epoch": 1.224323162870649,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982357948308401,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.1429854430258274,
|
|
"num_tokens": 2591258.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.509098243713379,
|
|
"epoch": 1.2286205414697036,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981939969649799,
|
|
"loss": 6.3916,
|
|
"mean_token_accuracy": 0.1318533204495907,
|
|
"num_tokens": 2600099.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.4922661781311035,
|
|
"epoch": 1.232917920068758,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981517117326404,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.14044687375426293,
|
|
"num_tokens": 2608845.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.376135206222534,
|
|
"epoch": 1.2372152986678127,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981089392261553,
|
|
"loss": 6.3137,
|
|
"mean_token_accuracy": 0.13984026685357093,
|
|
"num_tokens": 2618723.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.430540895462036,
|
|
"epoch": 1.2415126772668672,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498065679538923,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.1358903966844082,
|
|
"num_tokens": 2628542.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.445869493484497,
|
|
"epoch": 1.2458100558659218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980219327654049,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.14282078370451928,
|
|
"num_tokens": 2637395.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.394225835800171,
|
|
"epoch": 1.2501074344649763,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497977699001127,
|
|
"loss": 6.1983,
|
|
"mean_token_accuracy": 0.14897849634289742,
|
|
"num_tokens": 2645545.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.3761859893798825,
|
|
"epoch": 1.2544048130640308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979329783426778,
|
|
"loss": 6.3791,
|
|
"mean_token_accuracy": 0.14151204004883766,
|
|
"num_tokens": 2654000.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.437392139434815,
|
|
"epoch": 1.2587021916630854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978877708877094,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.13939365819096566,
|
|
"num_tokens": 2664017.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.415973091125489,
|
|
"epoch": 1.2629995702621402,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978420767349368,
|
|
"loss": 6.3758,
|
|
"mean_token_accuracy": 0.1392499901354313,
|
|
"num_tokens": 2673250.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.470103645324707,
|
|
"epoch": 1.2672969488611947,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977958959841379,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.13894930183887483,
|
|
"num_tokens": 2682190.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.462930536270141,
|
|
"epoch": 1.2715943274602493,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497749228736153,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.13693501725792884,
|
|
"num_tokens": 2691425.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.487558031082154,
|
|
"epoch": 1.2758917060593038,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004977020750928845,
|
|
"loss": 6.4314,
|
|
"mean_token_accuracy": 0.13328145816922188,
|
|
"num_tokens": 2701123.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.339822912216187,
|
|
"epoch": 1.2801890846583583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976544351572973,
|
|
"loss": 6.4283,
|
|
"mean_token_accuracy": 0.13217268735170365,
|
|
"num_tokens": 2710829.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.5346620082855225,
|
|
"epoch": 1.2844864632574131,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004976063090334179,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.13936254531145095,
|
|
"num_tokens": 2720313.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.357281064987182,
|
|
"epoch": 1.2887838418564677,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975576968263346,
|
|
"loss": 6.2811,
|
|
"mean_token_accuracy": 0.14250001460313796,
|
|
"num_tokens": 2729734.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 1.2887838418564677,
|
|
"eval_entropy": 6.225875508677852,
|
|
"eval_loss": 6.502307415008545,
|
|
"eval_mean_token_accuracy": 0.1380094436106381,
|
|
"eval_num_tokens": 2729734.0,
|
|
"eval_runtime": 2.6325,
|
|
"eval_samples_per_second": 1348.163,
|
|
"eval_steps_per_second": 168.663,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.396690702438354,
|
|
"epoch": 1.2930812204555222,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497508598642197,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.13525475636124612,
|
|
"num_tokens": 2739001.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.442233562469482,
|
|
"epoch": 1.2973785990545768,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497459014588216,
|
|
"loss": 6.2613,
|
|
"mean_token_accuracy": 0.1440258502960205,
|
|
"num_tokens": 2748460.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.321086597442627,
|
|
"epoch": 1.3016759776536313,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497408944772663,
|
|
"loss": 6.3893,
|
|
"mean_token_accuracy": 0.1376827046275139,
|
|
"num_tokens": 2757993.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.437920141220093,
|
|
"epoch": 1.3059733562526858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004973583893048707,
|
|
"loss": 6.4098,
|
|
"mean_token_accuracy": 0.13957171514630318,
|
|
"num_tokens": 2767380.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.435287952423096,
|
|
"epoch": 1.3102707348517404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973073482952321,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.14111845567822456,
|
|
"num_tokens": 2776207.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.3955525875091555,
|
|
"epoch": 1.314568113450795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972558218552004,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.14018303379416466,
|
|
"num_tokens": 2785857.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.43671350479126,
|
|
"epoch": 1.3188654920498495,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972038100972885,
|
|
"loss": 6.4667,
|
|
"mean_token_accuracy": 0.13432941138744353,
|
|
"num_tokens": 2795500.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.449034547805786,
|
|
"epoch": 1.323162870648904,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971513131350697,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.1369171641767025,
|
|
"num_tokens": 2804188.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.387170505523682,
|
|
"epoch": 1.3274602492479588,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970983310831759,
|
|
"loss": 6.3547,
|
|
"mean_token_accuracy": 0.13035919144749641,
|
|
"num_tokens": 2814255.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.4166727542877195,
|
|
"epoch": 1.3317576278470133,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004970448640572989,
|
|
"loss": 6.3329,
|
|
"mean_token_accuracy": 0.14074430763721466,
|
|
"num_tokens": 2823059.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.386816072463989,
|
|
"epoch": 1.336055006446068,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004969909121741895,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.14372179433703422,
|
|
"num_tokens": 2831729.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.37970085144043,
|
|
"epoch": 1.3403523850451224,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969364755516569,
|
|
"loss": 6.3209,
|
|
"mean_token_accuracy": 0.14519608169794082,
|
|
"num_tokens": 2839597.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.372022533416748,
|
|
"epoch": 1.344649763644177,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004968815543085689,
|
|
"loss": 6.1988,
|
|
"mean_token_accuracy": 0.14956804513931274,
|
|
"num_tokens": 2847964.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.318734455108642,
|
|
"epoch": 1.3489471422432318,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968261485648516,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.13511656373739242,
|
|
"num_tokens": 2857712.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.415015649795532,
|
|
"epoch": 1.3532445208422863,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000496770258441489,
|
|
"loss": 6.4039,
|
|
"mean_token_accuracy": 0.13150390312075616,
|
|
"num_tokens": 2866724.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.480535697937012,
|
|
"epoch": 1.3575418994413408,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004967138840605228,
|
|
"loss": 6.2821,
|
|
"mean_token_accuracy": 0.1422867201268673,
|
|
"num_tokens": 2875318.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.371291399002075,
|
|
"epoch": 1.3618392780403954,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000496657025545052,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.1330809101462364,
|
|
"num_tokens": 2883794.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.419414758682251,
|
|
"epoch": 1.36613665663945,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000496599683019233,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.1338125415146351,
|
|
"num_tokens": 2891996.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.391923189163208,
|
|
"epoch": 1.3704340352385045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000496541856608279,
|
|
"loss": 6.4484,
|
|
"mean_token_accuracy": 0.1343950994312763,
|
|
"num_tokens": 2901718.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.449080562591552,
|
|
"epoch": 1.374731413837559,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964835464384595,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.1431309886276722,
|
|
"num_tokens": 2910924.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.311095952987671,
|
|
"epoch": 1.3790287924366136,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000496424752637101,
|
|
"loss": 6.3674,
|
|
"mean_token_accuracy": 0.1359468601644039,
|
|
"num_tokens": 2920075.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.367361640930175,
|
|
"epoch": 1.3833261710356681,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004963654753325853,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.1429993435740471,
|
|
"num_tokens": 2928946.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.329522371292114,
|
|
"epoch": 1.387623549634723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004963057146543505,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.15131649672985076,
|
|
"num_tokens": 2936817.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.382766580581665,
|
|
"epoch": 1.3919209282337774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049624547073289,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.14377383068203925,
|
|
"num_tokens": 2946096.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.362337255477906,
|
|
"epoch": 1.396218306832832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961847436997526,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.14999890178442002,
|
|
"num_tokens": 2955632.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.366307544708252,
|
|
"epoch": 1.4005156854318865,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004961235336875416,
|
|
"loss": 6.2579,
|
|
"mean_token_accuracy": 0.14550368934869767,
|
|
"num_tokens": 2963779.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.358678722381592,
|
|
"epoch": 1.404813064030941,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004960618408299154,
|
|
"loss": 6.2494,
|
|
"mean_token_accuracy": 0.1504204198718071,
|
|
"num_tokens": 2972778.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.318516445159912,
|
|
"epoch": 1.4091104426299956,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004959996652615865,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.13637638315558434,
|
|
"num_tokens": 2982318.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.44262466430664,
|
|
"epoch": 1.4134078212290504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959370071183216,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.14733938425779342,
|
|
"num_tokens": 2991822.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.3717328071594235,
|
|
"epoch": 1.417705199828105,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004958738665369407,
|
|
"loss": 6.3792,
|
|
"mean_token_accuracy": 0.13971310779452323,
|
|
"num_tokens": 3001203.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.349838733673096,
|
|
"epoch": 1.4220025784271595,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958102436553179,
|
|
"loss": 6.2995,
|
|
"mean_token_accuracy": 0.13951244726777076,
|
|
"num_tokens": 3010445.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.399106740951538,
|
|
"epoch": 1.426299957026214,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049574613861238,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.13808537349104882,
|
|
"num_tokens": 3019919.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.476325130462646,
|
|
"epoch": 1.4305973356252686,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004956815515481069,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.13107064962387086,
|
|
"num_tokens": 3029469.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.404677104949951,
|
|
"epoch": 1.4348947142243231,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004956164826035309,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.14275707602500914,
|
|
"num_tokens": 3038627.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.359204912185669,
|
|
"epoch": 1.4391920928233777,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955509319207363,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.138480856269598,
|
|
"num_tokens": 3048124.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.322403764724731,
|
|
"epoch": 1.4434894714224322,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004954848996428601,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.14859130680561067,
|
|
"num_tokens": 3056394.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.297450351715088,
|
|
"epoch": 1.4477868500214868,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049541838591409,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.1398971401154995,
|
|
"num_tokens": 3066521.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.366423177719116,
|
|
"epoch": 1.4520842286205415,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004953513908796657,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.14321988448500633,
|
|
"num_tokens": 3076571.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.381562280654907,
|
|
"epoch": 1.456381607219596,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004952839146858773,
|
|
"loss": 6.428,
|
|
"mean_token_accuracy": 0.1346765175461769,
|
|
"num_tokens": 3086086.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.335469150543213,
|
|
"epoch": 1.4606789858186506,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004952159574800658,
|
|
"loss": 6.2967,
|
|
"mean_token_accuracy": 0.1462803915143013,
|
|
"num_tokens": 3095046.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.314669752120972,
|
|
"epoch": 1.4649763644177052,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004951475194106229,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.14232781156897545,
|
|
"num_tokens": 3104193.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.4825750350952145,
|
|
"epoch": 1.4692737430167597,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004950786006269898,
|
|
"loss": 6.3566,
|
|
"mean_token_accuracy": 0.1422339826822281,
|
|
"num_tokens": 3112965.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.331253480911255,
|
|
"epoch": 1.4735711216158143,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004950092012796576,
|
|
"loss": 6.4137,
|
|
"mean_token_accuracy": 0.1361984558403492,
|
|
"num_tokens": 3122883.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.377304458618164,
|
|
"epoch": 1.477868500214869,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949393215201666,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.15220774635672568,
|
|
"num_tokens": 3132182.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.340102863311768,
|
|
"epoch": 1.4821658788139236,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948689615011065,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.14068598598241805,
|
|
"num_tokens": 3141957.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.31355299949646,
|
|
"epoch": 1.4864632574129781,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004947981213761154,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.14872836396098138,
|
|
"num_tokens": 3151374.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.266488409042358,
|
|
"epoch": 1.4907606360120327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004947268012998797,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.1442766495049,
|
|
"num_tokens": 3160815.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.43033537864685,
|
|
"epoch": 1.4950580146110872,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000494655001428134,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.14629183933138848,
|
|
"num_tokens": 3169684.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.341884183883667,
|
|
"epoch": 1.4993553932101418,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004945827219176604,
|
|
"loss": 6.2666,
|
|
"mean_token_accuracy": 0.14152552783489228,
|
|
"num_tokens": 3178754.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.314790964126587,
|
|
"epoch": 1.5036527718091963,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004945099629262888,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.14713623374700546,
|
|
"num_tokens": 3187315.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.367385196685791,
|
|
"epoch": 1.5079501504082509,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004944367246128954,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.15467803478240966,
|
|
"num_tokens": 3195975.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.279762935638428,
|
|
"epoch": 1.5122475290073054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004943630071374036,
|
|
"loss": 6.2884,
|
|
"mean_token_accuracy": 0.14560731798410415,
|
|
"num_tokens": 3204071.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.352357530593872,
|
|
"epoch": 1.51654490760636,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004942888106607828,
|
|
"loss": 6.2805,
|
|
"mean_token_accuracy": 0.14571768492460252,
|
|
"num_tokens": 3213001.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.385111236572266,
|
|
"epoch": 1.5208422862054147,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942141353450486,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.13302915021777154,
|
|
"num_tokens": 3222576.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.397508764266968,
|
|
"epoch": 1.5251396648044693,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004941389813532619,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.14305002242326736,
|
|
"num_tokens": 3230474.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.347569131851197,
|
|
"epoch": 1.5294370434035238,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000494063348849529,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.14401185810565947,
|
|
"num_tokens": 3238723.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.265641689300537,
|
|
"epoch": 1.5337344220025786,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004939872379990011,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.1483248919248581,
|
|
"num_tokens": 3247844.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.41879940032959,
|
|
"epoch": 1.5380318006016331,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004939106489678739,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.14301740303635596,
|
|
"num_tokens": 3257228.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.408779001235962,
|
|
"epoch": 1.5423291792006877,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000493833581923387,
|
|
"loss": 6.3231,
|
|
"mean_token_accuracy": 0.13824094384908675,
|
|
"num_tokens": 3266655.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.3060040950775145,
|
|
"epoch": 1.5466265577997422,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004937560370338244,
|
|
"loss": 6.2434,
|
|
"mean_token_accuracy": 0.14510375261306763,
|
|
"num_tokens": 3275213.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.408991718292237,
|
|
"epoch": 1.5509239363987968,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493678014468513,
|
|
"loss": 6.3779,
|
|
"mean_token_accuracy": 0.13703251108527184,
|
|
"num_tokens": 3284447.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.350679492950439,
|
|
"epoch": 1.5552213149978513,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004935995143978227,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.13779493197798728,
|
|
"num_tokens": 3293568.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.285771989822388,
|
|
"epoch": 1.5595186935969059,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004935205369931664,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.14422329068183898,
|
|
"num_tokens": 3302055.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.356205034255981,
|
|
"epoch": 1.5638160721959604,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934410824269992,
|
|
"loss": 6.293,
|
|
"mean_token_accuracy": 0.14307598844170571,
|
|
"num_tokens": 3310672.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.324226570129395,
|
|
"epoch": 1.568113450795015,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004933611508728182,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.14398171454668046,
|
|
"num_tokens": 3319666.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.338666772842407,
|
|
"epoch": 1.5724108293940695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000493280742505162,
|
|
"loss": 6.2517,
|
|
"mean_token_accuracy": 0.14428381100296975,
|
|
"num_tokens": 3329121.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.26886887550354,
|
|
"epoch": 1.576708207993124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004931998574996102,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.14581965357065202,
|
|
"num_tokens": 3337868.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.31952691078186,
|
|
"epoch": 1.5810055865921788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004931184960327832,
|
|
"loss": 6.2743,
|
|
"mean_token_accuracy": 0.14775650948286057,
|
|
"num_tokens": 3346447.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.299622392654419,
|
|
"epoch": 1.5853029651912334,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004930366582823421,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.14039799869060515,
|
|
"num_tokens": 3355187.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.348891973495483,
|
|
"epoch": 1.589600343790288,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004929543444269879,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.12413048818707466,
|
|
"num_tokens": 3365978.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.397365522384644,
|
|
"epoch": 1.5938977223893425,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000492871554646461,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.14158129766583444,
|
|
"num_tokens": 3374607.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.336241769790649,
|
|
"epoch": 1.5981951009883972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927882891215413,
|
|
"loss": 6.3163,
|
|
"mean_token_accuracy": 0.13903330489993096,
|
|
"num_tokens": 3384541.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.361058235168457,
|
|
"epoch": 1.6024924795874518,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004927045480340475,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.13128943145275115,
|
|
"num_tokens": 3394009.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.38292350769043,
|
|
"epoch": 1.6067898581865063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004926203315668363,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.14705114364624022,
|
|
"num_tokens": 3402550.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.333295106887817,
|
|
"epoch": 1.6110872367855609,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925356399038032,
|
|
"loss": 6.2854,
|
|
"mean_token_accuracy": 0.14575798213481903,
|
|
"num_tokens": 3413230.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.227672910690307,
|
|
"epoch": 1.6153846153846154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004924504732298808,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.1498914524912834,
|
|
"num_tokens": 3422325.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.411320638656616,
|
|
"epoch": 1.61968199398367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923648317310391,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.13707044050097467,
|
|
"num_tokens": 3431758.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.262428092956543,
|
|
"epoch": 1.6239793725827245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004922787155942849,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.14557855874300002,
|
|
"num_tokens": 3441281.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.317093467712402,
|
|
"epoch": 1.628276751181779,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004921921250076611,
|
|
"loss": 6.2754,
|
|
"mean_token_accuracy": 0.14766671732068062,
|
|
"num_tokens": 3449822.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.347660970687866,
|
|
"epoch": 1.6325741297808336,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921050601602475,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.14015369564294816,
|
|
"num_tokens": 3459437.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.3261857509613035,
|
|
"epoch": 1.6368715083798882,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004920175212421587,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.14800578653812407,
|
|
"num_tokens": 3469546.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.411861324310303,
|
|
"epoch": 1.6411688869789427,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004919295084445445,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.13949010968208314,
|
|
"num_tokens": 3478521.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.252915906906128,
|
|
"epoch": 1.6454662655779975,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004918410219595899,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.1499532699584961,
|
|
"num_tokens": 3487958.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.255596494674682,
|
|
"epoch": 1.649763644177052,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000491752061980514,
|
|
"loss": 6.2476,
|
|
"mean_token_accuracy": 0.14446067586541175,
|
|
"num_tokens": 3495941.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.297366428375244,
|
|
"epoch": 1.6540610227761066,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004916626287015697,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.1459622099995613,
|
|
"num_tokens": 3505172.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.296765279769898,
|
|
"epoch": 1.658358401375161,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004915727223180436,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.14922861829400064,
|
|
"num_tokens": 3514084.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.42270679473877,
|
|
"epoch": 1.6626557799742159,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004914823430262554,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.1387872278690338,
|
|
"num_tokens": 3523318.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.304086303710937,
|
|
"epoch": 1.6669531585732704,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004913914910235573,
|
|
"loss": 6.2144,
|
|
"mean_token_accuracy": 0.14882446974515914,
|
|
"num_tokens": 3531681.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.264715385437012,
|
|
"epoch": 1.671250537172325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004913001665083337,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.14123921766877173,
|
|
"num_tokens": 3540326.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.336367464065551,
|
|
"epoch": 1.6755479157713795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004912083696800008,
|
|
"loss": 6.2498,
|
|
"mean_token_accuracy": 0.1417755626142025,
|
|
"num_tokens": 3548319.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.2093394756317135,
|
|
"epoch": 1.679845294370434,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004911161007390063,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.15048674941062928,
|
|
"num_tokens": 3557743.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.2037858963012695,
|
|
"epoch": 1.6841426729694886,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004910233598868287,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.15063542425632476,
|
|
"num_tokens": 3566810.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.319229221343994,
|
|
"epoch": 1.6884400515685432,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004909301473259769,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.14927951395511627,
|
|
"num_tokens": 3576273.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.224372720718383,
|
|
"epoch": 1.6927374301675977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004908364632599899,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.14561723917722702,
|
|
"num_tokens": 3585362.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.2979576110839846,
|
|
"epoch": 1.6970348087666522,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004907423078934362,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.1375780612230301,
|
|
"num_tokens": 3594445.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.296867942810058,
|
|
"epoch": 1.7013321873657068,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004906476814319134,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.13942770212888717,
|
|
"num_tokens": 3604046.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.365720796585083,
|
|
"epoch": 1.7056295659647613,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004905525840820481,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.14392739534378052,
|
|
"num_tokens": 3613264.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.303918886184692,
|
|
"epoch": 1.709926944563816,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004904570160514948,
|
|
"loss": 6.1724,
|
|
"mean_token_accuracy": 0.14787200540304185,
|
|
"num_tokens": 3620938.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.262858819961548,
|
|
"epoch": 1.7142243231628707,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004903609775489358,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.14155241400003432,
|
|
"num_tokens": 3629782.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.363343238830566,
|
|
"epoch": 1.7185217017619252,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004902644687840809,
|
|
"loss": 6.3347,
|
|
"mean_token_accuracy": 0.13947545289993285,
|
|
"num_tokens": 3638389.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.7185217017619252,
|
|
"eval_entropy": 6.028549555185679,
|
|
"eval_loss": 6.352311611175537,
|
|
"eval_mean_token_accuracy": 0.14357087935681814,
|
|
"eval_num_tokens": 3638389.0,
|
|
"eval_runtime": 2.6487,
|
|
"eval_samples_per_second": 1339.891,
|
|
"eval_steps_per_second": 167.628,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.196940898895264,
|
|
"epoch": 1.7228190803609797,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004901674899676667,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.15208130180835724,
|
|
"num_tokens": 3647196.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.18595404624939,
|
|
"epoch": 1.7271164589600345,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900700413114561,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.15374353379011155,
|
|
"num_tokens": 3655931.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.310988998413086,
|
|
"epoch": 1.731413837559089,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000489972123028238,
|
|
"loss": 6.2676,
|
|
"mean_token_accuracy": 0.1467567965388298,
|
|
"num_tokens": 3665340.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.268195533752442,
|
|
"epoch": 1.7357112161581436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004898737353318268,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.15013988465070724,
|
|
"num_tokens": 3674674.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.301918649673462,
|
|
"epoch": 1.7400085947571982,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000489774878437062,
|
|
"loss": 6.2572,
|
|
"mean_token_accuracy": 0.15027557015419007,
|
|
"num_tokens": 3683910.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.267896747589111,
|
|
"epoch": 1.7443059733562527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004896755525598074,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.14787854254245758,
|
|
"num_tokens": 3692772.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.2744200229644775,
|
|
"epoch": 1.7486033519553073,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895757579169511,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.15500140488147734,
|
|
"num_tokens": 3701875.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.258078145980835,
|
|
"epoch": 1.7529007305543618,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004894754947264047,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.14737177044153213,
|
|
"num_tokens": 3711059.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.273642301559448,
|
|
"epoch": 1.7571981091534163,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000489374763207103,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.15221278220415116,
|
|
"num_tokens": 3719667.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.176022243499756,
|
|
"epoch": 1.761495487752471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004892735635790033,
|
|
"loss": 6.1691,
|
|
"mean_token_accuracy": 0.14955660551786423,
|
|
"num_tokens": 3728905.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.270573949813842,
|
|
"epoch": 1.7657928663515254,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000489171896063085,
|
|
"loss": 6.2023,
|
|
"mean_token_accuracy": 0.14582386016845703,
|
|
"num_tokens": 3737973.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.205034065246582,
|
|
"epoch": 1.77009024495058,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004890697608813495,
|
|
"loss": 6.1614,
|
|
"mean_token_accuracy": 0.149971167743206,
|
|
"num_tokens": 3747160.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.202639961242676,
|
|
"epoch": 1.7743876235496348,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004889671582568193,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.14935097396373748,
|
|
"num_tokens": 3754908.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.299329328536987,
|
|
"epoch": 1.7786850021486893,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004888640884135374,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.13549285531044006,
|
|
"num_tokens": 3763588.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.21603832244873,
|
|
"epoch": 1.7829823807477438,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004887605515765671,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.15028423219919204,
|
|
"num_tokens": 3771932.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.286951112747192,
|
|
"epoch": 1.7872797593467986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004886565479719914,
|
|
"loss": 6.2865,
|
|
"mean_token_accuracy": 0.1433756723999977,
|
|
"num_tokens": 3780761.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.220171737670898,
|
|
"epoch": 1.7915771379458532,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004885520778269128,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.15441024005413057,
|
|
"num_tokens": 3789511.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.20865387916565,
|
|
"epoch": 1.7958745165449077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004884471413694523,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.1363023564219475,
|
|
"num_tokens": 3799068.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.3188676834106445,
|
|
"epoch": 1.8001718951439623,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004883417388287491,
|
|
"loss": 6.1667,
|
|
"mean_token_accuracy": 0.1450318641960621,
|
|
"num_tokens": 3807850.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.26737003326416,
|
|
"epoch": 1.8044692737430168,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004882358704349603,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.15362504720687867,
|
|
"num_tokens": 3816232.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.204585838317871,
|
|
"epoch": 1.8087666523420713,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004881295364192601,
|
|
"loss": 6.2312,
|
|
"mean_token_accuracy": 0.13994672447443007,
|
|
"num_tokens": 3825334.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.213073301315307,
|
|
"epoch": 1.813064030941126,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004880227370138394,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.1517607569694519,
|
|
"num_tokens": 3834756.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.338291358947754,
|
|
"epoch": 1.8173614095401804,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004879154724519057,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.14460117518901824,
|
|
"num_tokens": 3843852.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.261815309524536,
|
|
"epoch": 1.821658788139235,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004878077429676816,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.1576495312154293,
|
|
"num_tokens": 3852213.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.227415990829468,
|
|
"epoch": 1.8259561667382895,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004876995487964054,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.13798727393150328,
|
|
"num_tokens": 3861522.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.2565147399902346,
|
|
"epoch": 1.830253545337344,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048759089017432996,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.15773860663175582,
|
|
"num_tokens": 3870328.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.246215200424194,
|
|
"epoch": 1.8345509239363988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004874817673387222,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.14310137778520585,
|
|
"num_tokens": 3880399.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.259421873092651,
|
|
"epoch": 1.8388483025354534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048737218052786275,
|
|
"loss": 6.1678,
|
|
"mean_token_accuracy": 0.14924097061157227,
|
|
"num_tokens": 3889859.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.1444484233856205,
|
|
"epoch": 1.843145681134508,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048726212998104554,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.1519687682390213,
|
|
"num_tokens": 3899609.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.270504760742187,
|
|
"epoch": 1.8474430597335625,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004871516159385768,
|
|
"loss": 6.2271,
|
|
"mean_token_accuracy": 0.1401534102857113,
|
|
"num_tokens": 3909452.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.335358810424805,
|
|
"epoch": 1.8517404383326173,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004870406386417752,
|
|
"loss": 6.269,
|
|
"mean_token_accuracy": 0.14715837240219115,
|
|
"num_tokens": 3918579.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.262742137908935,
|
|
"epoch": 1.8560378169316718,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004869291983329707,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.15219318568706514,
|
|
"num_tokens": 3926951.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.181666231155395,
|
|
"epoch": 1.8603351955307263,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004868172952555044,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.1487558200955391,
|
|
"num_tokens": 3935771.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.242819786071777,
|
|
"epoch": 1.864632574129781,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004867049296537278,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.15747302025556564,
|
|
"num_tokens": 3944577.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.281427431106567,
|
|
"epoch": 1.8689299527288354,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004865921017730027,
|
|
"loss": 6.267,
|
|
"mean_token_accuracy": 0.14637882634997368,
|
|
"num_tokens": 3954499.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.216175651550293,
|
|
"epoch": 1.87322733132789,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048647881185969995,
|
|
"loss": 6.1862,
|
|
"mean_token_accuracy": 0.14351969063282013,
|
|
"num_tokens": 3963953.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.210945272445679,
|
|
"epoch": 1.8775247099269445,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004863650601611994,
|
|
"loss": 6.1971,
|
|
"mean_token_accuracy": 0.14761989265680314,
|
|
"num_tokens": 3973925.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.239703273773193,
|
|
"epoch": 1.881822088525999,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048625084692588937,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.14801398664712906,
|
|
"num_tokens": 3983280.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.194201278686523,
|
|
"epoch": 1.8861194671250536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048613617240316593,
|
|
"loss": 6.1691,
|
|
"mean_token_accuracy": 0.14983253479003905,
|
|
"num_tokens": 3992767.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.32085862159729,
|
|
"epoch": 1.8904168457241082,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004860210368434323,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.13981493264436723,
|
|
"num_tokens": 4001600.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.232434463500977,
|
|
"epoch": 1.8947142243231627,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048590544049809857,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.14904941469430924,
|
|
"num_tokens": 4010852.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.2208820343017575,
|
|
"epoch": 1.8990116029222175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000485789383619581,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.14979886412620544,
|
|
"num_tokens": 4020280.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.244888353347778,
|
|
"epoch": 1.903308981521272,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004856728664613015,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.15172455683350564,
|
|
"num_tokens": 4029283.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.2939231395721436,
|
|
"epoch": 1.9076063601203266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048555588927768674,
|
|
"loss": 6.2399,
|
|
"mean_token_accuracy": 0.15116785317659379,
|
|
"num_tokens": 4038704.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.17348461151123,
|
|
"epoch": 1.9119037387193811,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004854384523241683,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.14770452305674553,
|
|
"num_tokens": 4047492.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.251682472229004,
|
|
"epoch": 1.916201117318436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048532055585718143,
|
|
"loss": 6.2895,
|
|
"mean_token_accuracy": 0.14247784093022348,
|
|
"num_tokens": 4056792.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.257444572448731,
|
|
"epoch": 1.9204984959174904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048520220013416505,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.15522112101316451,
|
|
"num_tokens": 4065284.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.119591903686524,
|
|
"epoch": 1.924795874516545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004850833854135607,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.149675352871418,
|
|
"num_tokens": 4074727.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.340999507904053,
|
|
"epoch": 1.9290932531155995,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004849641119548122,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.1487278312444687,
|
|
"num_tokens": 4083360.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.237739086151123,
|
|
"epoch": 1.933390631714654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000484844380018365,
|
|
"loss": 6.3064,
|
|
"mean_token_accuracy": 0.13851014897227287,
|
|
"num_tokens": 4092431.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.2545881271362305,
|
|
"epoch": 1.9376880103137086,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000484724189865666,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.14804239720106124,
|
|
"num_tokens": 4102198.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.2334897994995115,
|
|
"epoch": 1.9419853889127632,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004846035417591624,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.1523241475224495,
|
|
"num_tokens": 4111568.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.23221755027771,
|
|
"epoch": 1.9462827675118177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004844824359623014,
|
|
"loss": 6.1998,
|
|
"mean_token_accuracy": 0.14418465942144393,
|
|
"num_tokens": 4121151.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.278671407699585,
|
|
"epoch": 1.9505801461108723,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048436087273952966,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.14655561298131942,
|
|
"num_tokens": 4130197.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.086948871612549,
|
|
"epoch": 1.9548775247099268,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048423885235629265,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.1391369014978409,
|
|
"num_tokens": 4138310.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.2306829452514645,
|
|
"epoch": 1.9591749033089814,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004841163750790342,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.1557426020503044,
|
|
"num_tokens": 4148270.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.210293531417847,
|
|
"epoch": 1.9634722819080361,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048399344117519555,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.1499612420797348,
|
|
"num_tokens": 4157276.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.134465265274048,
|
|
"epoch": 1.9677696605070907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048387005091321544,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.15338025540113448,
|
|
"num_tokens": 4166144.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.35327787399292,
|
|
"epoch": 1.9720670391061452,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048374620456252877,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14432276636362076,
|
|
"num_tokens": 4175146.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.164651250839233,
|
|
"epoch": 1.9763644177052,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048362190239356644,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.14050934612751007,
|
|
"num_tokens": 4184089.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.261477375030518,
|
|
"epoch": 1.9806617963042545,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048349714467775474,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.14885230213403702,
|
|
"num_tokens": 4192453.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.221670866012573,
|
|
"epoch": 1.984959174903309,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048337193168751464,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.15655480176210404,
|
|
"num_tokens": 4201323.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.134425449371338,
|
|
"epoch": 1.9892565535023636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004832462636962613,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.15031953081488608,
|
|
"num_tokens": 4209805.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.2537988185882565,
|
|
"epoch": 1.9935539321014182,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004831201409784034,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.14936504513025284,
|
|
"num_tokens": 4218562.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.205300283432007,
|
|
"epoch": 1.9978513107004727,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004829935638093424,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.1510600835084915,
|
|
"num_tokens": 4227605.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.255237208472358,
|
|
"epoch": 2.0017189514396216,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004828665324654724,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.15552079843150246,
|
|
"num_tokens": 4235441.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.2011861324310305,
|
|
"epoch": 2.006016330038676,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004827390472241791,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.1603270322084427,
|
|
"num_tokens": 4243982.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.090994930267334,
|
|
"epoch": 2.010313708637731,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004826111083638392,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.15214518457651138,
|
|
"num_tokens": 4253032.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.203659296035767,
|
|
"epoch": 2.0146110872367857,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048248271616382,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.16601352095603944,
|
|
"num_tokens": 4262000.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.0723145484924315,
|
|
"epoch": 2.0189084658358403,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048235387090447894,
|
|
"loss": 5.8301,
|
|
"mean_token_accuracy": 0.15925069227814675,
|
|
"num_tokens": 4271089.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.14722900390625,
|
|
"epoch": 2.023205844434895,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048222457286716235,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.16075642555952072,
|
|
"num_tokens": 4280064.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.140841007232666,
|
|
"epoch": 2.0275032230339494,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048209482233420564,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.1619458571076393,
|
|
"num_tokens": 4289096.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.0976330757141115,
|
|
"epoch": 2.031800601633004,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000481964619588932,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.15225235521793365,
|
|
"num_tokens": 4298341.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.118788385391236,
|
|
"epoch": 2.0360979802320585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004818339649156523,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.14997191429138185,
|
|
"num_tokens": 4307466.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.107895755767823,
|
|
"epoch": 2.040395358831113,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048170285859966395,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.1605072647333145,
|
|
"num_tokens": 4316559.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.136744546890259,
|
|
"epoch": 2.0446927374301676,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048157130092725087,
|
|
"loss": 5.8229,
|
|
"mean_token_accuracy": 0.15814021229743958,
|
|
"num_tokens": 4326002.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.073250246047974,
|
|
"epoch": 2.048990116029222,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004814392921856824,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.16814109385013581,
|
|
"num_tokens": 4333767.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.123864555358887,
|
|
"epoch": 2.0532874946282766,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004813068326632128,
|
|
"loss": 5.8407,
|
|
"mean_token_accuracy": 0.1677692249417305,
|
|
"num_tokens": 4342726.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.03325662612915,
|
|
"epoch": 2.057584873227331,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004811739226490809,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.164510577917099,
|
|
"num_tokens": 4351278.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.029361057281494,
|
|
"epoch": 2.0618822518263857,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048104056243350896,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.1730365440249443,
|
|
"num_tokens": 4360146.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.069676494598388,
|
|
"epoch": 2.0661796304254403,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004809067523077023,
|
|
"loss": 5.81,
|
|
"mean_token_accuracy": 0.1618461474776268,
|
|
"num_tokens": 4368474.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.122001266479492,
|
|
"epoch": 2.0704770090244953,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048077249256384884,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.15631877779960632,
|
|
"num_tokens": 4378430.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.074360942840576,
|
|
"epoch": 2.07477438762355,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004806377834951182,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.15965779721736909,
|
|
"num_tokens": 4387661.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.1412880420684814,
|
|
"epoch": 2.0790717662226044,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048050262539566104,
|
|
"loss": 5.8314,
|
|
"mean_token_accuracy": 0.1613117054104805,
|
|
"num_tokens": 4396568.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.996071815490723,
|
|
"epoch": 2.083369144821659,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004803670185606087,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.16476011425256729,
|
|
"num_tokens": 4405113.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.1124523162841795,
|
|
"epoch": 2.0876665234207135,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004802309632860724,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.1617572069168091,
|
|
"num_tokens": 4414930.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.101985788345337,
|
|
"epoch": 2.091963902019768,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048009445986914236,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.15561344623565673,
|
|
"num_tokens": 4424200.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.046984767913818,
|
|
"epoch": 2.0962612806188226,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047995750860788756,
|
|
"loss": 5.8467,
|
|
"mean_token_accuracy": 0.1636588454246521,
|
|
"num_tokens": 4433533.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.107754755020141,
|
|
"epoch": 2.100558659217877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004798201098013547,
|
|
"loss": 5.8871,
|
|
"mean_token_accuracy": 0.16322858333587648,
|
|
"num_tokens": 4442752.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.040629911422729,
|
|
"epoch": 2.1048560378169316,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047968226374956797,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.1524975925683975,
|
|
"num_tokens": 4453624.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.105652713775635,
|
|
"epoch": 2.109153416415986,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047954397075352794,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.1547384575009346,
|
|
"num_tokens": 4462101.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.125913143157959,
|
|
"epoch": 2.1134507950150407,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047940523111521136,
|
|
"loss": 5.9316,
|
|
"mean_token_accuracy": 0.1496809035539627,
|
|
"num_tokens": 4471274.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.113536024093628,
|
|
"epoch": 2.1177481736140953,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004792660451375701,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.15914952903985977,
|
|
"num_tokens": 4480281.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.109311866760254,
|
|
"epoch": 2.12204555221315,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047912641312453064,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.1615729033946991,
|
|
"num_tokens": 4489325.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.092775630950928,
|
|
"epoch": 2.1263429308122044,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047898633538099363,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1640813648700714,
|
|
"num_tokens": 4497977.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.024752140045166,
|
|
"epoch": 2.130640309411259,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004788458122128327,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.15297108441591262,
|
|
"num_tokens": 4509133.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.080051136016846,
|
|
"epoch": 2.134937688010314,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047870484392689434,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.1625355988740921,
|
|
"num_tokens": 4518431.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.0470091819763185,
|
|
"epoch": 2.1392350666093685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000478563430830997,
|
|
"loss": 5.8647,
|
|
"mean_token_accuracy": 0.16243069469928742,
|
|
"num_tokens": 4528489.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.141346740722656,
|
|
"epoch": 2.143532445208423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047842157323393035,
|
|
"loss": 5.772,
|
|
"mean_token_accuracy": 0.1622501254081726,
|
|
"num_tokens": 4537068.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.048506736755371,
|
|
"epoch": 2.1478298238074776,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004782792714454547,
|
|
"loss": 5.8698,
|
|
"mean_token_accuracy": 0.16409993469715117,
|
|
"num_tokens": 4545773.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 2.1478298238074776,
|
|
"eval_entropy": 5.904563934953363,
|
|
"eval_loss": 6.252427101135254,
|
|
"eval_mean_token_accuracy": 0.1526490680135048,
|
|
"eval_num_tokens": 4545773.0,
|
|
"eval_runtime": 2.6419,
|
|
"eval_samples_per_second": 1343.356,
|
|
"eval_steps_per_second": 168.061,
|
|
"step": 2500
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 11630,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 6872272353792000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|