18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.816400580551524,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.69149408340454,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 13.0625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7699,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9661.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691533756256103,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 12.8125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7409,
|
|
"mean_token_accuracy": 0.00011574074160307646,
|
|
"num_tokens": 21028.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691256523132324,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 9.6875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4719,
|
|
"mean_token_accuracy": 0.019357142923399805,
|
|
"num_tokens": 31794.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.684057140350342,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 5.8125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1776,
|
|
"mean_token_accuracy": 0.04135416336357593,
|
|
"num_tokens": 42892.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.636651706695556,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8988,
|
|
"mean_token_accuracy": 0.04433486089110374,
|
|
"num_tokens": 53015.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.585999393463135,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.7643,
|
|
"mean_token_accuracy": 0.04109931848943234,
|
|
"num_tokens": 63334.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.606278038024902,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6589,
|
|
"mean_token_accuracy": 0.04485522694885731,
|
|
"num_tokens": 74256.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.576828956604004,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6182,
|
|
"mean_token_accuracy": 0.046111271157860755,
|
|
"num_tokens": 84699.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.563911628723144,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.581,
|
|
"mean_token_accuracy": 0.04264976643025875,
|
|
"num_tokens": 95178.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.59095401763916,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.5471,
|
|
"mean_token_accuracy": 0.04867156893014908,
|
|
"num_tokens": 105438.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.587072944641113,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4759,
|
|
"mean_token_accuracy": 0.0453902505338192,
|
|
"num_tokens": 115518.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.536315631866454,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.377,
|
|
"mean_token_accuracy": 0.053391102328896524,
|
|
"num_tokens": 125636.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.496469593048095,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3108,
|
|
"mean_token_accuracy": 0.06191379800438881,
|
|
"num_tokens": 135990.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.413052368164063,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2425,
|
|
"mean_token_accuracy": 0.0613830640912056,
|
|
"num_tokens": 146069.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.440055561065673,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.1547,
|
|
"mean_token_accuracy": 0.07091366611421109,
|
|
"num_tokens": 156335.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.438591575622558,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0463,
|
|
"mean_token_accuracy": 0.06796186193823814,
|
|
"num_tokens": 166214.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.390478229522705,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.9608,
|
|
"mean_token_accuracy": 0.06832841411232948,
|
|
"num_tokens": 177010.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.332666969299316,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7359,
|
|
"mean_token_accuracy": 0.07582402378320693,
|
|
"num_tokens": 187829.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.192521572113037,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6972,
|
|
"mean_token_accuracy": 0.0755643829703331,
|
|
"num_tokens": 198107.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.20487937927246,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.5722,
|
|
"mean_token_accuracy": 0.07500871792435646,
|
|
"num_tokens": 208607.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.160844707489014,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.5622,
|
|
"mean_token_accuracy": 0.07453125491738319,
|
|
"num_tokens": 219899.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.124257946014405,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4797,
|
|
"mean_token_accuracy": 0.07378747165203095,
|
|
"num_tokens": 230625.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.023534488677978,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.332,
|
|
"mean_token_accuracy": 0.08365851938724518,
|
|
"num_tokens": 241156.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.936892032623291,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1824,
|
|
"mean_token_accuracy": 0.08069921731948852,
|
|
"num_tokens": 252297.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.793073558807373,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.1575,
|
|
"mean_token_accuracy": 0.07586940303444863,
|
|
"num_tokens": 263188.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.714948558807373,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9988,
|
|
"mean_token_accuracy": 0.07976540848612786,
|
|
"num_tokens": 274064.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.50658073425293,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8083,
|
|
"mean_token_accuracy": 0.08558063134551049,
|
|
"num_tokens": 283736.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.259089279174805,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7077,
|
|
"mean_token_accuracy": 0.08600766956806183,
|
|
"num_tokens": 294473.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.041689109802245,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6574,
|
|
"mean_token_accuracy": 0.08418083190917969,
|
|
"num_tokens": 303849.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.879548072814941,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5414,
|
|
"mean_token_accuracy": 0.08226052820682525,
|
|
"num_tokens": 314521.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.658054065704345,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.4964,
|
|
"mean_token_accuracy": 0.08540133312344551,
|
|
"num_tokens": 325210.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.465118217468262,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4289,
|
|
"mean_token_accuracy": 0.0857605628669262,
|
|
"num_tokens": 335035.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.27260684967041,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4279,
|
|
"mean_token_accuracy": 0.08624853491783142,
|
|
"num_tokens": 345402.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.192702579498292,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3865,
|
|
"mean_token_accuracy": 0.0875001959502697,
|
|
"num_tokens": 356161.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.096983528137207,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.3087,
|
|
"mean_token_accuracy": 0.08894997537136078,
|
|
"num_tokens": 366695.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.000302648544311,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2459,
|
|
"mean_token_accuracy": 0.08826502189040183,
|
|
"num_tokens": 376354.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.892614269256592,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.2853,
|
|
"mean_token_accuracy": 0.08936820179224014,
|
|
"num_tokens": 387468.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.8675158500671385,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.2366,
|
|
"mean_token_accuracy": 0.08572344705462456,
|
|
"num_tokens": 397658.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.800578165054321,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2295,
|
|
"mean_token_accuracy": 0.08996806442737579,
|
|
"num_tokens": 408009.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.81451735496521,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1252,
|
|
"mean_token_accuracy": 0.09177512675523758,
|
|
"num_tokens": 417781.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.679977512359619,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3176,
|
|
"mean_token_accuracy": 0.08960338979959488,
|
|
"num_tokens": 428009.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.7656045913696286,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1482,
|
|
"mean_token_accuracy": 0.0907668188214302,
|
|
"num_tokens": 438369.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.7085036277771,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1341,
|
|
"mean_token_accuracy": 0.09216333702206611,
|
|
"num_tokens": 449047.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.61162919998169,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1272,
|
|
"mean_token_accuracy": 0.093924118578434,
|
|
"num_tokens": 459992.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.708517932891846,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.207,
|
|
"mean_token_accuracy": 0.09182708933949471,
|
|
"num_tokens": 470542.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.576424551010132,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1577,
|
|
"mean_token_accuracy": 0.09969761073589326,
|
|
"num_tokens": 479983.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.695700073242188,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1299,
|
|
"mean_token_accuracy": 0.09077642261981964,
|
|
"num_tokens": 489827.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.514981985092163,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1267,
|
|
"mean_token_accuracy": 0.08924711495637894,
|
|
"num_tokens": 500257.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.638169956207276,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1507,
|
|
"mean_token_accuracy": 0.08717882186174393,
|
|
"num_tokens": 510227.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.506703805923462,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0492,
|
|
"mean_token_accuracy": 0.0963970109820366,
|
|
"num_tokens": 520442.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.448557662963867,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0689,
|
|
"mean_token_accuracy": 0.0880157247185707,
|
|
"num_tokens": 531075.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.53116626739502,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1308,
|
|
"mean_token_accuracy": 0.08964502289891244,
|
|
"num_tokens": 542576.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.471751165390015,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.0485,
|
|
"mean_token_accuracy": 0.09242086634039878,
|
|
"num_tokens": 552380.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.469887447357178,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0608,
|
|
"mean_token_accuracy": 0.08920432329177856,
|
|
"num_tokens": 563310.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.405267572402954,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.9664,
|
|
"mean_token_accuracy": 0.09448141977190971,
|
|
"num_tokens": 574113.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.440743923187256,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9802,
|
|
"mean_token_accuracy": 0.09543166309595108,
|
|
"num_tokens": 585198.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.435253047943116,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9734,
|
|
"mean_token_accuracy": 0.0946137085556984,
|
|
"num_tokens": 594837.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.340703868865967,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0063,
|
|
"mean_token_accuracy": 0.09453380405902863,
|
|
"num_tokens": 604000.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.364510869979858,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0165,
|
|
"mean_token_accuracy": 0.09476850554347038,
|
|
"num_tokens": 614831.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.43275899887085,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0328,
|
|
"mean_token_accuracy": 0.09851854294538498,
|
|
"num_tokens": 625584.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.33774585723877,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9117,
|
|
"mean_token_accuracy": 0.09698478281497955,
|
|
"num_tokens": 636282.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.42357873916626,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0307,
|
|
"mean_token_accuracy": 0.09482022523880004,
|
|
"num_tokens": 646556.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.372399139404297,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.9899,
|
|
"mean_token_accuracy": 0.09617659002542496,
|
|
"num_tokens": 656983.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.231950092315674,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9155,
|
|
"mean_token_accuracy": 0.1019688904285431,
|
|
"num_tokens": 668148.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.4007758617401125,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0107,
|
|
"mean_token_accuracy": 0.09772700667381287,
|
|
"num_tokens": 677400.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.2482020378112795,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.896,
|
|
"mean_token_accuracy": 0.09065234810113906,
|
|
"num_tokens": 687519.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.264542865753174,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8005,
|
|
"mean_token_accuracy": 0.10230840593576432,
|
|
"num_tokens": 698402.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.134629440307617,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8627,
|
|
"mean_token_accuracy": 0.10249442160129547,
|
|
"num_tokens": 710628.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.336190032958984,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9194,
|
|
"mean_token_accuracy": 0.09371023699641227,
|
|
"num_tokens": 720511.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.196484518051148,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9486,
|
|
"mean_token_accuracy": 0.10238764733076096,
|
|
"num_tokens": 731357.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.2075560092926025,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8483,
|
|
"mean_token_accuracy": 0.1011496514081955,
|
|
"num_tokens": 741569.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.342852926254272,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8818,
|
|
"mean_token_accuracy": 0.09690657183527947,
|
|
"num_tokens": 751194.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.139012861251831,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8674,
|
|
"mean_token_accuracy": 0.0964200034737587,
|
|
"num_tokens": 762554.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.168058109283447,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7947,
|
|
"mean_token_accuracy": 0.1081994466483593,
|
|
"num_tokens": 772819.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.116481113433838,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8457,
|
|
"mean_token_accuracy": 0.09905849322676659,
|
|
"num_tokens": 782717.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.275808191299438,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9231,
|
|
"mean_token_accuracy": 0.10113033130764962,
|
|
"num_tokens": 792523.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.136093997955323,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.852,
|
|
"mean_token_accuracy": 0.10536141693592072,
|
|
"num_tokens": 802696.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.199086666107178,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8945,
|
|
"mean_token_accuracy": 0.09893356338143348,
|
|
"num_tokens": 813041.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.261086368560791,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8549,
|
|
"mean_token_accuracy": 0.09995201453566552,
|
|
"num_tokens": 823366.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.149146509170532,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8201,
|
|
"mean_token_accuracy": 0.100285005569458,
|
|
"num_tokens": 835455.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.098216772079468,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8581,
|
|
"mean_token_accuracy": 0.10088052004575729,
|
|
"num_tokens": 846190.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.215963459014892,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.8161,
|
|
"mean_token_accuracy": 0.10391620472073555,
|
|
"num_tokens": 856303.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.0431232929229735,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7939,
|
|
"mean_token_accuracy": 0.09926707297563553,
|
|
"num_tokens": 866240.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.138209819793701,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9358,
|
|
"mean_token_accuracy": 0.09860606789588929,
|
|
"num_tokens": 877035.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.092493534088135,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8158,
|
|
"mean_token_accuracy": 0.09759353399276734,
|
|
"num_tokens": 887344.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.141839790344238,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8314,
|
|
"mean_token_accuracy": 0.10464526489377021,
|
|
"num_tokens": 897271.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.065910148620605,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7285,
|
|
"mean_token_accuracy": 0.1087069682776928,
|
|
"num_tokens": 908700.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.984343385696411,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7459,
|
|
"mean_token_accuracy": 0.10460741296410561,
|
|
"num_tokens": 918980.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.071007776260376,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.10659246519207954,
|
|
"num_tokens": 928616.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.033933305740357,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.897,
|
|
"mean_token_accuracy": 0.10052595734596252,
|
|
"num_tokens": 939066.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.086242055892944,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.1003576584160328,
|
|
"num_tokens": 949160.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.0361896514892575,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.10417447835206986,
|
|
"num_tokens": 959959.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.061341714859009,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8092,
|
|
"mean_token_accuracy": 0.10948210060596467,
|
|
"num_tokens": 969752.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.854967498779297,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.10138045027852058,
|
|
"num_tokens": 979917.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.039763593673706,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8134,
|
|
"mean_token_accuracy": 0.09902644529938698,
|
|
"num_tokens": 990613.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.048016119003296,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8134,
|
|
"mean_token_accuracy": 0.10063022077083587,
|
|
"num_tokens": 1000753.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.978139591217041,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7445,
|
|
"mean_token_accuracy": 0.10282852351665497,
|
|
"num_tokens": 1012141.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.031801795959472,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7459,
|
|
"mean_token_accuracy": 0.10179351791739463,
|
|
"num_tokens": 1023322.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.850466966629028,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6463,
|
|
"mean_token_accuracy": 0.09672334268689156,
|
|
"num_tokens": 1033949.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.988512468338013,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7366,
|
|
"mean_token_accuracy": 0.10716779977083206,
|
|
"num_tokens": 1043580.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.902674722671509,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.11081461235880852,
|
|
"num_tokens": 1052106.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.90415506362915,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6971,
|
|
"mean_token_accuracy": 0.1064011238515377,
|
|
"num_tokens": 1061764.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.838364171981811,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5697,
|
|
"mean_token_accuracy": 0.10854723304510117,
|
|
"num_tokens": 1071164.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.968482303619385,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.10352605357766151,
|
|
"num_tokens": 1082602.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.9721253395080565,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7378,
|
|
"mean_token_accuracy": 0.1052236057817936,
|
|
"num_tokens": 1091871.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.919319772720337,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.10676647424697876,
|
|
"num_tokens": 1102568.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.941032934188843,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6203,
|
|
"mean_token_accuracy": 0.10674264281988144,
|
|
"num_tokens": 1112777.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.716324281692505,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6119,
|
|
"mean_token_accuracy": 0.10510820895433426,
|
|
"num_tokens": 1123809.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.8692456722259525,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6644,
|
|
"mean_token_accuracy": 0.10762705281376839,
|
|
"num_tokens": 1133793.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.804552936553955,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5543,
|
|
"mean_token_accuracy": 0.10652651414275169,
|
|
"num_tokens": 1144478.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.81122727394104,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.595,
|
|
"mean_token_accuracy": 0.10836011320352554,
|
|
"num_tokens": 1155518.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.848041963577271,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6803,
|
|
"mean_token_accuracy": 0.10240246802568435,
|
|
"num_tokens": 1166494.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.864998054504395,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.10499662458896637,
|
|
"num_tokens": 1177052.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.7566328048706055,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.588,
|
|
"mean_token_accuracy": 0.1072057232260704,
|
|
"num_tokens": 1187382.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.84862585067749,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6371,
|
|
"mean_token_accuracy": 0.10280174314975739,
|
|
"num_tokens": 1197535.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.854958152770996,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.11012415438890458,
|
|
"num_tokens": 1207626.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.8038904666900635,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.10877829939126968,
|
|
"num_tokens": 1218433.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.773093318939209,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.10834594070911407,
|
|
"num_tokens": 1228698.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.839606189727784,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6608,
|
|
"mean_token_accuracy": 0.11245888248085975,
|
|
"num_tokens": 1239278.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.663392496109009,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6276,
|
|
"mean_token_accuracy": 0.11012510806322098,
|
|
"num_tokens": 1248976.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.770804977416992,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5805,
|
|
"mean_token_accuracy": 0.11286153569817543,
|
|
"num_tokens": 1259545.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.810527324676514,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.10805755332112313,
|
|
"num_tokens": 1269444.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.8169921875,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.10932271853089333,
|
|
"num_tokens": 1279821.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.654322671890259,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5238,
|
|
"mean_token_accuracy": 0.10867622718214989,
|
|
"num_tokens": 1290398.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.814783906936645,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6259,
|
|
"mean_token_accuracy": 0.10474204868078232,
|
|
"num_tokens": 1300920.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.690603113174438,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6062,
|
|
"mean_token_accuracy": 0.10462497025728226,
|
|
"num_tokens": 1311928.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.83460955619812,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6113,
|
|
"mean_token_accuracy": 0.10693813562393188,
|
|
"num_tokens": 1322554.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.699485635757446,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.11296007037162781,
|
|
"num_tokens": 1333195.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.70126633644104,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6557,
|
|
"mean_token_accuracy": 0.10681698620319366,
|
|
"num_tokens": 1343655.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.784696960449219,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5197,
|
|
"mean_token_accuracy": 0.11125476583838463,
|
|
"num_tokens": 1352528.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.562724494934082,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5629,
|
|
"mean_token_accuracy": 0.11251123249530792,
|
|
"num_tokens": 1363143.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.857563257217407,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.578,
|
|
"mean_token_accuracy": 0.1062569722533226,
|
|
"num_tokens": 1373049.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.634031963348389,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5634,
|
|
"mean_token_accuracy": 0.11504042670130729,
|
|
"num_tokens": 1384040.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.730848979949951,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6586,
|
|
"mean_token_accuracy": 0.11258623376488686,
|
|
"num_tokens": 1394511.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.641570663452148,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4682,
|
|
"mean_token_accuracy": 0.11615501791238785,
|
|
"num_tokens": 1405381.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.756093549728393,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.11007921248674393,
|
|
"num_tokens": 1415840.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.7638633251190186,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6825,
|
|
"mean_token_accuracy": 0.10886021852493286,
|
|
"num_tokens": 1426634.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.609492397308349,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5622,
|
|
"mean_token_accuracy": 0.11168285235762596,
|
|
"num_tokens": 1436794.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.853395700454712,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.6395,
|
|
"mean_token_accuracy": 0.11344821155071258,
|
|
"num_tokens": 1447114.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.582093334197998,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4899,
|
|
"mean_token_accuracy": 0.11673147901892662,
|
|
"num_tokens": 1456494.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.599524879455567,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.11297031342983246,
|
|
"num_tokens": 1466580.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.699067687988281,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5999,
|
|
"mean_token_accuracy": 0.10977515503764153,
|
|
"num_tokens": 1476854.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.683993911743164,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5426,
|
|
"mean_token_accuracy": 0.10898664593696594,
|
|
"num_tokens": 1487133.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.6332762241363525,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.11930395513772965,
|
|
"num_tokens": 1496974.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.615490865707398,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5058,
|
|
"mean_token_accuracy": 0.11035025268793106,
|
|
"num_tokens": 1507665.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.698334789276123,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4698,
|
|
"mean_token_accuracy": 0.11344846114516258,
|
|
"num_tokens": 1518625.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.690861082077026,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.10640608072280884,
|
|
"num_tokens": 1529184.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.481381893157959,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.526,
|
|
"mean_token_accuracy": 0.10988623276352882,
|
|
"num_tokens": 1540130.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.694868326187134,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.11159003973007202,
|
|
"num_tokens": 1550161.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.574037361145019,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4826,
|
|
"mean_token_accuracy": 0.11772774383425713,
|
|
"num_tokens": 1560076.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.67036771774292,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4693,
|
|
"mean_token_accuracy": 0.11172557696700096,
|
|
"num_tokens": 1570882.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.481294822692871,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4696,
|
|
"mean_token_accuracy": 0.11403056010603904,
|
|
"num_tokens": 1582227.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.62347674369812,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5213,
|
|
"mean_token_accuracy": 0.11278930827975273,
|
|
"num_tokens": 1592691.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.617785978317261,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4965,
|
|
"mean_token_accuracy": 0.11648303642868996,
|
|
"num_tokens": 1602258.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.573126649856567,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5672,
|
|
"mean_token_accuracy": 0.11526603251695633,
|
|
"num_tokens": 1611953.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.6316383361816404,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.11260883659124374,
|
|
"num_tokens": 1621944.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.496122121810913,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.11800124645233154,
|
|
"num_tokens": 1632702.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.6150144100189205,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5214,
|
|
"mean_token_accuracy": 0.11103227436542511,
|
|
"num_tokens": 1642622.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.574394226074219,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4592,
|
|
"mean_token_accuracy": 0.11586317420005798,
|
|
"num_tokens": 1652442.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.473141813278199,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4886,
|
|
"mean_token_accuracy": 0.11505223363637924,
|
|
"num_tokens": 1663022.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.656652927398682,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.11541026830673218,
|
|
"num_tokens": 1673825.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.590756893157959,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4718,
|
|
"mean_token_accuracy": 0.11257318034768105,
|
|
"num_tokens": 1683783.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.504452848434449,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.1076662614941597,
|
|
"num_tokens": 1694456.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.454553031921387,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5053,
|
|
"mean_token_accuracy": 0.11051234900951386,
|
|
"num_tokens": 1706108.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.532086324691773,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.1280963383615017,
|
|
"num_tokens": 1716273.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.5029052734375,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.11734267845749854,
|
|
"num_tokens": 1727271.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.529041481018067,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4755,
|
|
"mean_token_accuracy": 0.1184304565191269,
|
|
"num_tokens": 1737198.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.576714324951172,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5197,
|
|
"mean_token_accuracy": 0.11203703507781029,
|
|
"num_tokens": 1747077.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.594869232177734,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.5119,
|
|
"mean_token_accuracy": 0.1193366564810276,
|
|
"num_tokens": 1757626.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.527251434326172,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.11205081716179847,
|
|
"num_tokens": 1768431.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.592037868499756,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.11357785761356354,
|
|
"num_tokens": 1779071.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.481006050109864,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.504,
|
|
"mean_token_accuracy": 0.11291966959834099,
|
|
"num_tokens": 1788905.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.435082483291626,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.3973,
|
|
"mean_token_accuracy": 0.12037285566329955,
|
|
"num_tokens": 1799003.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.53296480178833,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.436,
|
|
"mean_token_accuracy": 0.11971265748143196,
|
|
"num_tokens": 1809262.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.4183008670806885,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4654,
|
|
"mean_token_accuracy": 0.11073716729879379,
|
|
"num_tokens": 1821059.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.492483615875244,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3791,
|
|
"mean_token_accuracy": 0.11755654066801072,
|
|
"num_tokens": 1830246.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.335828971862793,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.408,
|
|
"mean_token_accuracy": 0.12151500731706619,
|
|
"num_tokens": 1839950.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.464663171768189,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3876,
|
|
"mean_token_accuracy": 0.11592675521969795,
|
|
"num_tokens": 1852026.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.560555934906006,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4635,
|
|
"mean_token_accuracy": 0.11812743693590164,
|
|
"num_tokens": 1861672.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.551700782775879,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4836,
|
|
"mean_token_accuracy": 0.11402211338281631,
|
|
"num_tokens": 1872294.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.45425329208374,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4414,
|
|
"mean_token_accuracy": 0.11440050825476647,
|
|
"num_tokens": 1883049.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.345271444320678,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.12349174469709397,
|
|
"num_tokens": 1893026.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.415435361862182,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.11467023715376853,
|
|
"num_tokens": 1903987.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.59291787147522,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4365,
|
|
"mean_token_accuracy": 0.11061537489295006,
|
|
"num_tokens": 1914285.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.461905241012573,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4536,
|
|
"mean_token_accuracy": 0.1159026212990284,
|
|
"num_tokens": 1924841.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.357869672775268,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.11473607048392295,
|
|
"num_tokens": 1935536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.538698625564575,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.11677240207791328,
|
|
"num_tokens": 1946179.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.407983589172363,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.11190493553876876,
|
|
"num_tokens": 1956139.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.46036171913147,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4659,
|
|
"mean_token_accuracy": 0.11674941927194596,
|
|
"num_tokens": 1966944.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.424592447280884,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4265,
|
|
"mean_token_accuracy": 0.1166701041162014,
|
|
"num_tokens": 1976910.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.57973198890686,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.11671740487217903,
|
|
"num_tokens": 1987111.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.31265082359314,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.12392476126551628,
|
|
"num_tokens": 1996962.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.368039894104004,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.11986770704388619,
|
|
"num_tokens": 2006775.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.482371377944946,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.12042228356003762,
|
|
"num_tokens": 2016453.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.435760164260865,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.11267957463860512,
|
|
"num_tokens": 2029100.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.409471607208252,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4124,
|
|
"mean_token_accuracy": 0.11172624826431274,
|
|
"num_tokens": 2040041.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.419856071472168,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3962,
|
|
"mean_token_accuracy": 0.11573249772191048,
|
|
"num_tokens": 2050377.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.359882593154907,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.1218277484178543,
|
|
"num_tokens": 2060081.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.496881818771362,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.1156518079340458,
|
|
"num_tokens": 2070335.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.389731550216675,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.3597,
|
|
"mean_token_accuracy": 0.1212635301053524,
|
|
"num_tokens": 2079259.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.374619245529175,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.4764,
|
|
"mean_token_accuracy": 0.11514603495597839,
|
|
"num_tokens": 2089256.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.3883942604064945,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.11673571988940239,
|
|
"num_tokens": 2099141.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.387277984619141,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.12680575177073478,
|
|
"num_tokens": 2108934.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.33391375541687,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.4441,
|
|
"mean_token_accuracy": 0.1187924824655056,
|
|
"num_tokens": 2120302.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.453229522705078,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.4247,
|
|
"mean_token_accuracy": 0.1195537157356739,
|
|
"num_tokens": 2131096.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.416885185241699,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.4041,
|
|
"mean_token_accuracy": 0.12701962441205977,
|
|
"num_tokens": 2140603.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.377317237854004,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.4604,
|
|
"mean_token_accuracy": 0.11771498769521713,
|
|
"num_tokens": 2151150.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.381362867355347,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.3849,
|
|
"mean_token_accuracy": 0.11927906274795533,
|
|
"num_tokens": 2161237.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.435468864440918,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.11034503877162934,
|
|
"num_tokens": 2171861.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.281571960449218,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.3031,
|
|
"mean_token_accuracy": 0.12425279021263122,
|
|
"num_tokens": 2181415.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.323150634765625,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.1208683580160141,
|
|
"num_tokens": 2192036.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.358468723297119,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.1163475088775158,
|
|
"num_tokens": 2203001.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.384481906890869,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.1244203880429268,
|
|
"num_tokens": 2213310.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.250124216079712,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.12180497273802757,
|
|
"num_tokens": 2223909.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.361983823776245,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.11828529611229896,
|
|
"num_tokens": 2234547.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.273873519897461,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.12068448886275292,
|
|
"num_tokens": 2244493.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.257021093368531,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.1235893614590168,
|
|
"num_tokens": 2254881.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.276112365722656,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.3323,
|
|
"mean_token_accuracy": 0.11811816319823265,
|
|
"num_tokens": 2264964.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.486545896530151,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.11846130490303039,
|
|
"num_tokens": 2275507.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.27265567779541,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.12145883291959762,
|
|
"num_tokens": 2284405.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.259899759292603,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.324,
|
|
"mean_token_accuracy": 0.1184744507074356,
|
|
"num_tokens": 2294082.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.317243003845215,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.11865237578749657,
|
|
"num_tokens": 2303805.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.3640618324279785,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.11877703964710236,
|
|
"num_tokens": 2314974.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.386012029647827,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.1207954816520214,
|
|
"num_tokens": 2326719.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.265592050552368,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.11659505292773246,
|
|
"num_tokens": 2337379.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.320196676254272,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.12314697355031967,
|
|
"num_tokens": 2347509.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.3434178829193115,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.2882,
|
|
"mean_token_accuracy": 0.11846850141882896,
|
|
"num_tokens": 2357835.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.269227457046509,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.12629576474428178,
|
|
"num_tokens": 2368373.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.270691156387329,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.12598486691713334,
|
|
"num_tokens": 2379170.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.256811571121216,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.12656034380197526,
|
|
"num_tokens": 2389711.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.2689375400543215,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.13038562908768653,
|
|
"num_tokens": 2399710.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.235695457458496,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.11452672109007836,
|
|
"num_tokens": 2410567.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.344023704528809,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.307,
|
|
"mean_token_accuracy": 0.12359435632824897,
|
|
"num_tokens": 2420010.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.309238719940185,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.1272447846829891,
|
|
"num_tokens": 2429706.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.296723413467407,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.4111,
|
|
"mean_token_accuracy": 0.11686691716313362,
|
|
"num_tokens": 2441482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.422159862518311,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.3682,
|
|
"mean_token_accuracy": 0.11550676226615905,
|
|
"num_tokens": 2452094.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.148933982849121,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.12536179572343825,
|
|
"num_tokens": 2462174.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.300602436065674,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.1321061834692955,
|
|
"num_tokens": 2473294.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.228463363647461,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.1278726689517498,
|
|
"num_tokens": 2482954.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.31824312210083,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.12523070126771926,
|
|
"num_tokens": 2493894.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.202036809921265,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.12660781443119049,
|
|
"num_tokens": 2503983.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.2187714099884035,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.12330685779452324,
|
|
"num_tokens": 2513721.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.269692087173462,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.2502,
|
|
"mean_token_accuracy": 0.12575069963932037,
|
|
"num_tokens": 2523312.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.2597119331359865,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.12818494513630868,
|
|
"num_tokens": 2532685.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.278915119171143,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.12152358293533325,
|
|
"num_tokens": 2543324.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.2923393726348875,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.12113744467496872,
|
|
"num_tokens": 2554242.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.273481845855713,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.1278710223734379,
|
|
"num_tokens": 2563372.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.234022188186645,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12514663413167,
|
|
"num_tokens": 2574029.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.359460401535034,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.1290361575782299,
|
|
"num_tokens": 2583308.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.420801258087158,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.11551335826516151,
|
|
"num_tokens": 2595105.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.13080940246582,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.1801,
|
|
"mean_token_accuracy": 0.13008004054427147,
|
|
"num_tokens": 2604937.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.238644075393677,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.12672679945826532,
|
|
"num_tokens": 2615218.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.200268936157227,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.12415119707584381,
|
|
"num_tokens": 2625668.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.2111094951629635,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.12427769452333451,
|
|
"num_tokens": 2636233.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.263781785964966,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.12104817926883697,
|
|
"num_tokens": 2647725.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.226747751235962,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.2223,
|
|
"mean_token_accuracy": 0.13130831718444824,
|
|
"num_tokens": 2658670.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.139042472839355,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.13245302811264992,
|
|
"num_tokens": 2668782.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.23336877822876,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.2498,
|
|
"mean_token_accuracy": 0.12909818440675735,
|
|
"num_tokens": 2677973.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.244420528411865,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.12651574686169625,
|
|
"num_tokens": 2687813.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.160448169708252,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.1258676081895828,
|
|
"num_tokens": 2698664.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.191532325744629,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.13130440413951874,
|
|
"num_tokens": 2708936.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.242334794998169,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.1300816871225834,
|
|
"num_tokens": 2718711.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.0896015644073485,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.13144304975867271,
|
|
"num_tokens": 2729956.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.332587003707886,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.3051,
|
|
"mean_token_accuracy": 0.12343701347708702,
|
|
"num_tokens": 2740932.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.29391508102417,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.12498589381575584,
|
|
"num_tokens": 2750781.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.286653852462768,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.2415,
|
|
"mean_token_accuracy": 0.12924491837620736,
|
|
"num_tokens": 2761542.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.169296550750732,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.12321913093328477,
|
|
"num_tokens": 2772507.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.211149549484253,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.12625789046287536,
|
|
"num_tokens": 2782806.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.175951194763184,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.1991,
|
|
"mean_token_accuracy": 0.12693845182657243,
|
|
"num_tokens": 2793484.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.184288167953492,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.2731,
|
|
"mean_token_accuracy": 0.1297612629830837,
|
|
"num_tokens": 2804443.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.163767099380493,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.1262630842626095,
|
|
"num_tokens": 2814840.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.2059821605682375,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.1247759722173214,
|
|
"num_tokens": 2824789.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.2396345138549805,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.1775,
|
|
"mean_token_accuracy": 0.13116121515631676,
|
|
"num_tokens": 2834501.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.202531719207764,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.12950848862528802,
|
|
"num_tokens": 2845399.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.032520198822022,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14028632938861846,
|
|
"num_tokens": 2855146.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.3156661033630375,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.2597,
|
|
"mean_token_accuracy": 0.12432174906134605,
|
|
"num_tokens": 2866438.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.019028043746948,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.1301,
|
|
"mean_token_accuracy": 0.12995802015066146,
|
|
"num_tokens": 2876802.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.315221118927002,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.128648017346859,
|
|
"num_tokens": 2888657.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.177397584915161,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.1301404818892479,
|
|
"num_tokens": 2899605.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.116765117645263,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.1246509574353695,
|
|
"num_tokens": 2910332.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.126271677017212,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.1296907387673855,
|
|
"num_tokens": 2921226.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.1753684997558596,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.165,
|
|
"mean_token_accuracy": 0.129497080296278,
|
|
"num_tokens": 2930941.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.1793512344360355,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.13117415681481362,
|
|
"num_tokens": 2941383.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.207342672348022,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.1587,
|
|
"mean_token_accuracy": 0.12762442380189895,
|
|
"num_tokens": 2951634.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.203984594345092,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.12739467918872832,
|
|
"num_tokens": 2962240.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.187308359146118,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.12866248711943626,
|
|
"num_tokens": 2973466.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.248796129226685,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.1989,
|
|
"mean_token_accuracy": 0.13207736387848854,
|
|
"num_tokens": 2982986.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.168663787841797,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.1301150493323803,
|
|
"num_tokens": 2994151.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.106994342803955,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.1328746996819973,
|
|
"num_tokens": 3003481.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.062295961380005,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1257198430597782,
|
|
"num_tokens": 3013835.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.146769189834595,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.14100732132792473,
|
|
"num_tokens": 3024292.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.171922969818115,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.12596325874328612,
|
|
"num_tokens": 3035114.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.1891436100006105,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.1387,
|
|
"mean_token_accuracy": 0.13315948471426964,
|
|
"num_tokens": 3045151.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.107039928436279,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.13525033965706826,
|
|
"num_tokens": 3054552.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.211303329467773,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.2495,
|
|
"mean_token_accuracy": 0.12571337893605233,
|
|
"num_tokens": 3065386.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.1838174819946286,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.13161127269268036,
|
|
"num_tokens": 3075934.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.044588327407837,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.0649,
|
|
"mean_token_accuracy": 0.13151389360427856,
|
|
"num_tokens": 3086578.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.235484266281128,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.12512897700071335,
|
|
"num_tokens": 3098183.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.0513090133667,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.0581,
|
|
"mean_token_accuracy": 0.1343822069466114,
|
|
"num_tokens": 3107649.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.221631050109863,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.13448878824710847,
|
|
"num_tokens": 3117652.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.061485052108765,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.13679977506399155,
|
|
"num_tokens": 3127785.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.083025693893433,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.13337264955043793,
|
|
"num_tokens": 3138657.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.140411472320556,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.12004235461354255,
|
|
"num_tokens": 3150692.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.23555703163147,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.12430977448821068,
|
|
"num_tokens": 3161807.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.107507514953613,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.1393376462161541,
|
|
"num_tokens": 3172446.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.145687675476074,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 6.2071,
|
|
"mean_token_accuracy": 0.1238051250576973,
|
|
"num_tokens": 3183476.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.0691694736480715,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.13867690786719322,
|
|
"num_tokens": 3193586.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.1251280307769775,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.13339588195085525,
|
|
"num_tokens": 3203341.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.136832141876221,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.12823742404580116,
|
|
"num_tokens": 3214177.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.141563987731933,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.1269642286002636,
|
|
"num_tokens": 3224516.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.098951148986816,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.14152515679597855,
|
|
"num_tokens": 3234001.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.196884202957153,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.13318521454930304,
|
|
"num_tokens": 3246095.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.135161066055298,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.12648626491427423,
|
|
"num_tokens": 3255828.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.101465272903442,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.1378,
|
|
"mean_token_accuracy": 0.13857534304261207,
|
|
"num_tokens": 3265127.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.23589973449707,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.2083,
|
|
"mean_token_accuracy": 0.12722571119666098,
|
|
"num_tokens": 3277205.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.039449787139892,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.13461936116218567,
|
|
"num_tokens": 3287119.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.237564992904663,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.2073,
|
|
"mean_token_accuracy": 0.12796173691749574,
|
|
"num_tokens": 3297324.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.166965675354004,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.12957976162433624,
|
|
"num_tokens": 3308162.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.156198501586914,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 6.1587,
|
|
"mean_token_accuracy": 0.12751780077815056,
|
|
"num_tokens": 3319422.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.074300146102905,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.13079726696014404,
|
|
"num_tokens": 3328668.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.196269941329956,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.1789,
|
|
"mean_token_accuracy": 0.12973756417632104,
|
|
"num_tokens": 3338563.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.123033428192139,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.13245568349957465,
|
|
"num_tokens": 3348025.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.125161266326904,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.14053588956594468,
|
|
"num_tokens": 3359094.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.113393926620484,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.13681961521506308,
|
|
"num_tokens": 3368965.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.058830976486206,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.13101110011339187,
|
|
"num_tokens": 3378612.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.140189456939697,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.13366867899894713,
|
|
"num_tokens": 3389634.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.045487594604492,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.13442882299423217,
|
|
"num_tokens": 3399604.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.223248147964478,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.13319409787654876,
|
|
"num_tokens": 3410314.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.071327877044678,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.13651233538985252,
|
|
"num_tokens": 3420773.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.234537887573242,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.1285805732011795,
|
|
"num_tokens": 3431702.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.026836967468261,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.1376,
|
|
"mean_token_accuracy": 0.133916974067688,
|
|
"num_tokens": 3441925.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.225948667526245,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.13318530544638635,
|
|
"num_tokens": 3452391.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.018878602981568,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0672,
|
|
"mean_token_accuracy": 0.12874112129211426,
|
|
"num_tokens": 3463028.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.063703966140747,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 6.0641,
|
|
"mean_token_accuracy": 0.13683240562677385,
|
|
"num_tokens": 3473470.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.126550817489624,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 6.1066,
|
|
"mean_token_accuracy": 0.13182729333639145,
|
|
"num_tokens": 3484486.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.084259557723999,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.13736046478152275,
|
|
"num_tokens": 3494885.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.07341947555542,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.13572860211133958,
|
|
"num_tokens": 3506088.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.015376949310303,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.13501859828829765,
|
|
"num_tokens": 3516380.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.094719457626343,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.14153220504522324,
|
|
"num_tokens": 3525965.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.060795879364013,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.13283166736364366,
|
|
"num_tokens": 3536592.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.117245006561279,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.13683197945356368,
|
|
"num_tokens": 3546001.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.123035430908203,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.0487,
|
|
"mean_token_accuracy": 0.12888889610767365,
|
|
"num_tokens": 3555575.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.06559419631958,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.14311017096042633,
|
|
"num_tokens": 3565685.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.119355535507202,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.14001662507653237,
|
|
"num_tokens": 3575119.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.048756504058838,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.13779830187559128,
|
|
"num_tokens": 3584620.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.0873788356781,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.13565813079476358,
|
|
"num_tokens": 3595403.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.042232465744019,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.135944102704525,
|
|
"num_tokens": 3606355.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.039039087295532,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.1334886446595192,
|
|
"num_tokens": 3616222.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.117766857147217,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.1427782490849495,
|
|
"num_tokens": 3625179.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.066883754730225,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.13318037912249564,
|
|
"num_tokens": 3636256.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.9570455074310305,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.14086213558912278,
|
|
"num_tokens": 3645919.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.067557430267334,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.13390027210116387,
|
|
"num_tokens": 3657008.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.014396524429321,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.13444581776857376,
|
|
"num_tokens": 3667686.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.022483873367309,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.13489970788359643,
|
|
"num_tokens": 3678972.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.032540559768677,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.13953388929367067,
|
|
"num_tokens": 3688903.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.049791049957276,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.13899827301502227,
|
|
"num_tokens": 3697880.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.113507795333862,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.13196710646152496,
|
|
"num_tokens": 3708500.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.967461633682251,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.14808355420827865,
|
|
"num_tokens": 3718711.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.003653526306152,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.13483019024133683,
|
|
"num_tokens": 3729431.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.118337678909302,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.13496499881148338,
|
|
"num_tokens": 3741061.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.951924753189087,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.14013575315475463,
|
|
"num_tokens": 3751878.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.038108873367309,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.13939072266221048,
|
|
"num_tokens": 3762039.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.974385404586792,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.1419306755065918,
|
|
"num_tokens": 3770755.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.02751522064209,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.13299722522497176,
|
|
"num_tokens": 3781698.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.067613887786865,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.1488,
|
|
"mean_token_accuracy": 0.13327884972095488,
|
|
"num_tokens": 3792508.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.086944532394409,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.14385750517249107,
|
|
"num_tokens": 3803065.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.022203254699707,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.1315029554069042,
|
|
"num_tokens": 3813696.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.0408408641815186,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.14210820943117142,
|
|
"num_tokens": 3823786.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.0095936298370365,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.13492688685655593,
|
|
"num_tokens": 3835011.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.074155664443969,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 6.0408,
|
|
"mean_token_accuracy": 0.13303120210766792,
|
|
"num_tokens": 3846161.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.95374641418457,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.14118631407618523,
|
|
"num_tokens": 3856013.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.1738697528839115,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.1409381054341793,
|
|
"num_tokens": 3865521.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.912585163116455,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.14283333346247673,
|
|
"num_tokens": 3876290.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.980841970443725,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.13230404928326606,
|
|
"num_tokens": 3886437.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.112230062484741,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.13440538123250007,
|
|
"num_tokens": 3896501.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.15153021812439,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.13559964820742607,
|
|
"num_tokens": 3906725.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.02051043510437,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 5.9351,
|
|
"mean_token_accuracy": 0.1449750393629074,
|
|
"num_tokens": 3917428.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.859882068634033,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.1393364980816841,
|
|
"num_tokens": 3927298.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.047381448745727,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.1372090183198452,
|
|
"num_tokens": 3936727.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.062630701065063,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.13730003088712692,
|
|
"num_tokens": 3947246.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.838617277145386,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.14350975602865218,
|
|
"num_tokens": 3958535.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.161811971664429,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1353868529200554,
|
|
"num_tokens": 3969635.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.025433874130249,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 6.024,
|
|
"mean_token_accuracy": 0.1359100967645645,
|
|
"num_tokens": 3980227.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.06690092086792,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.14165394008159637,
|
|
"num_tokens": 3990915.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.958260536193848,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.13917687460780143,
|
|
"num_tokens": 4001273.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.072769498825073,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.141386017203331,
|
|
"num_tokens": 4011596.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.960225534439087,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 6.0366,
|
|
"mean_token_accuracy": 0.13730789497494697,
|
|
"num_tokens": 4022638.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.080376815795899,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.13227792233228683,
|
|
"num_tokens": 4032398.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.898893404006958,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 5.9724,
|
|
"mean_token_accuracy": 0.1371435798704624,
|
|
"num_tokens": 4042852.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.040456962585449,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.1349559858441353,
|
|
"num_tokens": 4053110.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.002525901794433,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.1401715062558651,
|
|
"num_tokens": 4064571.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.953612756729126,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.13749739825725554,
|
|
"num_tokens": 4075400.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.028836965560913,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.14185010865330697,
|
|
"num_tokens": 4085763.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.986079740524292,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 6.0109,
|
|
"mean_token_accuracy": 0.13681597337126733,
|
|
"num_tokens": 4095993.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.986701774597168,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9225,
|
|
"mean_token_accuracy": 0.1380699433386326,
|
|
"num_tokens": 4105012.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.942403030395508,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 5.9692,
|
|
"mean_token_accuracy": 0.1353602610528469,
|
|
"num_tokens": 4115142.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.031651258468628,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.13746799603104592,
|
|
"num_tokens": 4125297.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.977378511428833,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 6.0917,
|
|
"mean_token_accuracy": 0.132157414406538,
|
|
"num_tokens": 4136404.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.080759954452515,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14288827329874038,
|
|
"num_tokens": 4146228.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.95260910987854,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.1427669905126095,
|
|
"num_tokens": 4156435.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.975965404510498,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.1480802610516548,
|
|
"num_tokens": 4166525.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.0720906257629395,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.13352881222963334,
|
|
"num_tokens": 4176831.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.019681024551391,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.13369136229157447,
|
|
"num_tokens": 4187830.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.006418657302857,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 5.8688,
|
|
"mean_token_accuracy": 0.1393364667892456,
|
|
"num_tokens": 4198898.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.97959532737732,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 5.9709,
|
|
"mean_token_accuracy": 0.1392282821238041,
|
|
"num_tokens": 4210297.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.037605619430542,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.13221636712551116,
|
|
"num_tokens": 4221469.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.987315082550049,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.14053445905447007,
|
|
"num_tokens": 4233046.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.048150110244751,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.13854565769433974,
|
|
"num_tokens": 4243233.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.046663284301758,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.13540371656417846,
|
|
"num_tokens": 4254020.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.959017562866211,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.14246483519673347,
|
|
"num_tokens": 4263901.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.890605878829956,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.13970548510551453,
|
|
"num_tokens": 4274814.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.063959264755249,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.1417410969734192,
|
|
"num_tokens": 4284846.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.033328819274902,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.9731,
|
|
"mean_token_accuracy": 0.14464445784687996,
|
|
"num_tokens": 4294862.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.068034410476685,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.1416530877351761,
|
|
"num_tokens": 4305708.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.995953607559204,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.13258325606584548,
|
|
"num_tokens": 4315853.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.9227760314941404,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 5.9565,
|
|
"mean_token_accuracy": 0.13823306187987328,
|
|
"num_tokens": 4326607.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.959938955307007,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.13902745693922042,
|
|
"num_tokens": 4336050.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.056903553009033,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.14332208260893822,
|
|
"num_tokens": 4345453.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.951250743865967,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.1378558337688446,
|
|
"num_tokens": 4356372.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.958211088180542,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 6.0014,
|
|
"mean_token_accuracy": 0.14464358389377593,
|
|
"num_tokens": 4365500.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.067464399337768,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.14481838345527648,
|
|
"num_tokens": 4375031.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.901741409301758,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.1389401637017727,
|
|
"num_tokens": 4386409.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.059998941421509,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.13713788390159606,
|
|
"num_tokens": 4397040.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.938760089874267,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.14106623604893684,
|
|
"num_tokens": 4406723.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.02097454071045,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.14898034185171127,
|
|
"num_tokens": 4416013.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.96734733581543,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9793,
|
|
"mean_token_accuracy": 0.14236808717250823,
|
|
"num_tokens": 4426441.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.063247156143189,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 6.0948,
|
|
"mean_token_accuracy": 0.1332187458872795,
|
|
"num_tokens": 4437328.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.089685106277466,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.14083896055817605,
|
|
"num_tokens": 4447546.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.88359489440918,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.14243533834815025,
|
|
"num_tokens": 4457319.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.066173934936524,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 6.0624,
|
|
"mean_token_accuracy": 0.13416438773274422,
|
|
"num_tokens": 4468348.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.009496736526489,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.14601074978709222,
|
|
"num_tokens": 4478263.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.905720138549805,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.8817,
|
|
"mean_token_accuracy": 0.14295333474874497,
|
|
"num_tokens": 4488772.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.011665964126587,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.13327775821089743,
|
|
"num_tokens": 4499443.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.983055496215821,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.13847402930259706,
|
|
"num_tokens": 4509969.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.022305631637574,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.14845634549856185,
|
|
"num_tokens": 4519668.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.9130627632141115,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.14601308181881906,
|
|
"num_tokens": 4530303.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.992128801345825,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.14158663749694825,
|
|
"num_tokens": 4541801.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.938469648361206,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.1426684334874153,
|
|
"num_tokens": 4551346.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.922765111923217,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.14817361980676652,
|
|
"num_tokens": 4561835.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.904284858703614,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.145841383934021,
|
|
"num_tokens": 4572760.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.936977243423462,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.14006382599473,
|
|
"num_tokens": 4582884.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.961916112899781,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.14331716150045395,
|
|
"num_tokens": 4594297.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.988901615142822,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.13747334852814674,
|
|
"num_tokens": 4605072.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.911744117736816,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 5.8751,
|
|
"mean_token_accuracy": 0.15403711050748825,
|
|
"num_tokens": 4615207.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.916146278381348,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.14326297491788864,
|
|
"num_tokens": 4625552.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.068982744216919,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.13947765678167343,
|
|
"num_tokens": 4635864.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.9241475582122805,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.13143666759133338,
|
|
"num_tokens": 4646978.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.949285650253296,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.14171508550643921,
|
|
"num_tokens": 4656737.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.886570167541504,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 6.0072,
|
|
"mean_token_accuracy": 0.14202161729335785,
|
|
"num_tokens": 4667663.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.985239171981812,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9673,
|
|
"mean_token_accuracy": 0.13756298944354056,
|
|
"num_tokens": 4678814.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.042722129821778,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.13774357065558435,
|
|
"num_tokens": 4689446.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.971980857849121,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.13813588321208953,
|
|
"num_tokens": 4700207.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.003995275497436,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.1428474046289921,
|
|
"num_tokens": 4710743.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.981139850616455,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.14789393842220305,
|
|
"num_tokens": 4720964.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.965071296691894,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.13834339007735252,
|
|
"num_tokens": 4732022.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.995220470428467,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.9789,
|
|
"mean_token_accuracy": 0.13753922730684282,
|
|
"num_tokens": 4743428.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.996651983261108,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.14165481328964233,
|
|
"num_tokens": 4754530.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.848381853103637,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.8387,
|
|
"mean_token_accuracy": 0.14721979647874833,
|
|
"num_tokens": 4764453.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.030099821090698,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.14176427572965622,
|
|
"num_tokens": 4774788.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.991954565048218,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.1358835816383362,
|
|
"num_tokens": 4785827.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.9251960754394535,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.15004699677228928,
|
|
"num_tokens": 4795683.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.960970211029053,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.14288516640663146,
|
|
"num_tokens": 4805929.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.915129613876343,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.9297,
|
|
"mean_token_accuracy": 0.14064979255199433,
|
|
"num_tokens": 4816067.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.940646457672119,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.1419698029756546,
|
|
"num_tokens": 4826757.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.9893388748168945,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.9248,
|
|
"mean_token_accuracy": 0.14424414560198784,
|
|
"num_tokens": 4836548.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.0586730480194095,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.13741380125284194,
|
|
"num_tokens": 4847274.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.959125995635986,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.1400488071143627,
|
|
"num_tokens": 4857506.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.960813760757446,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.9773,
|
|
"mean_token_accuracy": 0.1386716030538082,
|
|
"num_tokens": 4868069.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.946921539306641,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 5.8775,
|
|
"mean_token_accuracy": 0.14960167706012725,
|
|
"num_tokens": 4877731.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.923819208145142,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.13987276405096055,
|
|
"num_tokens": 4887780.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.958174419403076,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.14128173291683196,
|
|
"num_tokens": 4897578.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.871128082275391,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.9053,
|
|
"mean_token_accuracy": 0.13984225764870645,
|
|
"num_tokens": 4908187.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.030574989318848,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.14696599096059798,
|
|
"num_tokens": 4918352.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.877168655395508,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.14657547250390052,
|
|
"num_tokens": 4928065.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.952869129180908,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.14537300616502763,
|
|
"num_tokens": 4939492.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.872677612304687,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 5.8546,
|
|
"mean_token_accuracy": 0.14155039489269255,
|
|
"num_tokens": 4949304.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.894457006454468,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.8853,
|
|
"mean_token_accuracy": 0.1352695107460022,
|
|
"num_tokens": 4959649.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.9166566848754885,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.13895038962364198,
|
|
"num_tokens": 4970029.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.966705751419068,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.14436866864562034,
|
|
"num_tokens": 4980431.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.862818002700806,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.9549,
|
|
"mean_token_accuracy": 0.14049403220415116,
|
|
"num_tokens": 4991448.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.938876914978027,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.8976,
|
|
"mean_token_accuracy": 0.1356552518904209,
|
|
"num_tokens": 5001225.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.924232530593872,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.14155457615852357,
|
|
"num_tokens": 5012096.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.954684495925903,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.13705262392759324,
|
|
"num_tokens": 5021675.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.930799150466919,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.1381124421954155,
|
|
"num_tokens": 5032250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.906846952438355,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.9758,
|
|
"mean_token_accuracy": 0.13671192824840545,
|
|
"num_tokens": 5042508.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.031311511993408,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.14089929684996605,
|
|
"num_tokens": 5052765.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.894246578216553,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.14432070553302764,
|
|
"num_tokens": 5062379.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.954690265655517,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.14122223407030104,
|
|
"num_tokens": 5072267.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.857289552688599,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.1439412847161293,
|
|
"num_tokens": 5082214.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.875279474258423,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14643458500504494,
|
|
"num_tokens": 5092129.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.914616823196411,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.13629107251763345,
|
|
"num_tokens": 5102924.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.9880273818969725,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.1420026421546936,
|
|
"num_tokens": 5113216.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.792202377319336,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1403028056025505,
|
|
"num_tokens": 5122978.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.964217710494995,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.14088138267397882,
|
|
"num_tokens": 5133167.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.898852062225342,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.14743937328457832,
|
|
"num_tokens": 5143848.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.9200560569763185,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.15123707801103592,
|
|
"num_tokens": 5154172.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.81275691986084,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.1486186221241951,
|
|
"num_tokens": 5164459.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.979988098144531,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.13727832362055778,
|
|
"num_tokens": 5175751.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.904782056808472,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.1466525003314018,
|
|
"num_tokens": 5186004.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.8142805099487305,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1469535768032074,
|
|
"num_tokens": 5195610.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.915460872650146,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.9106,
|
|
"mean_token_accuracy": 0.1398490011692047,
|
|
"num_tokens": 5205607.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.935828447341919,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1415001295506954,
|
|
"num_tokens": 5217372.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.895864343643188,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.14375398457050323,
|
|
"num_tokens": 5226782.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.875649499893188,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.1496797136962414,
|
|
"num_tokens": 5236209.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.870350313186646,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.14222536683082582,
|
|
"num_tokens": 5246041.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.970703125,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.14660589545965194,
|
|
"num_tokens": 5256902.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.928110027313233,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.14946367517113684,
|
|
"num_tokens": 5266180.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.936565351486206,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.13646556437015533,
|
|
"num_tokens": 5277475.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.029916381835937,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.14439473375678064,
|
|
"num_tokens": 5287108.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.854767751693726,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.13685449138283728,
|
|
"num_tokens": 5297598.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.062006139755249,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.1358692966401577,
|
|
"num_tokens": 5306953.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.887425899505615,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.9399,
|
|
"mean_token_accuracy": 0.15026361793279647,
|
|
"num_tokens": 5317608.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.862730932235718,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.13242100477218627,
|
|
"num_tokens": 5328503.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.914726114273071,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.883,
|
|
"mean_token_accuracy": 0.14427884221076964,
|
|
"num_tokens": 5338108.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.95159878730774,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.13466350510716438,
|
|
"num_tokens": 5349890.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.051620054244995,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.1407109409570694,
|
|
"num_tokens": 5361319.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.919955205917359,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.14855802059173584,
|
|
"num_tokens": 5370932.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.9046718120574955,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.14306004494428634,
|
|
"num_tokens": 5381661.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.818372058868408,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.14963757395744323,
|
|
"num_tokens": 5390999.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.943971872329712,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.14275056049227713,
|
|
"num_tokens": 5401175.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.954121685028076,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.8747,
|
|
"mean_token_accuracy": 0.14469726160168647,
|
|
"num_tokens": 5411644.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.812447595596313,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.14814821630716324,
|
|
"num_tokens": 5420923.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.941586923599243,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.14263342320919037,
|
|
"num_tokens": 5431475.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.9011571407318115,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.14849388152360915,
|
|
"num_tokens": 5441822.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.8005060195922855,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.13821850046515466,
|
|
"num_tokens": 5453266.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.917859411239624,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.8634,
|
|
"mean_token_accuracy": 0.14885092675685882,
|
|
"num_tokens": 5463023.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.934016132354737,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.14655044227838515,
|
|
"num_tokens": 5472345.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.923844289779663,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.1498401679098606,
|
|
"num_tokens": 5481468.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.773250436782837,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.8461,
|
|
"mean_token_accuracy": 0.14630547761917115,
|
|
"num_tokens": 5492107.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.871908712387085,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.8771,
|
|
"mean_token_accuracy": 0.1383388437330723,
|
|
"num_tokens": 5502196.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.904657554626465,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.1385428823530674,
|
|
"num_tokens": 5512859.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.975746059417725,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.14605885297060012,
|
|
"num_tokens": 5523041.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.764354801177978,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.15253512784838677,
|
|
"num_tokens": 5533967.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.947396564483642,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.14548483043909072,
|
|
"num_tokens": 5543460.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.93350305557251,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.1520221307873726,
|
|
"num_tokens": 5553139.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.793046188354492,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.1441502094268799,
|
|
"num_tokens": 5564550.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.9918012619018555,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.1459794595837593,
|
|
"num_tokens": 5574393.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.940083932876587,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.8813,
|
|
"mean_token_accuracy": 0.14294293597340585,
|
|
"num_tokens": 5584206.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.877155923843384,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.1417349547147751,
|
|
"num_tokens": 5594946.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.921493816375732,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.14902272820472717,
|
|
"num_tokens": 5605984.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.776959466934204,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.1488720089197159,
|
|
"num_tokens": 5616227.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.935484266281128,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.14310448318719865,
|
|
"num_tokens": 5626592.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.0017767429351805,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.8379,
|
|
"mean_token_accuracy": 0.14523325935006143,
|
|
"num_tokens": 5636486.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.846785545349121,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.14552611336112023,
|
|
"num_tokens": 5646025.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.828639936447144,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.1471302717924118,
|
|
"num_tokens": 5656523.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.8145918369293215,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.8303,
|
|
"mean_token_accuracy": 0.14437200129032135,
|
|
"num_tokens": 5667598.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.928363561630249,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.14459095299243926,
|
|
"num_tokens": 5677721.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.847347164154053,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.1417038306593895,
|
|
"num_tokens": 5688450.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.865340757369995,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.1495169907808304,
|
|
"num_tokens": 5698142.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.833406114578247,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.1465844228863716,
|
|
"num_tokens": 5708122.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.837479496002198,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.14600400999188423,
|
|
"num_tokens": 5718671.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.8692303657531735,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.14405162036418914,
|
|
"num_tokens": 5729463.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.922516870498657,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.8874,
|
|
"mean_token_accuracy": 0.14321258664131165,
|
|
"num_tokens": 5739212.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.901452112197876,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.8029,
|
|
"mean_token_accuracy": 0.14497288316488266,
|
|
"num_tokens": 5749159.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.932657766342163,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.993,
|
|
"mean_token_accuracy": 0.13827754259109498,
|
|
"num_tokens": 5759711.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.124020576477051,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.1372769333422184,
|
|
"num_tokens": 5771210.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.816952276229858,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.14726067781448365,
|
|
"num_tokens": 5780960.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.935285472869873,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.885,
|
|
"mean_token_accuracy": 0.14095496237277985,
|
|
"num_tokens": 5790891.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.894222116470337,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.14395667985081673,
|
|
"num_tokens": 5801078.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.885415887832641,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.1393453024327755,
|
|
"num_tokens": 5811025.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.909905290603637,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.8086,
|
|
"mean_token_accuracy": 0.1448357567191124,
|
|
"num_tokens": 5821242.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.845452737808228,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.14133516177535058,
|
|
"num_tokens": 5832039.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.914500284194946,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.1460021823644638,
|
|
"num_tokens": 5841723.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.9476793766021725,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.14610021114349364,
|
|
"num_tokens": 5852814.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.826781702041626,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.8323,
|
|
"mean_token_accuracy": 0.14333641827106475,
|
|
"num_tokens": 5863174.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.853058385848999,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.14737775102257727,
|
|
"num_tokens": 5873698.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.760656118392944,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.8211,
|
|
"mean_token_accuracy": 0.1456883355975151,
|
|
"num_tokens": 5883982.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.894684791564941,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.14917163103818892,
|
|
"num_tokens": 5894454.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.844020223617553,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.1445062406361103,
|
|
"num_tokens": 5904739.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.931279706954956,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.14103500097990035,
|
|
"num_tokens": 5914578.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.924049043655396,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.8417,
|
|
"mean_token_accuracy": 0.1458780586719513,
|
|
"num_tokens": 5923918.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.938410520553589,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.14107644706964492,
|
|
"num_tokens": 5934096.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.885492944717408,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.9094,
|
|
"mean_token_accuracy": 0.1389304779469967,
|
|
"num_tokens": 5945416.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.875432109832763,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.8406,
|
|
"mean_token_accuracy": 0.14503862857818603,
|
|
"num_tokens": 5956296.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.864486980438232,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.15628641992807388,
|
|
"num_tokens": 5966147.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.841119432449341,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.15209657400846482,
|
|
"num_tokens": 5976650.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.918705177307129,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.14683974608778955,
|
|
"num_tokens": 5986643.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.891564416885376,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.8697,
|
|
"mean_token_accuracy": 0.14015998244285582,
|
|
"num_tokens": 5997991.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.783881521224975,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.15556951612234116,
|
|
"num_tokens": 6007179.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.919160652160644,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.14572433680295943,
|
|
"num_tokens": 6017786.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.915647411346436,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.14329932779073715,
|
|
"num_tokens": 6027751.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.8271812915802,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.14923276603221894,
|
|
"num_tokens": 6037136.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.790592765808105,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.14568121135234832,
|
|
"num_tokens": 6047341.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.903992128372193,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.14674188792705536,
|
|
"num_tokens": 6058337.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.892431545257568,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.14313996583223343,
|
|
"num_tokens": 6068566.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.918859958648682,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.15070558488368987,
|
|
"num_tokens": 6078813.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.816320133209229,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.15071689635515212,
|
|
"num_tokens": 6090007.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.924297523498535,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.9844,
|
|
"mean_token_accuracy": 0.1373060829937458,
|
|
"num_tokens": 6100917.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.015955924987793,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.93,
|
|
"mean_token_accuracy": 0.147200308740139,
|
|
"num_tokens": 6110958.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.904809999465942,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.8316,
|
|
"mean_token_accuracy": 0.14588915333151817,
|
|
"num_tokens": 6120819.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.836217546463013,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.14316449761390687,
|
|
"num_tokens": 6131253.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.898743295669556,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.148350540548563,
|
|
"num_tokens": 6141338.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.846032381057739,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.14200861528515815,
|
|
"num_tokens": 6151081.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.9468964576721195,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.13914820924401283,
|
|
"num_tokens": 6160997.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.878990554809571,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.14771230965852739,
|
|
"num_tokens": 6171131.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.830885028839111,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.8911,
|
|
"mean_token_accuracy": 0.14644451886415483,
|
|
"num_tokens": 6181307.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.935413074493408,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.15274717211723327,
|
|
"num_tokens": 6191689.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.780738258361817,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.14987841248512268,
|
|
"num_tokens": 6201183.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.876131439208985,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.14560322165489198,
|
|
"num_tokens": 6211507.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.882185268402099,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.758,
|
|
"mean_token_accuracy": 0.15807864367961882,
|
|
"num_tokens": 6220899.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.707925649789663,
|
|
"eval_loss": 5.863901615142822,
|
|
"eval_mean_token_accuracy": 0.15150013840356968,
|
|
"eval_num_tokens": 6220899.0,
|
|
"eval_runtime": 26.8067,
|
|
"eval_samples_per_second": 1319.074,
|
|
"eval_steps_per_second": 164.884,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.864054012298584,
|
|
"epoch": 0.27258708272859217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996263683987316,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.13928473219275475,
|
|
"num_tokens": 6231591.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.858609437942505,
|
|
"epoch": 0.2730406386066763,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996245021631033,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.14948550909757613,
|
|
"num_tokens": 6240991.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.891993761062622,
|
|
"epoch": 0.27349419448476053,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499622631282183,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14875294119119645,
|
|
"num_tokens": 6251081.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.850441408157349,
|
|
"epoch": 0.2739477503628447,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004996207557560095,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.15141250863671302,
|
|
"num_tokens": 6260557.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.869618844985962,
|
|
"epoch": 0.2744013062409289,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996188755846216,
|
|
"loss": 5.8934,
|
|
"mean_token_accuracy": 0.14358878880739212,
|
|
"num_tokens": 6272325.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.905278873443604,
|
|
"epoch": 0.27485486211901305,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499616990768058,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.145791694521904,
|
|
"num_tokens": 6281672.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.862424087524414,
|
|
"epoch": 0.27530841799709727,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004996151013063579,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.14248670935630797,
|
|
"num_tokens": 6292908.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.848897933959961,
|
|
"epoch": 0.2757619738751814,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004996132071995601,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.14569919556379318,
|
|
"num_tokens": 6303244.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.873018789291382,
|
|
"epoch": 0.2762155297532656,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996113084477042,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.1410228006541729,
|
|
"num_tokens": 6313644.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.883062839508057,
|
|
"epoch": 0.2766690856313498,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996094050508291,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.1453947678208351,
|
|
"num_tokens": 6323498.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.905374526977539,
|
|
"epoch": 0.27712264150943394,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004996074970089741,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.14867558106780052,
|
|
"num_tokens": 6333253.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.8678144931793215,
|
|
"epoch": 0.27757619738751815,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004996055843221789,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.15047635659575462,
|
|
"num_tokens": 6343321.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.950027418136597,
|
|
"epoch": 0.2780297532656023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996036669904831,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.13945802450180053,
|
|
"num_tokens": 6353344.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.920107841491699,
|
|
"epoch": 0.2784833091436865,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996017450139261,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.14309242218732834,
|
|
"num_tokens": 6364082.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.91571273803711,
|
|
"epoch": 0.2789368650217707,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995998183925478,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.14139717817306519,
|
|
"num_tokens": 6375985.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.894878768920899,
|
|
"epoch": 0.2793904208998549,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995978871263881,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.14690662622451783,
|
|
"num_tokens": 6386065.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.843625783920288,
|
|
"epoch": 0.27984397677793904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995959512154868,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.14574623256921768,
|
|
"num_tokens": 6396732.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.851778793334961,
|
|
"epoch": 0.2802975326560232,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499594010659884,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.13981067016720772,
|
|
"num_tokens": 6407416.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.908939695358276,
|
|
"epoch": 0.2807510885341074,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995920654596199,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.14782450050115586,
|
|
"num_tokens": 6417673.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.937315511703491,
|
|
"epoch": 0.28120464441219156,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995901156147345,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.15051635801792146,
|
|
"num_tokens": 6426771.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.831364393234253,
|
|
"epoch": 0.2816582002902758,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995881611252684,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.15109678208827973,
|
|
"num_tokens": 6436906.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.869474411010742,
|
|
"epoch": 0.28211175616835993,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995862019912619,
|
|
"loss": 5.9014,
|
|
"mean_token_accuracy": 0.1423293836414814,
|
|
"num_tokens": 6447253.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.922127056121826,
|
|
"epoch": 0.28256531204644414,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995842382127555,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.14200060367584227,
|
|
"num_tokens": 6458486.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.880311489105225,
|
|
"epoch": 0.2830188679245283,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004995822697897897,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.14626570492982865,
|
|
"num_tokens": 6467614.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.846430110931396,
|
|
"epoch": 0.2834724238026125,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995802967224056,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15461970269680023,
|
|
"num_tokens": 6477857.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.848233366012574,
|
|
"epoch": 0.28392597968069666,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995783190106434,
|
|
"loss": 5.8375,
|
|
"mean_token_accuracy": 0.1500306785106659,
|
|
"num_tokens": 6488091.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.835888004302978,
|
|
"epoch": 0.2843795355587808,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995763366545445,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.14885595068335533,
|
|
"num_tokens": 6498725.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.856668138504029,
|
|
"epoch": 0.284833091436865,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995743496541497,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.1368933156132698,
|
|
"num_tokens": 6509850.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.8681940078735355,
|
|
"epoch": 0.2852866473149492,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995723580095001,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.1502167746424675,
|
|
"num_tokens": 6519758.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.899721384048462,
|
|
"epoch": 0.2857402031930334,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000499570361720637,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.1445355698466301,
|
|
"num_tokens": 6530422.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.885447835922241,
|
|
"epoch": 0.28619375907111755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995683607876015,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.14514559730887414,
|
|
"num_tokens": 6540785.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.865033054351807,
|
|
"epoch": 0.28664731494920176,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995663552104352,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.15479573905467986,
|
|
"num_tokens": 6550830.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.857868719100952,
|
|
"epoch": 0.2871008708272859,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004995643449891793,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.15413329899311065,
|
|
"num_tokens": 6560913.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.842754697799682,
|
|
"epoch": 0.2875544267053701,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995623301238757,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.14893174916505814,
|
|
"num_tokens": 6570596.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.851306915283203,
|
|
"epoch": 0.2880079825834543,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004995603106145657,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.15055156946182252,
|
|
"num_tokens": 6581307.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.850955390930176,
|
|
"epoch": 0.28846153846153844,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004995582864612913,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.14817112386226655,
|
|
"num_tokens": 6591917.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.81335563659668,
|
|
"epoch": 0.28891509433962265,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004995562576640943,
|
|
"loss": 5.8041,
|
|
"mean_token_accuracy": 0.14926037788391114,
|
|
"num_tokens": 6602917.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.88020806312561,
|
|
"epoch": 0.2893686502177068,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995542242230167,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.14859842211008073,
|
|
"num_tokens": 6612761.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.8096456050872805,
|
|
"epoch": 0.289822206095791,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995521861381006,
|
|
"loss": 5.7917,
|
|
"mean_token_accuracy": 0.15249492973089218,
|
|
"num_tokens": 6623563.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.811558675765991,
|
|
"epoch": 0.29027576197387517,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499550143409388,
|
|
"loss": 5.7817,
|
|
"mean_token_accuracy": 0.15435880571603774,
|
|
"num_tokens": 6633201.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.940117883682251,
|
|
"epoch": 0.2907293178519594,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995480960369211,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.14822371006011964,
|
|
"num_tokens": 6643738.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.8637003898620605,
|
|
"epoch": 0.29118287373004353,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995460440207425,
|
|
"loss": 5.7337,
|
|
"mean_token_accuracy": 0.15387465804815292,
|
|
"num_tokens": 6654053.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.793497085571289,
|
|
"epoch": 0.29163642960812775,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995439873608945,
|
|
"loss": 5.8239,
|
|
"mean_token_accuracy": 0.1479906916618347,
|
|
"num_tokens": 6665107.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.8725996017456055,
|
|
"epoch": 0.2920899854862119,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995419260574196,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.14110559597611427,
|
|
"num_tokens": 6675605.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.827268457412719,
|
|
"epoch": 0.29254354136429606,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004995398601103603,
|
|
"loss": 5.6143,
|
|
"mean_token_accuracy": 0.1541922315955162,
|
|
"num_tokens": 6684936.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.767840433120727,
|
|
"epoch": 0.29299709724238027,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995377895197597,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.14804428666830063,
|
|
"num_tokens": 6694695.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.8415192604064945,
|
|
"epoch": 0.2934506531204644,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995357142856602,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.15065886825323105,
|
|
"num_tokens": 6704862.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.764634227752685,
|
|
"epoch": 0.29390420899854863,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499533634408105,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.15840475410223007,
|
|
"num_tokens": 6713879.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.820394563674927,
|
|
"epoch": 0.2943577648766328,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000499531549887137,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1459912046790123,
|
|
"num_tokens": 6723435.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.909898471832276,
|
|
"epoch": 0.294811320754717,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995294607227993,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.15389380604028702,
|
|
"num_tokens": 6732739.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.78162317276001,
|
|
"epoch": 0.29526487663280115,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995273669151351,
|
|
"loss": 5.7835,
|
|
"mean_token_accuracy": 0.1508500948548317,
|
|
"num_tokens": 6743044.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.810116577148437,
|
|
"epoch": 0.29571843251088537,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000499525268464188,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.1529194064438343,
|
|
"num_tokens": 6752319.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.876325845718384,
|
|
"epoch": 0.2961719883889695,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004995231653700009,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.14905451089143754,
|
|
"num_tokens": 6762458.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.813838768005371,
|
|
"epoch": 0.2966255442670537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995210576326176,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.15428584665060044,
|
|
"num_tokens": 6772328.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.903802537918091,
|
|
"epoch": 0.2970791001451379,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995189452520816,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.14373027980327607,
|
|
"num_tokens": 6782754.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.917711305618286,
|
|
"epoch": 0.29753265602322204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995168282284366,
|
|
"loss": 5.8203,
|
|
"mean_token_accuracy": 0.14201931580901145,
|
|
"num_tokens": 6793197.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.823143529891968,
|
|
"epoch": 0.29798621190130625,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995147065617263,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.15240444839000702,
|
|
"num_tokens": 6802321.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.773812198638916,
|
|
"epoch": 0.2984397677793904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995125802519946,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.14767244458198547,
|
|
"num_tokens": 6813541.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.831119203567505,
|
|
"epoch": 0.2988933236574746,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004995104492992857,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.1455256797373295,
|
|
"num_tokens": 6824119.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.8984941959381105,
|
|
"epoch": 0.2993468795355588,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995083137036434,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.154207181930542,
|
|
"num_tokens": 6834315.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.8669695377349855,
|
|
"epoch": 0.299800435413643,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995061734651121,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.14483988136053086,
|
|
"num_tokens": 6844773.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.827662134170533,
|
|
"epoch": 0.30025399129172714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995040285837358,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.1427043065428734,
|
|
"num_tokens": 6855865.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.8488105773925785,
|
|
"epoch": 0.3007075471698113,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004995018790595589,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.1507802575826645,
|
|
"num_tokens": 6865142.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.828653955459595,
|
|
"epoch": 0.3011611030478955,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994997248926261,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.14814960435032845,
|
|
"num_tokens": 6876178.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.855875825881958,
|
|
"epoch": 0.30161465892597966,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994975660829817,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.14564612358808518,
|
|
"num_tokens": 6887391.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.866506433486938,
|
|
"epoch": 0.3020682148040639,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994954026306705,
|
|
"loss": 5.7831,
|
|
"mean_token_accuracy": 0.14443814307451247,
|
|
"num_tokens": 6897764.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.84368929862976,
|
|
"epoch": 0.30252177068214803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994932345357371,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.1517421394586563,
|
|
"num_tokens": 6909251.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.848319673538208,
|
|
"epoch": 0.30297532656023224,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004994910617982264,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.1507476307451725,
|
|
"num_tokens": 6919654.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.835614204406738,
|
|
"epoch": 0.3034288824383164,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994888844181833,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.13817089200019836,
|
|
"num_tokens": 6929673.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.9251823902130125,
|
|
"epoch": 0.3038824383164006,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994867023956529,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.14975906163454056,
|
|
"num_tokens": 6938994.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.901224994659424,
|
|
"epoch": 0.30433599419448476,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994845157306803,
|
|
"loss": 5.9223,
|
|
"mean_token_accuracy": 0.14631777852773667,
|
|
"num_tokens": 6950444.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.947768449783325,
|
|
"epoch": 0.3047895500725689,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994823244233107,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.14204518795013427,
|
|
"num_tokens": 6961702.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.8486240863800045,
|
|
"epoch": 0.3052431059506531,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004994801284735895,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.14448109567165374,
|
|
"num_tokens": 6972428.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.752938604354858,
|
|
"epoch": 0.3056966618287373,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994779278815619,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.14913846850395202,
|
|
"num_tokens": 6982364.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.852268695831299,
|
|
"epoch": 0.3061502177068215,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994757226472736,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.14681893065571786,
|
|
"num_tokens": 6992235.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.895943021774292,
|
|
"epoch": 0.30660377358490565,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994735127707702,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15772044211626052,
|
|
"num_tokens": 7003079.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.8661706924438475,
|
|
"epoch": 0.30705732946298986,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994712982520972,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.1421538583934307,
|
|
"num_tokens": 7013501.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.889679431915283,
|
|
"epoch": 0.307510885341074,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994690790913008,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.15045519173145294,
|
|
"num_tokens": 7023978.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.774082851409912,
|
|
"epoch": 0.3079644412191582,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004994668552884265,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.14592754542827607,
|
|
"num_tokens": 7032999.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.909044790267944,
|
|
"epoch": 0.3084179970972424,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994646268435204,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.1387397527694702,
|
|
"num_tokens": 7044776.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.976453256607056,
|
|
"epoch": 0.30887155297532654,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994623937566286,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.14521186649799347,
|
|
"num_tokens": 7054667.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.72452940940857,
|
|
"epoch": 0.30932510885341075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994601560277974,
|
|
"loss": 5.7793,
|
|
"mean_token_accuracy": 0.14921418875455855,
|
|
"num_tokens": 7065477.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.865390348434448,
|
|
"epoch": 0.3097786647314949,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499457913657073,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.15155483782291412,
|
|
"num_tokens": 7075704.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.871505212783814,
|
|
"epoch": 0.3102322206095791,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994556666445016,
|
|
"loss": 5.9229,
|
|
"mean_token_accuracy": 0.14383582025766373,
|
|
"num_tokens": 7086371.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.814038896560669,
|
|
"epoch": 0.31068577648766327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994534149901299,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.14878375381231307,
|
|
"num_tokens": 7097588.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.889452600479126,
|
|
"epoch": 0.3111393323657475,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994511586940044,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.14635036289691924,
|
|
"num_tokens": 7107650.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.833066129684449,
|
|
"epoch": 0.31159288824383163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994488977561717,
|
|
"loss": 5.808,
|
|
"mean_token_accuracy": 0.14654033184051513,
|
|
"num_tokens": 7118202.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.783775854110718,
|
|
"epoch": 0.31204644412191584,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994466321766786,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.15153429359197618,
|
|
"num_tokens": 7128834.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.866316509246826,
|
|
"epoch": 0.3125,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499444361955572,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.1500387281179428,
|
|
"num_tokens": 7138625.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.806637716293335,
|
|
"epoch": 0.31295355587808416,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994420870928988,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.15101150274276734,
|
|
"num_tokens": 7148815.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.821873950958252,
|
|
"epoch": 0.31340711175616837,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994398075887059,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.14523909389972686,
|
|
"num_tokens": 7158962.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.866718482971192,
|
|
"epoch": 0.3138606676342525,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994375234430407,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.1487603962421417,
|
|
"num_tokens": 7169281.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.858565902709961,
|
|
"epoch": 0.31431422351233673,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994352346559504,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1458689272403717,
|
|
"num_tokens": 7179934.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.853692817687988,
|
|
"epoch": 0.3147677793904209,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994329412274821,
|
|
"loss": 5.7938,
|
|
"mean_token_accuracy": 0.14809443354606627,
|
|
"num_tokens": 7190203.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.871757459640503,
|
|
"epoch": 0.3152213352685051,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994306431576835,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.14831513911485672,
|
|
"num_tokens": 7200327.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.730972814559936,
|
|
"epoch": 0.31567489114658925,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499428340446602,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.14930091053247452,
|
|
"num_tokens": 7211006.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.785858917236328,
|
|
"epoch": 0.31612844702467346,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994260330942851,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.15045426189899444,
|
|
"num_tokens": 7221249.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.857178020477295,
|
|
"epoch": 0.3165820029027576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994237211007808,
|
|
"loss": 5.7426,
|
|
"mean_token_accuracy": 0.15272777229547502,
|
|
"num_tokens": 7232534.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.88194055557251,
|
|
"epoch": 0.3170355587808418,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994214044661367,
|
|
"loss": 5.87,
|
|
"mean_token_accuracy": 0.14889724403619767,
|
|
"num_tokens": 7242776.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.828200054168701,
|
|
"epoch": 0.317489114658926,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004994190831904007,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.14493839144706727,
|
|
"num_tokens": 7253070.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.842406272888184,
|
|
"epoch": 0.31794267053701014,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499416757273621,
|
|
"loss": 5.7517,
|
|
"mean_token_accuracy": 0.14610901474952698,
|
|
"num_tokens": 7263398.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.83699779510498,
|
|
"epoch": 0.31839622641509435,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994144267158454,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.1461636394262314,
|
|
"num_tokens": 7273584.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.865672397613525,
|
|
"epoch": 0.3188497822931785,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994120915171224,
|
|
"loss": 5.7336,
|
|
"mean_token_accuracy": 0.15144022703170776,
|
|
"num_tokens": 7283403.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.699055528640747,
|
|
"epoch": 0.3193033381712627,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994097516775002,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.15417083352804184,
|
|
"num_tokens": 7293738.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.834370374679565,
|
|
"epoch": 0.3197568940493469,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994074071970271,
|
|
"loss": 5.8359,
|
|
"mean_token_accuracy": 0.14510649293661118,
|
|
"num_tokens": 7304069.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.931438398361206,
|
|
"epoch": 0.3202104499274311,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994050580757515,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.15269186496734619,
|
|
"num_tokens": 7314433.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.783717203140259,
|
|
"epoch": 0.32066400580551524,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004994027043137223,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.1535136118531227,
|
|
"num_tokens": 7324516.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.7936512470245365,
|
|
"epoch": 0.3211175616835994,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004994003459109879,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.14828921854496002,
|
|
"num_tokens": 7333746.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.862206029891968,
|
|
"epoch": 0.3215711175616836,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993979828675972,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.14887310564517975,
|
|
"num_tokens": 7344165.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.889583778381348,
|
|
"epoch": 0.32202467343976776,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000499395615183599,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.15327379256486892,
|
|
"num_tokens": 7353544.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.809433460235596,
|
|
"epoch": 0.32247822931785197,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993932428590422,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.15682561993598937,
|
|
"num_tokens": 7363387.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.836307859420776,
|
|
"epoch": 0.3229317851959361,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004993908658939762,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.15479713678359985,
|
|
"num_tokens": 7373738.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.846750164031983,
|
|
"epoch": 0.32338534107402034,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993884842884496,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.14990484118461608,
|
|
"num_tokens": 7383580.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.804448747634888,
|
|
"epoch": 0.3238388969521045,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993860980425121,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.1557959645986557,
|
|
"num_tokens": 7394047.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.866255474090576,
|
|
"epoch": 0.3242924528301887,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004993837071562131,
|
|
"loss": 5.8729,
|
|
"mean_token_accuracy": 0.14274352118372918,
|
|
"num_tokens": 7404834.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.947095918655395,
|
|
"epoch": 0.32474600870827286,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004993813116296017,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1503795638680458,
|
|
"num_tokens": 7416075.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.782832288742066,
|
|
"epoch": 0.325199564586357,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993789114627275,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.14573703706264496,
|
|
"num_tokens": 7426049.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.8114879608154295,
|
|
"epoch": 0.3256531204644412,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993765066556403,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.15304522216320038,
|
|
"num_tokens": 7436719.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.752126789093017,
|
|
"epoch": 0.3261066763425254,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004993740972083899,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.149585048109293,
|
|
"num_tokens": 7447215.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.785154199600219,
|
|
"epoch": 0.3265602322206096,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004993716831210259,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.14159765243530273,
|
|
"num_tokens": 7457602.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.8140160083770756,
|
|
"epoch": 0.32701378809869375,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993692643935983,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.1545745313167572,
|
|
"num_tokens": 7468392.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.876634788513184,
|
|
"epoch": 0.32746734397677796,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004993668410261571,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.15066123604774476,
|
|
"num_tokens": 7478320.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.794388294219971,
|
|
"epoch": 0.3279208998548621,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004993644130187525,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.1582022950053215,
|
|
"num_tokens": 7488557.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.816341876983643,
|
|
"epoch": 0.3283744557329463,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004993619803714347,
|
|
"loss": 5.7516,
|
|
"mean_token_accuracy": 0.1480060413479805,
|
|
"num_tokens": 7499108.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.820813465118408,
|
|
"epoch": 0.3288280116110305,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993595430842539,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.15406939685344695,
|
|
"num_tokens": 7508770.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.77728796005249,
|
|
"epoch": 0.32928156748911463,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993571011572606,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.150125253200531,
|
|
"num_tokens": 7519633.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.9409888744354244,
|
|
"epoch": 0.32973512336719885,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993546545905053,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.14048471823334693,
|
|
"num_tokens": 7531634.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.80763258934021,
|
|
"epoch": 0.330188679245283,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993522033840386,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.14995568990707397,
|
|
"num_tokens": 7541992.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.824553918838501,
|
|
"epoch": 0.3306422351233672,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000499349747537911,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.1440193310379982,
|
|
"num_tokens": 7552302.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.8929589748382565,
|
|
"epoch": 0.33109579100145137,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004993472870521736,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.14555299133062363,
|
|
"num_tokens": 7562806.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.79813232421875,
|
|
"epoch": 0.3315493468795356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004993448219268771,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.14852455332875253,
|
|
"num_tokens": 7572811.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.759467267990113,
|
|
"epoch": 0.33200290275761973,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004993423521620726,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.1495088294148445,
|
|
"num_tokens": 7583458.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.940987539291382,
|
|
"epoch": 0.33245645863570394,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004993398777578109,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1426645740866661,
|
|
"num_tokens": 7595227.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.8508298873901365,
|
|
"epoch": 0.3329100145137881,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993373987141435,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.14546542689204217,
|
|
"num_tokens": 7605446.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.858935737609864,
|
|
"epoch": 0.33336357039187225,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993349150311214,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.14503608867526055,
|
|
"num_tokens": 7616001.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.826646518707276,
|
|
"epoch": 0.33381712626995647,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993324267087962,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.15043987184762955,
|
|
"num_tokens": 7626747.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.828233861923218,
|
|
"epoch": 0.3342706821480406,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004993299337472192,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.15164113491773606,
|
|
"num_tokens": 7636687.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.7816657543182375,
|
|
"epoch": 0.33472423802612483,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000499327436146442,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.16283626556396485,
|
|
"num_tokens": 7647271.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.789823007583618,
|
|
"epoch": 0.335177793904209,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993249339065162,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.14822520613670348,
|
|
"num_tokens": 7657034.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.874470567703247,
|
|
"epoch": 0.3356313497822932,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993224270274937,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.14884890168905257,
|
|
"num_tokens": 7667833.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.901823997497559,
|
|
"epoch": 0.33608490566037735,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004993199155094263,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.14083609431982042,
|
|
"num_tokens": 7678247.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.87119836807251,
|
|
"epoch": 0.33653846153846156,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004993173993523658,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.1406989276409149,
|
|
"num_tokens": 7689293.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.767151117324829,
|
|
"epoch": 0.3369920174165457,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004993148785563643,
|
|
"loss": 5.8204,
|
|
"mean_token_accuracy": 0.14787752479314803,
|
|
"num_tokens": 7699462.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.892066431045532,
|
|
"epoch": 0.3374455732946299,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499312353121474,
|
|
"loss": 5.8631,
|
|
"mean_token_accuracy": 0.14873588383197783,
|
|
"num_tokens": 7709855.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.925738763809204,
|
|
"epoch": 0.3378991291727141,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004993098230477471,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.14335086718201637,
|
|
"num_tokens": 7720922.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.912420415878296,
|
|
"epoch": 0.33835268505079824,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004993072883352358,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.1521473616361618,
|
|
"num_tokens": 7730656.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.783479452133179,
|
|
"epoch": 0.33880624092888245,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993047489839927,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.15430137664079666,
|
|
"num_tokens": 7739769.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.798482847213745,
|
|
"epoch": 0.3392597968069666,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004993022049940702,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14408639296889306,
|
|
"num_tokens": 7749882.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.883006191253662,
|
|
"epoch": 0.3397133526850508,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004992996563655209,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.14932019859552384,
|
|
"num_tokens": 7760675.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.821650838851928,
|
|
"epoch": 0.340166908563135,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992971030983975,
|
|
"loss": 5.8316,
|
|
"mean_token_accuracy": 0.14970973134040833,
|
|
"num_tokens": 7771023.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.843093347549439,
|
|
"epoch": 0.3406204644412192,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992945451927531,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.14141693264245986,
|
|
"num_tokens": 7782014.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.882049036026001,
|
|
"epoch": 0.34107402031930334,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992919826486402,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.14652178436517715,
|
|
"num_tokens": 7792041.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.8244024276733395,
|
|
"epoch": 0.3415275761973875,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992894154661118,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.154453644156456,
|
|
"num_tokens": 7802027.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.750616121292114,
|
|
"epoch": 0.3419811320754717,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992868436452213,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.14698233753442763,
|
|
"num_tokens": 7812442.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.783560419082642,
|
|
"epoch": 0.34243468795355586,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004992842671860217,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.14647551104426385,
|
|
"num_tokens": 7823261.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.845564603805542,
|
|
"epoch": 0.34288824383164007,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992816860885662,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1526141047477722,
|
|
"num_tokens": 7833190.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.778737258911133,
|
|
"epoch": 0.3433417997097242,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004992791003529084,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.15017810985445976,
|
|
"num_tokens": 7842607.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.844851398468018,
|
|
"epoch": 0.34379535558780844,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004992765099791017,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.15202188193798066,
|
|
"num_tokens": 7852607.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.735257244110107,
|
|
"epoch": 0.3442489114658926,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992739149671995,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.15777993947267532,
|
|
"num_tokens": 7863500.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.822976922988891,
|
|
"epoch": 0.3447024673439768,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004992713153172556,
|
|
"loss": 5.8321,
|
|
"mean_token_accuracy": 0.1504603460431099,
|
|
"num_tokens": 7874403.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.9864270210266115,
|
|
"epoch": 0.34515602322206096,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004992687110293238,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.14370461404323578,
|
|
"num_tokens": 7885342.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.819399309158325,
|
|
"epoch": 0.3456095791001451,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004992661021034579,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1517915889620781,
|
|
"num_tokens": 7895905.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.808559989929199,
|
|
"epoch": 0.3460631349782293,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004992634885397118,
|
|
"loss": 5.8912,
|
|
"mean_token_accuracy": 0.14670953154563904,
|
|
"num_tokens": 7905293.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.8831467628479,
|
|
"epoch": 0.3465166908563135,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004992608703381396,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.1525384560227394,
|
|
"num_tokens": 7915996.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.855575037002564,
|
|
"epoch": 0.3469702467343977,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992582474987955,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.15123631060123444,
|
|
"num_tokens": 7926739.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.799056148529052,
|
|
"epoch": 0.34742380261248185,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992556200217337,
|
|
"loss": 5.7734,
|
|
"mean_token_accuracy": 0.14914042353630066,
|
|
"num_tokens": 7937109.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.815071058273316,
|
|
"epoch": 0.34787735849056606,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004992529879070085,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.15417693704366683,
|
|
"num_tokens": 7947562.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.822039318084717,
|
|
"epoch": 0.3483309143686502,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004992503511546745,
|
|
"loss": 5.7967,
|
|
"mean_token_accuracy": 0.15639951974153518,
|
|
"num_tokens": 7957400.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.814460420608521,
|
|
"epoch": 0.3487844702467344,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992477097647859,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.1585880383849144,
|
|
"num_tokens": 7967600.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.8076441287994385,
|
|
"epoch": 0.3492380261248186,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004992450637373976,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.1458221599459648,
|
|
"num_tokens": 7978012.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.746403789520263,
|
|
"epoch": 0.34969158200290273,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004992424130725642,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.14770088642835616,
|
|
"num_tokens": 7988495.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.911701726913452,
|
|
"epoch": 0.35014513788098695,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004992397577703406,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.14998696744441986,
|
|
"num_tokens": 7998125.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.80164270401001,
|
|
"epoch": 0.3505986937590711,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992370978307816,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.15145281702280045,
|
|
"num_tokens": 8009151.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.736188745498657,
|
|
"epoch": 0.3510522496371553,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004992344332539424,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.15478172451257705,
|
|
"num_tokens": 8019501.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.775134611129761,
|
|
"epoch": 0.35150580551523947,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004992317640398779,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.15074608698487282,
|
|
"num_tokens": 8030362.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.773638105392456,
|
|
"epoch": 0.3519593613933237,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992290901886434,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.14943585619330407,
|
|
"num_tokens": 8041671.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.83705472946167,
|
|
"epoch": 0.35241291727140783,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000499226411700294,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.14793721884489058,
|
|
"num_tokens": 8052609.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.854422664642334,
|
|
"epoch": 0.35286647314949204,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004992237285748855,
|
|
"loss": 5.7463,
|
|
"mean_token_accuracy": 0.15416623651981354,
|
|
"num_tokens": 8062611.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.8708113670349125,
|
|
"epoch": 0.3533200290275762,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992210408124731,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.15578939616680146,
|
|
"num_tokens": 8073542.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.816879558563232,
|
|
"epoch": 0.35377358490566035,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992183484131123,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.1484497994184494,
|
|
"num_tokens": 8083634.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.8308281898498535,
|
|
"epoch": 0.35422714078374457,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004992156513768591,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.15284653156995773,
|
|
"num_tokens": 8094710.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.889791870117188,
|
|
"epoch": 0.3546806966618287,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499212949703769,
|
|
"loss": 5.908,
|
|
"mean_token_accuracy": 0.14653956666588783,
|
|
"num_tokens": 8104191.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.7595172882080075,
|
|
"epoch": 0.35513425253991293,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992102433938981,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.15048497617244722,
|
|
"num_tokens": 8114744.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.854955530166626,
|
|
"epoch": 0.3555878084179971,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992075324473021,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.14852231740951538,
|
|
"num_tokens": 8124267.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.880210924148559,
|
|
"epoch": 0.3560413642960813,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004992048168640371,
|
|
"loss": 5.8157,
|
|
"mean_token_accuracy": 0.14342952743172646,
|
|
"num_tokens": 8134383.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.803681993484497,
|
|
"epoch": 0.35649492017416545,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992020966441595,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15491905063390732,
|
|
"num_tokens": 8144131.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.750734806060791,
|
|
"epoch": 0.35694847605224966,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004991993717877254,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15241849273443223,
|
|
"num_tokens": 8154947.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.78973536491394,
|
|
"epoch": 0.3574020319303338,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004991966422947911,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.14700091183185576,
|
|
"num_tokens": 8165692.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.8159383773803714,
|
|
"epoch": 0.357855587808418,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991939081654132,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.14284562468528747,
|
|
"num_tokens": 8177402.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.765165567398071,
|
|
"epoch": 0.3583091436865022,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499191169399648,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.15420890748500823,
|
|
"num_tokens": 8187545.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.743610429763794,
|
|
"epoch": 0.35876269956458634,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991884259975525,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.15421922504901886,
|
|
"num_tokens": 8198142.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.767709255218506,
|
|
"epoch": 0.35921625544267055,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000499185677959183,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15191758424043655,
|
|
"num_tokens": 8208131.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.7967020034790036,
|
|
"epoch": 0.3596698113207547,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991829252845966,
|
|
"loss": 5.7845,
|
|
"mean_token_accuracy": 0.14716573655605317,
|
|
"num_tokens": 8218091.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.77277889251709,
|
|
"epoch": 0.3601233671988389,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004991801679738502,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.15576295107603072,
|
|
"num_tokens": 8228392.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.767637395858765,
|
|
"epoch": 0.3605769230769231,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004991774060270008,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.15118133872747422,
|
|
"num_tokens": 8238272.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.802407693862915,
|
|
"epoch": 0.3610304789550073,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004991746394441055,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.147048220038414,
|
|
"num_tokens": 8248255.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.91586012840271,
|
|
"epoch": 0.36148403483309144,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991718682252216,
|
|
"loss": 5.8726,
|
|
"mean_token_accuracy": 0.1428057424724102,
|
|
"num_tokens": 8258839.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.771537828445434,
|
|
"epoch": 0.3619375907111756,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004991690923704063,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.1511303447186947,
|
|
"num_tokens": 8269400.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.940103054046631,
|
|
"epoch": 0.3623911465892598,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991663118797171,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1525319442152977,
|
|
"num_tokens": 8279468.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.80928750038147,
|
|
"epoch": 0.36284470246734396,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991635267532113,
|
|
"loss": 5.6949,
|
|
"mean_token_accuracy": 0.15478259027004243,
|
|
"num_tokens": 8289207.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.637155389785766,
|
|
"epoch": 0.36329825834542817,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991607369909468,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.15483498573303223,
|
|
"num_tokens": 8299819.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.815872097015381,
|
|
"epoch": 0.3637518142235123,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991579425929811,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.15534015893936157,
|
|
"num_tokens": 8310216.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.781091022491455,
|
|
"epoch": 0.36420537010159654,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499155143559372,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.15090734809637069,
|
|
"num_tokens": 8319967.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.850452327728272,
|
|
"epoch": 0.3646589259796807,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004991523398901773,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.1563695937395096,
|
|
"num_tokens": 8329271.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.788423871994018,
|
|
"epoch": 0.3651124818577649,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004991495315854553,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.15406767427921295,
|
|
"num_tokens": 8340042.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.86919207572937,
|
|
"epoch": 0.36556603773584906,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004991467186452637,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.14352630823850632,
|
|
"num_tokens": 8351005.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.810650253295899,
|
|
"epoch": 0.3660195936139332,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991439010696609,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.15218240916728973,
|
|
"num_tokens": 8360964.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.818238067626953,
|
|
"epoch": 0.3664731494920174,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004991410788587051,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.14673216938972472,
|
|
"num_tokens": 8370933.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.8133055686950685,
|
|
"epoch": 0.3669267053701016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991382520124547,
|
|
"loss": 5.7941,
|
|
"mean_token_accuracy": 0.15076968371868132,
|
|
"num_tokens": 8382422.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.8689398765563965,
|
|
"epoch": 0.3673802612481858,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004991354205309681,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.14591655284166336,
|
|
"num_tokens": 8392162.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.831794023513794,
|
|
"epoch": 0.36783381712626995,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499132584414304,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.14830462336540223,
|
|
"num_tokens": 8402145.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.808120536804199,
|
|
"epoch": 0.36828737300435416,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004991297436625207,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.15320413708686828,
|
|
"num_tokens": 8413117.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.78600697517395,
|
|
"epoch": 0.3687409288824383,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991268982756774,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.15311348736286162,
|
|
"num_tokens": 8422997.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.80166392326355,
|
|
"epoch": 0.3691944847605225,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004991240482538327,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.15038370192050934,
|
|
"num_tokens": 8432718.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.836380958557129,
|
|
"epoch": 0.3696480406386067,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004991211935970455,
|
|
"loss": 5.753,
|
|
"mean_token_accuracy": 0.14487562626600264,
|
|
"num_tokens": 8442808.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.758193063735962,
|
|
"epoch": 0.37010159651669083,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004991183343053748,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.15124204605817795,
|
|
"num_tokens": 8451919.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.852297353744507,
|
|
"epoch": 0.37055515239477504,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00049911547037888,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.14427137970924378,
|
|
"num_tokens": 8463593.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.772682237625122,
|
|
"epoch": 0.3710087082728592,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004991126018176202,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.14865192174911498,
|
|
"num_tokens": 8474025.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.847655487060547,
|
|
"epoch": 0.3714622641509434,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004991097286216545,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.14862846881151198,
|
|
"num_tokens": 8484225.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.888778352737427,
|
|
"epoch": 0.37191582002902757,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004991068507910427,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.15229319036006927,
|
|
"num_tokens": 8494173.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.863654279708863,
|
|
"epoch": 0.3723693759071118,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000499103968325844,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.15187404453754424,
|
|
"num_tokens": 8504731.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.6381782531738285,
|
|
"epoch": 0.37282293178519593,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991010812261181,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.15621297359466552,
|
|
"num_tokens": 8514814.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.740231275558472,
|
|
"epoch": 0.37327648766328014,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004990981894919248,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.1475978210568428,
|
|
"num_tokens": 8525486.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.844956254959106,
|
|
"epoch": 0.3737300435413643,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004990952931233238,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15925588607788085,
|
|
"num_tokens": 8535290.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.746306133270264,
|
|
"epoch": 0.37418359941944845,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499092392120375,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.15315198004245759,
|
|
"num_tokens": 8545506.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.788954257965088,
|
|
"epoch": 0.37463715529753266,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004990894864831385,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15347600281238555,
|
|
"num_tokens": 8555360.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.856559896469117,
|
|
"epoch": 0.3750907111756168,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004990865762116743,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.1511617124080658,
|
|
"num_tokens": 8565582.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.810130071640015,
|
|
"epoch": 0.37554426705370103,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004990836613060426,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.1501256100833416,
|
|
"num_tokens": 8576043.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.712186050415039,
|
|
"epoch": 0.3759978229317852,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004990807417663036,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.15447329580783845,
|
|
"num_tokens": 8586538.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.796316289901734,
|
|
"epoch": 0.3764513788098694,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004990778175925179,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.16033863127231598,
|
|
"num_tokens": 8596622.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.796439552307129,
|
|
"epoch": 0.37690493468795355,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004990748887847457,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.15430489629507066,
|
|
"num_tokens": 8605945.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.768828010559082,
|
|
"epoch": 0.37735849056603776,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004990719553430477,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.14899329990148544,
|
|
"num_tokens": 8615841.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.858073425292969,
|
|
"epoch": 0.3778120464441219,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990690172674847,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15224681198596954,
|
|
"num_tokens": 8627228.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.792933702468872,
|
|
"epoch": 0.3782656023222061,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004990660745581172,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.15444036573171616,
|
|
"num_tokens": 8637848.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.786196756362915,
|
|
"epoch": 0.3787191582002903,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004990631272150062,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.14932020604610444,
|
|
"num_tokens": 8648147.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.8579583168029785,
|
|
"epoch": 0.37917271407837444,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004990601752382127,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.14665968865156173,
|
|
"num_tokens": 8659464.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.8483274459838865,
|
|
"epoch": 0.37962626995645865,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004990572186277975,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.15550817549228668,
|
|
"num_tokens": 8670435.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.801906681060791,
|
|
"epoch": 0.3800798258345428,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004990542573838221,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.14839256703853607,
|
|
"num_tokens": 8681193.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.90633544921875,
|
|
"epoch": 0.380533381712627,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990512915063475,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.14305422231554984,
|
|
"num_tokens": 8692191.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.803619432449341,
|
|
"epoch": 0.38098693759071117,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004990483209954352,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.15340645760297775,
|
|
"num_tokens": 8703199.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.755993366241455,
|
|
"epoch": 0.3814404934687954,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004990453458511464,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.14746004939079285,
|
|
"num_tokens": 8713850.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.801353931427002,
|
|
"epoch": 0.38189404934687954,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990423660735428,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.1433395117521286,
|
|
"num_tokens": 8724045.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.807311630249023,
|
|
"epoch": 0.3823476052249637,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000499039381662686,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.15545451492071152,
|
|
"num_tokens": 8734187.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.832239580154419,
|
|
"epoch": 0.3828011611030479,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990363926186377,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.15328917652368546,
|
|
"num_tokens": 8744553.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.762201309204102,
|
|
"epoch": 0.38325471698113206,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004990333989414597,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.15205525010824203,
|
|
"num_tokens": 8755209.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.778427696228027,
|
|
"epoch": 0.38370827285921627,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990304006312138,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.147205713391304,
|
|
"num_tokens": 8765552.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.735978126525879,
|
|
"epoch": 0.3841618287373004,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990273976879622,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.15794021636247635,
|
|
"num_tokens": 8776118.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.715007734298706,
|
|
"epoch": 0.38461538461538464,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004990243901117669,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.15574559867382048,
|
|
"num_tokens": 8785927.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.883077335357666,
|
|
"epoch": 0.3850689404934688,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990213779026903,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.14674270004034043,
|
|
"num_tokens": 8797257.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.878513336181641,
|
|
"epoch": 0.385522496371553,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004990183610607944,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.14894410818815232,
|
|
"num_tokens": 8808266.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.755019950866699,
|
|
"epoch": 0.38597605224963716,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004990153395861415,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.15247720181941987,
|
|
"num_tokens": 8818989.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.732574892044068,
|
|
"epoch": 0.3864296081277213,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004990123134787946,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.1495862066745758,
|
|
"num_tokens": 8828352.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.792064380645752,
|
|
"epoch": 0.3868831640058055,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004990092827388159,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.15442929714918135,
|
|
"num_tokens": 8838743.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.794605159759522,
|
|
"epoch": 0.3873367198838897,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990062473662681,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.14651462882757188,
|
|
"num_tokens": 8848865.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.7486231327056885,
|
|
"epoch": 0.3877902757619739,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000499003207361214,
|
|
"loss": 5.6718,
|
|
"mean_token_accuracy": 0.15159275084733964,
|
|
"num_tokens": 8859156.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.886171054840088,
|
|
"epoch": 0.38824383164005805,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004990001627237165,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15245936065912247,
|
|
"num_tokens": 8868860.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.804189872741699,
|
|
"epoch": 0.38869738751814226,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004989971134538386,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.1453443519771099,
|
|
"num_tokens": 8879355.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.769974565505981,
|
|
"epoch": 0.3891509433962264,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004989940595516432,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.14543934911489487,
|
|
"num_tokens": 8890116.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.792919635772705,
|
|
"epoch": 0.3896044992743106,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004989910010171938,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.14830279499292373,
|
|
"num_tokens": 8901243.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.892558193206787,
|
|
"epoch": 0.3900580551523948,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004989879378505532,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.1488331064581871,
|
|
"num_tokens": 8911064.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.760198783874512,
|
|
"epoch": 0.39051161103047893,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004989848700517849,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.15363716781139375,
|
|
"num_tokens": 8921659.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.769484138488769,
|
|
"epoch": 0.39096516690856314,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004989817976209526,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.15186847597360612,
|
|
"num_tokens": 8932424.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.780123567581176,
|
|
"epoch": 0.3914187227866473,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004989787205581196,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.1513989195227623,
|
|
"num_tokens": 8943097.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.7439628601074215,
|
|
"epoch": 0.3918722786647315,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004989756388633496,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.15355851948261262,
|
|
"num_tokens": 8953817.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.824839019775391,
|
|
"epoch": 0.39232583454281567,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004989725525367063,
|
|
"loss": 5.7412,
|
|
"mean_token_accuracy": 0.15554174035787582,
|
|
"num_tokens": 8963731.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.878753566741944,
|
|
"epoch": 0.3927793904208999,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989694615782534,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.14490067809820176,
|
|
"num_tokens": 8974063.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.821165657043457,
|
|
"epoch": 0.39323294629898403,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004989663659880552,
|
|
"loss": 5.642,
|
|
"mean_token_accuracy": 0.15681983530521393,
|
|
"num_tokens": 8984153.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.798787260055542,
|
|
"epoch": 0.3936865021770682,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004989632657661754,
|
|
"loss": 5.6806,
|
|
"mean_token_accuracy": 0.15686829388141632,
|
|
"num_tokens": 8994043.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.813419961929322,
|
|
"epoch": 0.3941400580551524,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.000498960160912678,
|
|
"loss": 5.79,
|
|
"mean_token_accuracy": 0.14800060093402861,
|
|
"num_tokens": 9004852.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.790053844451904,
|
|
"epoch": 0.39459361393323655,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004989570514276276,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.15587036162614823,
|
|
"num_tokens": 9015314.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.7702381134033205,
|
|
"epoch": 0.39504716981132076,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004989539373110883,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.15190639197826386,
|
|
"num_tokens": 9026191.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.803680753707885,
|
|
"epoch": 0.3955007256894049,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989508185631245,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.15162685811519622,
|
|
"num_tokens": 9037160.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.825860404968262,
|
|
"epoch": 0.39595428156748913,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004989476951838006,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.14626863971352577,
|
|
"num_tokens": 9047397.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.858776044845581,
|
|
"epoch": 0.3964078374455733,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989445671731814,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.14717085361480714,
|
|
"num_tokens": 9057416.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.869134092330933,
|
|
"epoch": 0.3968613933236575,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004989414345313315,
|
|
"loss": 5.746,
|
|
"mean_token_accuracy": 0.15247844010591508,
|
|
"num_tokens": 9068428.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.849895668029785,
|
|
"epoch": 0.39731494920174165,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004989382972583156,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.1457201287150383,
|
|
"num_tokens": 9079443.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.742780542373657,
|
|
"epoch": 0.3977685050798258,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004989351553541986,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.1511688381433487,
|
|
"num_tokens": 9089856.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.7647631645202635,
|
|
"epoch": 0.39822206095791,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004989320088190456,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.15218283236026764,
|
|
"num_tokens": 9100893.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.862979936599731,
|
|
"epoch": 0.3986756168359942,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004989288576529216,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.14252141565084459,
|
|
"num_tokens": 9112308.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.785729789733887,
|
|
"epoch": 0.3991291727140784,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004989257018558917,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.14584366753697395,
|
|
"num_tokens": 9123052.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.81339020729065,
|
|
"epoch": 0.39958272859216254,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004989225414280213,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.15271426737308502,
|
|
"num_tokens": 9134117.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.829674625396729,
|
|
"epoch": 0.40003628447024675,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989193763693756,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.150883536785841,
|
|
"num_tokens": 9145737.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.812243700027466,
|
|
"epoch": 0.4004898403483309,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004989162066800202,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.1514497235417366,
|
|
"num_tokens": 9156443.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.752085208892822,
|
|
"epoch": 0.4009433962264151,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004989130323600205,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.15138549357652664,
|
|
"num_tokens": 9166657.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.812001085281372,
|
|
"epoch": 0.40139695210449927,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004989098534094424,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.14933129101991655,
|
|
"num_tokens": 9177475.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.821232891082763,
|
|
"epoch": 0.4018505079825834,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004989066698283512,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.15208391845226288,
|
|
"num_tokens": 9187250.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.799831676483154,
|
|
"epoch": 0.40230406386066764,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004989034816168132,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.14922597855329514,
|
|
"num_tokens": 9198071.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.785824966430664,
|
|
"epoch": 0.4027576197387518,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004989002887748941,
|
|
"loss": 5.6938,
|
|
"mean_token_accuracy": 0.1565877303481102,
|
|
"num_tokens": 9208102.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.717708539962769,
|
|
"epoch": 0.403211175616836,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004988970913026601,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1590559408068657,
|
|
"num_tokens": 9217564.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.740492057800293,
|
|
"epoch": 0.40366473149492016,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004988938892001771,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.15244835019111633,
|
|
"num_tokens": 9228027.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.846228504180909,
|
|
"epoch": 0.40411828737300437,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988906824675113,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.14298200979828835,
|
|
"num_tokens": 9239073.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.837181520462036,
|
|
"epoch": 0.4045718432510885,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004988874711047293,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.15341956913471222,
|
|
"num_tokens": 9249936.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.770998907089234,
|
|
"epoch": 0.40502539912917274,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988842551118972,
|
|
"loss": 5.7247,
|
|
"mean_token_accuracy": 0.15381136983633042,
|
|
"num_tokens": 9259758.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.762871217727661,
|
|
"epoch": 0.4054789550072569,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988810344890818,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.15472375750541686,
|
|
"num_tokens": 9270731.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.7881018161773685,
|
|
"epoch": 0.40593251088534105,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004988778092363494,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.14924555122852326,
|
|
"num_tokens": 9281377.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.760777235031128,
|
|
"epoch": 0.40638606676342526,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004988745793537671,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.15252517759799958,
|
|
"num_tokens": 9290477.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.755960464477539,
|
|
"epoch": 0.4068396226415094,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988713448414011,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.15938864648342133,
|
|
"num_tokens": 9300129.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.784805202484131,
|
|
"epoch": 0.4072931785195936,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498868105699319,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.1487440623342991,
|
|
"num_tokens": 9310734.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.710954809188843,
|
|
"epoch": 0.4077467343976778,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004988648619275872,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.1490918666124344,
|
|
"num_tokens": 9320470.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.719701671600342,
|
|
"epoch": 0.408200290275762,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004988616135262729,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.15467289835214615,
|
|
"num_tokens": 9330480.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.829697036743164,
|
|
"epoch": 0.40865384615384615,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004988583604954436,
|
|
"loss": 5.6992,
|
|
"mean_token_accuracy": 0.1557617023587227,
|
|
"num_tokens": 9342101.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.828498792648316,
|
|
"epoch": 0.40910740203193036,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004988551028351663,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.15712219029664992,
|
|
"num_tokens": 9352792.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.765654420852661,
|
|
"epoch": 0.4095609579100145,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004988518405455084,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.15821951627731323,
|
|
"num_tokens": 9363883.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.798408794403076,
|
|
"epoch": 0.41001451378809867,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004988485736265374,
|
|
"loss": 5.7814,
|
|
"mean_token_accuracy": 0.1483925238251686,
|
|
"num_tokens": 9375434.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.761251735687256,
|
|
"epoch": 0.4104680696661829,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498845302078321,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.14736573696136473,
|
|
"num_tokens": 9386430.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.8544196605682375,
|
|
"epoch": 0.41092162554426703,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004988420259009266,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.15411313623189926,
|
|
"num_tokens": 9396043.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.7836181640625,
|
|
"epoch": 0.41137518142235124,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000498838745094422,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.15280985534191133,
|
|
"num_tokens": 9406346.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.783379983901978,
|
|
"epoch": 0.4118287373004354,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004988354596588751,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.1566889375448227,
|
|
"num_tokens": 9416171.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.761880350112915,
|
|
"epoch": 0.4122822931785196,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004988321695943539,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.1549982585012913,
|
|
"num_tokens": 9426123.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.72822413444519,
|
|
"epoch": 0.41273584905660377,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004988288749009264,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.15963514298200607,
|
|
"num_tokens": 9437173.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.712554788589477,
|
|
"epoch": 0.413189404934688,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004988255755786608,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.14644763842225075,
|
|
"num_tokens": 9446928.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.7979991912841795,
|
|
"epoch": 0.41364296081277213,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004988222716276251,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.15122124552726746,
|
|
"num_tokens": 9458180.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.84049243927002,
|
|
"epoch": 0.4140965166908563,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498818963047888,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.15793658643960953,
|
|
"num_tokens": 9467791.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.761186265945435,
|
|
"epoch": 0.4145500725689405,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004988156498395176,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.14440502598881721,
|
|
"num_tokens": 9478567.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.799375820159912,
|
|
"epoch": 0.41500362844702465,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988123320025825,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.14579950124025345,
|
|
"num_tokens": 9489226.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.769663286209107,
|
|
"epoch": 0.41545718432510886,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988090095371514,
|
|
"loss": 5.7103,
|
|
"mean_token_accuracy": 0.14600292295217515,
|
|
"num_tokens": 9499598.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.799290132522583,
|
|
"epoch": 0.415910740203193,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988056824432928,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.1523233249783516,
|
|
"num_tokens": 9509128.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.859962844848633,
|
|
"epoch": 0.41636429608127723,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004988023507210758,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.15456788688898088,
|
|
"num_tokens": 9519564.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.826257753372192,
|
|
"epoch": 0.4168178519593614,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004987990143705692,
|
|
"loss": 5.748,
|
|
"mean_token_accuracy": 0.15228485465049743,
|
|
"num_tokens": 9530393.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.765258502960205,
|
|
"epoch": 0.4172714078374456,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987956733918418,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.1483850434422493,
|
|
"num_tokens": 9540746.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.794782209396362,
|
|
"epoch": 0.41772496371552975,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987923277849629,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.1539371058344841,
|
|
"num_tokens": 9550611.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.948241472244263,
|
|
"epoch": 0.4181785195936139,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987889775500017,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.14910096898674965,
|
|
"num_tokens": 9560273.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.828892946243286,
|
|
"epoch": 0.4186320754716981,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004987856226870272,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.15116819590330124,
|
|
"num_tokens": 9571199.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.7489643573760985,
|
|
"epoch": 0.4190856313497823,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987822631961092,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1496698245406151,
|
|
"num_tokens": 9580638.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.81583309173584,
|
|
"epoch": 0.4195391872278665,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498778899077317,
|
|
"loss": 5.7711,
|
|
"mean_token_accuracy": 0.1492114171385765,
|
|
"num_tokens": 9592067.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.745096969604492,
|
|
"epoch": 0.41999274310595064,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00049877553033072,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.15567420721054076,
|
|
"num_tokens": 9603151.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.748169183731079,
|
|
"epoch": 0.42044629898403485,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987721569563882,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.1470457211136818,
|
|
"num_tokens": 9613651.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.869939565658569,
|
|
"epoch": 0.420899854862119,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000498768778954391,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.1548364281654358,
|
|
"num_tokens": 9623705.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.814824962615967,
|
|
"epoch": 0.4213534107402032,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004987653963247985,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.14578017443418503,
|
|
"num_tokens": 9634663.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.807049417495728,
|
|
"epoch": 0.42180696661828737,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004987620090676805,
|
|
"loss": 5.7646,
|
|
"mean_token_accuracy": 0.15146553814411162,
|
|
"num_tokens": 9645071.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.720735311508179,
|
|
"epoch": 0.4222605224963715,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004987586171831072,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.15271254628896713,
|
|
"num_tokens": 9654942.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.712645530700684,
|
|
"epoch": 0.42271407837445574,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987552206711487,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15510569512844086,
|
|
"num_tokens": 9665379.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.8077527523040775,
|
|
"epoch": 0.4231676342525399,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004987518195318752,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.1477640151977539,
|
|
"num_tokens": 9674812.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.798747587203979,
|
|
"epoch": 0.4236211901306241,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000498748413765357,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.1464133784174919,
|
|
"num_tokens": 9685765.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.836048650741577,
|
|
"epoch": 0.42407474600870826,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004987450033716646,
|
|
"loss": 5.7455,
|
|
"mean_token_accuracy": 0.14856940880417824,
|
|
"num_tokens": 9696747.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.759535217285157,
|
|
"epoch": 0.42452830188679247,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987415883508686,
|
|
"loss": 5.7376,
|
|
"mean_token_accuracy": 0.1529595822095871,
|
|
"num_tokens": 9707431.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.876302242279053,
|
|
"epoch": 0.4249818577648766,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004987381687030394,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.14749758690595627,
|
|
"num_tokens": 9717454.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.872333002090454,
|
|
"epoch": 0.42543541364296084,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004987347444282479,
|
|
"loss": 5.756,
|
|
"mean_token_accuracy": 0.15242287069559096,
|
|
"num_tokens": 9726803.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.770662260055542,
|
|
"epoch": 0.425888969521045,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004987313155265649,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.14523900747299195,
|
|
"num_tokens": 9737089.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.7127138614654545,
|
|
"epoch": 0.42634252539912915,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004987278819980613,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.1546218603849411,
|
|
"num_tokens": 9748698.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.7299487590789795,
|
|
"epoch": 0.42679608127721336,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004987244438428081,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.15895820856094361,
|
|
"num_tokens": 9758940.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.66409649848938,
|
|
"epoch": 0.4272496371552975,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004987210010608764,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.15151547640562057,
|
|
"num_tokens": 9769051.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.661192941665649,
|
|
"epoch": 0.4277031930333817,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004987175536523373,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.1603727474808693,
|
|
"num_tokens": 9779421.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.846398544311524,
|
|
"epoch": 0.4281567489114659,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004987141016172622,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.15543566793203353,
|
|
"num_tokens": 9790003.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.727094078063965,
|
|
"epoch": 0.4286103047895501,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004987106449557225,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.15138356983661652,
|
|
"num_tokens": 9800085.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.669862222671509,
|
|
"epoch": 0.42906386066763424,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004987071836677896,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.1575853556394577,
|
|
"num_tokens": 9809873.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.779130697250366,
|
|
"epoch": 0.42951741654571846,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987037177535353,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.1511673741042614,
|
|
"num_tokens": 9820137.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.789821195602417,
|
|
"epoch": 0.4299709724238026,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004987002472130309,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.15311633199453353,
|
|
"num_tokens": 9830758.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.760760021209717,
|
|
"epoch": 0.43042452830188677,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004986967720463485,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.1549585849046707,
|
|
"num_tokens": 9841594.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.763367462158203,
|
|
"epoch": 0.430878084179971,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004986932922535598,
|
|
"loss": 5.7617,
|
|
"mean_token_accuracy": 0.1477864995598793,
|
|
"num_tokens": 9853640.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.851624822616577,
|
|
"epoch": 0.43133164005805513,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004986898078347368,
|
|
"loss": 5.7814,
|
|
"mean_token_accuracy": 0.15149234533309935,
|
|
"num_tokens": 9864550.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.867263603210449,
|
|
"epoch": 0.43178519593613934,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986863187899516,
|
|
"loss": 5.7169,
|
|
"mean_token_accuracy": 0.1487038627266884,
|
|
"num_tokens": 9875544.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.818501996994018,
|
|
"epoch": 0.4322387518142235,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004986828251192764,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.15489247292280198,
|
|
"num_tokens": 9886387.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.733272361755371,
|
|
"epoch": 0.4326923076923077,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004986793268227833,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15493058413267136,
|
|
"num_tokens": 9896340.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.778052186965942,
|
|
"epoch": 0.43314586357039186,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004986758239005448,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.1477018713951111,
|
|
"num_tokens": 9907587.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.782829904556275,
|
|
"epoch": 0.4335994194484761,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004986723163526331,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.15842603147029877,
|
|
"num_tokens": 9917477.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.7354288578033445,
|
|
"epoch": 0.43405297532656023,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004986688041791209,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.15261090695858,
|
|
"num_tokens": 9927808.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.717248201370239,
|
|
"epoch": 0.4345065312046444,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000498665287380081,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.1633790224790573,
|
|
"num_tokens": 9937322.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.747660779953003,
|
|
"epoch": 0.4349600870827286,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004986617659555859,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.15461928248405457,
|
|
"num_tokens": 9947259.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.845655250549316,
|
|
"epoch": 0.43541364296081275,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004986582399057085,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.14935103803873062,
|
|
"num_tokens": 9957660.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.751298189163208,
|
|
"epoch": 0.43586719883889696,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004986547092305216,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.15811071246862413,
|
|
"num_tokens": 9967460.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.832250690460205,
|
|
"epoch": 0.4363207547169811,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004986511739300984,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.1497562661767006,
|
|
"num_tokens": 9979176.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.822063636779785,
|
|
"epoch": 0.43677431059506533,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004986476340045119,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.1614718809723854,
|
|
"num_tokens": 9989025.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.800371837615967,
|
|
"epoch": 0.4372278664731495,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004986440894538354,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.14864002764225007,
|
|
"num_tokens": 9998887.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.843149709701538,
|
|
"epoch": 0.4376814223512337,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004986405402781421,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.14749663099646568,
|
|
"num_tokens": 10009425.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.774194431304932,
|
|
"epoch": 0.43813497822931785,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004986369864775054,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.1558217227458954,
|
|
"num_tokens": 10019733.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.798313045501709,
|
|
"epoch": 0.438588534107402,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004986334280519989,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.14939245581626892,
|
|
"num_tokens": 10029829.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.727769613265991,
|
|
"epoch": 0.4390420899854862,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000498629865001696,
|
|
"loss": 5.5467,
|
|
"mean_token_accuracy": 0.15010637938976287,
|
|
"num_tokens": 10040699.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.744697904586792,
|
|
"epoch": 0.43949564586357037,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004986262973266706,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.15142616853117943,
|
|
"num_tokens": 10051956.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.784964275360108,
|
|
"epoch": 0.4399492017416546,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004986227250269964,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.15234601348638535,
|
|
"num_tokens": 10062300.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.750584316253662,
|
|
"epoch": 0.44040275761973874,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004986191481027472,
|
|
"loss": 5.6152,
|
|
"mean_token_accuracy": 0.1578789621591568,
|
|
"num_tokens": 10072577.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.6763123035430905,
|
|
"epoch": 0.44085631349782295,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004986155665539971,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.15474955439567567,
|
|
"num_tokens": 10083041.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.720007038116455,
|
|
"epoch": 0.4413098693759071,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00049861198038082,
|
|
"loss": 5.7336,
|
|
"mean_token_accuracy": 0.15288010090589524,
|
|
"num_tokens": 10092927.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.853694152832031,
|
|
"epoch": 0.4417634252539913,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004986083895832903,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.15163737162947655,
|
|
"num_tokens": 10104033.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.834793519973755,
|
|
"epoch": 0.44221698113207547,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004986047941614821,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15353917330503464,
|
|
"num_tokens": 10113696.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.733519506454468,
|
|
"epoch": 0.4426705370101596,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986011941154696,
|
|
"loss": 5.7311,
|
|
"mean_token_accuracy": 0.1490173175930977,
|
|
"num_tokens": 10124725.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.866247892379761,
|
|
"epoch": 0.44312409288824384,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985975894453275,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.13853485733270646,
|
|
"num_tokens": 10135079.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.86741828918457,
|
|
"epoch": 0.443577648766328,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004985939801511304,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.15153541415929794,
|
|
"num_tokens": 10146518.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.655025863647461,
|
|
"epoch": 0.4440312046444122,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004985903662329527,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.15998917520046235,
|
|
"num_tokens": 10156329.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.750478982925415,
|
|
"epoch": 0.44448476052249636,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985867476908693,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.14420461431145667,
|
|
"num_tokens": 10167375.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.782648181915283,
|
|
"epoch": 0.44493831640058057,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004985831245249549,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.14595248699188232,
|
|
"num_tokens": 10177465.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.838851451873779,
|
|
"epoch": 0.4453918722786647,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004985794967352846,
|
|
"loss": 5.7494,
|
|
"mean_token_accuracy": 0.15075748264789582,
|
|
"num_tokens": 10187728.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.80021333694458,
|
|
"epoch": 0.44584542815674894,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004985758643219334,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1465687334537506,
|
|
"num_tokens": 10199289.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.745902061462402,
|
|
"epoch": 0.4462989840348331,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004985722272849762,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.15045904517173767,
|
|
"num_tokens": 10209073.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.78634090423584,
|
|
"epoch": 0.44675253991291725,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985685856244884,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.13826809749007224,
|
|
"num_tokens": 10220238.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.9017843246459964,
|
|
"epoch": 0.44720609579100146,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004985649393405453,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.145417732745409,
|
|
"num_tokens": 10230734.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.810334587097168,
|
|
"epoch": 0.4476596516690856,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004985612884332223,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.15715192556381224,
|
|
"num_tokens": 10240342.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.726405286788941,
|
|
"epoch": 0.4481132075471698,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004985576329025949,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.15500271767377855,
|
|
"num_tokens": 10250418.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.758911609649658,
|
|
"epoch": 0.448566763425254,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985539727487385,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.1564280316233635,
|
|
"num_tokens": 10260654.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.7844610691070555,
|
|
"epoch": 0.4490203193033382,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004985503079717292,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.15968757420778273,
|
|
"num_tokens": 10270535.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.795976734161377,
|
|
"epoch": 0.44947387518142234,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004985466385716425,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.15215763300657273,
|
|
"num_tokens": 10280724.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.7172832012176515,
|
|
"epoch": 0.44992743105950656,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004985429645485543,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.15808341056108474,
|
|
"num_tokens": 10290795.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.7305827140808105,
|
|
"epoch": 0.4503809869375907,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004985392859025407,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.15167693346738814,
|
|
"num_tokens": 10302223.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.719541883468628,
|
|
"epoch": 0.45083454281567487,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004985356026336776,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.16071119904518127,
|
|
"num_tokens": 10312733.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.861865758895874,
|
|
"epoch": 0.4512880986937591,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004985319147420414,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.14967662692070008,
|
|
"num_tokens": 10323315.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.841590309143067,
|
|
"epoch": 0.45174165457184323,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004985282222277082,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.1541038677096367,
|
|
"num_tokens": 10333633.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.7527015209198,
|
|
"epoch": 0.45219521044992744,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004985245250907544,
|
|
"loss": 5.7756,
|
|
"mean_token_accuracy": 0.14761256128549577,
|
|
"num_tokens": 10343410.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.879261684417725,
|
|
"epoch": 0.4526487663280116,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004985208233312564,
|
|
"loss": 5.7913,
|
|
"mean_token_accuracy": 0.14990729242563247,
|
|
"num_tokens": 10354029.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.8652578830719,
|
|
"epoch": 0.4531023222060958,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004985171169492908,
|
|
"loss": 5.7681,
|
|
"mean_token_accuracy": 0.14575513750314711,
|
|
"num_tokens": 10364875.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.772519302368164,
|
|
"epoch": 0.45355587808417996,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004985134059449344,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.15330636352300644,
|
|
"num_tokens": 10374127.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.794177436828614,
|
|
"epoch": 0.4540094339622642,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004985096903182637,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.15620183944702148,
|
|
"num_tokens": 10384583.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.832924699783325,
|
|
"epoch": 0.45446298984034833,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004985059700693557,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.14847754538059235,
|
|
"num_tokens": 10394476.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.807150220870971,
|
|
"epoch": 0.4549165457184325,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004985022451982872,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.14492400586605073,
|
|
"num_tokens": 10405558.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.819724702835083,
|
|
"epoch": 0.4553701015965167,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004984985157051354,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.15750367045402527,
|
|
"num_tokens": 10415746.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.732080554962158,
|
|
"epoch": 0.45582365747460085,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004984947815899774,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.15581783503293992,
|
|
"num_tokens": 10424824.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.7898101806640625,
|
|
"epoch": 0.45627721335268506,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004984910428528902,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.15406316369771958,
|
|
"num_tokens": 10434175.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.794450139999389,
|
|
"epoch": 0.4567307692307692,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004984872994939514,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.15420141369104384,
|
|
"num_tokens": 10444614.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.8216742992401125,
|
|
"epoch": 0.45718432510885343,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004984835515132382,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.14913367331027985,
|
|
"num_tokens": 10455605.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.80116376876831,
|
|
"epoch": 0.4576378809869376,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004984797989108282,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.148945339769125,
|
|
"num_tokens": 10466912.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.818288421630859,
|
|
"epoch": 0.4580914368650218,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004984760416867991,
|
|
"loss": 5.7743,
|
|
"mean_token_accuracy": 0.1489511951804161,
|
|
"num_tokens": 10477762.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.873276567459106,
|
|
"epoch": 0.45854499274310595,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004984722798412286,
|
|
"loss": 5.7312,
|
|
"mean_token_accuracy": 0.14897401630878448,
|
|
"num_tokens": 10488203.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.770886850357056,
|
|
"epoch": 0.4589985486211901,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004984685133741941,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.15436122566461563,
|
|
"num_tokens": 10498174.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.735772180557251,
|
|
"epoch": 0.4594521044992743,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000498464742285774,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.14874908924102784,
|
|
"num_tokens": 10508591.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.72156777381897,
|
|
"epoch": 0.45990566037735847,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000498460966576046,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.15871575921773912,
|
|
"num_tokens": 10518364.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.797338390350342,
|
|
"epoch": 0.4603592162554427,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004984571862450884,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.1542142927646637,
|
|
"num_tokens": 10528646.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.673431062698365,
|
|
"epoch": 0.46081277213352684,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984534012929791,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.14974019974470137,
|
|
"num_tokens": 10539282.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.775971269607544,
|
|
"epoch": 0.46126632801161105,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004984496117197967,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.14850226193666458,
|
|
"num_tokens": 10549713.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.795759105682373,
|
|
"epoch": 0.4617198838896952,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004984458175256193,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.1567995548248291,
|
|
"num_tokens": 10559068.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.7790666103363035,
|
|
"epoch": 0.4621734397677794,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004984420187105253,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.16136553436517714,
|
|
"num_tokens": 10569633.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.74684739112854,
|
|
"epoch": 0.46262699564586357,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004984382152745936,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.15542976260185243,
|
|
"num_tokens": 10579833.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.7991992950439455,
|
|
"epoch": 0.4630805515239477,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004984344072179026,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.1511756382882595,
|
|
"num_tokens": 10590864.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.815202140808106,
|
|
"epoch": 0.46353410740203194,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004984305945405312,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.1536037266254425,
|
|
"num_tokens": 10601180.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.73317403793335,
|
|
"epoch": 0.4639876632801161,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000498426777242558,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.15111695379018783,
|
|
"num_tokens": 10611760.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.7392219543457035,
|
|
"epoch": 0.4644412191582003,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984229553240623,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.16025138944387435,
|
|
"num_tokens": 10621926.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.762211799621582,
|
|
"epoch": 0.46489477503628446,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004984191287851228,
|
|
"loss": 5.7128,
|
|
"mean_token_accuracy": 0.15515776872634887,
|
|
"num_tokens": 10632890.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.688881206512451,
|
|
"epoch": 0.46534833091436867,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004984152976258188,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.15708402097225188,
|
|
"num_tokens": 10642572.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.825290489196777,
|
|
"epoch": 0.4658018867924528,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984114618462296,
|
|
"loss": 5.7265,
|
|
"mean_token_accuracy": 0.14965202361345292,
|
|
"num_tokens": 10653732.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.750692415237427,
|
|
"epoch": 0.46625544267053703,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984076214464343,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.15400146842002868,
|
|
"num_tokens": 10664089.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.721158790588379,
|
|
"epoch": 0.4667089985486212,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004984037764265126,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.15426179766654968,
|
|
"num_tokens": 10674584.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.777506303787232,
|
|
"epoch": 0.46716255442670535,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004983999267865438,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.15464306250214577,
|
|
"num_tokens": 10686455.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.876712417602539,
|
|
"epoch": 0.46761611030478956,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004983960725266078,
|
|
"loss": 5.8241,
|
|
"mean_token_accuracy": 0.15148961544036865,
|
|
"num_tokens": 10697124.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.800732183456421,
|
|
"epoch": 0.4680696661828737,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004983922136467838,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.1556944265961647,
|
|
"num_tokens": 10707599.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.733756446838379,
|
|
"epoch": 0.4685232220609579,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000498388350147152,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.15888160169124604,
|
|
"num_tokens": 10717866.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.662814092636109,
|
|
"epoch": 0.4689767779390421,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004983844820277922,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.15497540682554245,
|
|
"num_tokens": 10728482.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.770923233032226,
|
|
"epoch": 0.4694303338171263,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004983806092887843,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.14423309415578842,
|
|
"num_tokens": 10738978.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.77985143661499,
|
|
"epoch": 0.46988388969521044,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004983767319302086,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.15800116062164307,
|
|
"num_tokens": 10749618.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.8202619552612305,
|
|
"epoch": 0.47033744557329465,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004983728499521451,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.15779803246259688,
|
|
"num_tokens": 10759799.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.807422113418579,
|
|
"epoch": 0.4707910014513788,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004983689633546741,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.15637572407722472,
|
|
"num_tokens": 10769807.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.704042100906372,
|
|
"epoch": 0.47124455732946297,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004983650721378761,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.15547890961170197,
|
|
"num_tokens": 10780185.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.692027235031128,
|
|
"epoch": 0.4716981132075472,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004983611763018314,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.1588817447423935,
|
|
"num_tokens": 10791383.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.7197267532348635,
|
|
"epoch": 0.47215166908563133,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004983572758466208,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.15821144729852676,
|
|
"num_tokens": 10801624.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.77974762916565,
|
|
"epoch": 0.47260522496371554,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004983533707723247,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.1483788952231407,
|
|
"num_tokens": 10813293.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.776114368438721,
|
|
"epoch": 0.4730587808417997,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004983494610790241,
|
|
"loss": 5.5876,
|
|
"mean_token_accuracy": 0.1604739934206009,
|
|
"num_tokens": 10822560.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.70116868019104,
|
|
"epoch": 0.4735123367198839,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004983455467667996,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15497548133134842,
|
|
"num_tokens": 10833360.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.777570104598999,
|
|
"epoch": 0.47396589259796806,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004983416278357322,
|
|
"loss": 5.7556,
|
|
"mean_token_accuracy": 0.14502900540828706,
|
|
"num_tokens": 10844189.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.829122018814087,
|
|
"epoch": 0.4744194484760523,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004983377042859032,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.14976238906383516,
|
|
"num_tokens": 10855478.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.74685378074646,
|
|
"epoch": 0.47487300435413643,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004983337761173936,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15890851616859436,
|
|
"num_tokens": 10866853.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.838531494140625,
|
|
"epoch": 0.4753265602322206,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004983298433302843,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.14805135056376456,
|
|
"num_tokens": 10877194.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.716617250442505,
|
|
"epoch": 0.4757801161103048,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004983259059246572,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.15317686796188354,
|
|
"num_tokens": 10887210.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.771576976776123,
|
|
"epoch": 0.47623367198838895,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004983219639005934,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.14675695747137069,
|
|
"num_tokens": 10897742.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.771367502212525,
|
|
"epoch": 0.47668722786647316,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004983180172581745,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.15986000001430511,
|
|
"num_tokens": 10907863.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.753606605529785,
|
|
"epoch": 0.4771407837445573,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004983140659974819,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.14626236334443093,
|
|
"num_tokens": 10918917.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.780586099624633,
|
|
"epoch": 0.47759433962264153,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004983101101185977,
|
|
"loss": 5.7255,
|
|
"mean_token_accuracy": 0.1551913544535637,
|
|
"num_tokens": 10928614.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.856214570999145,
|
|
"epoch": 0.4780478955007257,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004983061496216035,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.151229590177536,
|
|
"num_tokens": 10939093.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.854237842559814,
|
|
"epoch": 0.4785014513788099,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004983021845065812,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15564595758914948,
|
|
"num_tokens": 10949339.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.681471300125122,
|
|
"epoch": 0.47895500725689405,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004982982147736128,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.15276624113321305,
|
|
"num_tokens": 10959482.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.7495543479919435,
|
|
"epoch": 0.4794085631349782,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004982942404227805,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.15499285459518433,
|
|
"num_tokens": 10970158.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.805167818069458,
|
|
"epoch": 0.4798621190130624,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004982902614541662,
|
|
"loss": 5.6769,
|
|
"mean_token_accuracy": 0.14199863746762276,
|
|
"num_tokens": 10982399.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.797307109832763,
|
|
"epoch": 0.48031567489114657,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004982862778678526,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.14736454486846923,
|
|
"num_tokens": 10992319.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.838883543014527,
|
|
"epoch": 0.4807692307692308,
|
|
"grad_norm": 3.859375,
|
|
"learning_rate": 0.0004982822896639218,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.14749011844396592,
|
|
"num_tokens": 11001828.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.852616786956787,
|
|
"epoch": 0.48122278664731494,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004982782968424563,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.15126340687274933,
|
|
"num_tokens": 11011059.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.8091569423675535,
|
|
"epoch": 0.48167634252539915,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004982742994035388,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.15086904913187027,
|
|
"num_tokens": 11021621.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.729885625839233,
|
|
"epoch": 0.4821298984034833,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004982702973472518,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.1491677612066269,
|
|
"num_tokens": 11032763.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.83299446105957,
|
|
"epoch": 0.4825834542815675,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004982662906736783,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.16112029701471328,
|
|
"num_tokens": 11042568.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.766739845275879,
|
|
"epoch": 0.48303701015965167,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004982622793829009,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.1589931309223175,
|
|
"num_tokens": 11052475.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.688635396957397,
|
|
"epoch": 0.4834905660377358,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004982582634750027,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.160682412981987,
|
|
"num_tokens": 11062417.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.717385482788086,
|
|
"epoch": 0.48394412191582004,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004982542429500667,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.15277392864227296,
|
|
"num_tokens": 11072282.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.879451084136963,
|
|
"epoch": 0.4843976777939042,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004982502178081761,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.15068399012088776,
|
|
"num_tokens": 11083333.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.78740553855896,
|
|
"epoch": 0.4848512336719884,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004982461880494141,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.1521876037120819,
|
|
"num_tokens": 11094094.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.790024709701538,
|
|
"epoch": 0.48530478955007256,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000498242153673864,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.1470420092344284,
|
|
"num_tokens": 11103999.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.805356550216675,
|
|
"epoch": 0.48575834542815677,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004982381146816094,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.15599775463342666,
|
|
"num_tokens": 11113459.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.768607950210571,
|
|
"epoch": 0.4862119013062409,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004982340710727336,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.1512758806347847,
|
|
"num_tokens": 11124743.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.793423318862915,
|
|
"epoch": 0.48666545718432513,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004982300228473203,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.15485051274299622,
|
|
"num_tokens": 11134953.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.773527050018311,
|
|
"epoch": 0.4871190130624093,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004982259700054533,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.15058848708868028,
|
|
"num_tokens": 11145275.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.723573064804077,
|
|
"epoch": 0.48757256894049344,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004982219125472163,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.15825372338294982,
|
|
"num_tokens": 11155155.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.732001161575317,
|
|
"epoch": 0.48802612481857766,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004982178504726933,
|
|
"loss": 5.648,
|
|
"mean_token_accuracy": 0.1569226548075676,
|
|
"num_tokens": 11165269.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.879735612869263,
|
|
"epoch": 0.4884796806966618,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004982137837819682,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.14773210883140564,
|
|
"num_tokens": 11175499.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.779443979263306,
|
|
"epoch": 0.488933236574746,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004982097124751252,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.14961470663547516,
|
|
"num_tokens": 11185662.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.7722508907318115,
|
|
"epoch": 0.4893867924528302,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004982056365522486,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.15671695321798323,
|
|
"num_tokens": 11196070.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.871857929229736,
|
|
"epoch": 0.4898403483309144,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004982015560134225,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.14437031298875808,
|
|
"num_tokens": 11209101.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.787049436569214,
|
|
"epoch": 0.49029390420899854,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981974708587312,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.1474752552807331,
|
|
"num_tokens": 11219828.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.812083530426025,
|
|
"epoch": 0.49074746008708275,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004981933810882594,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.15424271821975707,
|
|
"num_tokens": 11230681.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.779886293411255,
|
|
"epoch": 0.4912010159651669,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004981892867020917,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.14833626002073289,
|
|
"num_tokens": 11241963.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.785884189605713,
|
|
"epoch": 0.49165457184325106,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004981851877003125,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.14686497002840043,
|
|
"num_tokens": 11252950.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.7913336753845215,
|
|
"epoch": 0.4921081277213353,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004981810840830068,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.1526445686817169,
|
|
"num_tokens": 11262486.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.761009216308594,
|
|
"epoch": 0.49256168359941943,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004981769758502596,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15411523282527922,
|
|
"num_tokens": 11272950.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.753162050247193,
|
|
"epoch": 0.49301523947750364,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004981728630021555,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.1500825673341751,
|
|
"num_tokens": 11284775.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.908806085586548,
|
|
"epoch": 0.4934687953555878,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004981687455387797,
|
|
"loss": 5.6757,
|
|
"mean_token_accuracy": 0.15840519815683365,
|
|
"num_tokens": 11294810.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.816017150878906,
|
|
"epoch": 0.493922351233672,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004981646234602173,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.15476290434598922,
|
|
"num_tokens": 11306728.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.753983831405639,
|
|
"epoch": 0.49437590711175616,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004981604967665539,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.1476845324039459,
|
|
"num_tokens": 11317929.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.791211032867432,
|
|
"epoch": 0.4948294629898404,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004981563654578743,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.15718991905450821,
|
|
"num_tokens": 11327864.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.767108821868897,
|
|
"epoch": 0.49528301886792453,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004981522295342643,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.15040411800146103,
|
|
"num_tokens": 11337965.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.6784430027008055,
|
|
"epoch": 0.4957365747460087,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004981480889958092,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.15154165476560594,
|
|
"num_tokens": 11348942.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.779708576202393,
|
|
"epoch": 0.4961901306240929,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004981439438425949,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.15476672053337098,
|
|
"num_tokens": 11359702.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.912676811218262,
|
|
"epoch": 0.49664368650217705,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000498139794074707,
|
|
"loss": 5.8274,
|
|
"mean_token_accuracy": 0.14696455523371696,
|
|
"num_tokens": 11370238.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.7378565788269045,
|
|
"epoch": 0.49709724238026126,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004981356396922313,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.15095601379871368,
|
|
"num_tokens": 11380822.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.7243176937103275,
|
|
"epoch": 0.4975507982583454,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004981314806952535,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.1527250073850155,
|
|
"num_tokens": 11391858.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.761184549331665,
|
|
"epoch": 0.49800435413642963,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00049812731708386,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.16142940223217012,
|
|
"num_tokens": 11402036.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.7568670272827145,
|
|
"epoch": 0.4984579100145138,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004981231488581367,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14541575014591218,
|
|
"num_tokens": 11413242.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.818656730651855,
|
|
"epoch": 0.498911465892598,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004981189760181699,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15886023342609407,
|
|
"num_tokens": 11422927.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.790579175949096,
|
|
"epoch": 0.49936502177068215,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004981147985640456,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.15862198173999786,
|
|
"num_tokens": 11432669.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.771609878540039,
|
|
"epoch": 0.4998185776487663,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004981106164958506,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.152798593044281,
|
|
"num_tokens": 11442823.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.74314432144165,
|
|
"epoch": 0.5002721335268505,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004981064298136712,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.15345294028520584,
|
|
"num_tokens": 11453583.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.6962987899780275,
|
|
"epoch": 0.5007256894049347,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004981022385175939,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1497638240456581,
|
|
"num_tokens": 11463883.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.7916618347167965,
|
|
"epoch": 0.5011792452830188,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004980980426077054,
|
|
"loss": 5.6823,
|
|
"mean_token_accuracy": 0.14812253117561341,
|
|
"num_tokens": 11473966.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.681837892532348,
|
|
"epoch": 0.5016328011611031,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004980938420840926,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.1510275721549988,
|
|
"num_tokens": 11483898.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.684164094924927,
|
|
"epoch": 0.5020863570391872,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004980896369468423,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.15556384176015853,
|
|
"num_tokens": 11494190.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.841269779205322,
|
|
"epoch": 0.5025399129172714,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004980854271960415,
|
|
"loss": 5.7433,
|
|
"mean_token_accuracy": 0.1519545204937458,
|
|
"num_tokens": 11505339.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.82388334274292,
|
|
"epoch": 0.5029934687953556,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004980812128317772,
|
|
"loss": 5.7438,
|
|
"mean_token_accuracy": 0.15373214781284333,
|
|
"num_tokens": 11515892.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.760100889205932,
|
|
"epoch": 0.5034470246734397,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004980769938541364,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.15700885728001596,
|
|
"num_tokens": 11526540.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.811464118957519,
|
|
"epoch": 0.503900580551524,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004980727702632066,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.15401896983385086,
|
|
"num_tokens": 11536604.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.7957395076751705,
|
|
"epoch": 0.5043541364296081,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004980685420590752,
|
|
"loss": 5.7418,
|
|
"mean_token_accuracy": 0.15740367621183396,
|
|
"num_tokens": 11546764.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.724511289596558,
|
|
"epoch": 0.5048076923076923,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004980643092418294,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15534376949071885,
|
|
"num_tokens": 11556984.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.773011779785156,
|
|
"epoch": 0.5052612481857764,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004980600718115568,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.16305769681930543,
|
|
"num_tokens": 11567046.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.753465414047241,
|
|
"epoch": 0.5057148040638607,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004980558297683452,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.14825989305973053,
|
|
"num_tokens": 11577575.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.703629446029663,
|
|
"epoch": 0.5061683599419449,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004980515831122822,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.15776239931583405,
|
|
"num_tokens": 11587322.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.697418451309204,
|
|
"epoch": 0.506621915820029,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004980473318434555,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.16032545566558837,
|
|
"num_tokens": 11597544.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.7857341289520265,
|
|
"epoch": 0.5070754716981132,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004980430759619532,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.15705069452524184,
|
|
"num_tokens": 11607538.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.769230747222901,
|
|
"epoch": 0.5075290275761973,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004980388154678633,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.15760140269994735,
|
|
"num_tokens": 11617082.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.685442399978638,
|
|
"epoch": 0.5079825834542816,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004980345503612738,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.1552373379468918,
|
|
"num_tokens": 11627233.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.776123332977295,
|
|
"epoch": 0.5084361393323658,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004980302806422729,
|
|
"loss": 5.637,
|
|
"mean_token_accuracy": 0.1540546879172325,
|
|
"num_tokens": 11637520.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.741995143890381,
|
|
"epoch": 0.5088896952104499,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004980260063109491,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.1525841623544693,
|
|
"num_tokens": 11647525.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.774639463424682,
|
|
"epoch": 0.5093432510885341,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004980217273673906,
|
|
"loss": 5.6436,
|
|
"mean_token_accuracy": 0.15127140432596206,
|
|
"num_tokens": 11657996.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.770473194122315,
|
|
"epoch": 0.5097968069666183,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004980174438116859,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.15702126920223236,
|
|
"num_tokens": 11668752.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.724298429489136,
|
|
"epoch": 0.5102503628447025,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004980131556439236,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.1514161080121994,
|
|
"num_tokens": 11678989.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.748479270935059,
|
|
"epoch": 0.5107039187227866,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004980088628641925,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.1639922246336937,
|
|
"num_tokens": 11687907.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.693242740631104,
|
|
"epoch": 0.5111574746008708,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004980045654725812,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.1565706640481949,
|
|
"num_tokens": 11698293.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.8007673740386965,
|
|
"epoch": 0.511611030478955,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004980002634691787,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.14153425469994546,
|
|
"num_tokens": 11708142.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.827743053436279,
|
|
"epoch": 0.5120645863570392,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000497995956854074,
|
|
"loss": 5.8451,
|
|
"mean_token_accuracy": 0.14463640600442887,
|
|
"num_tokens": 11719472.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.9134735584259035,
|
|
"epoch": 0.5125181422351234,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004979916456273561,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.153484570980072,
|
|
"num_tokens": 11729689.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.771580600738526,
|
|
"epoch": 0.5129716981132075,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004979873297891141,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.15919430255889894,
|
|
"num_tokens": 11739222.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.761745595932007,
|
|
"epoch": 0.5134252539912917,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004979830093394372,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.15483780205249786,
|
|
"num_tokens": 11749043.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.756465101242066,
|
|
"epoch": 0.513878809869376,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004979786842784149,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.15349172800779343,
|
|
"num_tokens": 11759231.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.753206396102906,
|
|
"epoch": 0.5143323657474601,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004979743546061366,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.16228333860635757,
|
|
"num_tokens": 11768380.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.758825826644897,
|
|
"epoch": 0.5147859216255443,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979700203226918,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.14961437582969667,
|
|
"num_tokens": 11780101.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.7383798122406,
|
|
"epoch": 0.5152394775036284,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004979656814281702,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.1545555830001831,
|
|
"num_tokens": 11790524.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.727444219589233,
|
|
"epoch": 0.5156930333817126,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004979613379226615,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.15359244793653487,
|
|
"num_tokens": 11801393.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.752847623825073,
|
|
"epoch": 0.5161465892597968,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004979569898062554,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.16035476624965667,
|
|
"num_tokens": 11811117.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.701114749908447,
|
|
"epoch": 0.516600145137881,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000497952637079042,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.160872420668602,
|
|
"num_tokens": 11821389.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.75704665184021,
|
|
"epoch": 0.5170537010159652,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004979482797411114,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.16205394864082337,
|
|
"num_tokens": 11831082.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.7467203617095945,
|
|
"epoch": 0.5175072568940493,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004979439177925534,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.15308979004621506,
|
|
"num_tokens": 11841617.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.701697063446045,
|
|
"epoch": 0.5179608127721336,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004979395512334584,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.1621819481253624,
|
|
"num_tokens": 11851643.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.769807004928589,
|
|
"epoch": 0.5184143686502177,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979351800639166,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.144927167147398,
|
|
"num_tokens": 11862619.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.7512876987457275,
|
|
"epoch": 0.5188679245283019,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004979308042840186,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.15768488347530366,
|
|
"num_tokens": 11873574.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.751497602462768,
|
|
"epoch": 0.519321480406386,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004979264238938547,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.15962153673171997,
|
|
"num_tokens": 11883472.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.769440221786499,
|
|
"epoch": 0.5197750362844702,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004979220388935155,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.15895968824625015,
|
|
"num_tokens": 11894531.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.696563959121704,
|
|
"epoch": 0.5202285921625545,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004979176492830918,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.14857350289821625,
|
|
"num_tokens": 11905141.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.85057373046875,
|
|
"epoch": 0.5206821480406386,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004979132550626742,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.15559621453285216,
|
|
"num_tokens": 11916687.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.7491716861724855,
|
|
"epoch": 0.5211357039187228,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004979088562323538,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.1574707433581352,
|
|
"num_tokens": 11926722.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.713038301467895,
|
|
"epoch": 0.5215892597968069,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004979044527922214,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.1492026314139366,
|
|
"num_tokens": 11937268.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.701345777511596,
|
|
"epoch": 0.5220428156748912,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004979000447423681,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1611389324069023,
|
|
"num_tokens": 11947018.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.72505750656128,
|
|
"epoch": 0.5224963715529753,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004978956320828851,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.1561354696750641,
|
|
"num_tokens": 11956468.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.6504326343536375,
|
|
"epoch": 0.5229499274310595,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004978912148138637,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.1537265494465828,
|
|
"num_tokens": 11968206.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.73058066368103,
|
|
"epoch": 0.5234034833091437,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000497886792935395,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.15298595577478408,
|
|
"num_tokens": 11978513.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.773151540756226,
|
|
"epoch": 0.5238570391872278,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004978823664475707,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.15904878526926042,
|
|
"num_tokens": 11987995.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.708344984054565,
|
|
"epoch": 0.5243105950653121,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004978779353504824,
|
|
"loss": 5.6095,
|
|
"mean_token_accuracy": 0.1586873337626457,
|
|
"num_tokens": 11998142.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.680955839157105,
|
|
"epoch": 0.5247641509433962,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004978734996442214,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.1532874196767807,
|
|
"num_tokens": 12008640.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.74573163986206,
|
|
"epoch": 0.5252177068214804,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004978690593288798,
|
|
"loss": 5.6922,
|
|
"mean_token_accuracy": 0.15569562315940857,
|
|
"num_tokens": 12018481.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.796635341644287,
|
|
"epoch": 0.5256712626995645,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004978646144045491,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.14771561920642853,
|
|
"num_tokens": 12029230.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.70799150466919,
|
|
"epoch": 0.5261248185776488,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004978601648713215,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.15939762741327285,
|
|
"num_tokens": 12039194.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.741345453262329,
|
|
"epoch": 0.526578374455733,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004978557107292889,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.1500698059797287,
|
|
"num_tokens": 12049946.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.745180892944336,
|
|
"epoch": 0.5270319303338171,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.0004978512519785433,
|
|
"loss": 5.6339,
|
|
"mean_token_accuracy": 0.158860544860363,
|
|
"num_tokens": 12059961.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.831522703170776,
|
|
"epoch": 0.5274854862119013,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000497846788619177,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.14821714609861375,
|
|
"num_tokens": 12072787.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.755320024490357,
|
|
"epoch": 0.5279390420899854,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004978423206512825,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15618030428886415,
|
|
"num_tokens": 12082658.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.598514795303345,
|
|
"epoch": 0.5283925979680697,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.000497837848074952,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.16532057225704194,
|
|
"num_tokens": 12092906.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.697569561004639,
|
|
"epoch": 0.5288461538461539,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000497833370890278,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.15202219635248185,
|
|
"num_tokens": 12103659.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.728899145126343,
|
|
"epoch": 0.529299709724238,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004978288890973529,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.1601557657122612,
|
|
"num_tokens": 12113202.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.752268695831299,
|
|
"epoch": 0.5297532656023222,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004978244026962698,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.1585050493478775,
|
|
"num_tokens": 12123066.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.8051200866699215,
|
|
"epoch": 0.5302068214804064,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004978199116871212,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.14660870134830475,
|
|
"num_tokens": 12134288.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.806707048416138,
|
|
"epoch": 0.5306603773584906,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00049781541607,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.1543032556772232,
|
|
"num_tokens": 12146080.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.827581071853638,
|
|
"epoch": 0.5311139332365747,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004978109158449993,
|
|
"loss": 5.6961,
|
|
"mean_token_accuracy": 0.1560826063156128,
|
|
"num_tokens": 12156670.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.715680170059204,
|
|
"epoch": 0.5315674891146589,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004978064110122121,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.14724010676145555,
|
|
"num_tokens": 12168004.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.7901379585266115,
|
|
"epoch": 0.532021044992743,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004978019015717314,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.15376669615507127,
|
|
"num_tokens": 12178833.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.7304534912109375,
|
|
"epoch": 0.5324746008708273,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004977973875236508,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.1504141353070736,
|
|
"num_tokens": 12189357.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.748328971862793,
|
|
"epoch": 0.5329281567489115,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004977928688680634,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.1567172586917877,
|
|
"num_tokens": 12199023.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.787635803222656,
|
|
"epoch": 0.5333817126269956,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004977883456050626,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.14763975739479065,
|
|
"num_tokens": 12208789.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.852936601638794,
|
|
"epoch": 0.5338352685050798,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000497783817734742,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.15545896589756011,
|
|
"num_tokens": 12219483.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.809611368179321,
|
|
"epoch": 0.534288824383164,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004977792852571954,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.1538556322455406,
|
|
"num_tokens": 12229552.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.725105571746826,
|
|
"epoch": 0.5347423802612482,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004977747481725164,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.16032094955444337,
|
|
"num_tokens": 12239378.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.750143003463745,
|
|
"epoch": 0.5351959361393324,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004977702064807987,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.15214105546474457,
|
|
"num_tokens": 12249496.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.839286422729492,
|
|
"epoch": 0.5356494920174165,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004977656601821366,
|
|
"loss": 5.7695,
|
|
"mean_token_accuracy": 0.14929212182760238,
|
|
"num_tokens": 12259099.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.7886841773986815,
|
|
"epoch": 0.5361030478955007,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004977611092766238,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1530821517109871,
|
|
"num_tokens": 12269578.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.820439577102661,
|
|
"epoch": 0.5365566037735849,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004977565537643544,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.14760151132941246,
|
|
"num_tokens": 12280210.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.659420204162598,
|
|
"epoch": 0.5370101596516691,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004977519936454227,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16010452359914779,
|
|
"num_tokens": 12290830.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.735601472854614,
|
|
"epoch": 0.5374637155297532,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004977474289199231,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.1563941493630409,
|
|
"num_tokens": 12300233.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.7761067867279055,
|
|
"epoch": 0.5379172714078374,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004977428595879499,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.15967603921890258,
|
|
"num_tokens": 12310578.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.757687091827393,
|
|
"epoch": 0.5383708272859217,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004977382856495975,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.15673843175172805,
|
|
"num_tokens": 12320484.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.719855117797851,
|
|
"epoch": 0.5388243831640058,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 0.0004977337071049606,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.14939573258161545,
|
|
"num_tokens": 12331518.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.722897338867187,
|
|
"epoch": 0.53927793904209,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.000497729123954134,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.1570252627134323,
|
|
"num_tokens": 12342478.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.740108633041382,
|
|
"epoch": 0.5397314949201741,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004977245361972123,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.1535571664571762,
|
|
"num_tokens": 12352811.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.745780086517334,
|
|
"epoch": 0.5401850507982583,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004977199438342904,
|
|
"loss": 5.6519,
|
|
"mean_token_accuracy": 0.15965785086154938,
|
|
"num_tokens": 12363948.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.808036136627197,
|
|
"epoch": 0.5406386066763426,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004977153468654634,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.15435378551483153,
|
|
"num_tokens": 12373910.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.761662864685059,
|
|
"epoch": 0.5410921625544267,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004977107452908262,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.15638811737298966,
|
|
"num_tokens": 12385038.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.729135322570801,
|
|
"epoch": 0.5415457184325109,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000497706139110474,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.15953594893217088,
|
|
"num_tokens": 12395500.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.771009159088135,
|
|
"epoch": 0.541999274310595,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004977015283245021,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.1496681362390518,
|
|
"num_tokens": 12406249.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.748795080184936,
|
|
"epoch": 0.5424528301886793,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004976969129330059,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.15583853870630265,
|
|
"num_tokens": 12416685.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.776485395431519,
|
|
"epoch": 0.5429063860667634,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004976922929360808,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.15829548090696335,
|
|
"num_tokens": 12426794.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.757869243621826,
|
|
"epoch": 0.5433599419448476,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004976876683338222,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.15154862105846406,
|
|
"num_tokens": 12437115.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.823219347000122,
|
|
"epoch": 0.5438134978229318,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000497683039126326,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15575422197580338,
|
|
"num_tokens": 12446955.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.754256916046143,
|
|
"epoch": 0.5442670537010159,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004976784053136878,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.16049512177705766,
|
|
"num_tokens": 12456924.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5442670537010159,
|
|
"eval_entropy": 5.567713360225453,
|
|
"eval_loss": 5.68149471282959,
|
|
"eval_mean_token_accuracy": 0.16022676651142706,
|
|
"eval_num_tokens": 12456924.0,
|
|
"eval_runtime": 26.6019,
|
|
"eval_samples_per_second": 1329.227,
|
|
"eval_steps_per_second": 166.153,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.656931829452515,
|
|
"epoch": 0.5447206095791002,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004976737668960034,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.16199954599142075,
|
|
"num_tokens": 12467712.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.799897336959839,
|
|
"epoch": 0.5451741654571843,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004976691238733688,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15725044012069703,
|
|
"num_tokens": 12477374.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.818873882293701,
|
|
"epoch": 0.5456277213352685,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00049766447624588,
|
|
"loss": 5.7068,
|
|
"mean_token_accuracy": 0.15485058575868607,
|
|
"num_tokens": 12488038.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.812593078613281,
|
|
"epoch": 0.5460812772133526,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000497659824013633,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.16121876537799834,
|
|
"num_tokens": 12498393.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.676734733581543,
|
|
"epoch": 0.5465348330914369,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004976551671767241,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.15978361070156097,
|
|
"num_tokens": 12507926.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.705279302597046,
|
|
"epoch": 0.5469883889695211,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004976505057352496,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.1612431913614273,
|
|
"num_tokens": 12517835.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.756604337692261,
|
|
"epoch": 0.5474419448476052,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004976458396893059,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.14765057265758513,
|
|
"num_tokens": 12528067.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.684308671951294,
|
|
"epoch": 0.5478955007256894,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004976411690389896,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.15649594962596894,
|
|
"num_tokens": 12537583.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.780689907073975,
|
|
"epoch": 0.5483490566037735,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000497636493784397,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.1508394107222557,
|
|
"num_tokens": 12548750.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.810310411453247,
|
|
"epoch": 0.5488026124818578,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004976318139256251,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.1568623587489128,
|
|
"num_tokens": 12560197.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.8327185153961185,
|
|
"epoch": 0.549256168359942,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004976271294627706,
|
|
"loss": 5.7512,
|
|
"mean_token_accuracy": 0.15411142259836197,
|
|
"num_tokens": 12570958.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.764525985717773,
|
|
"epoch": 0.5497097242380261,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004976224403959303,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.14998921155929565,
|
|
"num_tokens": 12581525.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.765351819992065,
|
|
"epoch": 0.5501632801161103,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004976177467252012,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.15715673416852952,
|
|
"num_tokens": 12591765.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.695242023468017,
|
|
"epoch": 0.5506168359941945,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004976130484506804,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16310595273971557,
|
|
"num_tokens": 12602471.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.756214284896851,
|
|
"epoch": 0.5510703918722787,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004976083455724649,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15674155652523042,
|
|
"num_tokens": 12613656.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.754758644104004,
|
|
"epoch": 0.5515239477503628,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004976036380906523,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.153932623565197,
|
|
"num_tokens": 12623922.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.739032125473022,
|
|
"epoch": 0.551977503628447,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975989260053395,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.14958422929048537,
|
|
"num_tokens": 12634213.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.745124387741089,
|
|
"epoch": 0.5524310595065312,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004975942093166242,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.15570274442434312,
|
|
"num_tokens": 12643154.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.684883737564087,
|
|
"epoch": 0.5528846153846154,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004975894880246041,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.15252370536327362,
|
|
"num_tokens": 12654533.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.738387107849121,
|
|
"epoch": 0.5533381712626996,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004975847621293766,
|
|
"loss": 5.6101,
|
|
"mean_token_accuracy": 0.15831225514411926,
|
|
"num_tokens": 12663417.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.799705648422242,
|
|
"epoch": 0.5537917271407837,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004975800316310394,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.16197383552789688,
|
|
"num_tokens": 12673301.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.688973093032837,
|
|
"epoch": 0.5542452830188679,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004975752965296906,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.1532282665371895,
|
|
"num_tokens": 12684343.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.712090110778808,
|
|
"epoch": 0.5546988388969522,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004975705568254278,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.15773797631263733,
|
|
"num_tokens": 12694513.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.777080440521241,
|
|
"epoch": 0.5551523947750363,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004975658125183493,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.1541421577334404,
|
|
"num_tokens": 12704778.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.689303159713745,
|
|
"epoch": 0.5556059506531205,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000497561063608553,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.16233552545309066,
|
|
"num_tokens": 12714171.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.755212259292603,
|
|
"epoch": 0.5560595065312046,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004975563100961372,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.1541602686047554,
|
|
"num_tokens": 12724792.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.836889219284058,
|
|
"epoch": 0.5565130624092888,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004975515519812002,
|
|
"loss": 5.6838,
|
|
"mean_token_accuracy": 0.15421807914972305,
|
|
"num_tokens": 12735737.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.7207098484039305,
|
|
"epoch": 0.556966618287373,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004975467892638402,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.15962569713592528,
|
|
"num_tokens": 12745640.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.719398260116577,
|
|
"epoch": 0.5574201741654572,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004975420219441561,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.15408140271902085,
|
|
"num_tokens": 12756374.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.6853748798370365,
|
|
"epoch": 0.5578737300435413,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004975372500222462,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.1519828200340271,
|
|
"num_tokens": 12767399.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.724702787399292,
|
|
"epoch": 0.5583272859216255,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004975324734982094,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.15775190591812133,
|
|
"num_tokens": 12777890.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.760837507247925,
|
|
"epoch": 0.5587808417997098,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004975276923721442,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.1617153435945511,
|
|
"num_tokens": 12788094.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.804059791564941,
|
|
"epoch": 0.5592343976777939,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004975229066441496,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.1464136704802513,
|
|
"num_tokens": 12799365.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.7211967468261715,
|
|
"epoch": 0.5596879535558781,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004975181163143247,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.16188412457704543,
|
|
"num_tokens": 12808856.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.753667974472046,
|
|
"epoch": 0.5601415094339622,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004975133213827684,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.1628005862236023,
|
|
"num_tokens": 12818354.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.742711210250855,
|
|
"epoch": 0.5605950653120464,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004975085218495798,
|
|
"loss": 5.6906,
|
|
"mean_token_accuracy": 0.15329492092132568,
|
|
"num_tokens": 12829263.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.8331944942474365,
|
|
"epoch": 0.5610486211901307,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004975037177148585,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.15159093886613845,
|
|
"num_tokens": 12840000.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.762791109085083,
|
|
"epoch": 0.5615021770682148,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004974989089787035,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.14673184007406234,
|
|
"num_tokens": 12850632.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.7715616703033445,
|
|
"epoch": 0.561955732946299,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004974940956412143,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15445255488157272,
|
|
"num_tokens": 12860834.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.722901725769043,
|
|
"epoch": 0.5624092888243831,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004974892777024905,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.16279343515634537,
|
|
"num_tokens": 12871267.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.717096328735352,
|
|
"epoch": 0.5628628447024674,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004974844551626318,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.15960216373205185,
|
|
"num_tokens": 12881601.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.685572910308838,
|
|
"epoch": 0.5633164005805515,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004974796280217379,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1577148512005806,
|
|
"num_tokens": 12891872.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.670578336715698,
|
|
"epoch": 0.5637699564586357,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004974747962799086,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.15749485790729523,
|
|
"num_tokens": 12901408.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.73646183013916,
|
|
"epoch": 0.5642235123367199,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004974699599372437,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.14751680940389633,
|
|
"num_tokens": 12911830.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.7733705043792725,
|
|
"epoch": 0.564677068214804,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004974651189938434,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.16175662279129027,
|
|
"num_tokens": 12921974.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.6916648864746096,
|
|
"epoch": 0.5651306240928883,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004974602734498079,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.1593949794769287,
|
|
"num_tokens": 12932504.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.777950477600098,
|
|
"epoch": 0.5655841799709724,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000497455423305237,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.15056953430175782,
|
|
"num_tokens": 12942800.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.796639394760132,
|
|
"epoch": 0.5660377358490566,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004974505685602314,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.15575093477964402,
|
|
"num_tokens": 12952718.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.704430627822876,
|
|
"epoch": 0.5664912917271407,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004974457092148912,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.15887019783258438,
|
|
"num_tokens": 12962233.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.628510761260986,
|
|
"epoch": 0.566944847605225,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004974408452693172,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.1609184190630913,
|
|
"num_tokens": 12972177.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.69896502494812,
|
|
"epoch": 0.5673984034833092,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004974359767236099,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.15473490655422212,
|
|
"num_tokens": 12984282.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.79969048500061,
|
|
"epoch": 0.5678519593613933,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004974311035778698,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.1635651931166649,
|
|
"num_tokens": 12994541.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.725707530975342,
|
|
"epoch": 0.5683055152394775,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004974262258321979,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.15191208347678184,
|
|
"num_tokens": 13005417.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.8123057842254635,
|
|
"epoch": 0.5687590711175616,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004974213434866949,
|
|
"loss": 5.8124,
|
|
"mean_token_accuracy": 0.14900366365909576,
|
|
"num_tokens": 13015665.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.83261456489563,
|
|
"epoch": 0.5692126269956459,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004974164565414617,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.15868498533964157,
|
|
"num_tokens": 13025677.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.756546258926392,
|
|
"epoch": 0.56966618287373,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004974115649965998,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.1580974504351616,
|
|
"num_tokens": 13037539.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.594256162643433,
|
|
"epoch": 0.5701197387518142,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004974066688522098,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.14920975863933564,
|
|
"num_tokens": 13048520.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.690824413299561,
|
|
"epoch": 0.5705732946298984,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004974017681083934,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.15977879911661147,
|
|
"num_tokens": 13058751.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.809173583984375,
|
|
"epoch": 0.5710268505079826,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004973968627652516,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.15209317505359649,
|
|
"num_tokens": 13068808.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.700589227676391,
|
|
"epoch": 0.5714804063860668,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000497391952822886,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.15689846128225327,
|
|
"num_tokens": 13078602.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.748346757888794,
|
|
"epoch": 0.5719339622641509,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004973870382813983,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.15334153771400452,
|
|
"num_tokens": 13088628.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.744019412994385,
|
|
"epoch": 0.5723875181422351,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004973821191408899,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16003611981868743,
|
|
"num_tokens": 13097938.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.781156444549561,
|
|
"epoch": 0.5728410740203193,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004973771954014626,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.15123680084943772,
|
|
"num_tokens": 13107574.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.764164829254151,
|
|
"epoch": 0.5732946298984035,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004973722670632182,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.15441531240940093,
|
|
"num_tokens": 13117617.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.778414916992188,
|
|
"epoch": 0.5737481857764877,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004973673341262587,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.1492793843150139,
|
|
"num_tokens": 13128580.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.809693336486816,
|
|
"epoch": 0.5742017416545718,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.000497362396590686,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.15329949483275412,
|
|
"num_tokens": 13139114.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.781783246994019,
|
|
"epoch": 0.574655297532656,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004973574544566024,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.15328806936740874,
|
|
"num_tokens": 13148195.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.687791872024536,
|
|
"epoch": 0.5751088534107403,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004973525077241098,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.15689401775598527,
|
|
"num_tokens": 13159018.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.711198997497559,
|
|
"epoch": 0.5755624092888244,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004973475563933109,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.16024598926305772,
|
|
"num_tokens": 13169257.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.754970455169678,
|
|
"epoch": 0.5760159651669086,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004973426004643077,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.1545379042625427,
|
|
"num_tokens": 13180009.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.736854362487793,
|
|
"epoch": 0.5764695210449927,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004973376399372029,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.15409892797470093,
|
|
"num_tokens": 13190828.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.788819360733032,
|
|
"epoch": 0.5769230769230769,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004973326748120991,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15394369661808013,
|
|
"num_tokens": 13202037.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.778576374053955,
|
|
"epoch": 0.5773766328011611,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004973277050890988,
|
|
"loss": 5.6793,
|
|
"mean_token_accuracy": 0.15594272464513778,
|
|
"num_tokens": 13212105.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.913066387176514,
|
|
"epoch": 0.5778301886792453,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004973227307683049,
|
|
"loss": 5.8369,
|
|
"mean_token_accuracy": 0.14454605802893639,
|
|
"num_tokens": 13222643.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.719876337051391,
|
|
"epoch": 0.5782837445573294,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004973177518498204,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.15246522575616836,
|
|
"num_tokens": 13232009.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.771259593963623,
|
|
"epoch": 0.5787373004354136,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004973127683337482,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.14938376992940902,
|
|
"num_tokens": 13243084.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.844303846359253,
|
|
"epoch": 0.5791908563134979,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004973077802201911,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.14356016516685485,
|
|
"num_tokens": 13254065.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.796073770523071,
|
|
"epoch": 0.579644412191582,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004973027875092526,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.1564701795578003,
|
|
"num_tokens": 13263239.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.830417013168335,
|
|
"epoch": 0.5800979680696662,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004972977902010357,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.15366180315613748,
|
|
"num_tokens": 13273917.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.757380867004395,
|
|
"epoch": 0.5805515239477503,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004972927882956439,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.16490886062383653,
|
|
"num_tokens": 13283695.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.76453332901001,
|
|
"epoch": 0.5810050798258345,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004972877817931807,
|
|
"loss": 5.6334,
|
|
"mean_token_accuracy": 0.16031342446804048,
|
|
"num_tokens": 13293691.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.77696533203125,
|
|
"epoch": 0.5814586357039188,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004972827706937493,
|
|
"loss": 5.7093,
|
|
"mean_token_accuracy": 0.15516743883490564,
|
|
"num_tokens": 13304973.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.698088932037353,
|
|
"epoch": 0.5819121915820029,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004972777549974537,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.1618632659316063,
|
|
"num_tokens": 13313968.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.772373199462891,
|
|
"epoch": 0.5823657474600871,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004972727347043975,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.1542307913303375,
|
|
"num_tokens": 13325086.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.764491415023803,
|
|
"epoch": 0.5828193033381712,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004972677098146845,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.15369413495063783,
|
|
"num_tokens": 13335937.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.808954524993896,
|
|
"epoch": 0.5832728592162555,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004972626803284185,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.15450548529624938,
|
|
"num_tokens": 13346227.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.73987832069397,
|
|
"epoch": 0.5837264150943396,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004972576462457038,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.1589360609650612,
|
|
"num_tokens": 13355536.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.779764604568482,
|
|
"epoch": 0.5841799709724238,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004972526075666442,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.1520060807466507,
|
|
"num_tokens": 13367027.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.719965982437134,
|
|
"epoch": 0.584633526850508,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004972475642913442,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.15796410590410231,
|
|
"num_tokens": 13377079.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.715342378616333,
|
|
"epoch": 0.5850870827285921,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004972425164199078,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.16331557035446168,
|
|
"num_tokens": 13387189.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.784458303451538,
|
|
"epoch": 0.5855406386066764,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004972374639524396,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.149605430662632,
|
|
"num_tokens": 13399446.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.708137845993042,
|
|
"epoch": 0.5859941944847605,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000497232406889044,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.15906617194414138,
|
|
"num_tokens": 13410320.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.732756042480469,
|
|
"epoch": 0.5864477503628447,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004972273452298255,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.15970333516597748,
|
|
"num_tokens": 13421458.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.789757585525512,
|
|
"epoch": 0.5869013062409288,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004972222789748888,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.15411718487739562,
|
|
"num_tokens": 13431815.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.804319143295288,
|
|
"epoch": 0.5873548621190131,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004972172081243389,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.1476941503584385,
|
|
"num_tokens": 13442263.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.7650422096252445,
|
|
"epoch": 0.5878084179970973,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004972121326782806,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.15558512806892394,
|
|
"num_tokens": 13452360.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.68228588104248,
|
|
"epoch": 0.5882619738751814,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004972070526368186,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.16493213623762132,
|
|
"num_tokens": 13461329.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.768403005599976,
|
|
"epoch": 0.5887155297532656,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004972019680000582,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.15866607874631883,
|
|
"num_tokens": 13472042.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.682829475402832,
|
|
"epoch": 0.5891690856313497,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004971968787681044,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.1655348628759384,
|
|
"num_tokens": 13482190.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.666314172744751,
|
|
"epoch": 0.589622641509434,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004971917849410627,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.15198497027158736,
|
|
"num_tokens": 13493053.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.810998582839966,
|
|
"epoch": 0.5900761973875182,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004971866865190381,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.15123215317726135,
|
|
"num_tokens": 13503629.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.829623794555664,
|
|
"epoch": 0.5905297532656023,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004971815835021362,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.15927340015769004,
|
|
"num_tokens": 13513776.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.787638854980469,
|
|
"epoch": 0.5909833091436865,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004971764758904626,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.15258469730615615,
|
|
"num_tokens": 13524705.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.681888914108276,
|
|
"epoch": 0.5914368650217707,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004971713636841229,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15930082648992538,
|
|
"num_tokens": 13535799.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.808771467208862,
|
|
"epoch": 0.5918904208998549,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004971662468832228,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.1564719334244728,
|
|
"num_tokens": 13545067.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.733100175857544,
|
|
"epoch": 0.592343976777939,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000497161125487868,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.1602954849600792,
|
|
"num_tokens": 13555227.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.634074878692627,
|
|
"epoch": 0.5927975326560232,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004971559994981645,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.16385299414396287,
|
|
"num_tokens": 13565559.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.695637798309326,
|
|
"epoch": 0.5932510885341074,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004971508689142184,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16074319779872895,
|
|
"num_tokens": 13575313.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.783664608001709,
|
|
"epoch": 0.5937046444121916,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004971457337361356,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.15695622861385344,
|
|
"num_tokens": 13584876.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.6620879650115965,
|
|
"epoch": 0.5941582002902758,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004971405939640225,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.16317103505134584,
|
|
"num_tokens": 13594811.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.703128814697266,
|
|
"epoch": 0.5946117561683599,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004971354495979854,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.15475962609052657,
|
|
"num_tokens": 13605806.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.799729585647583,
|
|
"epoch": 0.5950653120464441,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004971303006381305,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.15541718900203705,
|
|
"num_tokens": 13616267.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.854510402679443,
|
|
"epoch": 0.5955188679245284,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004971251470845643,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.15333730578422547,
|
|
"num_tokens": 13625692.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.799213027954101,
|
|
"epoch": 0.5959724238026125,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004971199889373935,
|
|
"loss": 5.7124,
|
|
"mean_token_accuracy": 0.1410965643823147,
|
|
"num_tokens": 13636832.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.8232988834381105,
|
|
"epoch": 0.5964259796806967,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004971148261967249,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.15864029079675673,
|
|
"num_tokens": 13646657.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.697556734085083,
|
|
"epoch": 0.5968795355587808,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004971096588626649,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.16281556636095046,
|
|
"num_tokens": 13657612.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.752542018890381,
|
|
"epoch": 0.597333091436865,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004971044869353206,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.15236000567674637,
|
|
"num_tokens": 13668263.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.754230117797851,
|
|
"epoch": 0.5977866473149492,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000497099310414799,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.1575901046395302,
|
|
"num_tokens": 13678298.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.782630681991577,
|
|
"epoch": 0.5982402031930334,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004970941293012069,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.1556815966963768,
|
|
"num_tokens": 13688981.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.75571575164795,
|
|
"epoch": 0.5986937590711175,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004970889435946518,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.1614097535610199,
|
|
"num_tokens": 13699318.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.660605525970459,
|
|
"epoch": 0.5991473149492017,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004970837532952406,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.15405092388391495,
|
|
"num_tokens": 13709708.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.737271451950074,
|
|
"epoch": 0.599600870827286,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004970785584030808,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.1567952439188957,
|
|
"num_tokens": 13719480.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.748212814331055,
|
|
"epoch": 0.6000544267053701,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004970733589182799,
|
|
"loss": 5.6305,
|
|
"mean_token_accuracy": 0.15508442372083664,
|
|
"num_tokens": 13729090.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.683683729171753,
|
|
"epoch": 0.6005079825834543,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004970681548409452,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.16317861676216125,
|
|
"num_tokens": 13739094.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.714485454559326,
|
|
"epoch": 0.6009615384615384,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004970629461711846,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.1589211955666542,
|
|
"num_tokens": 13749646.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.841981315612793,
|
|
"epoch": 0.6014150943396226,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004970577329091057,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.1531035877764225,
|
|
"num_tokens": 13760331.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.843902492523194,
|
|
"epoch": 0.6018686502177069,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004970525150548162,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1472798280417919,
|
|
"num_tokens": 13771034.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.775877141952515,
|
|
"epoch": 0.602322206095791,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004970472926084242,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.1525774747133255,
|
|
"num_tokens": 13782816.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.647054958343506,
|
|
"epoch": 0.6027757619738752,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004970420655700375,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.16223322451114655,
|
|
"num_tokens": 13792626.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.694581604003906,
|
|
"epoch": 0.6032293178519593,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004970368339397643,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.16072896718978882,
|
|
"num_tokens": 13802863.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.853788375854492,
|
|
"epoch": 0.6036828737300436,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004970315977177129,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.1542016237974167,
|
|
"num_tokens": 13812714.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.775206995010376,
|
|
"epoch": 0.6041364296081277,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004970263569039914,
|
|
"loss": 5.6497,
|
|
"mean_token_accuracy": 0.15461187213659286,
|
|
"num_tokens": 13822634.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.716327905654907,
|
|
"epoch": 0.6045899854862119,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004970211114987083,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.1629389226436615,
|
|
"num_tokens": 13833291.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.710997629165649,
|
|
"epoch": 0.6050435413642961,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004970158615019719,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.16321856826543807,
|
|
"num_tokens": 13843882.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.720949459075928,
|
|
"epoch": 0.6054970972423802,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004970106069138912,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.15597841441631316,
|
|
"num_tokens": 13853883.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.796688604354858,
|
|
"epoch": 0.6059506531204645,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004970053477345743,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.1547415718436241,
|
|
"num_tokens": 13864440.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.750747394561768,
|
|
"epoch": 0.6064042089985486,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004970000839641304,
|
|
"loss": 5.6915,
|
|
"mean_token_accuracy": 0.15220630168914795,
|
|
"num_tokens": 13875902.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.720804738998413,
|
|
"epoch": 0.6068577648766328,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004969948156026681,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.15204009115695954,
|
|
"num_tokens": 13886252.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.732796478271484,
|
|
"epoch": 0.6073113207547169,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004969895426502965,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.16024616360664368,
|
|
"num_tokens": 13896641.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.797425937652588,
|
|
"epoch": 0.6077648766328012,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004969842651071246,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.15383680015802384,
|
|
"num_tokens": 13907504.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.783607053756714,
|
|
"epoch": 0.6082184325108854,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004969789829732615,
|
|
"loss": 5.6327,
|
|
"mean_token_accuracy": 0.15362875834107398,
|
|
"num_tokens": 13917743.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.6884692192077635,
|
|
"epoch": 0.6086719883889695,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004969736962488164,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.1540693961083889,
|
|
"num_tokens": 13927626.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.808768081665039,
|
|
"epoch": 0.6091255442670537,
|
|
"grad_norm": 4.3125,
|
|
"learning_rate": 0.0004969684049338987,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15174802988767624,
|
|
"num_tokens": 13938863.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.797508382797242,
|
|
"epoch": 0.6095791001451378,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000496963109028618,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.1577400431036949,
|
|
"num_tokens": 13948699.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.698787689208984,
|
|
"epoch": 0.6100326560232221,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004969578085330834,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16206391006708146,
|
|
"num_tokens": 13958880.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.684061765670776,
|
|
"epoch": 0.6104862119013063,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004969525034474049,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.14983780905604363,
|
|
"num_tokens": 13968982.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.791654348373413,
|
|
"epoch": 0.6109397677793904,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000496947193771692,
|
|
"loss": 5.6594,
|
|
"mean_token_accuracy": 0.15571676939725876,
|
|
"num_tokens": 13978298.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.81650333404541,
|
|
"epoch": 0.6113933236574746,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004969418795060548,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.15728780776262283,
|
|
"num_tokens": 13988239.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.666800928115845,
|
|
"epoch": 0.6118468795355588,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004969365606506027,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.16210765689611434,
|
|
"num_tokens": 13997352.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.769309043884277,
|
|
"epoch": 0.612300435413643,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004969312372054461,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.1455084577202797,
|
|
"num_tokens": 14007662.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.798659944534302,
|
|
"epoch": 0.6127539912917271,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004969259091706948,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.15299142152071,
|
|
"num_tokens": 14017078.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.724830627441406,
|
|
"epoch": 0.6132075471698113,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004969205765464593,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.15806994438171387,
|
|
"num_tokens": 14028050.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.763033485412597,
|
|
"epoch": 0.6136611030478955,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004969152393328497,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.14964941665530204,
|
|
"num_tokens": 14037792.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.815360116958618,
|
|
"epoch": 0.6141146589259797,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004969098975299764,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.15568995475769043,
|
|
"num_tokens": 14047780.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.777581834793091,
|
|
"epoch": 0.6145682148040639,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004969045511379499,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.1585965633392334,
|
|
"num_tokens": 14058076.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.751511955261231,
|
|
"epoch": 0.615021770682148,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004968992001568806,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.1500725895166397,
|
|
"num_tokens": 14068082.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.764723587036133,
|
|
"epoch": 0.6154753265602322,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004968938445868795,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.15336300283670426,
|
|
"num_tokens": 14077905.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.799530506134033,
|
|
"epoch": 0.6159288824383164,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004968884844280569,
|
|
"loss": 5.6548,
|
|
"mean_token_accuracy": 0.1536657318472862,
|
|
"num_tokens": 14087113.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.8303056240081785,
|
|
"epoch": 0.6163824383164006,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004968831196805242,
|
|
"loss": 5.6767,
|
|
"mean_token_accuracy": 0.15169122070074081,
|
|
"num_tokens": 14097684.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.560121488571167,
|
|
"epoch": 0.6168359941944848,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004968777503443918,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.161190202832222,
|
|
"num_tokens": 14106871.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.70657000541687,
|
|
"epoch": 0.6172895500725689,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004968723764197711,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1636699452996254,
|
|
"num_tokens": 14117480.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.843404817581177,
|
|
"epoch": 0.6177431059506531,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.000496866997906773,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.16347150653600692,
|
|
"num_tokens": 14128153.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.701880931854248,
|
|
"epoch": 0.6181966618287373,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004968616148055089,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.1551259309053421,
|
|
"num_tokens": 14137920.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.715606927871704,
|
|
"epoch": 0.6186502177068215,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004968562271160901,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.16260792315006256,
|
|
"num_tokens": 14148160.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.7415777206420895,
|
|
"epoch": 0.6191037735849056,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.000496850834838628,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.1547149032354355,
|
|
"num_tokens": 14158646.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.684873151779175,
|
|
"epoch": 0.6195573294629898,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004968454379732342,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15305895507335662,
|
|
"num_tokens": 14168719.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.805060291290284,
|
|
"epoch": 0.6200108853410741,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00049684003652002,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.15023768320679665,
|
|
"num_tokens": 14179859.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.772373104095459,
|
|
"epoch": 0.6204644412191582,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004968346304790973,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.15124039947986603,
|
|
"num_tokens": 14190413.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.786475276947021,
|
|
"epoch": 0.6209179970972424,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004968292198505781,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.1573897510766983,
|
|
"num_tokens": 14200337.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.827665328979492,
|
|
"epoch": 0.6213715529753265,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.000496823804634574,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.15085174515843391,
|
|
"num_tokens": 14210848.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.803124332427979,
|
|
"epoch": 0.6218251088534107,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004968183848311972,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.14558184519410133,
|
|
"num_tokens": 14221358.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.849875497817993,
|
|
"epoch": 0.622278664731495,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004968129604405596,
|
|
"loss": 5.7384,
|
|
"mean_token_accuracy": 0.15821532607078553,
|
|
"num_tokens": 14232580.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.735620450973511,
|
|
"epoch": 0.6227322206095791,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004968075314627734,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.14964599311351776,
|
|
"num_tokens": 14243339.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.699955081939697,
|
|
"epoch": 0.6231857764876633,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000496802097897951,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1629217967391014,
|
|
"num_tokens": 14254121.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.7439658641815186,
|
|
"epoch": 0.6236393323657474,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004967966597462046,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.1599903240799904,
|
|
"num_tokens": 14264196.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.756141281127929,
|
|
"epoch": 0.6240928882438317,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004967912170076469,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.1576563149690628,
|
|
"num_tokens": 14274610.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.682001352310181,
|
|
"epoch": 0.6245464441219158,
|
|
"grad_norm": 5.96875,
|
|
"learning_rate": 0.0004967857696823901,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.15772237703204156,
|
|
"num_tokens": 14286355.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.726107454299926,
|
|
"epoch": 0.625,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004967803177705472,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.15741511732339858,
|
|
"num_tokens": 14296155.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.737909030914307,
|
|
"epoch": 0.6254535558780842,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004967748612722308,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.15493713021278382,
|
|
"num_tokens": 14305073.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.770492029190064,
|
|
"epoch": 0.6259071117561683,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004967694001875538,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1596616804599762,
|
|
"num_tokens": 14315646.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.777948188781738,
|
|
"epoch": 0.6263606676342526,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.000496763934516629,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.15220129936933519,
|
|
"num_tokens": 14327058.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.656092357635498,
|
|
"epoch": 0.6268142235123367,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004967584642595696,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16333331912755966,
|
|
"num_tokens": 14336661.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.767233991622925,
|
|
"epoch": 0.6272677793904209,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004967529894164887,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.1614171862602234,
|
|
"num_tokens": 14346840.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.7081750392913815,
|
|
"epoch": 0.627721335268505,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004967475099874992,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.1632200375199318,
|
|
"num_tokens": 14356342.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.696488571166992,
|
|
"epoch": 0.6281748911465893,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.000496742025972715,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.16221774816513063,
|
|
"num_tokens": 14365301.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.713243579864502,
|
|
"epoch": 0.6286284470246735,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000496736537372249,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.15672291368246077,
|
|
"num_tokens": 14376497.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.74711127281189,
|
|
"epoch": 0.6290820029027576,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004967310441862151,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.16105988919734954,
|
|
"num_tokens": 14386982.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.778274869918823,
|
|
"epoch": 0.6295355587808418,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004967255464147265,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.15858430564403533,
|
|
"num_tokens": 14397944.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.689877605438232,
|
|
"epoch": 0.6299891146589259,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004967200440578972,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.16407246887683868,
|
|
"num_tokens": 14408875.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.654283905029297,
|
|
"epoch": 0.6304426705370102,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004967145371158408,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.1663491263985634,
|
|
"num_tokens": 14418719.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.779173421859741,
|
|
"epoch": 0.6308962264150944,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004967090255886714,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.15254574865102768,
|
|
"num_tokens": 14429333.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.743547868728638,
|
|
"epoch": 0.6313497822931785,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004967035094765028,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.1506338968873024,
|
|
"num_tokens": 14439787.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.786348295211792,
|
|
"epoch": 0.6318033381712627,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004966979887794491,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.16431703865528108,
|
|
"num_tokens": 14449711.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.736811542510987,
|
|
"epoch": 0.6322568940493469,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004966924634976245,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.16069522500038147,
|
|
"num_tokens": 14458750.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.7178483486175535,
|
|
"epoch": 0.6327104499274311,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004966869336311433,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.1585947498679161,
|
|
"num_tokens": 14468517.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.704970598220825,
|
|
"epoch": 0.6331640058055152,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004966813991801197,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.15538498759269714,
|
|
"num_tokens": 14478666.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.865767621994019,
|
|
"epoch": 0.6336175616835994,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004966758601446684,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.1615960031747818,
|
|
"num_tokens": 14489227.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.835824489593506,
|
|
"epoch": 0.6340711175616836,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004966703165249038,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.14500172287225724,
|
|
"num_tokens": 14498955.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.853192472457886,
|
|
"epoch": 0.6345246734397678,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004966647683209406,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.15712972432374955,
|
|
"num_tokens": 14510565.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.708524417877197,
|
|
"epoch": 0.634978229317852,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004966592155328935,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.15350938439369202,
|
|
"num_tokens": 14521367.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.751900768280029,
|
|
"epoch": 0.6354317851959361,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004966536581608771,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.1562518835067749,
|
|
"num_tokens": 14531198.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.774559879302979,
|
|
"epoch": 0.6358853410740203,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004966480962050069,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.15649291574954988,
|
|
"num_tokens": 14542603.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.839611196517945,
|
|
"epoch": 0.6363388969521045,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004966425296653974,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.15144390612840652,
|
|
"num_tokens": 14553431.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.765762996673584,
|
|
"epoch": 0.6367924528301887,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.000496636958542164,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.15698604434728622,
|
|
"num_tokens": 14563334.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.729667615890503,
|
|
"epoch": 0.6372460087082729,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004966313828354218,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.1549726501107216,
|
|
"num_tokens": 14573330.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.790589046478272,
|
|
"epoch": 0.637699564586357,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.000496625802545286,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.1527685448527336,
|
|
"num_tokens": 14584994.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.837193155288697,
|
|
"epoch": 0.6381531204644412,
|
|
"grad_norm": 5.5,
|
|
"learning_rate": 0.0004966202176718723,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.15974610447883605,
|
|
"num_tokens": 14596324.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.807248115539551,
|
|
"epoch": 0.6386066763425254,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004966146282152959,
|
|
"loss": 5.6255,
|
|
"mean_token_accuracy": 0.15620894283056258,
|
|
"num_tokens": 14606159.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.863836669921875,
|
|
"epoch": 0.6390602322206096,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004966090341756726,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.14900389909744263,
|
|
"num_tokens": 14616851.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.695793914794922,
|
|
"epoch": 0.6395137880986937,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000496603435553118,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16355661302804947,
|
|
"num_tokens": 14627729.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.7164922714233395,
|
|
"epoch": 0.6399673439767779,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004965978323477478,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.1598214849829674,
|
|
"num_tokens": 14637591.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.759249687194824,
|
|
"epoch": 0.6404208998548622,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.000496592224559678,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.158864888548851,
|
|
"num_tokens": 14647507.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.6821815967559814,
|
|
"epoch": 0.6408744557329463,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004965866121890245,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.1597239226102829,
|
|
"num_tokens": 14657339.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.70623517036438,
|
|
"epoch": 0.6413280116110305,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004965809952359034,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.16201654821634293,
|
|
"num_tokens": 14668621.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.767104053497315,
|
|
"epoch": 0.6417815674891146,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004965753737004309,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.1593472570180893,
|
|
"num_tokens": 14678530.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.714475059509278,
|
|
"epoch": 0.6422351233671988,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004965697475827231,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.16647264808416368,
|
|
"num_tokens": 14688303.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.7584463596344,
|
|
"epoch": 0.6426886792452831,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004965641168828965,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.1570249542593956,
|
|
"num_tokens": 14698697.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.656041288375855,
|
|
"epoch": 0.6431422351233672,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004965584816010676,
|
|
"loss": 5.5214,
|
|
"mean_token_accuracy": 0.165100035071373,
|
|
"num_tokens": 14708541.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.7682939052581785,
|
|
"epoch": 0.6435957910014514,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004965528417373528,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.14949500411748887,
|
|
"num_tokens": 14720123.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.793861341476441,
|
|
"epoch": 0.6440493468795355,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004965471972918688,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.15569858253002167,
|
|
"num_tokens": 14731439.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.753037643432617,
|
|
"epoch": 0.6445029027576198,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004965415482647322,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.15246612578630447,
|
|
"num_tokens": 14742243.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.741925859451294,
|
|
"epoch": 0.6449564586357039,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00049653589465606,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.1528177335858345,
|
|
"num_tokens": 14751997.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.77686767578125,
|
|
"epoch": 0.6454100145137881,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.000496530236465969,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.15989938303828238,
|
|
"num_tokens": 14762293.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.820109605789185,
|
|
"epoch": 0.6458635703918723,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004965245736945763,
|
|
"loss": 5.6293,
|
|
"mean_token_accuracy": 0.15774548649787903,
|
|
"num_tokens": 14771332.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.7409556865692135,
|
|
"epoch": 0.6463171262699564,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004965189063419989,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.15244969725608826,
|
|
"num_tokens": 14781757.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.74225435256958,
|
|
"epoch": 0.6467706821480407,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004965132344083541,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.15569283962249755,
|
|
"num_tokens": 14791338.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.740928411483765,
|
|
"epoch": 0.6472242380261248,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004965075578937593,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.1521914705634117,
|
|
"num_tokens": 14802033.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.70343713760376,
|
|
"epoch": 0.647677793904209,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004965018767983316,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.16235738694667817,
|
|
"num_tokens": 14812341.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.829333400726318,
|
|
"epoch": 0.6481313497822931,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004964961911221886,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1459219217300415,
|
|
"num_tokens": 14824334.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.769096899032593,
|
|
"epoch": 0.6485849056603774,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000496490500865448,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.15827197432518006,
|
|
"num_tokens": 14834200.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.7518878936767575,
|
|
"epoch": 0.6490384615384616,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004964848060282275,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.1599769726395607,
|
|
"num_tokens": 14845425.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.8009261131286625,
|
|
"epoch": 0.6494920174165457,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004964791066106447,
|
|
"loss": 5.6985,
|
|
"mean_token_accuracy": 0.15522825419902803,
|
|
"num_tokens": 14856029.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.7412573337554935,
|
|
"epoch": 0.6499455732946299,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004964734026128175,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.15963159501552582,
|
|
"num_tokens": 14865481.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.7057243347167965,
|
|
"epoch": 0.650399129172714,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004964676940348638,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.15293650478124618,
|
|
"num_tokens": 14875109.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.813092994689941,
|
|
"epoch": 0.6508526850507983,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000496461980876902,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.16277963519096375,
|
|
"num_tokens": 14885302.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.786996841430664,
|
|
"epoch": 0.6513062409288825,
|
|
"grad_norm": 11.375,
|
|
"learning_rate": 0.0004964562631390498,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.1609741762280464,
|
|
"num_tokens": 14894418.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.749535274505615,
|
|
"epoch": 0.6517597968069666,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004964505408214257,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.16198379248380662,
|
|
"num_tokens": 14904738.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.735393428802491,
|
|
"epoch": 0.6522133526850508,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.000496444813924148,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.15685581415891647,
|
|
"num_tokens": 14916012.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.778084564208984,
|
|
"epoch": 0.652666908563135,
|
|
"grad_norm": 5.59375,
|
|
"learning_rate": 0.0004964390824473351,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.15826205611228944,
|
|
"num_tokens": 14927239.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.801933240890503,
|
|
"epoch": 0.6531204644412192,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.0004964333463911056,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1508314147591591,
|
|
"num_tokens": 14937915.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.7537510871887205,
|
|
"epoch": 0.6535740203193033,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004964276057555779,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.15559779703617097,
|
|
"num_tokens": 14948360.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.762653732299805,
|
|
"epoch": 0.6540275761973875,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.000496421860540871,
|
|
"loss": 5.7211,
|
|
"mean_token_accuracy": 0.14721062853932382,
|
|
"num_tokens": 14958838.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.84288854598999,
|
|
"epoch": 0.6544811320754716,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004964161107471036,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.15069502517580985,
|
|
"num_tokens": 14968960.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.786521244049072,
|
|
"epoch": 0.6549346879535559,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004964103563743946,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.164300574362278,
|
|
"num_tokens": 14978550.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.754683971405029,
|
|
"epoch": 0.6553882438316401,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000496404597422863,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.15014653727412225,
|
|
"num_tokens": 14990390.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.76729564666748,
|
|
"epoch": 0.6558417997097242,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000496398833892628,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.15480599403381348,
|
|
"num_tokens": 15001563.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.853767395019531,
|
|
"epoch": 0.6562953555878084,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004963930657838086,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.15056831240653992,
|
|
"num_tokens": 15012740.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.868458700180054,
|
|
"epoch": 0.6567489114658926,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004963872930965242,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.1523576334118843,
|
|
"num_tokens": 15024082.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.750052881240845,
|
|
"epoch": 0.6572024673439768,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004963815158308941,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.15408817678689957,
|
|
"num_tokens": 15034300.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.751996660232544,
|
|
"epoch": 0.657656023222061,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004963757339870379,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.16331602334976197,
|
|
"num_tokens": 15043277.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.784009408950806,
|
|
"epoch": 0.6581095791001451,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004963699475650751,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.15816349685192108,
|
|
"num_tokens": 15053686.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.7810920715332035,
|
|
"epoch": 0.6585631349782293,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004963641565651255,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.1629945904016495,
|
|
"num_tokens": 15063144.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.741094255447388,
|
|
"epoch": 0.6590166908563135,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004963583609873084,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.1572900578379631,
|
|
"num_tokens": 15072564.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.760691785812378,
|
|
"epoch": 0.6594702467343977,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004963525608317443,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.15416491776704788,
|
|
"num_tokens": 15082273.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.754504013061523,
|
|
"epoch": 0.6599238026124818,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004963467560985527,
|
|
"loss": 5.6003,
|
|
"mean_token_accuracy": 0.15689957588911058,
|
|
"num_tokens": 15091662.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.782180547714233,
|
|
"epoch": 0.660377358490566,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004963409467878538,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.16143929287791253,
|
|
"num_tokens": 15101188.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.780669927597046,
|
|
"epoch": 0.6608309143686503,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004963351328997678,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.1538732334971428,
|
|
"num_tokens": 15111352.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.881281089782715,
|
|
"epoch": 0.6612844702467344,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004963293144344148,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.1468665912747383,
|
|
"num_tokens": 15122225.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.771633052825928,
|
|
"epoch": 0.6617380261248186,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004963234913919151,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.1548286035656929,
|
|
"num_tokens": 15132807.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.7575364112854,
|
|
"epoch": 0.6621915820029027,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004963176637723893,
|
|
"loss": 5.6775,
|
|
"mean_token_accuracy": 0.14549415707588195,
|
|
"num_tokens": 15143664.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.808767509460449,
|
|
"epoch": 0.6626451378809869,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004963118315759578,
|
|
"loss": 5.6371,
|
|
"mean_token_accuracy": 0.15712959915399552,
|
|
"num_tokens": 15153977.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.759644079208374,
|
|
"epoch": 0.6630986937590712,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004963059948027411,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16429376006126403,
|
|
"num_tokens": 15163128.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.832194375991821,
|
|
"epoch": 0.6635522496371553,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004963001534528601,
|
|
"loss": 5.7649,
|
|
"mean_token_accuracy": 0.15502927601337432,
|
|
"num_tokens": 15173516.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.745299291610718,
|
|
"epoch": 0.6640058055152395,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004962943075264355,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.15902740955352784,
|
|
"num_tokens": 15183872.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.77251558303833,
|
|
"epoch": 0.6644593613933236,
|
|
"grad_norm": 7.5,
|
|
"learning_rate": 0.0004962884570235884,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.15652472153306007,
|
|
"num_tokens": 15193830.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.676307487487793,
|
|
"epoch": 0.6649129172714079,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004962826019444394,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.1557547003030777,
|
|
"num_tokens": 15204021.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.72134370803833,
|
|
"epoch": 0.665366473149492,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004962767422891099,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.16044427454471588,
|
|
"num_tokens": 15213820.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.777765989303589,
|
|
"epoch": 0.6658200290275762,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.000496270878057721,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.15643776059150696,
|
|
"num_tokens": 15223285.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.8106386184692385,
|
|
"epoch": 0.6662735849056604,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004962650092503939,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.16323304921388626,
|
|
"num_tokens": 15233759.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.796981859207153,
|
|
"epoch": 0.6667271407837445,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004962591358672502,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.1529715485870838,
|
|
"num_tokens": 15244633.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.76887469291687,
|
|
"epoch": 0.6671806966618288,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000496253257908411,
|
|
"loss": 5.684,
|
|
"mean_token_accuracy": 0.15396681278944016,
|
|
"num_tokens": 15255160.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.887839603424072,
|
|
"epoch": 0.6676342525399129,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004962473753739981,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15530455261468887,
|
|
"num_tokens": 15264641.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.847436571121216,
|
|
"epoch": 0.6680878084179971,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.000496241488264133,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.15171343982219695,
|
|
"num_tokens": 15274945.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.727545833587646,
|
|
"epoch": 0.6685413642960812,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004962355965789377,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.15616238862276077,
|
|
"num_tokens": 15284692.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.712421989440918,
|
|
"epoch": 0.6689949201741655,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 0.0004962297003185338,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.15451953560113907,
|
|
"num_tokens": 15294199.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.770094490051269,
|
|
"epoch": 0.6694484760522497,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004962237994830433,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.15364942699670792,
|
|
"num_tokens": 15304401.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.804858446121216,
|
|
"epoch": 0.6699020319303338,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004962178940725883,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.16549576073884964,
|
|
"num_tokens": 15314520.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.732750177383423,
|
|
"epoch": 0.670355587808418,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 0.0004962119840872908,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.16173245906829833,
|
|
"num_tokens": 15324071.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.73241810798645,
|
|
"epoch": 0.6708091436865021,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004962060695272733,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1608823835849762,
|
|
"num_tokens": 15334245.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.7757049083709715,
|
|
"epoch": 0.6712626995645864,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004962001503926577,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.15362300872802734,
|
|
"num_tokens": 15344425.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.763125705718994,
|
|
"epoch": 0.6717162554426706,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004961942266835667,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.1443048521876335,
|
|
"num_tokens": 15355237.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.750442314147949,
|
|
"epoch": 0.6721698113207547,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004961882984001227,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16058864295482636,
|
|
"num_tokens": 15365323.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.7392988204956055,
|
|
"epoch": 0.6726233671988389,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004961823655424484,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.16431051939725877,
|
|
"num_tokens": 15374652.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.758931493759155,
|
|
"epoch": 0.6730769230769231,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004961764281106664,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.16057585924863815,
|
|
"num_tokens": 15384582.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.7668619632720945,
|
|
"epoch": 0.6735304789550073,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004961704861048995,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.15404267162084578,
|
|
"num_tokens": 15394292.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.796910285949707,
|
|
"epoch": 0.6739840348330914,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004961645395252705,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.14948946088552476,
|
|
"num_tokens": 15404036.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.787111520767212,
|
|
"epoch": 0.6744375907111756,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004961585883719025,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.1580713450908661,
|
|
"num_tokens": 15414289.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.8226477146148685,
|
|
"epoch": 0.6748911465892597,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004961526326449186,
|
|
"loss": 5.6941,
|
|
"mean_token_accuracy": 0.15350158140063286,
|
|
"num_tokens": 15425404.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.799039840698242,
|
|
"epoch": 0.675344702467344,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004961466723444419,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.14718335643410682,
|
|
"num_tokens": 15435437.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.734977293014526,
|
|
"epoch": 0.6757982583454282,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004961407074705955,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.1534969449043274,
|
|
"num_tokens": 15446434.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.886393976211548,
|
|
"epoch": 0.6762518142235123,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004961347380235031,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.14869626760482788,
|
|
"num_tokens": 15456346.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.814081239700317,
|
|
"epoch": 0.6767053701015965,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004961287640032879,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.15773403644561768,
|
|
"num_tokens": 15466214.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.6498833179473875,
|
|
"epoch": 0.6771589259796807,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004961227854100734,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1564796581864357,
|
|
"num_tokens": 15476229.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.7101973533630375,
|
|
"epoch": 0.6776124818577649,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004961168022439835,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.15887040942907332,
|
|
"num_tokens": 15486735.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.866124248504638,
|
|
"epoch": 0.6780660377358491,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004961108145051417,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.1500288352370262,
|
|
"num_tokens": 15497201.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.75830602645874,
|
|
"epoch": 0.6785195936139332,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.000496104822193672,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.1587577998638153,
|
|
"num_tokens": 15507053.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.746447610855102,
|
|
"epoch": 0.6789731494920174,
|
|
"grad_norm": 4.6875,
|
|
"learning_rate": 0.0004960988253096982,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.1482136368751526,
|
|
"num_tokens": 15518032.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.688390159606934,
|
|
"epoch": 0.6794267053701016,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004960928238533443,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.1566487208008766,
|
|
"num_tokens": 15529034.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.769197702407837,
|
|
"epoch": 0.6798802612481858,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004960868178247344,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.15801844000816345,
|
|
"num_tokens": 15539153.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.762501573562622,
|
|
"epoch": 0.68033381712627,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004960808072239929,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.16039573326706885,
|
|
"num_tokens": 15549427.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.753922939300537,
|
|
"epoch": 0.6807873730043541,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004960747920512439,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15405466556549072,
|
|
"num_tokens": 15558834.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.762908124923706,
|
|
"epoch": 0.6812409288824384,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000496068772306612,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.15160716623067855,
|
|
"num_tokens": 15569209.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.750273180007935,
|
|
"epoch": 0.6816944847605225,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004960627479902214,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.15494249761104584,
|
|
"num_tokens": 15579239.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.739710664749145,
|
|
"epoch": 0.6821480406386067,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.000496056719102197,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.1585078254342079,
|
|
"num_tokens": 15590036.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.736978149414062,
|
|
"epoch": 0.6826015965166908,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004960506856426631,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.16314262002706528,
|
|
"num_tokens": 15600375.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.713376426696778,
|
|
"epoch": 0.683055152394775,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004960446476117448,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.15013087242841722,
|
|
"num_tokens": 15610859.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.815583229064941,
|
|
"epoch": 0.6835087082728593,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004960386050095668,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.1477643832564354,
|
|
"num_tokens": 15621914.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.8543415546417235,
|
|
"epoch": 0.6839622641509434,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004960325578362543,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.1533266767859459,
|
|
"num_tokens": 15632379.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.728507375717163,
|
|
"epoch": 0.6844158200290276,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.000496026506091932,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.1556667357683182,
|
|
"num_tokens": 15643253.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.796116685867309,
|
|
"epoch": 0.6848693759071117,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004960204497767253,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.1523918628692627,
|
|
"num_tokens": 15653557.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.780343818664551,
|
|
"epoch": 0.685322931785196,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004960143888907594,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.1578650578856468,
|
|
"num_tokens": 15664034.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.793070936203003,
|
|
"epoch": 0.6857764876632801,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004960083234341595,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.15654636919498444,
|
|
"num_tokens": 15674951.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.752449369430542,
|
|
"epoch": 0.6862300435413643,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004960022534070513,
|
|
"loss": 5.5547,
|
|
"mean_token_accuracy": 0.16121672391891478,
|
|
"num_tokens": 15684446.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.732784175872803,
|
|
"epoch": 0.6866835994194485,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00049599617880956,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.1626044824719429,
|
|
"num_tokens": 15694672.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.7013763904571535,
|
|
"epoch": 0.6871371552975326,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004959900996418115,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.15530735701322557,
|
|
"num_tokens": 15704637.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.715182638168335,
|
|
"epoch": 0.6875907111756169,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004959840159039315,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.1568412646651268,
|
|
"num_tokens": 15713865.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.808747720718384,
|
|
"epoch": 0.688044267053701,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004959779275960456,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.15349928438663482,
|
|
"num_tokens": 15724258.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.770686054229737,
|
|
"epoch": 0.6884978229317852,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00049597183471828,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.15678472965955734,
|
|
"num_tokens": 15735180.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.754590940475464,
|
|
"epoch": 0.6889513788098693,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004959657372707604,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.1512817457318306,
|
|
"num_tokens": 15745209.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.839451551437378,
|
|
"epoch": 0.6894049346879536,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004959596352536132,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.1502077430486679,
|
|
"num_tokens": 15756976.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.798298025131226,
|
|
"epoch": 0.6898584905660378,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004959535286669643,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.1565860003232956,
|
|
"num_tokens": 15767362.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.7720561027526855,
|
|
"epoch": 0.6903120464441219,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004959474175109402,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.1568397358059883,
|
|
"num_tokens": 15778260.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.784616327285766,
|
|
"epoch": 0.6907656023222061,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004959413017856672,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.15804268270730973,
|
|
"num_tokens": 15789025.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.771534585952759,
|
|
"epoch": 0.6912191582002902,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004959351814912716,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.1604921668767929,
|
|
"num_tokens": 15798706.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.746160173416138,
|
|
"epoch": 0.6916727140783745,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004959290566278803,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.16115242391824722,
|
|
"num_tokens": 15808071.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.828521633148194,
|
|
"epoch": 0.6921262699564587,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004959229271956199,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.15412043929100036,
|
|
"num_tokens": 15819317.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.742588758468628,
|
|
"epoch": 0.6925798258345428,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004959167931946169,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.15941284745931625,
|
|
"num_tokens": 15830147.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.749380874633789,
|
|
"epoch": 0.693033381712627,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004959106546249984,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.17110419124364853,
|
|
"num_tokens": 15840107.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.819102001190186,
|
|
"epoch": 0.6934869375907112,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004959045114868913,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.15552862137556075,
|
|
"num_tokens": 15849987.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.849531269073486,
|
|
"epoch": 0.6939404934687954,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004958983637804225,
|
|
"loss": 5.6429,
|
|
"mean_token_accuracy": 0.15638294517993928,
|
|
"num_tokens": 15859837.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.783810472488403,
|
|
"epoch": 0.6943940493468795,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004958922115057194,
|
|
"loss": 5.7022,
|
|
"mean_token_accuracy": 0.1505706086754799,
|
|
"num_tokens": 15871504.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.751116704940796,
|
|
"epoch": 0.6948476052249637,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004958860546629089,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.16299662739038467,
|
|
"num_tokens": 15881745.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.777749395370483,
|
|
"epoch": 0.6953011611030478,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 0.0004958798932521186,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.15549626499414443,
|
|
"num_tokens": 15892320.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.7372252464294435,
|
|
"epoch": 0.6957547169811321,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 0.0004958737272734759,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.15911678075790406,
|
|
"num_tokens": 15902754.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.759205341339111,
|
|
"epoch": 0.6962082728592163,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004958675567271081,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.16049185246229172,
|
|
"num_tokens": 15913247.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.815482807159424,
|
|
"epoch": 0.6966618287373004,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.000495861381613143,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.15289407670497895,
|
|
"num_tokens": 15922828.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.720240736007691,
|
|
"epoch": 0.6971153846153846,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004958552019317082,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.15427517890930176,
|
|
"num_tokens": 15932921.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.761741065979004,
|
|
"epoch": 0.6975689404934688,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004958490176829316,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1560848221182823,
|
|
"num_tokens": 15942457.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.747310972213745,
|
|
"epoch": 0.698022496371553,
|
|
"grad_norm": 6.875,
|
|
"learning_rate": 0.000495842828866941,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.15387596637010575,
|
|
"num_tokens": 15952275.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.649684906005859,
|
|
"epoch": 0.6984760522496372,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.0004958366354838645,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.16529976576566696,
|
|
"num_tokens": 15962110.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.704395055770874,
|
|
"epoch": 0.6989296081277213,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00049583043753383,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.15852983072400093,
|
|
"num_tokens": 15972634.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.791731977462769,
|
|
"epoch": 0.6993831640058055,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004958242350169658,
|
|
"loss": 5.6513,
|
|
"mean_token_accuracy": 0.15203508138656616,
|
|
"num_tokens": 15983132.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.738736534118653,
|
|
"epoch": 0.6998367198838897,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004958180279334001,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.154992463439703,
|
|
"num_tokens": 15994149.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.822169208526612,
|
|
"epoch": 0.7002902757619739,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004958118162832614,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.15574501156806947,
|
|
"num_tokens": 16005104.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.780132913589478,
|
|
"epoch": 0.700743831640058,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004958056000666781,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.15719846412539482,
|
|
"num_tokens": 16015629.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.852429294586182,
|
|
"epoch": 0.7011973875181422,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004957993792837786,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1519222602248192,
|
|
"num_tokens": 16025960.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.691937446594238,
|
|
"epoch": 0.7016509433962265,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004957931539346917,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.16283216029405595,
|
|
"num_tokens": 16036083.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.707127094268799,
|
|
"epoch": 0.7021044992743106,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004957869240195462,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.16615657061338424,
|
|
"num_tokens": 16046448.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.784661531448364,
|
|
"epoch": 0.7025580551523948,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004957806895384707,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.15175288319587707,
|
|
"num_tokens": 16056807.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.795204210281372,
|
|
"epoch": 0.7030116110304789,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004957744504915944,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.15674785524606705,
|
|
"num_tokens": 16067129.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.7949577331542965,
|
|
"epoch": 0.7034651669085631,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004957682068790463,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15278994292020798,
|
|
"num_tokens": 16078565.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.699900054931641,
|
|
"epoch": 0.7039187227866474,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004957619587009553,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.15987293422222137,
|
|
"num_tokens": 16089068.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.74468960762024,
|
|
"epoch": 0.7043722786647315,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004957557059574507,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.14614630565047265,
|
|
"num_tokens": 16100008.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.792629146575928,
|
|
"epoch": 0.7048258345428157,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004957494486486618,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.14775043427944184,
|
|
"num_tokens": 16111444.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.866617870330811,
|
|
"epoch": 0.7052793904208998,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004957431867747182,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1542788103222847,
|
|
"num_tokens": 16122020.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.778904294967651,
|
|
"epoch": 0.7057329462989841,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004957369203357492,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.16568806916475295,
|
|
"num_tokens": 16131281.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.7513092994689945,
|
|
"epoch": 0.7061865021770682,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004957306493318844,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15769600570201875,
|
|
"num_tokens": 16142087.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.760253143310547,
|
|
"epoch": 0.7066400580551524,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004957243737632535,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.16361806243658067,
|
|
"num_tokens": 16152120.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.787371969223022,
|
|
"epoch": 0.7070936139332366,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004957180936299863,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.1611701652407646,
|
|
"num_tokens": 16163432.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.750684547424316,
|
|
"epoch": 0.7075471698113207,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004957118089322127,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.1521909862756729,
|
|
"num_tokens": 16174070.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.7357985496521,
|
|
"epoch": 0.708000725689405,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.0004957055196700628,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.1614537939429283,
|
|
"num_tokens": 16183727.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.744387292861939,
|
|
"epoch": 0.7084542815674891,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004956992258436663,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.16315926909446715,
|
|
"num_tokens": 16194056.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.729212713241577,
|
|
"epoch": 0.7089078374455733,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004956929274531536,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.15964651107788086,
|
|
"num_tokens": 16204039.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.736894512176514,
|
|
"epoch": 0.7093613933236574,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000495686624498655,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.15911562889814376,
|
|
"num_tokens": 16214329.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.819330215454102,
|
|
"epoch": 0.7098149492017417,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004956803169803007,
|
|
"loss": 5.729,
|
|
"mean_token_accuracy": 0.14540325105190277,
|
|
"num_tokens": 16226396.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.778207397460937,
|
|
"epoch": 0.7102685050798259,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004956740048982212,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.16062480062246323,
|
|
"num_tokens": 16236753.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.836630821228027,
|
|
"epoch": 0.71072206095791,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004956676882525472,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.14720023572444915,
|
|
"num_tokens": 16246270.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.851115322113037,
|
|
"epoch": 0.7111756168359942,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000495661367043409,
|
|
"loss": 5.6441,
|
|
"mean_token_accuracy": 0.16027983278036118,
|
|
"num_tokens": 16256071.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.766817235946656,
|
|
"epoch": 0.7116291727140783,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004956550412709376,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.15271955505013465,
|
|
"num_tokens": 16266995.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.844926357269287,
|
|
"epoch": 0.7120827285921626,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004956487109352637,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.15099674612283706,
|
|
"num_tokens": 16279787.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.8208479404449465,
|
|
"epoch": 0.7125362844702468,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004956423760365181,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.1538202553987503,
|
|
"num_tokens": 16290826.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.783289957046509,
|
|
"epoch": 0.7129898403483309,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004956360365748321,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16150108724832535,
|
|
"num_tokens": 16300599.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.755193996429443,
|
|
"epoch": 0.7134433962264151,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004956296925503367,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.15755392462015153,
|
|
"num_tokens": 16310240.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.810258483886718,
|
|
"epoch": 0.7138969521044993,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004956233439631628,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.1576920837163925,
|
|
"num_tokens": 16320580.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.671935606002807,
|
|
"epoch": 0.7143505079825835,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004956169908134421,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.15596351623535157,
|
|
"num_tokens": 16330246.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.774977493286133,
|
|
"epoch": 0.7148040638606676,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004956106331013057,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.16086281836032867,
|
|
"num_tokens": 16339769.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.781713151931763,
|
|
"epoch": 0.7152576197387518,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004956042708268853,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.15815801322460174,
|
|
"num_tokens": 16349196.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.7052558898925785,
|
|
"epoch": 0.715711175616836,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955979039903123,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.15750451236963273,
|
|
"num_tokens": 16360072.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.69798698425293,
|
|
"epoch": 0.7161647314949202,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.0004955915325917183,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.15827955752611161,
|
|
"num_tokens": 16370469.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.796889019012451,
|
|
"epoch": 0.7166182873730044,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004955851566312354,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.1537104293704033,
|
|
"num_tokens": 16381252.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.848946905136108,
|
|
"epoch": 0.7170718432510885,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004955787761089952,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.15734365135431289,
|
|
"num_tokens": 16391785.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.804285717010498,
|
|
"epoch": 0.7175253991291727,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004955723910251296,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.15833539739251137,
|
|
"num_tokens": 16401937.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.739145565032959,
|
|
"epoch": 0.717978955007257,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.0004955660013797709,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.1670544058084488,
|
|
"num_tokens": 16411816.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.644951677322387,
|
|
"epoch": 0.7184325108853411,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.000495559607173051,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.1513867750763893,
|
|
"num_tokens": 16423010.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.748967218399048,
|
|
"epoch": 0.7188860667634253,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004955532084051022,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15736083835363388,
|
|
"num_tokens": 16433345.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.803564500808716,
|
|
"epoch": 0.7193396226415094,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004955468050760568,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.15658929497003554,
|
|
"num_tokens": 16444508.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.7014247417449955,
|
|
"epoch": 0.7197931785195936,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004955403971860474,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.16188954263925553,
|
|
"num_tokens": 16454248.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.683907747268677,
|
|
"epoch": 0.7202467343976778,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004955339847352063,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.1645732879638672,
|
|
"num_tokens": 16463762.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.744384622573852,
|
|
"epoch": 0.720700290275762,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004955275677236662,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.1514907330274582,
|
|
"num_tokens": 16474059.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.758716773986817,
|
|
"epoch": 0.7211538461538461,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004955211461515599,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.17130780220031738,
|
|
"num_tokens": 16483352.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.820909595489502,
|
|
"epoch": 0.7216074020319303,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.00049551472001902,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.15455454140901564,
|
|
"num_tokens": 16494714.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.76343355178833,
|
|
"epoch": 0.7220609579100146,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955082893261796,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.15796139240264892,
|
|
"num_tokens": 16505610.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.7450456619262695,
|
|
"epoch": 0.7225145137880987,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004955018540731714,
|
|
"loss": 5.5919,
|
|
"mean_token_accuracy": 0.15026113539934158,
|
|
"num_tokens": 16515515.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.799071168899536,
|
|
"epoch": 0.7229680696661829,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004954954142601288,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.14915079474449158,
|
|
"num_tokens": 16525359.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.8566121578216555,
|
|
"epoch": 0.723421625544267,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004954889698871849,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.15901191681623458,
|
|
"num_tokens": 16535113.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.744398498535157,
|
|
"epoch": 0.7238751814223512,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004954825209544728,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.16029145419597626,
|
|
"num_tokens": 16545638.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.814827013015747,
|
|
"epoch": 0.7243287373004355,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 0.000495476067462126,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.1573385030031204,
|
|
"num_tokens": 16555807.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.8214493751525875,
|
|
"epoch": 0.7247822931785196,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000495469609410278,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.15442904829978943,
|
|
"num_tokens": 16566143.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.75347580909729,
|
|
"epoch": 0.7252358490566038,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004954631467990622,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.15699395090341567,
|
|
"num_tokens": 16576192.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.796687459945678,
|
|
"epoch": 0.7256894049346879,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004954566796286124,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.14983606934547425,
|
|
"num_tokens": 16587841.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.856884336471557,
|
|
"epoch": 0.7261429608127722,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004954502078990623,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1537812352180481,
|
|
"num_tokens": 16598700.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.831228494644165,
|
|
"epoch": 0.7265965166908563,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004954437316105457,
|
|
"loss": 5.6951,
|
|
"mean_token_accuracy": 0.14877633303403853,
|
|
"num_tokens": 16609916.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.7455119609832765,
|
|
"epoch": 0.7270500725689405,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004954372507631965,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.15734955966472625,
|
|
"num_tokens": 16620508.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.800483751296997,
|
|
"epoch": 0.7275036284470247,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004954307653571489,
|
|
"loss": 5.6854,
|
|
"mean_token_accuracy": 0.15541286170482635,
|
|
"num_tokens": 16632128.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.829589605331421,
|
|
"epoch": 0.7279571843251088,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004954242753925367,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.1550593614578247,
|
|
"num_tokens": 16643447.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.80330080986023,
|
|
"epoch": 0.7284107402031931,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004954177808694946,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.16055452525615693,
|
|
"num_tokens": 16653237.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.792874145507812,
|
|
"epoch": 0.7288642960812772,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004954112817881565,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15150015503168107,
|
|
"num_tokens": 16663532.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.802073526382446,
|
|
"epoch": 0.7293178519593614,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004954047781486568,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.16309236139059066,
|
|
"num_tokens": 16673236.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.775296831130982,
|
|
"epoch": 0.7297714078374455,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004953982699511303,
|
|
"loss": 5.6399,
|
|
"mean_token_accuracy": 0.15158257484436036,
|
|
"num_tokens": 16684731.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.714089298248291,
|
|
"epoch": 0.7302249637155298,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004953917571957114,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.15534164160490035,
|
|
"num_tokens": 16694498.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.83448486328125,
|
|
"epoch": 0.730678519593614,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004953852398825346,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.15397260934114457,
|
|
"num_tokens": 16705514.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.70955262184143,
|
|
"epoch": 0.7311320754716981,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.000495378718011735,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.15810254365205764,
|
|
"num_tokens": 16714926.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.682147645950318,
|
|
"epoch": 0.7315856313497823,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004953721915834473,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.15791282206773757,
|
|
"num_tokens": 16725894.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.730485343933106,
|
|
"epoch": 0.7320391872278664,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004953656605978067,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.1612203910946846,
|
|
"num_tokens": 16735551.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.785016202926636,
|
|
"epoch": 0.7324927431059507,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000495359125054948,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.15639185756444932,
|
|
"num_tokens": 16746840.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.784290552139282,
|
|
"epoch": 0.7329462989840348,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004953525849550063,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.1611862748861313,
|
|
"num_tokens": 16756653.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.719831895828247,
|
|
"epoch": 0.733399854862119,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004953460402981172,
|
|
"loss": 5.706,
|
|
"mean_token_accuracy": 0.15862376540899276,
|
|
"num_tokens": 16767767.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.76441707611084,
|
|
"epoch": 0.7338534107402032,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004953394910844157,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.1488182619214058,
|
|
"num_tokens": 16778345.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.759904861450195,
|
|
"epoch": 0.7343069666182874,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004953329373140374,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.15454471111297607,
|
|
"num_tokens": 16788739.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.811275768280029,
|
|
"epoch": 0.7347605224963716,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004953263789871179,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.15244855135679244,
|
|
"num_tokens": 16799439.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.757402181625366,
|
|
"epoch": 0.7352140783744557,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004953198161037925,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.16849865913391113,
|
|
"num_tokens": 16808756.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.7503485679626465,
|
|
"epoch": 0.7356676342525399,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004953132486641975,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.15480702742934227,
|
|
"num_tokens": 16818973.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.709172677993775,
|
|
"epoch": 0.736121190130624,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000495306676668468,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.15501116514205932,
|
|
"num_tokens": 16828635.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.714795160293579,
|
|
"epoch": 0.7365747460087083,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004953001001167406,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.1607098326086998,
|
|
"num_tokens": 16838762.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.690447664260864,
|
|
"epoch": 0.7370283018867925,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004952935190091508,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.15998412072658538,
|
|
"num_tokens": 16849623.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.686318635940552,
|
|
"epoch": 0.7374818577648766,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004952869333458349,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.1523797407746315,
|
|
"num_tokens": 16860214.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.70399751663208,
|
|
"epoch": 0.7379354136429608,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004952803431269292,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.1519754208624363,
|
|
"num_tokens": 16871723.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.808839225769043,
|
|
"epoch": 0.738388969521045,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004952737483525699,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.1518370732665062,
|
|
"num_tokens": 16882500.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.797318315505981,
|
|
"epoch": 0.7388425253991292,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004952671490228932,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.15521494448184966,
|
|
"num_tokens": 16893386.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.798702096939087,
|
|
"epoch": 0.7392960812772134,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004952605451380357,
|
|
"loss": 5.704,
|
|
"mean_token_accuracy": 0.1514693468809128,
|
|
"num_tokens": 16904770.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.919784784317017,
|
|
"epoch": 0.7397496371552975,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004952539366981342,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.15494561344385147,
|
|
"num_tokens": 16915858.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.744434642791748,
|
|
"epoch": 0.7402031930333817,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000495247323703325,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.15603308826684953,
|
|
"num_tokens": 16926731.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.759461069107056,
|
|
"epoch": 0.7406567489114659,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.000495240706153745,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.15482465475797652,
|
|
"num_tokens": 16938108.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.690951871871948,
|
|
"epoch": 0.7411103047895501,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004952340840495312,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.1668120801448822,
|
|
"num_tokens": 16948516.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.74252872467041,
|
|
"epoch": 0.7415638606676342,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004952274573908203,
|
|
"loss": 5.5839,
|
|
"mean_token_accuracy": 0.15991057008504866,
|
|
"num_tokens": 16958642.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.717390298843384,
|
|
"epoch": 0.7420174165457184,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004952208261777496,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.15802238434553145,
|
|
"num_tokens": 16968429.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.745699214935303,
|
|
"epoch": 0.7424709724238027,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.000495214190410456,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.16200145781040193,
|
|
"num_tokens": 16978846.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.645253658294678,
|
|
"epoch": 0.7429245283018868,
|
|
"grad_norm": 5.25,
|
|
"learning_rate": 0.0004952075500890768,
|
|
"loss": 5.512,
|
|
"mean_token_accuracy": 0.1618196815252304,
|
|
"num_tokens": 16988353.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.665030670166016,
|
|
"epoch": 0.743378084179971,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004952009052137493,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.1606283813714981,
|
|
"num_tokens": 16998774.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.729429912567139,
|
|
"epoch": 0.7438316400580551,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004951942557846112,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.15656651556491852,
|
|
"num_tokens": 17009286.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.716187524795532,
|
|
"epoch": 0.7442851959361393,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004951876018017997,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.15400404408574103,
|
|
"num_tokens": 17020067.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.793141412734985,
|
|
"epoch": 0.7447387518142236,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004951809432654524,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.1583374872803688,
|
|
"num_tokens": 17031512.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.776523923873901,
|
|
"epoch": 0.7451923076923077,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.000495174280175707,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.15665111243724822,
|
|
"num_tokens": 17042928.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.641525316238403,
|
|
"epoch": 0.7456458635703919,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004951676125327015,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.14974198192358018,
|
|
"num_tokens": 17053327.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.80580325126648,
|
|
"epoch": 0.746099419448476,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004951609403365737,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.15747711509466172,
|
|
"num_tokens": 17063100.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.8813153266906735,
|
|
"epoch": 0.7465529753265603,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004951542635874615,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.15747971534729005,
|
|
"num_tokens": 17072715.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.8548980236053465,
|
|
"epoch": 0.7470065312046444,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004951475822855029,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.15097569525241852,
|
|
"num_tokens": 17082889.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.713144540786743,
|
|
"epoch": 0.7474600870827286,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004951408964308364,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.15977087765932083,
|
|
"num_tokens": 17093143.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.691396188735962,
|
|
"epoch": 0.7479136429608128,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004951342060236,
|
|
"loss": 5.5846,
|
|
"mean_token_accuracy": 0.15049274563789367,
|
|
"num_tokens": 17103818.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.7963649272918705,
|
|
"epoch": 0.7483671988388969,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004951275110639321,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.15465376079082488,
|
|
"num_tokens": 17114299.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.75806770324707,
|
|
"epoch": 0.7488207547169812,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004951208115519712,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1583488866686821,
|
|
"num_tokens": 17124309.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.780774116516113,
|
|
"epoch": 0.7492743105950653,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004951141074878558,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.1523465171456337,
|
|
"num_tokens": 17135493.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.785015106201172,
|
|
"epoch": 0.7497278664731495,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004951073988717246,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.15537115484476088,
|
|
"num_tokens": 17145054.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.764077663421631,
|
|
"epoch": 0.7501814223512336,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004951006857037163,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.15082504153251647,
|
|
"num_tokens": 17155401.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.824543714523315,
|
|
"epoch": 0.7506349782293179,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004950939679839696,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15418027192354203,
|
|
"num_tokens": 17165989.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.841431903839111,
|
|
"epoch": 0.7510885341074021,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004950872457126237,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.15596235692501068,
|
|
"num_tokens": 17176072.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.784214973449707,
|
|
"epoch": 0.7515420899854862,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004950805188898175,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.15422232523560525,
|
|
"num_tokens": 17186261.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.748292112350464,
|
|
"epoch": 0.7519956458635704,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00049507378751569,
|
|
"loss": 5.6683,
|
|
"mean_token_accuracy": 0.15558717995882035,
|
|
"num_tokens": 17197738.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.874657726287841,
|
|
"epoch": 0.7524492017416545,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004950670515903805,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.15427183508872985,
|
|
"num_tokens": 17208038.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.794052314758301,
|
|
"epoch": 0.7529027576197388,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004950603111140283,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.16207809001207352,
|
|
"num_tokens": 17218145.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.809648418426514,
|
|
"epoch": 0.753356313497823,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004950535660867728,
|
|
"loss": 5.7441,
|
|
"mean_token_accuracy": 0.14609585851430892,
|
|
"num_tokens": 17227281.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.744253730773925,
|
|
"epoch": 0.7538098693759071,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004950468165087535,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.1575057849287987,
|
|
"num_tokens": 17237571.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.737435293197632,
|
|
"epoch": 0.7542634252539913,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004950400623801098,
|
|
"loss": 5.6568,
|
|
"mean_token_accuracy": 0.1578634724020958,
|
|
"num_tokens": 17247088.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.797852087020874,
|
|
"epoch": 0.7547169811320755,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004950333037009818,
|
|
"loss": 5.5828,
|
|
"mean_token_accuracy": 0.1587523862719536,
|
|
"num_tokens": 17257638.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.803178405761718,
|
|
"epoch": 0.7551705370101597,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004950265404715089,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.1560966521501541,
|
|
"num_tokens": 17268421.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.787026023864746,
|
|
"epoch": 0.7556240928882438,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000495019772691831,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.14926135241985322,
|
|
"num_tokens": 17279264.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.759759044647216,
|
|
"epoch": 0.756077648766328,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004950130003620882,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15707915723323823,
|
|
"num_tokens": 17290913.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.737857341766357,
|
|
"epoch": 0.7565312046444121,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004950062234824204,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.1518915608525276,
|
|
"num_tokens": 17302366.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.773913192749023,
|
|
"epoch": 0.7569847605224964,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004949994420529679,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.16011033803224564,
|
|
"num_tokens": 17312855.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.766496276855468,
|
|
"epoch": 0.7574383164005806,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004949926560738709,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.15467959642410278,
|
|
"num_tokens": 17324644.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.727313995361328,
|
|
"epoch": 0.7578918722786647,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004949858655452697,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.149393293261528,
|
|
"num_tokens": 17334862.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.771681880950927,
|
|
"epoch": 0.7583454281567489,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004949790704673048,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.15446821749210357,
|
|
"num_tokens": 17345369.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.800436162948609,
|
|
"epoch": 0.7587989840348331,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004949722708401166,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.15178182274103164,
|
|
"num_tokens": 17356521.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.7372547626495365,
|
|
"epoch": 0.7592525399129173,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004949654666638457,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.15822072923183442,
|
|
"num_tokens": 17367919.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.7388671875,
|
|
"epoch": 0.7597060957910015,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000494958657938633,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.15761556178331376,
|
|
"num_tokens": 17378377.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.727004051208496,
|
|
"epoch": 0.7601596516690856,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004949518446646192,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.1600989006459713,
|
|
"num_tokens": 17388657.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.759643650054931,
|
|
"epoch": 0.7606132075471698,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004949450268419451,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.1576221317052841,
|
|
"num_tokens": 17399168.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.613120746612549,
|
|
"epoch": 0.761066763425254,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000494938204470752,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.16362162977457045,
|
|
"num_tokens": 17409426.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.706241512298584,
|
|
"epoch": 0.7615203193033382,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004949313775511806,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.15745215564966203,
|
|
"num_tokens": 17419850.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.735220050811767,
|
|
"epoch": 0.7619738751814223,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004949245460833723,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.15268349796533584,
|
|
"num_tokens": 17431936.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.778987169265747,
|
|
"epoch": 0.7624274310595065,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004949177100674684,
|
|
"loss": 5.6947,
|
|
"mean_token_accuracy": 0.1501627579331398,
|
|
"num_tokens": 17442814.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.8641212463378904,
|
|
"epoch": 0.7628809869375908,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004949108695036102,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15486170947551728,
|
|
"num_tokens": 17452723.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.77443037033081,
|
|
"epoch": 0.7633345428156749,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004949040243919392,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.15803532302379608,
|
|
"num_tokens": 17463332.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.717780447006225,
|
|
"epoch": 0.7637880986937591,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004948971747325968,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.1539319097995758,
|
|
"num_tokens": 17474338.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.765063953399658,
|
|
"epoch": 0.7642416545718432,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000494890320525725,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.15345966815948486,
|
|
"num_tokens": 17485236.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.743877935409546,
|
|
"epoch": 0.7646952104499274,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004948834617714652,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.15759633481502533,
|
|
"num_tokens": 17495795.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.741341543197632,
|
|
"epoch": 0.7651487663280117,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004948765984699595,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.14975285530090332,
|
|
"num_tokens": 17506756.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.7913984775543215,
|
|
"epoch": 0.7656023222060958,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004948697306213494,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.1652184545993805,
|
|
"num_tokens": 17516198.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.8136650085449215,
|
|
"epoch": 0.76605587808418,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004948628582257775,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.15337755233049394,
|
|
"num_tokens": 17527024.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.654916906356812,
|
|
"epoch": 0.7665094339622641,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004948559812833857,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.16364773660898208,
|
|
"num_tokens": 17536952.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.75989294052124,
|
|
"epoch": 0.7669629898403484,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004948490997943162,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15758652240037918,
|
|
"num_tokens": 17548879.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.799036121368408,
|
|
"epoch": 0.7674165457184325,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004948422137587111,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.16287029832601546,
|
|
"num_tokens": 17559149.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.788899993896484,
|
|
"epoch": 0.7678701015965167,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004948353231767131,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.15707586258649825,
|
|
"num_tokens": 17569995.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.841172218322754,
|
|
"epoch": 0.7683236574746009,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004948284280484645,
|
|
"loss": 5.6797,
|
|
"mean_token_accuracy": 0.15439939200878144,
|
|
"num_tokens": 17581336.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.832214212417602,
|
|
"epoch": 0.768777213352685,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004948215283741081,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1576690025627613,
|
|
"num_tokens": 17592680.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.737134313583374,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004948146241537866,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.16077874451875687,
|
|
"num_tokens": 17603049.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.670020675659179,
|
|
"epoch": 0.7696843251088534,
|
|
"grad_norm": 8.0625,
|
|
"learning_rate": 0.0004948077153876425,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.1587527170777321,
|
|
"num_tokens": 17612761.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.740362167358398,
|
|
"epoch": 0.7701378809869376,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004948008020758188,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.15385191291570663,
|
|
"num_tokens": 17622343.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.714895582199096,
|
|
"epoch": 0.7705914368650217,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004947938842184585,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.158719938993454,
|
|
"num_tokens": 17632949.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.802890920639038,
|
|
"epoch": 0.771044992743106,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004947869618157048,
|
|
"loss": 5.6555,
|
|
"mean_token_accuracy": 0.15329065024852753,
|
|
"num_tokens": 17643199.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.879572439193725,
|
|
"epoch": 0.7714985486211902,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004947800348677006,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.14939892888069153,
|
|
"num_tokens": 17653708.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.754754877090454,
|
|
"epoch": 0.7719521044992743,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004947731033745893,
|
|
"loss": 5.674,
|
|
"mean_token_accuracy": 0.15467614233493804,
|
|
"num_tokens": 17664360.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.729792642593384,
|
|
"epoch": 0.7724056603773585,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004947661673365142,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.15840732157230378,
|
|
"num_tokens": 17674614.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.753319120407104,
|
|
"epoch": 0.7728592162554426,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004947592267536188,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.15683589577674867,
|
|
"num_tokens": 17683990.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.761773586273193,
|
|
"epoch": 0.7733127721335269,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004947522816260466,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.1477172538638115,
|
|
"num_tokens": 17694188.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.736271381378174,
|
|
"epoch": 0.773766328011611,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004947453319539411,
|
|
"loss": 5.628,
|
|
"mean_token_accuracy": 0.1537310317158699,
|
|
"num_tokens": 17705466.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.7209672927856445,
|
|
"epoch": 0.7742198838896952,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004947383777374462,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.16311814337968827,
|
|
"num_tokens": 17715002.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.681128740310669,
|
|
"epoch": 0.7746734397677794,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004947314189767058,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.15525227189064025,
|
|
"num_tokens": 17725616.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.754605531692505,
|
|
"epoch": 0.7751269956458636,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004947244556718635,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.1498018816113472,
|
|
"num_tokens": 17736970.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.7690338611602785,
|
|
"epoch": 0.7755805515239478,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004947174878230635,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.15429942607879638,
|
|
"num_tokens": 17747235.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.724594306945801,
|
|
"epoch": 0.7760341074020319,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004947105154304498,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.1567047655582428,
|
|
"num_tokens": 17758345.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.745009088516236,
|
|
"epoch": 0.7764876632801161,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004947035384941667,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.15353951454162598,
|
|
"num_tokens": 17768226.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.820920133590699,
|
|
"epoch": 0.7769412191582002,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004946965570143584,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.15955789536237716,
|
|
"num_tokens": 17777742.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.8193521976470945,
|
|
"epoch": 0.7773947750362845,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004946895709911695,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1583583325147629,
|
|
"num_tokens": 17787529.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.719511461257935,
|
|
"epoch": 0.7778483309143687,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004946825804247442,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.15740730315446855,
|
|
"num_tokens": 17799499.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.65519962310791,
|
|
"epoch": 0.7783018867924528,
|
|
"grad_norm": 4.28125,
|
|
"learning_rate": 0.000494675585315227,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.16181525439023972,
|
|
"num_tokens": 17809622.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.734025955200195,
|
|
"epoch": 0.778755442670537,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004946685856627628,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.1616109773516655,
|
|
"num_tokens": 17820677.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.733445692062378,
|
|
"epoch": 0.7792089985486212,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004946615814674963,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.15883141607046128,
|
|
"num_tokens": 17830288.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.746526098251342,
|
|
"epoch": 0.7796625544267054,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004946545727295724,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.15067204385995864,
|
|
"num_tokens": 17840854.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.709014177322388,
|
|
"epoch": 0.7801161103047896,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004946475594491359,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1614265039563179,
|
|
"num_tokens": 17850860.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.734700679779053,
|
|
"epoch": 0.7805696661828737,
|
|
"grad_norm": 3.5,
|
|
"learning_rate": 0.0004946405416263319,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.15939305275678634,
|
|
"num_tokens": 17860254.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.708762884140015,
|
|
"epoch": 0.7810232220609579,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004946335192613054,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.15273386538028716,
|
|
"num_tokens": 17871705.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.860450887680054,
|
|
"epoch": 0.7814767779390421,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004946264923542019,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.15346125960350038,
|
|
"num_tokens": 17883184.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.795368385314942,
|
|
"epoch": 0.7819303338171263,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004946194609051664,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.1526493489742279,
|
|
"num_tokens": 17894696.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.6946038722991945,
|
|
"epoch": 0.7823838896952104,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004946124249143447,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.157182414829731,
|
|
"num_tokens": 17904454.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.7621626377105715,
|
|
"epoch": 0.7828374455732946,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000494605384381882,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.15995606780052185,
|
|
"num_tokens": 17915097.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.823960685729981,
|
|
"epoch": 0.7832910014513788,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004945983393079239,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.15308469980955125,
|
|
"num_tokens": 17926234.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.75256199836731,
|
|
"epoch": 0.783744557329463,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004945912896926163,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.16132265329360962,
|
|
"num_tokens": 17936492.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.686544179916382,
|
|
"epoch": 0.7841981132075472,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004945842355361049,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.15452968776226045,
|
|
"num_tokens": 17946541.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.759810876846314,
|
|
"epoch": 0.7846516690856313,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004945771768385355,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.17018820494413375,
|
|
"num_tokens": 17956257.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.747081756591797,
|
|
"epoch": 0.7851052249637155,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.000494570113600054,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16424116641283035,
|
|
"num_tokens": 17966108.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.712142896652222,
|
|
"epoch": 0.7855587808417998,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004945630458208068,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.16179561316967012,
|
|
"num_tokens": 17975487.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.725969219207764,
|
|
"epoch": 0.7860123367198839,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004945559735009397,
|
|
"loss": 5.6136,
|
|
"mean_token_accuracy": 0.1575325086712837,
|
|
"num_tokens": 17986308.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.775984191894532,
|
|
"epoch": 0.7864658925979681,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004945488966405993,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15036723241209984,
|
|
"num_tokens": 17996844.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.75177230834961,
|
|
"epoch": 0.7869194484760522,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004945418152399317,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.15092529505491256,
|
|
"num_tokens": 18007648.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.729442882537842,
|
|
"epoch": 0.7873730043541364,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004945347292990833,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.1617960065603256,
|
|
"num_tokens": 18017971.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.704108619689942,
|
|
"epoch": 0.7878265602322206,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004945276388182008,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16510131061077118,
|
|
"num_tokens": 18028500.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.76072244644165,
|
|
"epoch": 0.7882801161103048,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004945205437974309,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.16115738749504088,
|
|
"num_tokens": 18038101.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.81218113899231,
|
|
"epoch": 0.788733671988389,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004945134442369201,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.15752734541893004,
|
|
"num_tokens": 18048416.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.749841165542603,
|
|
"epoch": 0.7891872278664731,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004945063401368154,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.15486560091376306,
|
|
"num_tokens": 18058711.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.753841733932495,
|
|
"epoch": 0.7896407837445574,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004944992314972637,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.1602311372756958,
|
|
"num_tokens": 18068855.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.681754302978516,
|
|
"epoch": 0.7900943396226415,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004944921183184118,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.16171472668647766,
|
|
"num_tokens": 18079025.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.77334885597229,
|
|
"epoch": 0.7905478955007257,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000494485000600407,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.14843253791332245,
|
|
"num_tokens": 18091032.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.69298734664917,
|
|
"epoch": 0.7910014513788098,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004944778783433965,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.16092147380113603,
|
|
"num_tokens": 18101398.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.712299537658692,
|
|
"epoch": 0.791455007256894,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004944707515475276,
|
|
"loss": 5.5059,
|
|
"mean_token_accuracy": 0.15996126383543013,
|
|
"num_tokens": 18111029.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.668330574035645,
|
|
"epoch": 0.7919085631349783,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004944636202129475,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.1612555891275406,
|
|
"num_tokens": 18120593.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.784639167785644,
|
|
"epoch": 0.7923621190130624,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004944564843398039,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.1531424716114998,
|
|
"num_tokens": 18131692.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.766321182250977,
|
|
"epoch": 0.7928156748911466,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004944493439282443,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.16134166419506074,
|
|
"num_tokens": 18141244.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.73597526550293,
|
|
"epoch": 0.7932692307692307,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004944421989784162,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.15590226352214814,
|
|
"num_tokens": 18150585.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.686997890472412,
|
|
"epoch": 0.793722786647315,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004944350494904676,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.16071152836084365,
|
|
"num_tokens": 18160981.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.771206426620483,
|
|
"epoch": 0.7941763425253991,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004944278954645463,
|
|
"loss": 5.5691,
|
|
"mean_token_accuracy": 0.15511913746595382,
|
|
"num_tokens": 18171181.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.806949472427368,
|
|
"epoch": 0.7946298984034833,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004944207369008002,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.1530435189604759,
|
|
"num_tokens": 18181095.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.734293699264526,
|
|
"epoch": 0.7950834542815675,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004944135737993773,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.15290747284889222,
|
|
"num_tokens": 18190153.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.646497964859009,
|
|
"epoch": 0.7955370101596516,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004944064061604258,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.15470516681671143,
|
|
"num_tokens": 18201413.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.656438779830933,
|
|
"epoch": 0.7959905660377359,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004943992339840939,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.16347565948963166,
|
|
"num_tokens": 18211200.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.8274603366851805,
|
|
"epoch": 0.79644412191582,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.00049439205727053,
|
|
"loss": 5.7226,
|
|
"mean_token_accuracy": 0.14984723031520844,
|
|
"num_tokens": 18222730.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.841176557540893,
|
|
"epoch": 0.7968976777939042,
|
|
"grad_norm": 3.828125,
|
|
"learning_rate": 0.0004943848760198823,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.15421689599752425,
|
|
"num_tokens": 18232905.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.892225837707519,
|
|
"epoch": 0.7973512336719883,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004943776902322995,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.14882886409759521,
|
|
"num_tokens": 18243010.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.775762557983398,
|
|
"epoch": 0.7978047895500726,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004943704999079302,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.16070357263088225,
|
|
"num_tokens": 18254093.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.7349199771881105,
|
|
"epoch": 0.7982583454281568,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004943633050469231,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.15499844700098037,
|
|
"num_tokens": 18264103.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.7692304134368895,
|
|
"epoch": 0.7987119013062409,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004943561056494269,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.15571623742580415,
|
|
"num_tokens": 18276051.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.779341125488282,
|
|
"epoch": 0.7991654571843251,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004943489017155906,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.15946148782968522,
|
|
"num_tokens": 18286854.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.752212572097778,
|
|
"epoch": 0.7996190130624092,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004943416932455631,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.15069335103034973,
|
|
"num_tokens": 18298404.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.673287105560303,
|
|
"epoch": 0.8000725689404935,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004943344802394935,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.15464189201593398,
|
|
"num_tokens": 18309541.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.746518754959107,
|
|
"epoch": 0.8005261248185777,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004943272626975309,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.1546555534005165,
|
|
"num_tokens": 18320438.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.830396270751953,
|
|
"epoch": 0.8009796806966618,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004943200406198246,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.15161113142967225,
|
|
"num_tokens": 18331964.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.8303650379180905,
|
|
"epoch": 0.801433236574746,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.000494312814006524,
|
|
"loss": 5.637,
|
|
"mean_token_accuracy": 0.149752576649189,
|
|
"num_tokens": 18342479.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.762335300445557,
|
|
"epoch": 0.8018867924528302,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 0.0004943055828577784,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.15963243693113327,
|
|
"num_tokens": 18353428.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.714380741119385,
|
|
"epoch": 0.8023403483309144,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.0004942983471737376,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.16554586738348007,
|
|
"num_tokens": 18362440.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.777411890029907,
|
|
"epoch": 0.8027939042089985,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 0.0004942911069545511,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.1575615018606186,
|
|
"num_tokens": 18372130.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.781487846374512,
|
|
"epoch": 0.8032474600870827,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004942838622003686,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.15949161052703859,
|
|
"num_tokens": 18383262.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.784262704849243,
|
|
"epoch": 0.8037010159651669,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004942766129113399,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.15410858765244484,
|
|
"num_tokens": 18394036.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.731306695938111,
|
|
"epoch": 0.8041545718432511,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004942693590876151,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.16315408200025558,
|
|
"num_tokens": 18404249.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.722614669799805,
|
|
"epoch": 0.8046081277213353,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.000494262100729344,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.15265329629182817,
|
|
"num_tokens": 18415410.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.736243772506714,
|
|
"epoch": 0.8050616835994194,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004942548378366768,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.15731293857097625,
|
|
"num_tokens": 18425762.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.70797061920166,
|
|
"epoch": 0.8055152394775036,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004942475704097635,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.15828103423118592,
|
|
"num_tokens": 18436378.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.767156314849854,
|
|
"epoch": 0.8059687953555879,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004942402984487548,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.15951280891895295,
|
|
"num_tokens": 18445062.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.708318996429443,
|
|
"epoch": 0.806422351233672,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004942330219538008,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15844014585018157,
|
|
"num_tokens": 18455555.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.820754480361939,
|
|
"epoch": 0.8068759071117562,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.000494225740925052,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.162959423661232,
|
|
"num_tokens": 18465703.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.713505792617798,
|
|
"epoch": 0.8073294629898403,
|
|
"grad_norm": 6.53125,
|
|
"learning_rate": 0.0004942184553626591,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.16358105093240738,
|
|
"num_tokens": 18475640.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.80126953125,
|
|
"epoch": 0.8077830188679245,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004942111652667726,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.15995924472808837,
|
|
"num_tokens": 18485135.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.706670236587525,
|
|
"epoch": 0.8082365747460087,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004942038706375433,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.1538008600473404,
|
|
"num_tokens": 18496086.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.665920352935791,
|
|
"epoch": 0.8086901306240929,
|
|
"grad_norm": 5.40625,
|
|
"learning_rate": 0.0004941965714751222,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.15753740072250366,
|
|
"num_tokens": 18506004.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.753987216949463,
|
|
"epoch": 0.809143686502177,
|
|
"grad_norm": 5.5625,
|
|
"learning_rate": 0.0004941892677796601,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15734172016382217,
|
|
"num_tokens": 18515732.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.8059326171875,
|
|
"epoch": 0.8095972423802612,
|
|
"grad_norm": 4.40625,
|
|
"learning_rate": 0.0004941819595513081,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.15974941700696946,
|
|
"num_tokens": 18525782.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.767988824844361,
|
|
"epoch": 0.8100507982583455,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004941746467902173,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.1544948175549507,
|
|
"num_tokens": 18536049.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.749485301971435,
|
|
"epoch": 0.8105043541364296,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 0.000494167329496539,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.16105745136737823,
|
|
"num_tokens": 18547392.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.813601493835449,
|
|
"epoch": 0.8109579100145138,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004941600076704244,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.15198875218629837,
|
|
"num_tokens": 18558841.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.809838914871216,
|
|
"epoch": 0.8114114658925979,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004941526813120251,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.1533591032028198,
|
|
"num_tokens": 18570727.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.755561828613281,
|
|
"epoch": 0.8118650217706821,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004941453504214924,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.15869819819927217,
|
|
"num_tokens": 18581168.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.794755649566651,
|
|
"epoch": 0.8123185776487664,
|
|
"grad_norm": 3.6875,
|
|
"learning_rate": 0.0004941380149989781,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.15217462480068206,
|
|
"num_tokens": 18590800.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.759859037399292,
|
|
"epoch": 0.8127721335268505,
|
|
"grad_norm": 3.953125,
|
|
"learning_rate": 0.0004941306750446336,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.1570788413286209,
|
|
"num_tokens": 18601847.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.813338756561279,
|
|
"epoch": 0.8132256894049347,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000494123330558611,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.15837844759225844,
|
|
"num_tokens": 18613105.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.797929859161377,
|
|
"epoch": 0.8136792452830188,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004941159815410622,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1564161814749241,
|
|
"num_tokens": 18622945.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.773069620132446,
|
|
"epoch": 0.8141328011611031,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.000494108627992139,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.15942140966653823,
|
|
"num_tokens": 18632726.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.771838808059693,
|
|
"epoch": 0.8145863570391872,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.0004941012699119936,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.1561790868639946,
|
|
"num_tokens": 18642984.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.749499177932739,
|
|
"epoch": 0.8150399129172714,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004940939073007779,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.15468558818101882,
|
|
"num_tokens": 18653399.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.741241455078125,
|
|
"epoch": 0.8154934687953556,
|
|
"grad_norm": 3.90625,
|
|
"learning_rate": 0.0004940865401586446,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.15652735829353331,
|
|
"num_tokens": 18664641.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.765671825408935,
|
|
"epoch": 0.8159470246734397,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004940791684857458,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.15982917249202727,
|
|
"num_tokens": 18674890.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.710493898391723,
|
|
"epoch": 0.816400580551524,
|
|
"grad_norm": 6.9375,
|
|
"learning_rate": 0.0004940717922822339,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.15173522233963013,
|
|
"num_tokens": 18686455.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.816400580551524,
|
|
"eval_entropy": 5.556482378929449,
|
|
"eval_loss": 5.628951549530029,
|
|
"eval_mean_token_accuracy": 0.16274379363275088,
|
|
"eval_num_tokens": 18686455.0,
|
|
"eval_runtime": 26.5865,
|
|
"eval_samples_per_second": 1329.999,
|
|
"eval_steps_per_second": 166.25,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2.7373590171648e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|