924089098f
Model: fpadovani/heb-hebr-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3210444646583552,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.438523864746093,
|
|
"epoch": 0.0005350741077639254,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.9918,
|
|
"mean_token_accuracy": 0.07089582867920399,
|
|
"num_tokens": 10038.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.456669139862061,
|
|
"epoch": 0.0010701482155278507,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 8.0207,
|
|
"mean_token_accuracy": 0.06915676817297936,
|
|
"num_tokens": 21916.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.433949184417724,
|
|
"epoch": 0.0016052223232917758,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.9738,
|
|
"mean_token_accuracy": 0.07175181061029434,
|
|
"num_tokens": 33434.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.42863655090332,
|
|
"epoch": 0.0021402964310557014,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.9992,
|
|
"mean_token_accuracy": 0.07069024555385113,
|
|
"num_tokens": 44216.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.486217021942139,
|
|
"epoch": 0.0026753705388196263,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 8.0517,
|
|
"mean_token_accuracy": 0.06462443582713603,
|
|
"num_tokens": 54874.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.387908840179444,
|
|
"epoch": 0.0032104446465835517,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 8.0177,
|
|
"mean_token_accuracy": 0.06798936054110527,
|
|
"num_tokens": 65085.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.35386152267456,
|
|
"epoch": 0.003745518754347477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.9437,
|
|
"mean_token_accuracy": 0.07121415473520756,
|
|
"num_tokens": 75601.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.347406768798828,
|
|
"epoch": 0.004280592862111403,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.9581,
|
|
"mean_token_accuracy": 0.06999797709286212,
|
|
"num_tokens": 86193.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.334976387023925,
|
|
"epoch": 0.004815666969875327,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.9684,
|
|
"mean_token_accuracy": 0.07105263583362102,
|
|
"num_tokens": 96957.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.303908538818359,
|
|
"epoch": 0.005350741077639253,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.9762,
|
|
"mean_token_accuracy": 0.07353106662631034,
|
|
"num_tokens": 108408.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.298726749420165,
|
|
"epoch": 0.005885815185403178,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.9953,
|
|
"mean_token_accuracy": 0.07212709933519364,
|
|
"num_tokens": 119273.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.286288166046143,
|
|
"epoch": 0.006420889293167103,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.9905,
|
|
"mean_token_accuracy": 0.07027627490460872,
|
|
"num_tokens": 130817.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.316905498504639,
|
|
"epoch": 0.006955963400931029,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.9532,
|
|
"mean_token_accuracy": 0.07230342477560044,
|
|
"num_tokens": 142599.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.320288467407227,
|
|
"epoch": 0.007491037508694954,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 8.0265,
|
|
"mean_token_accuracy": 0.07138649448752403,
|
|
"num_tokens": 153617.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.27239990234375,
|
|
"epoch": 0.00802611161645888,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 8.0025,
|
|
"mean_token_accuracy": 0.07099051140248776,
|
|
"num_tokens": 165280.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.26258363723755,
|
|
"epoch": 0.008561185724222806,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 8.0114,
|
|
"mean_token_accuracy": 0.06905640251934528,
|
|
"num_tokens": 176896.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.284344100952149,
|
|
"epoch": 0.00909625983198673,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.0257,
|
|
"mean_token_accuracy": 0.07325906008481979,
|
|
"num_tokens": 188000.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.30929183959961,
|
|
"epoch": 0.009631333939750655,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.0456,
|
|
"mean_token_accuracy": 0.07206745408475398,
|
|
"num_tokens": 199360.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.334034061431884,
|
|
"epoch": 0.01016640804751458,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.0372,
|
|
"mean_token_accuracy": 0.06812816448509693,
|
|
"num_tokens": 210214.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.277380561828613,
|
|
"epoch": 0.010701482155278505,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.9812,
|
|
"mean_token_accuracy": 0.0726207286119461,
|
|
"num_tokens": 220567.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.28692798614502,
|
|
"epoch": 0.011236556263042432,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.9213,
|
|
"mean_token_accuracy": 0.0739015869796276,
|
|
"num_tokens": 230585.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.240860843658448,
|
|
"epoch": 0.011771630370806356,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.9529,
|
|
"mean_token_accuracy": 0.07597600407898426,
|
|
"num_tokens": 241996.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.269025707244873,
|
|
"epoch": 0.012306704478570282,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.0585,
|
|
"mean_token_accuracy": 0.0713857039809227,
|
|
"num_tokens": 253348.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.29678030014038,
|
|
"epoch": 0.012841778586334207,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.9934,
|
|
"mean_token_accuracy": 0.07136886790394784,
|
|
"num_tokens": 264239.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.290089511871338,
|
|
"epoch": 0.013376852694098133,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.9854,
|
|
"mean_token_accuracy": 0.0759938657283783,
|
|
"num_tokens": 274522.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.258779525756836,
|
|
"epoch": 0.013911926801862057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9162,
|
|
"mean_token_accuracy": 0.07372806034982204,
|
|
"num_tokens": 284492.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.259482097625732,
|
|
"epoch": 0.014447000909625984,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9495,
|
|
"mean_token_accuracy": 0.0691726591438055,
|
|
"num_tokens": 294796.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.262565422058106,
|
|
"epoch": 0.014982075017389908,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.9688,
|
|
"mean_token_accuracy": 0.06928434409201145,
|
|
"num_tokens": 305252.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.28972578048706,
|
|
"epoch": 0.015517149125153834,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.9392,
|
|
"mean_token_accuracy": 0.07088566608726979,
|
|
"num_tokens": 315505.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.30866813659668,
|
|
"epoch": 0.01605222323291776,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.9823,
|
|
"mean_token_accuracy": 0.07642340660095215,
|
|
"num_tokens": 326997.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.21926565170288,
|
|
"epoch": 0.016587297340681685,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.965,
|
|
"mean_token_accuracy": 0.07135060504078865,
|
|
"num_tokens": 338089.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.278623867034913,
|
|
"epoch": 0.01712237144844561,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.941,
|
|
"mean_token_accuracy": 0.07322553470730782,
|
|
"num_tokens": 348536.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.384468746185302,
|
|
"epoch": 0.017657445556209534,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9822,
|
|
"mean_token_accuracy": 0.07200570702552796,
|
|
"num_tokens": 359776.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.223766422271728,
|
|
"epoch": 0.01819251966397346,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9346,
|
|
"mean_token_accuracy": 0.07174736969172954,
|
|
"num_tokens": 370810.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.291064643859864,
|
|
"epoch": 0.018727593771737387,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.9297,
|
|
"mean_token_accuracy": 0.06886534281075,
|
|
"num_tokens": 381788.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.28944501876831,
|
|
"epoch": 0.01926266787950131,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.9655,
|
|
"mean_token_accuracy": 0.07360603064298629,
|
|
"num_tokens": 391984.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.233330154418946,
|
|
"epoch": 0.019797741987265235,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.9263,
|
|
"mean_token_accuracy": 0.0702251672744751,
|
|
"num_tokens": 403430.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.325261878967286,
|
|
"epoch": 0.02033281609502916,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.9371,
|
|
"mean_token_accuracy": 0.07427182346582413,
|
|
"num_tokens": 414467.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.184919452667236,
|
|
"epoch": 0.020867890202793088,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.9317,
|
|
"mean_token_accuracy": 0.07251705303788185,
|
|
"num_tokens": 425752.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.154995250701905,
|
|
"epoch": 0.02140296431055701,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.9332,
|
|
"mean_token_accuracy": 0.07673878967761993,
|
|
"num_tokens": 435908.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.37842092514038,
|
|
"epoch": 0.021938038418320937,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.9546,
|
|
"mean_token_accuracy": 0.07372537180781365,
|
|
"num_tokens": 446424.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.196290493011475,
|
|
"epoch": 0.022473112526084863,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.9501,
|
|
"mean_token_accuracy": 0.07161405347287655,
|
|
"num_tokens": 456854.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.268616867065429,
|
|
"epoch": 0.02300818663384879,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.9591,
|
|
"mean_token_accuracy": 0.07364804670214653,
|
|
"num_tokens": 467899.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.188086223602294,
|
|
"epoch": 0.023543260741612712,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.8925,
|
|
"mean_token_accuracy": 0.07161371931433677,
|
|
"num_tokens": 478683.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.310243034362793,
|
|
"epoch": 0.02407833484937664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.9332,
|
|
"mean_token_accuracy": 0.07252216972410679,
|
|
"num_tokens": 488745.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.256323719024659,
|
|
"epoch": 0.024613408957140565,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.0014,
|
|
"mean_token_accuracy": 0.06898210793733597,
|
|
"num_tokens": 499448.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.350125885009765,
|
|
"epoch": 0.02514848306490449,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.9571,
|
|
"mean_token_accuracy": 0.07444347888231277,
|
|
"num_tokens": 510148.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.19766731262207,
|
|
"epoch": 0.025683557172668414,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8968,
|
|
"mean_token_accuracy": 0.06857617050409318,
|
|
"num_tokens": 522093.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.271492099761963,
|
|
"epoch": 0.02621863128043234,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.9091,
|
|
"mean_token_accuracy": 0.07259679697453976,
|
|
"num_tokens": 532598.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.260428142547607,
|
|
"epoch": 0.026753705388196266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.9073,
|
|
"mean_token_accuracy": 0.07138925977051258,
|
|
"num_tokens": 542652.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.230937385559082,
|
|
"epoch": 0.027288779495960192,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.9364,
|
|
"mean_token_accuracy": 0.0716529581695795,
|
|
"num_tokens": 552526.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.221650218963623,
|
|
"epoch": 0.027823853603724115,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.9482,
|
|
"mean_token_accuracy": 0.07255502007901668,
|
|
"num_tokens": 563143.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.36287260055542,
|
|
"epoch": 0.02835892771148804,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.914,
|
|
"mean_token_accuracy": 0.07049775309860706,
|
|
"num_tokens": 573814.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.100260066986085,
|
|
"epoch": 0.028894001819251967,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.8981,
|
|
"mean_token_accuracy": 0.08190436586737633,
|
|
"num_tokens": 585367.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.38329620361328,
|
|
"epoch": 0.02942907592701589,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.97,
|
|
"mean_token_accuracy": 0.07323053516447545,
|
|
"num_tokens": 595902.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.164136409759521,
|
|
"epoch": 0.029964150034779816,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.8714,
|
|
"mean_token_accuracy": 0.06739694848656655,
|
|
"num_tokens": 607178.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.225701713562012,
|
|
"epoch": 0.030499224142543743,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.8633,
|
|
"mean_token_accuracy": 0.07506305202841759,
|
|
"num_tokens": 618604.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.170948696136474,
|
|
"epoch": 0.03103429825030767,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.9374,
|
|
"mean_token_accuracy": 0.08010841310024261,
|
|
"num_tokens": 628111.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.36645040512085,
|
|
"epoch": 0.03156937235807159,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.9578,
|
|
"mean_token_accuracy": 0.0780744157731533,
|
|
"num_tokens": 639358.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.155040645599366,
|
|
"epoch": 0.03210444646583552,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.8323,
|
|
"mean_token_accuracy": 0.0761849269270897,
|
|
"num_tokens": 649504.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.273955917358398,
|
|
"epoch": 0.032639520573599444,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.8248,
|
|
"mean_token_accuracy": 0.07312047109007835,
|
|
"num_tokens": 659924.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.170460605621338,
|
|
"epoch": 0.03317459468136337,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.9094,
|
|
"mean_token_accuracy": 0.07122809328138828,
|
|
"num_tokens": 671120.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.215112972259522,
|
|
"epoch": 0.033709668789127296,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.9236,
|
|
"mean_token_accuracy": 0.0743540145456791,
|
|
"num_tokens": 681956.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.37024908065796,
|
|
"epoch": 0.03424474289689122,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.9141,
|
|
"mean_token_accuracy": 0.07260976172983646,
|
|
"num_tokens": 693226.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.151279401779174,
|
|
"epoch": 0.03477981700465514,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.916,
|
|
"mean_token_accuracy": 0.07916250079870224,
|
|
"num_tokens": 704691.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.25889320373535,
|
|
"epoch": 0.03531489111241907,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.8971,
|
|
"mean_token_accuracy": 0.07115237936377525,
|
|
"num_tokens": 716000.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.184357643127441,
|
|
"epoch": 0.035849965220182994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.8192,
|
|
"mean_token_accuracy": 0.07512345798313617,
|
|
"num_tokens": 726723.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.12232265472412,
|
|
"epoch": 0.03638503932794692,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.839,
|
|
"mean_token_accuracy": 0.07773829847574235,
|
|
"num_tokens": 736740.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.21993284225464,
|
|
"epoch": 0.03692011343571085,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.8836,
|
|
"mean_token_accuracy": 0.07603165321052074,
|
|
"num_tokens": 747567.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.259039783477784,
|
|
"epoch": 0.03745518754347477,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.8234,
|
|
"mean_token_accuracy": 0.07849031463265418,
|
|
"num_tokens": 757937.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.095407104492187,
|
|
"epoch": 0.0379902616512387,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.8581,
|
|
"mean_token_accuracy": 0.07850076630711555,
|
|
"num_tokens": 768003.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.291385746002197,
|
|
"epoch": 0.03852533575900262,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.8925,
|
|
"mean_token_accuracy": 0.0735244907438755,
|
|
"num_tokens": 779098.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.161334991455078,
|
|
"epoch": 0.039060409866766545,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.84,
|
|
"mean_token_accuracy": 0.06926697231829167,
|
|
"num_tokens": 790002.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.280758094787597,
|
|
"epoch": 0.03959548397453047,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.8499,
|
|
"mean_token_accuracy": 0.07700608000159263,
|
|
"num_tokens": 800444.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.134241199493408,
|
|
"epoch": 0.0401305580822944,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.8075,
|
|
"mean_token_accuracy": 0.07820181213319302,
|
|
"num_tokens": 810912.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.192010021209716,
|
|
"epoch": 0.04066563219005832,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.8624,
|
|
"mean_token_accuracy": 0.07260131053626537,
|
|
"num_tokens": 822809.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.224451732635497,
|
|
"epoch": 0.04120070629782225,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.8217,
|
|
"mean_token_accuracy": 0.07982959300279617,
|
|
"num_tokens": 833362.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.141465377807616,
|
|
"epoch": 0.041735780405586176,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.8313,
|
|
"mean_token_accuracy": 0.077750289067626,
|
|
"num_tokens": 844239.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.161445951461792,
|
|
"epoch": 0.0422708545133501,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.8359,
|
|
"mean_token_accuracy": 0.07241239324212075,
|
|
"num_tokens": 855178.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.187870597839355,
|
|
"epoch": 0.04280592862111402,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.8156,
|
|
"mean_token_accuracy": 0.07676684893667698,
|
|
"num_tokens": 866120.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.141285848617553,
|
|
"epoch": 0.04334100272887795,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.8404,
|
|
"mean_token_accuracy": 0.07553332224488259,
|
|
"num_tokens": 876569.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.255392122268677,
|
|
"epoch": 0.043876076836641874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.8992,
|
|
"mean_token_accuracy": 0.0690174788236618,
|
|
"num_tokens": 887580.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.085278511047363,
|
|
"epoch": 0.0444111509444058,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.7913,
|
|
"mean_token_accuracy": 0.07601235955953597,
|
|
"num_tokens": 897922.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.172503471374512,
|
|
"epoch": 0.044946225052169726,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.7577,
|
|
"mean_token_accuracy": 0.0789629127830267,
|
|
"num_tokens": 908522.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.165214443206787,
|
|
"epoch": 0.04548129915993365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.7885,
|
|
"mean_token_accuracy": 0.07326138317584992,
|
|
"num_tokens": 918253.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.115808629989624,
|
|
"epoch": 0.04601637326769758,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.8016,
|
|
"mean_token_accuracy": 0.08077133670449257,
|
|
"num_tokens": 929150.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.195698833465576,
|
|
"epoch": 0.0465514473754615,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.8347,
|
|
"mean_token_accuracy": 0.07574150152504444,
|
|
"num_tokens": 941041.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.075660133361817,
|
|
"epoch": 0.047086521483225424,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.7722,
|
|
"mean_token_accuracy": 0.08273379057645798,
|
|
"num_tokens": 952714.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.142275619506837,
|
|
"epoch": 0.04762159559098935,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.8408,
|
|
"mean_token_accuracy": 0.07047965601086617,
|
|
"num_tokens": 964330.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.172155475616455,
|
|
"epoch": 0.04815666969875328,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.7753,
|
|
"mean_token_accuracy": 0.07703164294362068,
|
|
"num_tokens": 975257.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.126901054382325,
|
|
"epoch": 0.0486917438065172,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.7927,
|
|
"mean_token_accuracy": 0.07552689984440804,
|
|
"num_tokens": 986335.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.074871110916138,
|
|
"epoch": 0.04922681791428113,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.6976,
|
|
"mean_token_accuracy": 0.08165326192975045,
|
|
"num_tokens": 997521.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.101482772827149,
|
|
"epoch": 0.049761892022045055,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.7373,
|
|
"mean_token_accuracy": 0.07321427799761296,
|
|
"num_tokens": 1008383.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.052536773681641,
|
|
"epoch": 0.05029696612980898,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.7954,
|
|
"mean_token_accuracy": 0.0785468976944685,
|
|
"num_tokens": 1020552.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.111948776245118,
|
|
"epoch": 0.0508320402375729,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.777,
|
|
"mean_token_accuracy": 0.07793653532862663,
|
|
"num_tokens": 1031127.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.031802463531495,
|
|
"epoch": 0.05136711434533683,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.7047,
|
|
"mean_token_accuracy": 0.08362473249435425,
|
|
"num_tokens": 1043209.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.201984310150147,
|
|
"epoch": 0.05190218845310075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.8272,
|
|
"mean_token_accuracy": 0.07358191162347794,
|
|
"num_tokens": 1054032.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.945471096038818,
|
|
"epoch": 0.05243726256086468,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.6616,
|
|
"mean_token_accuracy": 0.08464075922966004,
|
|
"num_tokens": 1064565.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.197793436050414,
|
|
"epoch": 0.052972336668628606,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.8045,
|
|
"mean_token_accuracy": 0.0828012503683567,
|
|
"num_tokens": 1076352.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.114227867126464,
|
|
"epoch": 0.05350741077639253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.7318,
|
|
"mean_token_accuracy": 0.08148737102746964,
|
|
"num_tokens": 1087697.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.048880052566528,
|
|
"epoch": 0.05404248488415646,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6889,
|
|
"mean_token_accuracy": 0.08205336779356003,
|
|
"num_tokens": 1098056.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.030955266952514,
|
|
"epoch": 0.054577558991920384,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6531,
|
|
"mean_token_accuracy": 0.08614925965666771,
|
|
"num_tokens": 1109219.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.043565845489502,
|
|
"epoch": 0.055112633099684304,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.7548,
|
|
"mean_token_accuracy": 0.07777477391064166,
|
|
"num_tokens": 1120248.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.027316761016845,
|
|
"epoch": 0.05564770720744823,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.76,
|
|
"mean_token_accuracy": 0.08049454391002656,
|
|
"num_tokens": 1131278.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.131014013290406,
|
|
"epoch": 0.056182781315212156,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.7705,
|
|
"mean_token_accuracy": 0.07245919480919838,
|
|
"num_tokens": 1143147.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.059695053100587,
|
|
"epoch": 0.05671785542297608,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.6859,
|
|
"mean_token_accuracy": 0.07856054306030273,
|
|
"num_tokens": 1154316.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.993293809890747,
|
|
"epoch": 0.05725292953074001,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.7234,
|
|
"mean_token_accuracy": 0.07792837470769882,
|
|
"num_tokens": 1164696.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.043428564071656,
|
|
"epoch": 0.057788003638503935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.7068,
|
|
"mean_token_accuracy": 0.08335861712694168,
|
|
"num_tokens": 1176129.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.078899621963501,
|
|
"epoch": 0.05832307774626786,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.7054,
|
|
"mean_token_accuracy": 0.07883682176470756,
|
|
"num_tokens": 1186499.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.940136432647705,
|
|
"epoch": 0.05885815185403178,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.6918,
|
|
"mean_token_accuracy": 0.07827556133270264,
|
|
"num_tokens": 1196841.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.093690872192383,
|
|
"epoch": 0.059393225961795706,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.6333,
|
|
"mean_token_accuracy": 0.08411285057663917,
|
|
"num_tokens": 1207647.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.92292013168335,
|
|
"epoch": 0.05992830006955963,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.6327,
|
|
"mean_token_accuracy": 0.08724270015954971,
|
|
"num_tokens": 1217072.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.077197456359864,
|
|
"epoch": 0.06046337417732356,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.7452,
|
|
"mean_token_accuracy": 0.07838767245411873,
|
|
"num_tokens": 1228564.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.018522500991821,
|
|
"epoch": 0.060998448285087485,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.6793,
|
|
"mean_token_accuracy": 0.08147106729447842,
|
|
"num_tokens": 1238755.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.919596767425537,
|
|
"epoch": 0.06153352239285141,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.6333,
|
|
"mean_token_accuracy": 0.08646477684378624,
|
|
"num_tokens": 1248968.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.03002233505249,
|
|
"epoch": 0.06206859650061534,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.6137,
|
|
"mean_token_accuracy": 0.08215007483959198,
|
|
"num_tokens": 1259256.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.944347524642945,
|
|
"epoch": 0.06260367060837926,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.643,
|
|
"mean_token_accuracy": 0.08642460480332374,
|
|
"num_tokens": 1270469.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.007751417160033,
|
|
"epoch": 0.06313874471614318,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.6181,
|
|
"mean_token_accuracy": 0.08229104541242123,
|
|
"num_tokens": 1280558.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.976322603225708,
|
|
"epoch": 0.06367381882390712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.674,
|
|
"mean_token_accuracy": 0.07687576077878475,
|
|
"num_tokens": 1291372.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.998635149002075,
|
|
"epoch": 0.06420889293167104,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7289,
|
|
"mean_token_accuracy": 0.07478231713175773,
|
|
"num_tokens": 1302521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.969287395477295,
|
|
"epoch": 0.06474396703943497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.5754,
|
|
"mean_token_accuracy": 0.08087456151843071,
|
|
"num_tokens": 1313632.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.923420429229736,
|
|
"epoch": 0.06527904114719889,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.6678,
|
|
"mean_token_accuracy": 0.08702994361519814,
|
|
"num_tokens": 1325247.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.002186822891236,
|
|
"epoch": 0.06581411525496281,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.6436,
|
|
"mean_token_accuracy": 0.08546153195202351,
|
|
"num_tokens": 1336026.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.921476411819458,
|
|
"epoch": 0.06634918936272674,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.5697,
|
|
"mean_token_accuracy": 0.08310725018382073,
|
|
"num_tokens": 1346920.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.907757997512817,
|
|
"epoch": 0.06688426347049066,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.7126,
|
|
"mean_token_accuracy": 0.0809940081089735,
|
|
"num_tokens": 1359752.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.077805948257446,
|
|
"epoch": 0.06741933757825459,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7158,
|
|
"mean_token_accuracy": 0.0815380372107029,
|
|
"num_tokens": 1370874.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.973085069656372,
|
|
"epoch": 0.06795441168601851,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6168,
|
|
"mean_token_accuracy": 0.08611245974898338,
|
|
"num_tokens": 1382316.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.903048658370972,
|
|
"epoch": 0.06848948579378245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6414,
|
|
"mean_token_accuracy": 0.07778934091329574,
|
|
"num_tokens": 1394656.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.872803163528443,
|
|
"epoch": 0.06902455990154636,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.606,
|
|
"mean_token_accuracy": 0.08503136709332466,
|
|
"num_tokens": 1405061.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.917471504211425,
|
|
"epoch": 0.06955963400931028,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.5769,
|
|
"mean_token_accuracy": 0.09031685814261436,
|
|
"num_tokens": 1415573.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.893562746047974,
|
|
"epoch": 0.07009470811707422,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.6178,
|
|
"mean_token_accuracy": 0.08216161504387856,
|
|
"num_tokens": 1426103.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.87309250831604,
|
|
"epoch": 0.07062978222483814,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.6244,
|
|
"mean_token_accuracy": 0.0775572419166565,
|
|
"num_tokens": 1437256.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.008783912658691,
|
|
"epoch": 0.07116485633260207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.567,
|
|
"mean_token_accuracy": 0.08571906089782715,
|
|
"num_tokens": 1446975.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.912457418441773,
|
|
"epoch": 0.07169993044036599,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.5982,
|
|
"mean_token_accuracy": 0.08147824630141258,
|
|
"num_tokens": 1457751.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.847382688522339,
|
|
"epoch": 0.07223500454812992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.5696,
|
|
"mean_token_accuracy": 0.08593818917870522,
|
|
"num_tokens": 1468186.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.877796840667725,
|
|
"epoch": 0.07277007865589384,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.6083,
|
|
"mean_token_accuracy": 0.0857892669737339,
|
|
"num_tokens": 1479780.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.932244157791137,
|
|
"epoch": 0.07330515276365776,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.5388,
|
|
"mean_token_accuracy": 0.08653553798794747,
|
|
"num_tokens": 1490565.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.894024896621704,
|
|
"epoch": 0.0738402268714217,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.5761,
|
|
"mean_token_accuracy": 0.08645963147282601,
|
|
"num_tokens": 1501552.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.909371280670166,
|
|
"epoch": 0.07437530097918561,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.5771,
|
|
"mean_token_accuracy": 0.07754943668842315,
|
|
"num_tokens": 1513311.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.87781400680542,
|
|
"epoch": 0.07491037508694955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.6125,
|
|
"mean_token_accuracy": 0.08723289221525192,
|
|
"num_tokens": 1524142.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.864214611053467,
|
|
"epoch": 0.07544544919471347,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5963,
|
|
"mean_token_accuracy": 0.08427691981196403,
|
|
"num_tokens": 1535571.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.935462474822998,
|
|
"epoch": 0.0759805233024774,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.5832,
|
|
"mean_token_accuracy": 0.0857673317193985,
|
|
"num_tokens": 1546528.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.834042024612427,
|
|
"epoch": 0.07651559741024132,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.605,
|
|
"mean_token_accuracy": 0.07878369390964508,
|
|
"num_tokens": 1557264.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.917755889892578,
|
|
"epoch": 0.07705067151800524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.5516,
|
|
"mean_token_accuracy": 0.08911938816308976,
|
|
"num_tokens": 1566773.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.75898847579956,
|
|
"epoch": 0.07758574562576917,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.5218,
|
|
"mean_token_accuracy": 0.08892029449343682,
|
|
"num_tokens": 1578173.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.871085929870605,
|
|
"epoch": 0.07812081973353309,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5015,
|
|
"mean_token_accuracy": 0.09052813053131104,
|
|
"num_tokens": 1588537.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.736292791366577,
|
|
"epoch": 0.07865589384129702,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.5115,
|
|
"mean_token_accuracy": 0.0933248370885849,
|
|
"num_tokens": 1599159.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.805051469802857,
|
|
"epoch": 0.07919096794906094,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.5827,
|
|
"mean_token_accuracy": 0.0800521731376648,
|
|
"num_tokens": 1610378.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.855951356887817,
|
|
"epoch": 0.07972604205682488,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5855,
|
|
"mean_token_accuracy": 0.08528665937483311,
|
|
"num_tokens": 1621215.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.891303634643554,
|
|
"epoch": 0.0802611161645888,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.5505,
|
|
"mean_token_accuracy": 0.08498321324586869,
|
|
"num_tokens": 1631170.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.851488780975342,
|
|
"epoch": 0.08079619027235273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5277,
|
|
"mean_token_accuracy": 0.08108025044202805,
|
|
"num_tokens": 1641897.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.834504079818726,
|
|
"epoch": 0.08133126438011665,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.6102,
|
|
"mean_token_accuracy": 0.08256747871637345,
|
|
"num_tokens": 1653592.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.763096284866333,
|
|
"epoch": 0.08186633848788057,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5449,
|
|
"mean_token_accuracy": 0.07726698741316795,
|
|
"num_tokens": 1665760.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.829190349578857,
|
|
"epoch": 0.0824014125956445,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.5258,
|
|
"mean_token_accuracy": 0.08868773877620698,
|
|
"num_tokens": 1676211.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.830986452102661,
|
|
"epoch": 0.08293648670340842,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.5557,
|
|
"mean_token_accuracy": 0.08339334577322007,
|
|
"num_tokens": 1686405.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.9128564357757565,
|
|
"epoch": 0.08347156081117235,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5381,
|
|
"mean_token_accuracy": 0.08266621455550194,
|
|
"num_tokens": 1697340.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.817310953140259,
|
|
"epoch": 0.08400663491893627,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.452,
|
|
"mean_token_accuracy": 0.09346645250916481,
|
|
"num_tokens": 1707250.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.762820196151734,
|
|
"epoch": 0.0845417090267002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4204,
|
|
"mean_token_accuracy": 0.08826526999473572,
|
|
"num_tokens": 1718333.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.728808927536011,
|
|
"epoch": 0.08507678313446412,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.5294,
|
|
"mean_token_accuracy": 0.08095861524343491,
|
|
"num_tokens": 1730520.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.858559417724609,
|
|
"epoch": 0.08561185724222804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.606,
|
|
"mean_token_accuracy": 0.0792750682681799,
|
|
"num_tokens": 1741898.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.734847450256348,
|
|
"epoch": 0.08614693134999198,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5398,
|
|
"mean_token_accuracy": 0.08668501451611518,
|
|
"num_tokens": 1751671.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.7590573787689205,
|
|
"epoch": 0.0866820054577559,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5585,
|
|
"mean_token_accuracy": 0.08537478670477867,
|
|
"num_tokens": 1762076.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.856442165374756,
|
|
"epoch": 0.08721707956551983,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5235,
|
|
"mean_token_accuracy": 0.08367472253739834,
|
|
"num_tokens": 1772666.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.803241539001465,
|
|
"epoch": 0.08775215367328375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5335,
|
|
"mean_token_accuracy": 0.08659583106637,
|
|
"num_tokens": 1783621.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.801509761810303,
|
|
"epoch": 0.08828722778104768,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.5852,
|
|
"mean_token_accuracy": 0.08275783434510231,
|
|
"num_tokens": 1794654.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.688510131835938,
|
|
"epoch": 0.0888223018888116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.493,
|
|
"mean_token_accuracy": 0.08838511407375335,
|
|
"num_tokens": 1805853.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.636126375198364,
|
|
"epoch": 0.08935737599657552,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.4698,
|
|
"mean_token_accuracy": 0.08840174004435539,
|
|
"num_tokens": 1817006.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.8402852535247805,
|
|
"epoch": 0.08989245010433945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.448,
|
|
"mean_token_accuracy": 0.08388116732239723,
|
|
"num_tokens": 1827166.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.859126186370849,
|
|
"epoch": 0.09042752421210337,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.5503,
|
|
"mean_token_accuracy": 0.08400027453899384,
|
|
"num_tokens": 1837182.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.651750469207764,
|
|
"epoch": 0.0909625983198673,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4924,
|
|
"mean_token_accuracy": 0.08740468397736549,
|
|
"num_tokens": 1849034.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.723634433746338,
|
|
"epoch": 0.09149767242763122,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3845,
|
|
"mean_token_accuracy": 0.09687676578760147,
|
|
"num_tokens": 1859033.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.652846193313598,
|
|
"epoch": 0.09203274653539516,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5075,
|
|
"mean_token_accuracy": 0.08564021959900855,
|
|
"num_tokens": 1870274.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.640428161621093,
|
|
"epoch": 0.09256782064315908,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.4539,
|
|
"mean_token_accuracy": 0.09071687236428261,
|
|
"num_tokens": 1881306.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.692183208465576,
|
|
"epoch": 0.093102894750923,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4264,
|
|
"mean_token_accuracy": 0.08375559784471989,
|
|
"num_tokens": 1892464.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.758206844329834,
|
|
"epoch": 0.09363796885868693,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.5176,
|
|
"mean_token_accuracy": 0.08049059696495534,
|
|
"num_tokens": 1903743.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.696184396743774,
|
|
"epoch": 0.09417304296645085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4571,
|
|
"mean_token_accuracy": 0.09152743741869926,
|
|
"num_tokens": 1915253.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.781573963165283,
|
|
"epoch": 0.09470811707421478,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4231,
|
|
"mean_token_accuracy": 0.08950318545103073,
|
|
"num_tokens": 1926113.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.6220146179199215,
|
|
"epoch": 0.0952431911819787,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5132,
|
|
"mean_token_accuracy": 0.08815172389149666,
|
|
"num_tokens": 1937718.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.792479753494263,
|
|
"epoch": 0.09577826528974263,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.5057,
|
|
"mean_token_accuracy": 0.08395625352859497,
|
|
"num_tokens": 1948307.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.598356580734253,
|
|
"epoch": 0.09631333939750655,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.3317,
|
|
"mean_token_accuracy": 0.09360581710934639,
|
|
"num_tokens": 1957861.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.642369413375855,
|
|
"epoch": 0.09684841350527049,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.3681,
|
|
"mean_token_accuracy": 0.09893451556563378,
|
|
"num_tokens": 1967984.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.604398155212403,
|
|
"epoch": 0.0973834876130344,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.3759,
|
|
"mean_token_accuracy": 0.09232855439186097,
|
|
"num_tokens": 1978608.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.716477394104004,
|
|
"epoch": 0.09791856172079832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4074,
|
|
"mean_token_accuracy": 0.08800688162446021,
|
|
"num_tokens": 1989355.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.572091436386108,
|
|
"epoch": 0.09845363582856226,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4119,
|
|
"mean_token_accuracy": 0.09684325829148292,
|
|
"num_tokens": 1999754.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.6609354496002195,
|
|
"epoch": 0.09898870993632618,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.4062,
|
|
"mean_token_accuracy": 0.08911203108727932,
|
|
"num_tokens": 2010877.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.788305807113647,
|
|
"epoch": 0.09952378404409011,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.5041,
|
|
"mean_token_accuracy": 0.08517451658844948,
|
|
"num_tokens": 2022301.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.598736047744751,
|
|
"epoch": 0.10005885815185403,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.3915,
|
|
"mean_token_accuracy": 0.08908470198512078,
|
|
"num_tokens": 2033537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.638715362548828,
|
|
"epoch": 0.10059393225961796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.3259,
|
|
"mean_token_accuracy": 0.09137255176901818,
|
|
"num_tokens": 2044360.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.618311262130737,
|
|
"epoch": 0.10112900636738188,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.4346,
|
|
"mean_token_accuracy": 0.09060494303703308,
|
|
"num_tokens": 2055000.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.6215578556060795,
|
|
"epoch": 0.1016640804751458,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4345,
|
|
"mean_token_accuracy": 0.09276226311922073,
|
|
"num_tokens": 2064807.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.6775514602661135,
|
|
"epoch": 0.10219915458290973,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.388,
|
|
"mean_token_accuracy": 0.08689953982830048,
|
|
"num_tokens": 2075618.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.565038728713989,
|
|
"epoch": 0.10273422869067365,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.4017,
|
|
"mean_token_accuracy": 0.09201253950595856,
|
|
"num_tokens": 2086226.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.6390989303588865,
|
|
"epoch": 0.10326930279843759,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3809,
|
|
"mean_token_accuracy": 0.089516381919384,
|
|
"num_tokens": 2097222.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.637884330749512,
|
|
"epoch": 0.1038043769062015,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4336,
|
|
"mean_token_accuracy": 0.08956842273473739,
|
|
"num_tokens": 2108919.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.543793439865112,
|
|
"epoch": 0.10433945101396544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3864,
|
|
"mean_token_accuracy": 0.09276443049311638,
|
|
"num_tokens": 2120215.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.648025798797607,
|
|
"epoch": 0.10487452512172936,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4028,
|
|
"mean_token_accuracy": 0.08867455273866653,
|
|
"num_tokens": 2131503.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.59724988937378,
|
|
"epoch": 0.10540959922949328,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3502,
|
|
"mean_token_accuracy": 0.09892218187451363,
|
|
"num_tokens": 2141551.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.537188291549683,
|
|
"epoch": 0.10594467333725721,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3504,
|
|
"mean_token_accuracy": 0.09664613753557205,
|
|
"num_tokens": 2151821.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.562666654586792,
|
|
"epoch": 0.10647974744502113,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3981,
|
|
"mean_token_accuracy": 0.09231663644313812,
|
|
"num_tokens": 2162474.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.636927556991577,
|
|
"epoch": 0.10701482155278506,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4335,
|
|
"mean_token_accuracy": 0.09290018305182457,
|
|
"num_tokens": 2173985.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.617586851119995,
|
|
"epoch": 0.10754989566054898,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999999979210101,
|
|
"loss": 7.4622,
|
|
"mean_token_accuracy": 0.08503897748887539,
|
|
"num_tokens": 2186432.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.613157415390015,
|
|
"epoch": 0.10808496976831292,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999894751138,
|
|
"loss": 7.319,
|
|
"mean_token_accuracy": 0.09168538153171539,
|
|
"num_tokens": 2197085.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.5148844718933105,
|
|
"epoch": 0.10862004387607684,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999745323744,
|
|
"loss": 7.3385,
|
|
"mean_token_accuracy": 0.09940625280141831,
|
|
"num_tokens": 2207162.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.578830003738403,
|
|
"epoch": 0.10915511798384077,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999530927923,
|
|
"loss": 7.4313,
|
|
"mean_token_accuracy": 0.08353616371750831,
|
|
"num_tokens": 2218714.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.619533395767212,
|
|
"epoch": 0.10969019209160469,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999999251563682,
|
|
"loss": 7.3555,
|
|
"mean_token_accuracy": 0.09379282593727112,
|
|
"num_tokens": 2229711.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.5392170429229735,
|
|
"epoch": 0.11022526619936861,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999998907231029,
|
|
"loss": 7.362,
|
|
"mean_token_accuracy": 0.08969447389245033,
|
|
"num_tokens": 2239885.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.563538312911987,
|
|
"epoch": 0.11076034030713254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999998497929974,
|
|
"loss": 7.3694,
|
|
"mean_token_accuracy": 0.09183109104633332,
|
|
"num_tokens": 2250221.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.545528268814087,
|
|
"epoch": 0.11129541441489646,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999998023660527,
|
|
"loss": 7.4576,
|
|
"mean_token_accuracy": 0.08111430704593658,
|
|
"num_tokens": 2261059.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.582445907592773,
|
|
"epoch": 0.11183048852266039,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999997484422705,
|
|
"loss": 7.3177,
|
|
"mean_token_accuracy": 0.09453473016619682,
|
|
"num_tokens": 2271174.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.515632486343383,
|
|
"epoch": 0.11236556263042431,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999996880216521,
|
|
"loss": 7.3957,
|
|
"mean_token_accuracy": 0.08888304755091667,
|
|
"num_tokens": 2282431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.579671001434326,
|
|
"epoch": 0.11290063673818825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999996211041994,
|
|
"loss": 7.3598,
|
|
"mean_token_accuracy": 0.09435788094997406,
|
|
"num_tokens": 2292891.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.555691480636597,
|
|
"epoch": 0.11343571084595216,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999995476899141,
|
|
"loss": 7.3887,
|
|
"mean_token_accuracy": 0.09046673066914082,
|
|
"num_tokens": 2303764.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.537960243225098,
|
|
"epoch": 0.11397078495371608,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999994677787987,
|
|
"loss": 7.285,
|
|
"mean_token_accuracy": 0.09388632029294967,
|
|
"num_tokens": 2314172.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.508009004592895,
|
|
"epoch": 0.11450585906148002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993813708551,
|
|
"loss": 7.275,
|
|
"mean_token_accuracy": 0.09821050018072128,
|
|
"num_tokens": 2324848.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.425210809707641,
|
|
"epoch": 0.11504093316924394,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499999288466086,
|
|
"loss": 7.2959,
|
|
"mean_token_accuracy": 0.09002227783203125,
|
|
"num_tokens": 2336601.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.546649742126465,
|
|
"epoch": 0.11557600727700787,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999991890644941,
|
|
"loss": 7.2955,
|
|
"mean_token_accuracy": 0.08926705792546272,
|
|
"num_tokens": 2347281.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.484306001663208,
|
|
"epoch": 0.11611108138477179,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999990831660822,
|
|
"loss": 7.3103,
|
|
"mean_token_accuracy": 0.09891931042075157,
|
|
"num_tokens": 2358199.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.616579532623291,
|
|
"epoch": 0.11664615549253572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999989707708534,
|
|
"loss": 7.3777,
|
|
"mean_token_accuracy": 0.09024567492306232,
|
|
"num_tokens": 2369092.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.433844470977784,
|
|
"epoch": 0.11718122960029964,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999988518788111,
|
|
"loss": 7.3356,
|
|
"mean_token_accuracy": 0.09163245111703873,
|
|
"num_tokens": 2378849.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.5147758483886715,
|
|
"epoch": 0.11771630370806356,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999987264899583,
|
|
"loss": 7.3396,
|
|
"mean_token_accuracy": 0.10027010887861251,
|
|
"num_tokens": 2389587.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.58909420967102,
|
|
"epoch": 0.1182513778158275,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499998594604299,
|
|
"loss": 7.3173,
|
|
"mean_token_accuracy": 0.0916910171508789,
|
|
"num_tokens": 2400442.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.389149761199951,
|
|
"epoch": 0.11878645192359141,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499998456221837,
|
|
"loss": 7.3048,
|
|
"mean_token_accuracy": 0.09734596312046051,
|
|
"num_tokens": 2410771.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.558002853393555,
|
|
"epoch": 0.11932152603135535,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999983113425762,
|
|
"loss": 7.3078,
|
|
"mean_token_accuracy": 0.09927843883633614,
|
|
"num_tokens": 2421112.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.441386699676514,
|
|
"epoch": 0.11985660013911927,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999981599665207,
|
|
"loss": 7.2965,
|
|
"mean_token_accuracy": 0.09117154404520988,
|
|
"num_tokens": 2431891.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.384634399414063,
|
|
"epoch": 0.1203916742468832,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999980020936748,
|
|
"loss": 7.2236,
|
|
"mean_token_accuracy": 0.09755842089653015,
|
|
"num_tokens": 2442987.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.493775987625122,
|
|
"epoch": 0.12092674835464712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999978377240434,
|
|
"loss": 7.2897,
|
|
"mean_token_accuracy": 0.09286157116293907,
|
|
"num_tokens": 2452703.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.4751733303070065,
|
|
"epoch": 0.12146182246241104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499997666857631,
|
|
"loss": 7.3319,
|
|
"mean_token_accuracy": 0.09701350852847099,
|
|
"num_tokens": 2462975.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.449129343032837,
|
|
"epoch": 0.12199689657017497,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999974894944426,
|
|
"loss": 7.3014,
|
|
"mean_token_accuracy": 0.09147868603467942,
|
|
"num_tokens": 2473853.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.502261209487915,
|
|
"epoch": 0.12253197067793889,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999973056344832,
|
|
"loss": 7.2549,
|
|
"mean_token_accuracy": 0.09436609894037247,
|
|
"num_tokens": 2485633.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.396411418914795,
|
|
"epoch": 0.12306704478570282,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999971152777583,
|
|
"loss": 7.2291,
|
|
"mean_token_accuracy": 0.09493016004562378,
|
|
"num_tokens": 2496922.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.55364203453064,
|
|
"epoch": 0.12360211889346674,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999969184242733,
|
|
"loss": 7.2786,
|
|
"mean_token_accuracy": 0.0976612240076065,
|
|
"num_tokens": 2507890.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.390556716918946,
|
|
"epoch": 0.12413719300123068,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499996715074034,
|
|
"loss": 7.2968,
|
|
"mean_token_accuracy": 0.09774711057543754,
|
|
"num_tokens": 2519749.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.444743871688843,
|
|
"epoch": 0.1246722671089946,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999965052270461,
|
|
"loss": 7.3059,
|
|
"mean_token_accuracy": 0.09634796604514122,
|
|
"num_tokens": 2530666.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.455366611480713,
|
|
"epoch": 0.12520734121675853,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999962888833157,
|
|
"loss": 7.3092,
|
|
"mean_token_accuracy": 0.09370963051915168,
|
|
"num_tokens": 2541594.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.467764949798584,
|
|
"epoch": 0.12574241532452243,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999960660428491,
|
|
"loss": 7.2981,
|
|
"mean_token_accuracy": 0.09601110816001893,
|
|
"num_tokens": 2552330.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.525752019882202,
|
|
"epoch": 0.12627748943228637,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999958367056526,
|
|
"loss": 7.3475,
|
|
"mean_token_accuracy": 0.08845235630869866,
|
|
"num_tokens": 2564601.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.461506700515747,
|
|
"epoch": 0.1268125635400503,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499995600871733,
|
|
"loss": 7.3073,
|
|
"mean_token_accuracy": 0.09456743821501731,
|
|
"num_tokens": 2575539.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.43174114227295,
|
|
"epoch": 0.12734763764781423,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999953585410971,
|
|
"loss": 7.2571,
|
|
"mean_token_accuracy": 0.09316419437527657,
|
|
"num_tokens": 2586635.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.452692031860352,
|
|
"epoch": 0.12788271175557814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999951097137518,
|
|
"loss": 7.2849,
|
|
"mean_token_accuracy": 0.09696812853217125,
|
|
"num_tokens": 2596814.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.484006023406982,
|
|
"epoch": 0.12841778586334207,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999948543897044,
|
|
"loss": 7.2936,
|
|
"mean_token_accuracy": 0.0926486037671566,
|
|
"num_tokens": 2608087.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.4842170715332035,
|
|
"epoch": 0.128952859971106,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999945925689621,
|
|
"loss": 7.2941,
|
|
"mean_token_accuracy": 0.09290322735905647,
|
|
"num_tokens": 2619377.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.412310266494751,
|
|
"epoch": 0.12948793407886994,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999943242515325,
|
|
"loss": 7.2048,
|
|
"mean_token_accuracy": 0.09525894671678543,
|
|
"num_tokens": 2629089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.460006856918335,
|
|
"epoch": 0.13002300818663384,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999940494374236,
|
|
"loss": 7.2583,
|
|
"mean_token_accuracy": 0.0955949753522873,
|
|
"num_tokens": 2639743.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.50310869216919,
|
|
"epoch": 0.13055808229439778,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499993768126643,
|
|
"loss": 7.3021,
|
|
"mean_token_accuracy": 0.09231485202908515,
|
|
"num_tokens": 2650631.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.416416263580322,
|
|
"epoch": 0.1310931564021617,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499993480319199,
|
|
"loss": 7.2524,
|
|
"mean_token_accuracy": 0.09885071963071823,
|
|
"num_tokens": 2660197.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.421104145050049,
|
|
"epoch": 0.13162823050992561,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999931860150999,
|
|
"loss": 7.2498,
|
|
"mean_token_accuracy": 0.09282487407326698,
|
|
"num_tokens": 2670162.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.4543742656707765,
|
|
"epoch": 0.13216330461768955,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999928852143541,
|
|
"loss": 7.2266,
|
|
"mean_token_accuracy": 0.09868842884898185,
|
|
"num_tokens": 2681233.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.335949897766113,
|
|
"epoch": 0.13269837872545348,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999925779169703,
|
|
"loss": 7.2096,
|
|
"mean_token_accuracy": 0.09607721045613289,
|
|
"num_tokens": 2692145.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.435535430908203,
|
|
"epoch": 0.13323345283321741,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999922641229575,
|
|
"loss": 7.2486,
|
|
"mean_token_accuracy": 0.0961481548845768,
|
|
"num_tokens": 2703192.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.459595155715943,
|
|
"epoch": 0.13376852694098132,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999919438323248,
|
|
"loss": 7.2295,
|
|
"mean_token_accuracy": 0.09703788831830025,
|
|
"num_tokens": 2714804.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.351469707489014,
|
|
"epoch": 0.13430360104874525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999916170450812,
|
|
"loss": 7.2056,
|
|
"mean_token_accuracy": 0.09724929109215737,
|
|
"num_tokens": 2724340.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.416718339920044,
|
|
"epoch": 0.13483867515650919,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999912837612364,
|
|
"loss": 7.2184,
|
|
"mean_token_accuracy": 0.09883825629949569,
|
|
"num_tokens": 2735767.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.457541751861572,
|
|
"epoch": 0.1353737492642731,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999909439807997,
|
|
"loss": 7.2705,
|
|
"mean_token_accuracy": 0.09218380376696586,
|
|
"num_tokens": 2747658.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.386063003540039,
|
|
"epoch": 0.13590882337203702,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999905977037813,
|
|
"loss": 7.1422,
|
|
"mean_token_accuracy": 0.10068641230463982,
|
|
"num_tokens": 2757901.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.36779899597168,
|
|
"epoch": 0.13644389747980096,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999902449301909,
|
|
"loss": 7.172,
|
|
"mean_token_accuracy": 0.09674012139439583,
|
|
"num_tokens": 2768945.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.264365386962891,
|
|
"epoch": 0.1369789715875649,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999898856600387,
|
|
"loss": 7.166,
|
|
"mean_token_accuracy": 0.10965741202235221,
|
|
"num_tokens": 2780276.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.459382247924805,
|
|
"epoch": 0.1375140456953288,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999895198933354,
|
|
"loss": 7.2378,
|
|
"mean_token_accuracy": 0.10283863544464111,
|
|
"num_tokens": 2791183.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.318519878387451,
|
|
"epoch": 0.13804911980309273,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999891476300911,
|
|
"loss": 7.1516,
|
|
"mean_token_accuracy": 0.09706087186932563,
|
|
"num_tokens": 2801928.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.452125787734985,
|
|
"epoch": 0.13858419391085666,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499988768870317,
|
|
"loss": 7.2435,
|
|
"mean_token_accuracy": 0.09266786351799965,
|
|
"num_tokens": 2813415.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.373220777511596,
|
|
"epoch": 0.13911926801862057,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999883836140236,
|
|
"loss": 7.2345,
|
|
"mean_token_accuracy": 0.09608653336763381,
|
|
"num_tokens": 2825288.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.364097929000854,
|
|
"epoch": 0.1396543421263845,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999879918612224,
|
|
"loss": 7.2026,
|
|
"mean_token_accuracy": 0.10053072422742844,
|
|
"num_tokens": 2836298.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.3803223133087155,
|
|
"epoch": 0.14018941623414843,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999875936119245,
|
|
"loss": 7.1813,
|
|
"mean_token_accuracy": 0.09865912646055222,
|
|
"num_tokens": 2846367.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.317546463012695,
|
|
"epoch": 0.14072449034191237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999871888661415,
|
|
"loss": 7.1958,
|
|
"mean_token_accuracy": 0.09692684262990951,
|
|
"num_tokens": 2856832.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.4061461925506595,
|
|
"epoch": 0.14125956444967627,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499986777623885,
|
|
"loss": 7.2165,
|
|
"mean_token_accuracy": 0.09264067932963371,
|
|
"num_tokens": 2867954.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.441576623916626,
|
|
"epoch": 0.1417946385574402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999863598851669,
|
|
"loss": 7.2364,
|
|
"mean_token_accuracy": 0.09773402959108353,
|
|
"num_tokens": 2878714.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.256839084625244,
|
|
"epoch": 0.14232971266520414,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999859356499992,
|
|
"loss": 7.1963,
|
|
"mean_token_accuracy": 0.10057443976402283,
|
|
"num_tokens": 2890697.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.345799779891967,
|
|
"epoch": 0.14286478677296804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999855049183943,
|
|
"loss": 7.1988,
|
|
"mean_token_accuracy": 0.09554307758808137,
|
|
"num_tokens": 2901468.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.406107616424561,
|
|
"epoch": 0.14339986088073198,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999850676903646,
|
|
"loss": 7.1647,
|
|
"mean_token_accuracy": 0.09928919821977615,
|
|
"num_tokens": 2913466.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.291070365905762,
|
|
"epoch": 0.1439349349884959,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999846239659226,
|
|
"loss": 7.1297,
|
|
"mean_token_accuracy": 0.10534956604242325,
|
|
"num_tokens": 2923638.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.3443274974823,
|
|
"epoch": 0.14447000909625984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999841737450812,
|
|
"loss": 7.2055,
|
|
"mean_token_accuracy": 0.10216673240065574,
|
|
"num_tokens": 2934790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.326418018341064,
|
|
"epoch": 0.14500508320402375,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999837170278535,
|
|
"loss": 7.1587,
|
|
"mean_token_accuracy": 0.09593354463577271,
|
|
"num_tokens": 2946320.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.404071521759033,
|
|
"epoch": 0.14554015731178768,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999832538142526,
|
|
"loss": 7.1353,
|
|
"mean_token_accuracy": 0.09594233520328999,
|
|
"num_tokens": 2957077.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.260494947433472,
|
|
"epoch": 0.14607523141955162,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999827841042917,
|
|
"loss": 7.1527,
|
|
"mean_token_accuracy": 0.09421777650713921,
|
|
"num_tokens": 2967286.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.368058109283448,
|
|
"epoch": 0.14661030552731552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999823078979846,
|
|
"loss": 7.1789,
|
|
"mean_token_accuracy": 0.09925442337989807,
|
|
"num_tokens": 2979516.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.417810440063477,
|
|
"epoch": 0.14714537963507945,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999818251953449,
|
|
"loss": 7.3148,
|
|
"mean_token_accuracy": 0.09026813432574272,
|
|
"num_tokens": 2991594.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.327701044082642,
|
|
"epoch": 0.1476804537428434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999813359963867,
|
|
"loss": 7.2032,
|
|
"mean_token_accuracy": 0.09660282731056213,
|
|
"num_tokens": 3002487.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.425524950027466,
|
|
"epoch": 0.14821552785060732,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999808403011241,
|
|
"loss": 7.2007,
|
|
"mean_token_accuracy": 0.10151680260896682,
|
|
"num_tokens": 3013197.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.276321983337402,
|
|
"epoch": 0.14875060195837123,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999803381095712,
|
|
"loss": 7.2218,
|
|
"mean_token_accuracy": 0.09807800725102425,
|
|
"num_tokens": 3024512.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.4200609683990475,
|
|
"epoch": 0.14928567606613516,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999798294217428,
|
|
"loss": 7.1825,
|
|
"mean_token_accuracy": 0.09805043935775756,
|
|
"num_tokens": 3035621.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.345406723022461,
|
|
"epoch": 0.1498207501738991,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999793142376533,
|
|
"loss": 7.1908,
|
|
"mean_token_accuracy": 0.09579893574118614,
|
|
"num_tokens": 3046492.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.27450737953186,
|
|
"epoch": 0.150355824281663,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999787925573177,
|
|
"loss": 7.2026,
|
|
"mean_token_accuracy": 0.09809928759932518,
|
|
"num_tokens": 3057715.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.418025636672974,
|
|
"epoch": 0.15089089838942693,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999782643807513,
|
|
"loss": 7.1677,
|
|
"mean_token_accuracy": 0.09324793964624405,
|
|
"num_tokens": 3068344.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.248358297348022,
|
|
"epoch": 0.15142597249719086,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999777297079689,
|
|
"loss": 7.1387,
|
|
"mean_token_accuracy": 0.09640576764941215,
|
|
"num_tokens": 3079576.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.383429050445557,
|
|
"epoch": 0.1519610466049548,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999771885389863,
|
|
"loss": 7.1275,
|
|
"mean_token_accuracy": 0.09900425672531128,
|
|
"num_tokens": 3090201.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.219635438919068,
|
|
"epoch": 0.1524961207127187,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999766408738189,
|
|
"loss": 7.0935,
|
|
"mean_token_accuracy": 0.10336209312081338,
|
|
"num_tokens": 3099824.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.271921253204345,
|
|
"epoch": 0.15303119482048264,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999760867124827,
|
|
"loss": 7.1606,
|
|
"mean_token_accuracy": 0.09842971935868264,
|
|
"num_tokens": 3109948.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.358252620697021,
|
|
"epoch": 0.15356626892824657,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999755260549937,
|
|
"loss": 7.1509,
|
|
"mean_token_accuracy": 0.10161449760198593,
|
|
"num_tokens": 3121492.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.261369752883911,
|
|
"epoch": 0.15410134303601047,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999749589013677,
|
|
"loss": 6.9304,
|
|
"mean_token_accuracy": 0.12006463333964348,
|
|
"num_tokens": 3131990.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.158350992202759,
|
|
"epoch": 0.1546364171437744,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999743852516217,
|
|
"loss": 7.1339,
|
|
"mean_token_accuracy": 0.0991136908531189,
|
|
"num_tokens": 3142567.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.441296768188477,
|
|
"epoch": 0.15517149125153834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999738051057717,
|
|
"loss": 7.1426,
|
|
"mean_token_accuracy": 0.10513922050595284,
|
|
"num_tokens": 3153083.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.258410024642944,
|
|
"epoch": 0.15570656535930227,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999732184638347,
|
|
"loss": 7.1468,
|
|
"mean_token_accuracy": 0.09554859325289726,
|
|
"num_tokens": 3163985.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.333807802200317,
|
|
"epoch": 0.15624163946706618,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999726253258278,
|
|
"loss": 7.1223,
|
|
"mean_token_accuracy": 0.10332410857081413,
|
|
"num_tokens": 3175259.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.253304290771484,
|
|
"epoch": 0.1567767135748301,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999720256917678,
|
|
"loss": 7.1025,
|
|
"mean_token_accuracy": 0.1024249516427517,
|
|
"num_tokens": 3185487.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.2388721942901615,
|
|
"epoch": 0.15731178768259405,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999714195616723,
|
|
"loss": 7.0921,
|
|
"mean_token_accuracy": 0.10349318385124207,
|
|
"num_tokens": 3196200.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.378126955032348,
|
|
"epoch": 0.15784686179035795,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999708069355586,
|
|
"loss": 7.195,
|
|
"mean_token_accuracy": 0.09435631409287452,
|
|
"num_tokens": 3207675.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.208775520324707,
|
|
"epoch": 0.15838193589812188,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999701878134445,
|
|
"loss": 7.0677,
|
|
"mean_token_accuracy": 0.09957077801227569,
|
|
"num_tokens": 3218117.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.286599016189575,
|
|
"epoch": 0.15891701000588582,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999695621953477,
|
|
"loss": 7.135,
|
|
"mean_token_accuracy": 0.1040462613105774,
|
|
"num_tokens": 3229208.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.260603237152099,
|
|
"epoch": 0.15945208411364975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999689300812866,
|
|
"loss": 7.0175,
|
|
"mean_token_accuracy": 0.10989507064223289,
|
|
"num_tokens": 3239586.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.345709609985351,
|
|
"epoch": 0.15998715822141366,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999682914712791,
|
|
"loss": 7.1179,
|
|
"mean_token_accuracy": 0.10247820466756821,
|
|
"num_tokens": 3250103.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.25383825302124,
|
|
"epoch": 0.1605222323291776,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999676463653439,
|
|
"loss": 7.1085,
|
|
"mean_token_accuracy": 0.10868085250258445,
|
|
"num_tokens": 3261844.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.256972217559815,
|
|
"epoch": 0.16105730643694152,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999669947634996,
|
|
"loss": 7.0699,
|
|
"mean_token_accuracy": 0.10102801620960236,
|
|
"num_tokens": 3272073.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.2481122493743895,
|
|
"epoch": 0.16159238054470546,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999663366657647,
|
|
"loss": 7.0516,
|
|
"mean_token_accuracy": 0.10147380158305168,
|
|
"num_tokens": 3281725.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.277080392837524,
|
|
"epoch": 0.16212745465246936,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999656720721586,
|
|
"loss": 7.1979,
|
|
"mean_token_accuracy": 0.09956115409731865,
|
|
"num_tokens": 3292708.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.331699419021606,
|
|
"epoch": 0.1626625287602333,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999650009827004,
|
|
"loss": 7.1915,
|
|
"mean_token_accuracy": 0.09656458497047424,
|
|
"num_tokens": 3303548.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.242523336410523,
|
|
"epoch": 0.16319760286799723,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999643233974092,
|
|
"loss": 7.0463,
|
|
"mean_token_accuracy": 0.10843227058649063,
|
|
"num_tokens": 3314261.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.228282165527344,
|
|
"epoch": 0.16373267697576113,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999636393163049,
|
|
"loss": 7.0516,
|
|
"mean_token_accuracy": 0.10321945995092392,
|
|
"num_tokens": 3324833.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.150654458999634,
|
|
"epoch": 0.16426775108352507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999629487394071,
|
|
"loss": 6.9631,
|
|
"mean_token_accuracy": 0.1133572869002819,
|
|
"num_tokens": 3334790.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.260952281951904,
|
|
"epoch": 0.164802825191289,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999622516667358,
|
|
"loss": 7.087,
|
|
"mean_token_accuracy": 0.10121001973748207,
|
|
"num_tokens": 3345115.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.210820865631104,
|
|
"epoch": 0.16533789929905293,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499961548098311,
|
|
"loss": 6.9993,
|
|
"mean_token_accuracy": 0.1076305091381073,
|
|
"num_tokens": 3356187.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.183248662948609,
|
|
"epoch": 0.16587297340681684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999608380341533,
|
|
"loss": 7.0048,
|
|
"mean_token_accuracy": 0.10645373165607452,
|
|
"num_tokens": 3367218.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.158462381362915,
|
|
"epoch": 0.16640804751458077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999601214742829,
|
|
"loss": 7.1499,
|
|
"mean_token_accuracy": 0.09607289656996727,
|
|
"num_tokens": 3377557.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.422818040847778,
|
|
"epoch": 0.1669431216223447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999593984187206,
|
|
"loss": 7.1374,
|
|
"mean_token_accuracy": 0.10575096979737282,
|
|
"num_tokens": 3387402.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.176465892791748,
|
|
"epoch": 0.1674781957301086,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999586688674872,
|
|
"loss": 7.0164,
|
|
"mean_token_accuracy": 0.10627634450793266,
|
|
"num_tokens": 3397924.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.243451929092407,
|
|
"epoch": 0.16801326983787254,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499957932820604,
|
|
"loss": 7.1062,
|
|
"mean_token_accuracy": 0.09752621129155159,
|
|
"num_tokens": 3408622.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.281120538711548,
|
|
"epoch": 0.16854834394563648,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499957190278092,
|
|
"loss": 7.07,
|
|
"mean_token_accuracy": 0.10029838010668754,
|
|
"num_tokens": 3419692.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.165713167190551,
|
|
"epoch": 0.1690834180534004,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999564412399728,
|
|
"loss": 7.0902,
|
|
"mean_token_accuracy": 0.10087467208504677,
|
|
"num_tokens": 3430986.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.255892705917359,
|
|
"epoch": 0.1696184921611643,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499955685706268,
|
|
"loss": 7.0265,
|
|
"mean_token_accuracy": 0.10308083444833756,
|
|
"num_tokens": 3442211.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.082983922958374,
|
|
"epoch": 0.17015356626892825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999549236769993,
|
|
"loss": 7.0131,
|
|
"mean_token_accuracy": 0.11085021272301673,
|
|
"num_tokens": 3453585.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.169584274291992,
|
|
"epoch": 0.17068864037669218,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999541551521888,
|
|
"loss": 7.0625,
|
|
"mean_token_accuracy": 0.10282246991991997,
|
|
"num_tokens": 3464156.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.334958791732788,
|
|
"epoch": 0.17122371448445609,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999533801318587,
|
|
"loss": 7.1152,
|
|
"mean_token_accuracy": 0.10011868923902512,
|
|
"num_tokens": 3474853.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.2555193424224855,
|
|
"epoch": 0.17175878859222002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999525986160313,
|
|
"loss": 7.0942,
|
|
"mean_token_accuracy": 0.10751360654830933,
|
|
"num_tokens": 3486841.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.2923766613006595,
|
|
"epoch": 0.17229386269998395,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999518106047293,
|
|
"loss": 7.1048,
|
|
"mean_token_accuracy": 0.10046511143445969,
|
|
"num_tokens": 3498735.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.134558773040771,
|
|
"epoch": 0.17282893680774788,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999510160979754,
|
|
"loss": 7.1368,
|
|
"mean_token_accuracy": 0.1078067108988762,
|
|
"num_tokens": 3508829.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.254569244384766,
|
|
"epoch": 0.1733640109155118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999502150957925,
|
|
"loss": 7.0501,
|
|
"mean_token_accuracy": 0.10457162857055664,
|
|
"num_tokens": 3519465.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.2145932674407955,
|
|
"epoch": 0.17389908502327572,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999494075982037,
|
|
"loss": 7.0002,
|
|
"mean_token_accuracy": 0.1088636189699173,
|
|
"num_tokens": 3530401.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.202526950836182,
|
|
"epoch": 0.17443415913103966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999485936052324,
|
|
"loss": 7.0715,
|
|
"mean_token_accuracy": 0.10668305307626724,
|
|
"num_tokens": 3541136.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.254500436782837,
|
|
"epoch": 0.17496923323880356,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499947773116902,
|
|
"loss": 7.0683,
|
|
"mean_token_accuracy": 0.1051873467862606,
|
|
"num_tokens": 3552525.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.152193355560303,
|
|
"epoch": 0.1755043073465675,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999469461332365,
|
|
"loss": 7.0334,
|
|
"mean_token_accuracy": 0.10791850909590721,
|
|
"num_tokens": 3563028.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.228841304779053,
|
|
"epoch": 0.17603938145433143,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999461126542592,
|
|
"loss": 6.9812,
|
|
"mean_token_accuracy": 0.10489355474710464,
|
|
"num_tokens": 3573354.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.04385290145874,
|
|
"epoch": 0.17657445556209536,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999452726799947,
|
|
"loss": 6.972,
|
|
"mean_token_accuracy": 0.10788829922676087,
|
|
"num_tokens": 3585576.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.2881652355194095,
|
|
"epoch": 0.17710952966985927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999444262104671,
|
|
"loss": 7.0801,
|
|
"mean_token_accuracy": 0.09990740865468979,
|
|
"num_tokens": 3596478.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.210688781738281,
|
|
"epoch": 0.1776446037776232,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999435732457007,
|
|
"loss": 7.0409,
|
|
"mean_token_accuracy": 0.102048097550869,
|
|
"num_tokens": 3608014.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.225692462921143,
|
|
"epoch": 0.17817967788538713,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999427137857203,
|
|
"loss": 7.0942,
|
|
"mean_token_accuracy": 0.1017175205051899,
|
|
"num_tokens": 3620120.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.182433652877807,
|
|
"epoch": 0.17871475199315104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999418478305506,
|
|
"loss": 7.0086,
|
|
"mean_token_accuracy": 0.10466994717717171,
|
|
"num_tokens": 3632578.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.138683795928955,
|
|
"epoch": 0.17924982610091497,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999409753802167,
|
|
"loss": 7.0291,
|
|
"mean_token_accuracy": 0.10857005342841149,
|
|
"num_tokens": 3643245.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.196502923965454,
|
|
"epoch": 0.1797849002086789,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999400964347437,
|
|
"loss": 7.0241,
|
|
"mean_token_accuracy": 0.10519987344741821,
|
|
"num_tokens": 3655832.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.195584011077881,
|
|
"epoch": 0.18031997431644284,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999392109941571,
|
|
"loss": 7.0048,
|
|
"mean_token_accuracy": 0.10431592911481857,
|
|
"num_tokens": 3666566.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.214022207260132,
|
|
"epoch": 0.18085504842420674,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999383190584822,
|
|
"loss": 7.0241,
|
|
"mean_token_accuracy": 0.10619666650891305,
|
|
"num_tokens": 3677572.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.175317907333374,
|
|
"epoch": 0.18139012253197068,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999374206277451,
|
|
"loss": 6.9444,
|
|
"mean_token_accuracy": 0.107360577583313,
|
|
"num_tokens": 3687116.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.116744756698608,
|
|
"epoch": 0.1819251966397346,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999365157019717,
|
|
"loss": 7.0551,
|
|
"mean_token_accuracy": 0.10737907141447067,
|
|
"num_tokens": 3697961.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.191368770599365,
|
|
"epoch": 0.18246027074749852,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999356042811878,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.11243351176381111,
|
|
"num_tokens": 3708834.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.122293138504029,
|
|
"epoch": 0.18299534485526245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049993468636542,
|
|
"loss": 7.0408,
|
|
"mean_token_accuracy": 0.103644710034132,
|
|
"num_tokens": 3719835.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.188800382614136,
|
|
"epoch": 0.18353041896302638,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999337619546948,
|
|
"loss": 6.9403,
|
|
"mean_token_accuracy": 0.10948617681860924,
|
|
"num_tokens": 3730408.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.120905017852783,
|
|
"epoch": 0.18406549307079031,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999328310490387,
|
|
"loss": 7.003,
|
|
"mean_token_accuracy": 0.11111332178115844,
|
|
"num_tokens": 3741257.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.155314970016479,
|
|
"epoch": 0.18460056717855422,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999318936484789,
|
|
"loss": 6.9984,
|
|
"mean_token_accuracy": 0.10944901183247566,
|
|
"num_tokens": 3752615.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.138224458694458,
|
|
"epoch": 0.18513564128631815,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999309497530422,
|
|
"loss": 7.0367,
|
|
"mean_token_accuracy": 0.09998197108507156,
|
|
"num_tokens": 3763656.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.118561792373657,
|
|
"epoch": 0.1856707153940821,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999299993627558,
|
|
"loss": 7.0105,
|
|
"mean_token_accuracy": 0.10840073600411415,
|
|
"num_tokens": 3775257.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.14077525138855,
|
|
"epoch": 0.186205789501846,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999290424776475,
|
|
"loss": 6.9713,
|
|
"mean_token_accuracy": 0.11179318875074387,
|
|
"num_tokens": 3786094.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.301455545425415,
|
|
"epoch": 0.18674086360960993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999280790977445,
|
|
"loss": 7.0599,
|
|
"mean_token_accuracy": 0.10067834705114365,
|
|
"num_tokens": 3796672.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.208122396469117,
|
|
"epoch": 0.18727593771737386,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499927109223075,
|
|
"loss": 7.0296,
|
|
"mean_token_accuracy": 0.10581944286823272,
|
|
"num_tokens": 3807910.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.052106761932373,
|
|
"epoch": 0.1878110118251378,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999261328536667,
|
|
"loss": 6.9894,
|
|
"mean_token_accuracy": 0.1093970462679863,
|
|
"num_tokens": 3820792.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.085962009429932,
|
|
"epoch": 0.1883460859329017,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999251499895479,
|
|
"loss": 6.9168,
|
|
"mean_token_accuracy": 0.10804818868637085,
|
|
"num_tokens": 3831126.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.155363321304321,
|
|
"epoch": 0.18888116004066563,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999241606307471,
|
|
"loss": 7.0462,
|
|
"mean_token_accuracy": 0.10382814705371857,
|
|
"num_tokens": 3841923.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.154525423049927,
|
|
"epoch": 0.18941623414842956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999231647772927,
|
|
"loss": 6.9501,
|
|
"mean_token_accuracy": 0.10774912610650063,
|
|
"num_tokens": 3852504.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.044074583053589,
|
|
"epoch": 0.1899513082561935,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999221624292136,
|
|
"loss": 6.9444,
|
|
"mean_token_accuracy": 0.1107519470155239,
|
|
"num_tokens": 3862761.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.173216724395752,
|
|
"epoch": 0.1904863823639574,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999211535865385,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.10836640074849128,
|
|
"num_tokens": 3873662.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.095516538619995,
|
|
"epoch": 0.19102145647172133,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999201382492969,
|
|
"loss": 6.8982,
|
|
"mean_token_accuracy": 0.10540294200181961,
|
|
"num_tokens": 3884835.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.106392192840576,
|
|
"epoch": 0.19155653057948527,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999191164175178,
|
|
"loss": 7.0488,
|
|
"mean_token_accuracy": 0.10533409044146538,
|
|
"num_tokens": 3895073.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.235964441299439,
|
|
"epoch": 0.19209160468724917,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999180880912309,
|
|
"loss": 6.9963,
|
|
"mean_token_accuracy": 0.10814031064510346,
|
|
"num_tokens": 3905440.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.081749439239502,
|
|
"epoch": 0.1926266787950131,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999170532704657,
|
|
"loss": 7.0097,
|
|
"mean_token_accuracy": 0.1047128364443779,
|
|
"num_tokens": 3917135.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.200995445251465,
|
|
"epoch": 0.19316175290277704,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999160119552523,
|
|
"loss": 7.0099,
|
|
"mean_token_accuracy": 0.11308202221989631,
|
|
"num_tokens": 3928247.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.104423236846924,
|
|
"epoch": 0.19369682701054097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999149641456206,
|
|
"loss": 6.9878,
|
|
"mean_token_accuracy": 0.10651118457317352,
|
|
"num_tokens": 3938609.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.210849142074585,
|
|
"epoch": 0.19423190111830488,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499913909841601,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.10978263765573501,
|
|
"num_tokens": 3949221.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.029234981536865,
|
|
"epoch": 0.1947669752260688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999128490432238,
|
|
"loss": 6.9535,
|
|
"mean_token_accuracy": 0.10435856580734253,
|
|
"num_tokens": 3959475.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.078148365020752,
|
|
"epoch": 0.19530204933383274,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999117817505196,
|
|
"loss": 6.9502,
|
|
"mean_token_accuracy": 0.11588959023356438,
|
|
"num_tokens": 3969638.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.13325138092041,
|
|
"epoch": 0.19583712344159665,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999107079635194,
|
|
"loss": 7.0101,
|
|
"mean_token_accuracy": 0.10802074894309044,
|
|
"num_tokens": 3980543.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.252430629730225,
|
|
"epoch": 0.19637219754936058,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499909627682254,
|
|
"loss": 7.0509,
|
|
"mean_token_accuracy": 0.09712937101721764,
|
|
"num_tokens": 3993518.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.18526782989502,
|
|
"epoch": 0.19690727165712452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999085409067549,
|
|
"loss": 7.0277,
|
|
"mean_token_accuracy": 0.10725011304020882,
|
|
"num_tokens": 4002940.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.085262203216553,
|
|
"epoch": 0.19744234576488845,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999074476370531,
|
|
"loss": 6.9717,
|
|
"mean_token_accuracy": 0.10763022303581238,
|
|
"num_tokens": 4013982.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.159320735931397,
|
|
"epoch": 0.19797741987265235,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999063478731805,
|
|
"loss": 6.942,
|
|
"mean_token_accuracy": 0.11397543847560883,
|
|
"num_tokens": 4025607.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.066693544387817,
|
|
"epoch": 0.1985124939804163,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999052416151687,
|
|
"loss": 6.9913,
|
|
"mean_token_accuracy": 0.10893454253673554,
|
|
"num_tokens": 4037467.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.134395265579224,
|
|
"epoch": 0.19904756808818022,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999041288630496,
|
|
"loss": 7.0057,
|
|
"mean_token_accuracy": 0.10700632855296136,
|
|
"num_tokens": 4049146.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.200011968612671,
|
|
"epoch": 0.19958264219594413,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999030096168553,
|
|
"loss": 7.0526,
|
|
"mean_token_accuracy": 0.10376486778259278,
|
|
"num_tokens": 4060500.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.182278490066528,
|
|
"epoch": 0.20011771630370806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999018838766182,
|
|
"loss": 6.9838,
|
|
"mean_token_accuracy": 0.10422982573509217,
|
|
"num_tokens": 4070553.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.1447615146636965,
|
|
"epoch": 0.200652790411472,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499900751642371,
|
|
"loss": 6.9331,
|
|
"mean_token_accuracy": 0.12131592780351638,
|
|
"num_tokens": 4079653.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.0817211151123045,
|
|
"epoch": 0.20118786451923593,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998996129141461,
|
|
"loss": 7.0107,
|
|
"mean_token_accuracy": 0.10711610466241836,
|
|
"num_tokens": 4089912.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.1709511280059814,
|
|
"epoch": 0.20172293862699983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998984676919764,
|
|
"loss": 6.9674,
|
|
"mean_token_accuracy": 0.10553688108921051,
|
|
"num_tokens": 4100577.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.151998662948609,
|
|
"epoch": 0.20225801273476376,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998973159758952,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.10634929835796356,
|
|
"num_tokens": 4111752.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.046214628219604,
|
|
"epoch": 0.2027930868425277,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998961577659355,
|
|
"loss": 6.9473,
|
|
"mean_token_accuracy": 0.10678009986877442,
|
|
"num_tokens": 4122616.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.194829511642456,
|
|
"epoch": 0.2033281609502916,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998949930621309,
|
|
"loss": 7.0551,
|
|
"mean_token_accuracy": 0.10694845020771027,
|
|
"num_tokens": 4134275.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.1025816917419435,
|
|
"epoch": 0.20386323505805554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998938218645149,
|
|
"loss": 6.9425,
|
|
"mean_token_accuracy": 0.10776922106742859,
|
|
"num_tokens": 4146412.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.024503421783447,
|
|
"epoch": 0.20439830916581947,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998926441731215,
|
|
"loss": 6.9416,
|
|
"mean_token_accuracy": 0.10820029228925705,
|
|
"num_tokens": 4157592.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.106622838973999,
|
|
"epoch": 0.2049333832735834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998914599879845,
|
|
"loss": 6.9208,
|
|
"mean_token_accuracy": 0.10948476865887642,
|
|
"num_tokens": 4168637.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.10308952331543,
|
|
"epoch": 0.2054684573813473,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998902693091382,
|
|
"loss": 6.9663,
|
|
"mean_token_accuracy": 0.10619650930166244,
|
|
"num_tokens": 4179951.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.086925888061524,
|
|
"epoch": 0.20600353148911124,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998890721366171,
|
|
"loss": 6.8677,
|
|
"mean_token_accuracy": 0.10923162400722504,
|
|
"num_tokens": 4189895.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.098230361938477,
|
|
"epoch": 0.20653860559687517,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998878684704556,
|
|
"loss": 6.9011,
|
|
"mean_token_accuracy": 0.1140952430665493,
|
|
"num_tokens": 4199796.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.0652295589447025,
|
|
"epoch": 0.20707367970463908,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998866583106884,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.10857674703001977,
|
|
"num_tokens": 4210428.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.12544617652893,
|
|
"epoch": 0.207608753812403,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998854416573506,
|
|
"loss": 6.998,
|
|
"mean_token_accuracy": 0.11166770830750465,
|
|
"num_tokens": 4221515.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.1380102157592775,
|
|
"epoch": 0.20814382792016695,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998842185104772,
|
|
"loss": 7.0288,
|
|
"mean_token_accuracy": 0.10675298646092415,
|
|
"num_tokens": 4232580.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.047916030883789,
|
|
"epoch": 0.20867890202793088,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998829888701036,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.11182363629341126,
|
|
"num_tokens": 4242871.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.13678822517395,
|
|
"epoch": 0.20921397613569478,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998817527362654,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.10563497394323348,
|
|
"num_tokens": 4253419.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.076486873626709,
|
|
"epoch": 0.20974905024345872,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998805101089982,
|
|
"loss": 6.9417,
|
|
"mean_token_accuracy": 0.10947482511401177,
|
|
"num_tokens": 4264327.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.137678337097168,
|
|
"epoch": 0.21028412435122265,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998792609883378,
|
|
"loss": 6.9144,
|
|
"mean_token_accuracy": 0.11335683837532998,
|
|
"num_tokens": 4274568.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.063451051712036,
|
|
"epoch": 0.21081919845898656,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998780053743203,
|
|
"loss": 6.9016,
|
|
"mean_token_accuracy": 0.11350873038172722,
|
|
"num_tokens": 4284895.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.0390349388122555,
|
|
"epoch": 0.2113542725667505,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998767432669822,
|
|
"loss": 6.9389,
|
|
"mean_token_accuracy": 0.10549373626708984,
|
|
"num_tokens": 4297258.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.111899423599243,
|
|
"epoch": 0.21188934667451442,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998754746663595,
|
|
"loss": 6.881,
|
|
"mean_token_accuracy": 0.11032110527157783,
|
|
"num_tokens": 4308307.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.049768352508545,
|
|
"epoch": 0.21242442078227836,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998741995724892,
|
|
"loss": 6.9502,
|
|
"mean_token_accuracy": 0.11004350334405899,
|
|
"num_tokens": 4318801.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.070007371902466,
|
|
"epoch": 0.21295949489004226,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998729179854079,
|
|
"loss": 6.913,
|
|
"mean_token_accuracy": 0.10913456007838249,
|
|
"num_tokens": 4329531.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.077743101119995,
|
|
"epoch": 0.2134945689978062,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998716299051527,
|
|
"loss": 6.9029,
|
|
"mean_token_accuracy": 0.11192808151245118,
|
|
"num_tokens": 4341203.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.02212815284729,
|
|
"epoch": 0.21402964310557013,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998703353317609,
|
|
"loss": 6.9553,
|
|
"mean_token_accuracy": 0.10663387700915336,
|
|
"num_tokens": 4352426.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.1021686553955075,
|
|
"epoch": 0.21456471721333403,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998690342652697,
|
|
"loss": 6.8922,
|
|
"mean_token_accuracy": 0.1153487928211689,
|
|
"num_tokens": 4363413.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.031656312942505,
|
|
"epoch": 0.21509979132109797,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998677267057166,
|
|
"loss": 6.8375,
|
|
"mean_token_accuracy": 0.11453943327069283,
|
|
"num_tokens": 4373470.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.010087633132935,
|
|
"epoch": 0.2156348654288619,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998664126531397,
|
|
"loss": 6.9018,
|
|
"mean_token_accuracy": 0.11389576569199562,
|
|
"num_tokens": 4384438.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.090394735336304,
|
|
"epoch": 0.21616993953662583,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998650921075766,
|
|
"loss": 6.8786,
|
|
"mean_token_accuracy": 0.11450627520680427,
|
|
"num_tokens": 4395100.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.041706991195679,
|
|
"epoch": 0.21670501364438974,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998637650690656,
|
|
"loss": 6.993,
|
|
"mean_token_accuracy": 0.1060309000313282,
|
|
"num_tokens": 4407131.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.066201686859131,
|
|
"epoch": 0.21724008775215367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499862431537645,
|
|
"loss": 6.8292,
|
|
"mean_token_accuracy": 0.1086798407137394,
|
|
"num_tokens": 4417701.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 7.037751197814941,
|
|
"epoch": 0.2177751618599176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998610915133533,
|
|
"loss": 6.9028,
|
|
"mean_token_accuracy": 0.1083365522325039,
|
|
"num_tokens": 4429309.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.060035514831543,
|
|
"epoch": 0.21831023596768154,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998597449962292,
|
|
"loss": 6.9723,
|
|
"mean_token_accuracy": 0.10615406855940819,
|
|
"num_tokens": 4440850.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.043385744094849,
|
|
"epoch": 0.21884531007544544,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998583919863115,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.1061348296701908,
|
|
"num_tokens": 4451995.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.994556903839111,
|
|
"epoch": 0.21938038418320938,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998570324836393,
|
|
"loss": 6.8568,
|
|
"mean_token_accuracy": 0.11581476256251336,
|
|
"num_tokens": 4461916.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.012522411346436,
|
|
"epoch": 0.2199154582909733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499855666488252,
|
|
"loss": 6.9325,
|
|
"mean_token_accuracy": 0.10941380187869072,
|
|
"num_tokens": 4471603.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.203369617462158,
|
|
"epoch": 0.22045053239873721,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998542940001889,
|
|
"loss": 6.9765,
|
|
"mean_token_accuracy": 0.1062982976436615,
|
|
"num_tokens": 4483166.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.995989227294922,
|
|
"epoch": 0.22098560650650115,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998529150194895,
|
|
"loss": 6.8848,
|
|
"mean_token_accuracy": 0.10458490177989006,
|
|
"num_tokens": 4493824.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.03889012336731,
|
|
"epoch": 0.22152068061426508,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998515295461939,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.1276262767612934,
|
|
"num_tokens": 4505674.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.970796203613281,
|
|
"epoch": 0.22205575472202901,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499850137580342,
|
|
"loss": 6.8791,
|
|
"mean_token_accuracy": 0.1157338224351406,
|
|
"num_tokens": 4516516.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.061030149459839,
|
|
"epoch": 0.22259082882979292,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998487391219739,
|
|
"loss": 6.8821,
|
|
"mean_token_accuracy": 0.10787423551082612,
|
|
"num_tokens": 4527811.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.023014736175537,
|
|
"epoch": 0.22312590293755685,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998473341711301,
|
|
"loss": 6.8298,
|
|
"mean_token_accuracy": 0.10802056044340133,
|
|
"num_tokens": 4538988.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.010777187347412,
|
|
"epoch": 0.22366097704532079,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998459227278512,
|
|
"loss": 6.8458,
|
|
"mean_token_accuracy": 0.11393861100077629,
|
|
"num_tokens": 4550049.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.15531325340271,
|
|
"epoch": 0.2241960511530847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998445047921777,
|
|
"loss": 6.9713,
|
|
"mean_token_accuracy": 0.11392002254724502,
|
|
"num_tokens": 4559784.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.074538469314575,
|
|
"epoch": 0.22473112526084862,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998430803641509,
|
|
"loss": 6.8138,
|
|
"mean_token_accuracy": 0.11510861515998841,
|
|
"num_tokens": 4569982.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.908378839492798,
|
|
"epoch": 0.22526619936861256,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998416494438118,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.11351708471775054,
|
|
"num_tokens": 4581117.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.025954914093018,
|
|
"epoch": 0.2258012734763765,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998402120312014,
|
|
"loss": 6.8923,
|
|
"mean_token_accuracy": 0.11487512886524201,
|
|
"num_tokens": 4592012.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.058220863342285,
|
|
"epoch": 0.2263363475841404,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998387681263616,
|
|
"loss": 6.9393,
|
|
"mean_token_accuracy": 0.10974757522344589,
|
|
"num_tokens": 4602591.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.071815109252929,
|
|
"epoch": 0.22687142169190433,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499837317729334,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.11159347370266914,
|
|
"num_tokens": 4613418.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.025975751876831,
|
|
"epoch": 0.22740649579966826,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998358608401603,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.12081962004303932,
|
|
"num_tokens": 4625156.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.025455379486084,
|
|
"epoch": 0.22794156990743217,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499834397458883,
|
|
"loss": 6.8316,
|
|
"mean_token_accuracy": 0.11804601326584815,
|
|
"num_tokens": 4634523.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.948561143875122,
|
|
"epoch": 0.2284766440151961,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998329275855438,
|
|
"loss": 6.8168,
|
|
"mean_token_accuracy": 0.1192819207906723,
|
|
"num_tokens": 4646292.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.014158439636231,
|
|
"epoch": 0.22901171812296003,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998314512201855,
|
|
"loss": 6.8009,
|
|
"mean_token_accuracy": 0.10840347334742546,
|
|
"num_tokens": 4656417.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.955240058898926,
|
|
"epoch": 0.22954679223072397,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998299683628507,
|
|
"loss": 6.8215,
|
|
"mean_token_accuracy": 0.11493450030684471,
|
|
"num_tokens": 4666933.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.043175792694091,
|
|
"epoch": 0.23008186633848787,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998284790135821,
|
|
"loss": 6.9814,
|
|
"mean_token_accuracy": 0.10535553693771363,
|
|
"num_tokens": 4678482.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.038923978805542,
|
|
"epoch": 0.2306169404462518,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998269831724228,
|
|
"loss": 6.8373,
|
|
"mean_token_accuracy": 0.11513779833912849,
|
|
"num_tokens": 4688454.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.988160562515259,
|
|
"epoch": 0.23115201455401574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998254808394159,
|
|
"loss": 6.8731,
|
|
"mean_token_accuracy": 0.11315513700246811,
|
|
"num_tokens": 4699545.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.063672733306885,
|
|
"epoch": 0.23168708866177964,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998239720146048,
|
|
"loss": 6.8762,
|
|
"mean_token_accuracy": 0.1088165782392025,
|
|
"num_tokens": 4711149.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.939060354232788,
|
|
"epoch": 0.23222216276954358,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998224566980332,
|
|
"loss": 6.8926,
|
|
"mean_token_accuracy": 0.1109717458486557,
|
|
"num_tokens": 4722651.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.021150684356689,
|
|
"epoch": 0.2327572368773075,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998209348897447,
|
|
"loss": 6.8808,
|
|
"mean_token_accuracy": 0.10639935210347176,
|
|
"num_tokens": 4733883.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.1795416355133055,
|
|
"epoch": 0.23329231098507144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998194065897833,
|
|
"loss": 6.8588,
|
|
"mean_token_accuracy": 0.11214026883244514,
|
|
"num_tokens": 4744517.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.939247798919678,
|
|
"epoch": 0.23382738509283535,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499817871798193,
|
|
"loss": 6.8688,
|
|
"mean_token_accuracy": 0.12289264723658562,
|
|
"num_tokens": 4755481.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.936901998519898,
|
|
"epoch": 0.23436245920059928,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998163305150185,
|
|
"loss": 6.7796,
|
|
"mean_token_accuracy": 0.12206417769193649,
|
|
"num_tokens": 4765535.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 7.031427049636841,
|
|
"epoch": 0.23489753330836322,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998147827403038,
|
|
"loss": 6.896,
|
|
"mean_token_accuracy": 0.11192756742238999,
|
|
"num_tokens": 4777045.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.11299991607666,
|
|
"epoch": 0.23543260741612712,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499813228474094,
|
|
"loss": 6.7736,
|
|
"mean_token_accuracy": 0.1204762414097786,
|
|
"num_tokens": 4787958.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.87829556465149,
|
|
"epoch": 0.23596768152389105,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998116677164338,
|
|
"loss": 6.8352,
|
|
"mean_token_accuracy": 0.11555254310369492,
|
|
"num_tokens": 4798502.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.991652488708496,
|
|
"epoch": 0.236502755631655,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998101004673682,
|
|
"loss": 6.8393,
|
|
"mean_token_accuracy": 0.1141854278743267,
|
|
"num_tokens": 4809179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.067083883285522,
|
|
"epoch": 0.23703782973941892,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998085267269426,
|
|
"loss": 6.8898,
|
|
"mean_token_accuracy": 0.10678831562399864,
|
|
"num_tokens": 4819803.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.071384286880493,
|
|
"epoch": 0.23757290384718283,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998069464952025,
|
|
"loss": 6.88,
|
|
"mean_token_accuracy": 0.11006908938288688,
|
|
"num_tokens": 4831226.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.991342973709107,
|
|
"epoch": 0.23810797795494676,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998053597721932,
|
|
"loss": 6.8957,
|
|
"mean_token_accuracy": 0.11495887637138366,
|
|
"num_tokens": 4842168.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.976592063903809,
|
|
"epoch": 0.2386430520627107,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998037665579608,
|
|
"loss": 6.8553,
|
|
"mean_token_accuracy": 0.11443870812654496,
|
|
"num_tokens": 4852655.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.9272545337677,
|
|
"epoch": 0.2391781261704746,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998021668525513,
|
|
"loss": 6.7459,
|
|
"mean_token_accuracy": 0.11380679160356522,
|
|
"num_tokens": 4862164.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.040174579620361,
|
|
"epoch": 0.23971320027823853,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998005606560107,
|
|
"loss": 6.8763,
|
|
"mean_token_accuracy": 0.11493096947669983,
|
|
"num_tokens": 4874233.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.048814058303833,
|
|
"epoch": 0.24024827438600246,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997989479683856,
|
|
"loss": 6.8835,
|
|
"mean_token_accuracy": 0.1131036177277565,
|
|
"num_tokens": 4885948.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.949912738800049,
|
|
"epoch": 0.2407833484937664,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997973287897224,
|
|
"loss": 6.8498,
|
|
"mean_token_accuracy": 0.11797192841768264,
|
|
"num_tokens": 4897128.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.004365396499634,
|
|
"epoch": 0.2413184226015303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997957031200681,
|
|
"loss": 6.8378,
|
|
"mean_token_accuracy": 0.1178452044725418,
|
|
"num_tokens": 4907699.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.862322807312012,
|
|
"epoch": 0.24185349670929424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997940709594692,
|
|
"loss": 6.7581,
|
|
"mean_token_accuracy": 0.11488514393568039,
|
|
"num_tokens": 4918772.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.0672924518585205,
|
|
"epoch": 0.24238857081705817,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997924323079733,
|
|
"loss": 6.8086,
|
|
"mean_token_accuracy": 0.11449672654271126,
|
|
"num_tokens": 4930046.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.9590620517730715,
|
|
"epoch": 0.24292364492482207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997907871656273,
|
|
"loss": 6.8473,
|
|
"mean_token_accuracy": 0.11889113560318947,
|
|
"num_tokens": 4940609.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.953554725646972,
|
|
"epoch": 0.243458719032586,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997891355324791,
|
|
"loss": 6.8548,
|
|
"mean_token_accuracy": 0.11316049173474312,
|
|
"num_tokens": 4951339.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.965586376190186,
|
|
"epoch": 0.24399379314034994,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997874774085761,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.11162809878587723,
|
|
"num_tokens": 4961083.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.9387928485870365,
|
|
"epoch": 0.24452886724811387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997858127939662,
|
|
"loss": 6.7786,
|
|
"mean_token_accuracy": 0.11602784022688865,
|
|
"num_tokens": 4971399.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.045397090911865,
|
|
"epoch": 0.24506394135587778,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997841416886976,
|
|
"loss": 6.8494,
|
|
"mean_token_accuracy": 0.11378169581294059,
|
|
"num_tokens": 4982429.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 7.015939521789551,
|
|
"epoch": 0.2455990154636417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997824640928186,
|
|
"loss": 6.9026,
|
|
"mean_token_accuracy": 0.11243998631834984,
|
|
"num_tokens": 4993706.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.973430252075195,
|
|
"epoch": 0.24613408957140565,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997807800063774,
|
|
"loss": 6.7987,
|
|
"mean_token_accuracy": 0.11612713485956191,
|
|
"num_tokens": 5005411.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.023290300369263,
|
|
"epoch": 0.24666916367916958,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499779089429423,
|
|
"loss": 6.9079,
|
|
"mean_token_accuracy": 0.11179403588175774,
|
|
"num_tokens": 5016011.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.000566244125366,
|
|
"epoch": 0.24720423778693348,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997773923620037,
|
|
"loss": 6.8623,
|
|
"mean_token_accuracy": 0.111385428160429,
|
|
"num_tokens": 5027841.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 7.045706176757813,
|
|
"epoch": 0.24773931189469742,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997756888041689,
|
|
"loss": 6.8724,
|
|
"mean_token_accuracy": 0.10345056504011155,
|
|
"num_tokens": 5038640.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.902830696105957,
|
|
"epoch": 0.24827438600246135,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997739787559677,
|
|
"loss": 6.8095,
|
|
"mean_token_accuracy": 0.11510297358036041,
|
|
"num_tokens": 5050423.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.9570495128631595,
|
|
"epoch": 0.24880946011022526,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997722622174494,
|
|
"loss": 6.8245,
|
|
"mean_token_accuracy": 0.1107373408973217,
|
|
"num_tokens": 5060654.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.980988788604736,
|
|
"epoch": 0.2493445342179892,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997705391886636,
|
|
"loss": 6.74,
|
|
"mean_token_accuracy": 0.11879942938685417,
|
|
"num_tokens": 5070165.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.876005411148071,
|
|
"epoch": 0.24987960832575312,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997688096696601,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.1089643731713295,
|
|
"num_tokens": 5080937.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.925089263916016,
|
|
"epoch": 0.25041468243351706,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997670736604888,
|
|
"loss": 6.7563,
|
|
"mean_token_accuracy": 0.1205267108976841,
|
|
"num_tokens": 5090955.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 7.03852686882019,
|
|
"epoch": 0.250949756541281,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997653311611998,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.11155789867043495,
|
|
"num_tokens": 5102201.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.987645435333252,
|
|
"epoch": 0.25148483064904487,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997635821718435,
|
|
"loss": 6.824,
|
|
"mean_token_accuracy": 0.11684843078255654,
|
|
"num_tokens": 5112235.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.894544506072998,
|
|
"epoch": 0.2520199047568088,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997618266924704,
|
|
"loss": 6.6918,
|
|
"mean_token_accuracy": 0.11397716328501702,
|
|
"num_tokens": 5122360.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.953846549987793,
|
|
"epoch": 0.25255497886457273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499760064723131,
|
|
"loss": 6.8561,
|
|
"mean_token_accuracy": 0.11097584813833236,
|
|
"num_tokens": 5133084.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.926644515991211,
|
|
"epoch": 0.25309005297233667,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997582962638764,
|
|
"loss": 6.807,
|
|
"mean_token_accuracy": 0.11033241674304009,
|
|
"num_tokens": 5144495.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.99140362739563,
|
|
"epoch": 0.2536251270801006,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997565213147575,
|
|
"loss": 6.8124,
|
|
"mean_token_accuracy": 0.1126865342259407,
|
|
"num_tokens": 5154824.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.981679964065552,
|
|
"epoch": 0.25416020118786453,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997547398758257,
|
|
"loss": 6.7919,
|
|
"mean_token_accuracy": 0.11184171065688134,
|
|
"num_tokens": 5165061.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.904257774353027,
|
|
"epoch": 0.25469527529562846,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997529519471323,
|
|
"loss": 6.7544,
|
|
"mean_token_accuracy": 0.11957130804657937,
|
|
"num_tokens": 5174964.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.897611808776856,
|
|
"epoch": 0.25523034940339234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997511575287291,
|
|
"loss": 6.7779,
|
|
"mean_token_accuracy": 0.11545832976698875,
|
|
"num_tokens": 5185458.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.9422607421875,
|
|
"epoch": 0.2557654235111563,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997493566206677,
|
|
"loss": 6.7832,
|
|
"mean_token_accuracy": 0.11810909807682038,
|
|
"num_tokens": 5196193.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.955947160720825,
|
|
"epoch": 0.2563004976189202,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997475492230003,
|
|
"loss": 6.9005,
|
|
"mean_token_accuracy": 0.10454355254769325,
|
|
"num_tokens": 5208541.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.962620639801026,
|
|
"epoch": 0.25683557172668414,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499745735335779,
|
|
"loss": 6.735,
|
|
"mean_token_accuracy": 0.11618000417947769,
|
|
"num_tokens": 5218567.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.940538597106934,
|
|
"epoch": 0.2573706458344481,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997439149590561,
|
|
"loss": 6.8348,
|
|
"mean_token_accuracy": 0.1160251334309578,
|
|
"num_tokens": 5228293.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.943749809265137,
|
|
"epoch": 0.257905719942212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997420880928843,
|
|
"loss": 6.773,
|
|
"mean_token_accuracy": 0.11500717997550965,
|
|
"num_tokens": 5238880.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.971029949188233,
|
|
"epoch": 0.25844079404997594,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997402547373162,
|
|
"loss": 6.8681,
|
|
"mean_token_accuracy": 0.11088483035564423,
|
|
"num_tokens": 5250104.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.003297328948975,
|
|
"epoch": 0.2589758681577399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997384148924049,
|
|
"loss": 6.8911,
|
|
"mean_token_accuracy": 0.10915096178650856,
|
|
"num_tokens": 5260355.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.9441088199615475,
|
|
"epoch": 0.25951094226550375,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997365685582035,
|
|
"loss": 6.8279,
|
|
"mean_token_accuracy": 0.11006084382534027,
|
|
"num_tokens": 5272117.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.993571662902832,
|
|
"epoch": 0.2600460163732677,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997347157347651,
|
|
"loss": 6.9055,
|
|
"mean_token_accuracy": 0.10792700424790383,
|
|
"num_tokens": 5284583.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.9657491683959964,
|
|
"epoch": 0.2605810904810316,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997328564221435,
|
|
"loss": 6.7043,
|
|
"mean_token_accuracy": 0.12548126876354218,
|
|
"num_tokens": 5295846.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.922348833084106,
|
|
"epoch": 0.26111616458879555,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997309906203922,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.11150647774338722,
|
|
"num_tokens": 5307802.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.020015811920166,
|
|
"epoch": 0.2616512386965595,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997291183295652,
|
|
"loss": 6.7684,
|
|
"mean_token_accuracy": 0.11495870873332023,
|
|
"num_tokens": 5318263.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.966686868667603,
|
|
"epoch": 0.2621863128043234,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997272395497164,
|
|
"loss": 6.8393,
|
|
"mean_token_accuracy": 0.11350447610020638,
|
|
"num_tokens": 5328555.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.924846744537353,
|
|
"epoch": 0.26272138691208735,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997253542809002,
|
|
"loss": 6.7822,
|
|
"mean_token_accuracy": 0.11584390923380852,
|
|
"num_tokens": 5339954.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.011740589141846,
|
|
"epoch": 0.26325646101985123,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997234625231709,
|
|
"loss": 6.833,
|
|
"mean_token_accuracy": 0.11277272999286651,
|
|
"num_tokens": 5350919.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.9140222549438475,
|
|
"epoch": 0.26379153512761516,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997215642765832,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.11968391984701157,
|
|
"num_tokens": 5361844.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.95019302368164,
|
|
"epoch": 0.2643266092353791,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499719659541192,
|
|
"loss": 6.817,
|
|
"mean_token_accuracy": 0.11521307304501534,
|
|
"num_tokens": 5372026.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.988909292221069,
|
|
"epoch": 0.26486168334314303,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997177483170521,
|
|
"loss": 6.8607,
|
|
"mean_token_accuracy": 0.1169206328690052,
|
|
"num_tokens": 5382965.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.892836618423462,
|
|
"epoch": 0.26539675745090696,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997158306042188,
|
|
"loss": 6.8263,
|
|
"mean_token_accuracy": 0.11475292220711708,
|
|
"num_tokens": 5393738.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.926968002319336,
|
|
"epoch": 0.2659318315586709,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997139064027476,
|
|
"loss": 6.6846,
|
|
"mean_token_accuracy": 0.12196357250213623,
|
|
"num_tokens": 5404059.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.927339553833008,
|
|
"epoch": 0.26646690566643483,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997119757126938,
|
|
"loss": 6.7177,
|
|
"mean_token_accuracy": 0.12148095294833183,
|
|
"num_tokens": 5414152.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.945639944076538,
|
|
"epoch": 0.2670019797741987,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997100385341133,
|
|
"loss": 6.9211,
|
|
"mean_token_accuracy": 0.11438909769058228,
|
|
"num_tokens": 5425227.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.89841046333313,
|
|
"epoch": 0.26753705388196264,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997080948670621,
|
|
"loss": 6.7386,
|
|
"mean_token_accuracy": 0.11951160728931427,
|
|
"num_tokens": 5435716.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.952828311920166,
|
|
"epoch": 0.26807212798972657,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997061447115962,
|
|
"loss": 6.7994,
|
|
"mean_token_accuracy": 0.11123032942414283,
|
|
"num_tokens": 5446519.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.972070121765137,
|
|
"epoch": 0.2686072020974905,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997041880677719,
|
|
"loss": 6.7854,
|
|
"mean_token_accuracy": 0.11640850678086281,
|
|
"num_tokens": 5457496.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.81004490852356,
|
|
"epoch": 0.26914227620525444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997022249356457,
|
|
"loss": 6.6897,
|
|
"mean_token_accuracy": 0.11792643666267395,
|
|
"num_tokens": 5469059.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.968305969238282,
|
|
"epoch": 0.26967735031301837,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997002553152745,
|
|
"loss": 6.7763,
|
|
"mean_token_accuracy": 0.1165540061891079,
|
|
"num_tokens": 5480324.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.9082786560058596,
|
|
"epoch": 0.2702124244207823,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996982792067148,
|
|
"loss": 6.7982,
|
|
"mean_token_accuracy": 0.10845497250556946,
|
|
"num_tokens": 5491513.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.845801305770874,
|
|
"epoch": 0.2707474985285462,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499696296610024,
|
|
"loss": 6.7141,
|
|
"mean_token_accuracy": 0.1153460405766964,
|
|
"num_tokens": 5502414.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.895366764068603,
|
|
"epoch": 0.2712825726363101,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996943075252592,
|
|
"loss": 6.8524,
|
|
"mean_token_accuracy": 0.11012412756681442,
|
|
"num_tokens": 5512962.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.915656995773316,
|
|
"epoch": 0.27181764674407405,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996923119524777,
|
|
"loss": 6.7113,
|
|
"mean_token_accuracy": 0.11564896106719971,
|
|
"num_tokens": 5524648.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.831974935531616,
|
|
"epoch": 0.272352720851838,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996903098917375,
|
|
"loss": 6.7874,
|
|
"mean_token_accuracy": 0.11287342086434364,
|
|
"num_tokens": 5536158.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.899387216567993,
|
|
"epoch": 0.2728877949596019,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499688301343096,
|
|
"loss": 6.7079,
|
|
"mean_token_accuracy": 0.1191154383122921,
|
|
"num_tokens": 5547374.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 7.005048942565918,
|
|
"epoch": 0.27342286906736585,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996862863066114,
|
|
"loss": 6.7796,
|
|
"mean_token_accuracy": 0.11790791600942611,
|
|
"num_tokens": 5559212.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.890092992782593,
|
|
"epoch": 0.2739579431751298,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996842647823419,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.11599445417523384,
|
|
"num_tokens": 5569302.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.870169162750244,
|
|
"epoch": 0.27449301728289366,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996822367703458,
|
|
"loss": 6.7614,
|
|
"mean_token_accuracy": 0.1111794389784336,
|
|
"num_tokens": 5581688.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.951163101196289,
|
|
"epoch": 0.2750280913906576,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996802022706817,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.12126608714461326,
|
|
"num_tokens": 5591376.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.821857643127442,
|
|
"epoch": 0.2755631654984215,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996781612834083,
|
|
"loss": 6.7398,
|
|
"mean_token_accuracy": 0.11958454847335816,
|
|
"num_tokens": 5601510.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 7.014713430404663,
|
|
"epoch": 0.27609823960618546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996761138085846,
|
|
"loss": 6.8168,
|
|
"mean_token_accuracy": 0.11218597292900086,
|
|
"num_tokens": 5611436.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.935541868209839,
|
|
"epoch": 0.2766333137139494,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996740598462697,
|
|
"loss": 6.8095,
|
|
"mean_token_accuracy": 0.11031911820173264,
|
|
"num_tokens": 5620470.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.8055510997772215,
|
|
"epoch": 0.2771683878217133,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996719993965229,
|
|
"loss": 6.706,
|
|
"mean_token_accuracy": 0.11797739341855049,
|
|
"num_tokens": 5630740.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.850885009765625,
|
|
"epoch": 0.27770346192947726,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996699324594036,
|
|
"loss": 6.7039,
|
|
"mean_token_accuracy": 0.12097388580441475,
|
|
"num_tokens": 5641138.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.978074979782105,
|
|
"epoch": 0.27823853603724114,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996678590349717,
|
|
"loss": 6.8357,
|
|
"mean_token_accuracy": 0.11379286721348762,
|
|
"num_tokens": 5652474.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.878711938858032,
|
|
"epoch": 0.27877361014500507,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996657791232868,
|
|
"loss": 6.7386,
|
|
"mean_token_accuracy": 0.11961781904101372,
|
|
"num_tokens": 5663178.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.925683259963989,
|
|
"epoch": 0.279308684252769,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996636927244092,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.1120869092643261,
|
|
"num_tokens": 5673565.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.962445402145386,
|
|
"epoch": 0.27984375836053293,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499661599838399,
|
|
"loss": 6.8024,
|
|
"mean_token_accuracy": 0.11387971341609955,
|
|
"num_tokens": 5684651.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.835036849975586,
|
|
"epoch": 0.28037883246829687,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996595004653167,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.11756563186645508,
|
|
"num_tokens": 5696081.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.892896032333374,
|
|
"epoch": 0.2809139065760608,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996573946052229,
|
|
"loss": 6.7302,
|
|
"mean_token_accuracy": 0.1182306431233883,
|
|
"num_tokens": 5706830.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.870751905441284,
|
|
"epoch": 0.28144898068382473,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996552822581783,
|
|
"loss": 6.7497,
|
|
"mean_token_accuracy": 0.11799419671297073,
|
|
"num_tokens": 5717261.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.895398330688477,
|
|
"epoch": 0.2819840547915886,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499653163424244,
|
|
"loss": 6.7162,
|
|
"mean_token_accuracy": 0.11693291366100311,
|
|
"num_tokens": 5727280.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.914795780181885,
|
|
"epoch": 0.28251912889935255,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996510381034814,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.11307182461023331,
|
|
"num_tokens": 5737485.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.847374200820923,
|
|
"epoch": 0.2830542030071165,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996489062959515,
|
|
"loss": 6.7455,
|
|
"mean_token_accuracy": 0.11446416452527046,
|
|
"num_tokens": 5747683.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.875591611862182,
|
|
"epoch": 0.2835892771148804,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996467680017159,
|
|
"loss": 6.8008,
|
|
"mean_token_accuracy": 0.10731672197580337,
|
|
"num_tokens": 5758148.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.893660068511963,
|
|
"epoch": 0.28412435122264434,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996446232208365,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.11981129944324494,
|
|
"num_tokens": 5769109.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.8458967208862305,
|
|
"epoch": 0.2846594253304083,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996424719533753,
|
|
"loss": 6.7689,
|
|
"mean_token_accuracy": 0.11590512916445732,
|
|
"num_tokens": 5780344.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.854043436050415,
|
|
"epoch": 0.2851944994381722,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996403141993941,
|
|
"loss": 6.574,
|
|
"mean_token_accuracy": 0.12556484565138817,
|
|
"num_tokens": 5790167.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.847289323806763,
|
|
"epoch": 0.2857295735459361,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996381499589555,
|
|
"loss": 6.736,
|
|
"mean_token_accuracy": 0.1166438452899456,
|
|
"num_tokens": 5800076.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.958036756515503,
|
|
"epoch": 0.2862646476537,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996359792321219,
|
|
"loss": 6.6761,
|
|
"mean_token_accuracy": 0.12416882291436196,
|
|
"num_tokens": 5810547.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.771701908111572,
|
|
"epoch": 0.28679972176146395,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499633802018956,
|
|
"loss": 6.7178,
|
|
"mean_token_accuracy": 0.12147761583328247,
|
|
"num_tokens": 5821210.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.8582275867462155,
|
|
"epoch": 0.2873347958692279,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996316183195204,
|
|
"loss": 6.7428,
|
|
"mean_token_accuracy": 0.11563531160354615,
|
|
"num_tokens": 5832361.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.957939958572387,
|
|
"epoch": 0.2878698699769918,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996294281338786,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.11480305045843124,
|
|
"num_tokens": 5843242.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.903535652160644,
|
|
"epoch": 0.28840494408475575,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996272314620936,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.11267708018422126,
|
|
"num_tokens": 5855163.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.856528568267822,
|
|
"epoch": 0.2889400181925197,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996250283042288,
|
|
"loss": 6.7295,
|
|
"mean_token_accuracy": 0.11896763294935227,
|
|
"num_tokens": 5866908.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.895650959014892,
|
|
"epoch": 0.28947509230028357,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499622818660348,
|
|
"loss": 6.77,
|
|
"mean_token_accuracy": 0.11609848588705063,
|
|
"num_tokens": 5877342.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.855501699447632,
|
|
"epoch": 0.2900101664080475,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996206025305147,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.11352964714169503,
|
|
"num_tokens": 5887960.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.8687375545501705,
|
|
"epoch": 0.29054524051581143,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996183799147932,
|
|
"loss": 6.7099,
|
|
"mean_token_accuracy": 0.11922564879059791,
|
|
"num_tokens": 5899887.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.900043058395386,
|
|
"epoch": 0.29108031462357536,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996161508132475,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.11077265068888664,
|
|
"num_tokens": 5911022.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.9139257907867435,
|
|
"epoch": 0.2916153887313393,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499613915225942,
|
|
"loss": 6.7896,
|
|
"mean_token_accuracy": 0.12132234573364258,
|
|
"num_tokens": 5922780.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.895234394073486,
|
|
"epoch": 0.29215046283910323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996116731529412,
|
|
"loss": 6.7943,
|
|
"mean_token_accuracy": 0.11419421285390854,
|
|
"num_tokens": 5934112.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.880492639541626,
|
|
"epoch": 0.29268553694686716,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049960942459431,
|
|
"loss": 6.7463,
|
|
"mean_token_accuracy": 0.11509791687130928,
|
|
"num_tokens": 5944386.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.831871843338012,
|
|
"epoch": 0.29322061105463104,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996071695501132,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.12181662246584893,
|
|
"num_tokens": 5955552.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.863772535324097,
|
|
"epoch": 0.293755685162395,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996049080204159,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.11952602937817573,
|
|
"num_tokens": 5966790.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.894785785675049,
|
|
"epoch": 0.2942907592701589,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996026400052835,
|
|
"loss": 6.696,
|
|
"mean_token_accuracy": 0.1183117188513279,
|
|
"num_tokens": 5977704.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.789415884017944,
|
|
"epoch": 0.29482583337792284,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996003655047814,
|
|
"loss": 6.6998,
|
|
"mean_token_accuracy": 0.11984472051262855,
|
|
"num_tokens": 5989221.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.840144300460816,
|
|
"epoch": 0.2953609074856868,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995980845189753,
|
|
"loss": 6.7539,
|
|
"mean_token_accuracy": 0.1141133077442646,
|
|
"num_tokens": 6000906.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.915990352630615,
|
|
"epoch": 0.2958959815934507,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995957970479312,
|
|
"loss": 6.7618,
|
|
"mean_token_accuracy": 0.1168858326971531,
|
|
"num_tokens": 6012039.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.821195030212403,
|
|
"epoch": 0.29643105570121464,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995935030917148,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.11786336153745651,
|
|
"num_tokens": 6024383.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.907906627655029,
|
|
"epoch": 0.2969661298089785,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995912026503926,
|
|
"loss": 6.711,
|
|
"mean_token_accuracy": 0.11563370078802108,
|
|
"num_tokens": 6034904.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.826932573318482,
|
|
"epoch": 0.29750120391674245,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499588895724031,
|
|
"loss": 6.7199,
|
|
"mean_token_accuracy": 0.11507032215595245,
|
|
"num_tokens": 6044449.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.915383815765381,
|
|
"epoch": 0.2980362780245064,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995865823126968,
|
|
"loss": 6.728,
|
|
"mean_token_accuracy": 0.11910260394215584,
|
|
"num_tokens": 6054465.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.816167879104614,
|
|
"epoch": 0.2985713521322703,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995842624164564,
|
|
"loss": 6.7675,
|
|
"mean_token_accuracy": 0.11578667089343071,
|
|
"num_tokens": 6065539.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.870489883422851,
|
|
"epoch": 0.29910642624003425,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499581936035377,
|
|
"loss": 6.7168,
|
|
"mean_token_accuracy": 0.11584314554929734,
|
|
"num_tokens": 6076135.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.812382507324219,
|
|
"epoch": 0.2996415003477982,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995796031695257,
|
|
"loss": 6.7066,
|
|
"mean_token_accuracy": 0.12096717059612275,
|
|
"num_tokens": 6086604.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.905838060379028,
|
|
"epoch": 0.3001765744555621,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049957726381897,
|
|
"loss": 6.7253,
|
|
"mean_token_accuracy": 0.1189133383333683,
|
|
"num_tokens": 6095672.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.821977853775024,
|
|
"epoch": 0.300711648563326,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995749179837773,
|
|
"loss": 6.6077,
|
|
"mean_token_accuracy": 0.12966387793421746,
|
|
"num_tokens": 6105652.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.798386573791504,
|
|
"epoch": 0.30124672267108993,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995725656640155,
|
|
"loss": 6.6614,
|
|
"mean_token_accuracy": 0.11868161782622337,
|
|
"num_tokens": 6116930.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.807754468917847,
|
|
"epoch": 0.30178179677885386,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995702068597524,
|
|
"loss": 6.6468,
|
|
"mean_token_accuracy": 0.1246480442583561,
|
|
"num_tokens": 6126659.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.8313295364379885,
|
|
"epoch": 0.3023168708866178,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995678415710561,
|
|
"loss": 6.6907,
|
|
"mean_token_accuracy": 0.11699030175805092,
|
|
"num_tokens": 6137227.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.9275243282318115,
|
|
"epoch": 0.3028519449943817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499565469797995,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.11795717254281043,
|
|
"num_tokens": 6147800.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.778878402709961,
|
|
"epoch": 0.30338701910214566,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995630915406374,
|
|
"loss": 6.5835,
|
|
"mean_token_accuracy": 0.12834293246269227,
|
|
"num_tokens": 6157671.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.863351917266845,
|
|
"epoch": 0.3039220932099096,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995607067990521,
|
|
"loss": 6.7337,
|
|
"mean_token_accuracy": 0.11715143024921418,
|
|
"num_tokens": 6168651.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.778136157989502,
|
|
"epoch": 0.30445716731767347,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499558315573308,
|
|
"loss": 6.7207,
|
|
"mean_token_accuracy": 0.11487283408641816,
|
|
"num_tokens": 6179925.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.853423357009888,
|
|
"epoch": 0.3049922414254374,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995559178634741,
|
|
"loss": 6.6948,
|
|
"mean_token_accuracy": 0.11927086412906647,
|
|
"num_tokens": 6190541.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.928079080581665,
|
|
"epoch": 0.30552731553320134,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995535136696196,
|
|
"loss": 6.7445,
|
|
"mean_token_accuracy": 0.1103590488433838,
|
|
"num_tokens": 6201491.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.75769829750061,
|
|
"epoch": 0.30606238964096527,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499551102991814,
|
|
"loss": 6.5634,
|
|
"mean_token_accuracy": 0.1230486162006855,
|
|
"num_tokens": 6212443.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.851051998138428,
|
|
"epoch": 0.3065974637487292,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995486858301268,
|
|
"loss": 6.7632,
|
|
"mean_token_accuracy": 0.10713932886719704,
|
|
"num_tokens": 6222623.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.818279552459717,
|
|
"epoch": 0.30713253785649314,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995462621846279,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.11947918683290482,
|
|
"num_tokens": 6233712.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.875202989578247,
|
|
"epoch": 0.30766761196425707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995438320553871,
|
|
"loss": 6.7124,
|
|
"mean_token_accuracy": 0.1145969197154045,
|
|
"num_tokens": 6244254.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.819658660888672,
|
|
"epoch": 0.30820268607202095,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995413954424748,
|
|
"loss": 6.6202,
|
|
"mean_token_accuracy": 0.12699596509337424,
|
|
"num_tokens": 6254202.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.796465873718262,
|
|
"epoch": 0.3087377601797849,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995389523459612,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.11479482129216194,
|
|
"num_tokens": 6264496.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.763580942153931,
|
|
"epoch": 0.3092728342875488,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499536502765917,
|
|
"loss": 6.7048,
|
|
"mean_token_accuracy": 0.12205370739102364,
|
|
"num_tokens": 6275835.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.8645845413208,
|
|
"epoch": 0.30980790839531275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995340467024128,
|
|
"loss": 6.6453,
|
|
"mean_token_accuracy": 0.12240780219435692,
|
|
"num_tokens": 6286805.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.7850439071655275,
|
|
"epoch": 0.3103429825030767,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995315841555195,
|
|
"loss": 6.6525,
|
|
"mean_token_accuracy": 0.11469742059707641,
|
|
"num_tokens": 6298444.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.765648126602173,
|
|
"epoch": 0.3108780566108406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995291151253083,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.12251365631818771,
|
|
"num_tokens": 6308259.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.776980543136597,
|
|
"epoch": 0.31141313071860455,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995266396118505,
|
|
"loss": 6.6738,
|
|
"mean_token_accuracy": 0.11214960515499114,
|
|
"num_tokens": 6320058.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.818608903884888,
|
|
"epoch": 0.3119482048263684,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995241576152174,
|
|
"loss": 6.6341,
|
|
"mean_token_accuracy": 0.11381927952170372,
|
|
"num_tokens": 6331203.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.873639345169067,
|
|
"epoch": 0.31248327893413236,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499521669135481,
|
|
"loss": 6.7543,
|
|
"mean_token_accuracy": 0.1158191867172718,
|
|
"num_tokens": 6342027.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.846279573440552,
|
|
"epoch": 0.3130183530418963,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995191741727128,
|
|
"loss": 6.6493,
|
|
"mean_token_accuracy": 0.11973418965935707,
|
|
"num_tokens": 6352580.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.811291313171386,
|
|
"epoch": 0.3135534271496602,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499516672726985,
|
|
"loss": 6.6519,
|
|
"mean_token_accuracy": 0.1260712191462517,
|
|
"num_tokens": 6363997.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.809375381469726,
|
|
"epoch": 0.31408850125742416,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995141647983699,
|
|
"loss": 6.7114,
|
|
"mean_token_accuracy": 0.12156427055597305,
|
|
"num_tokens": 6375284.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.7512000560760494,
|
|
"epoch": 0.3146235753651881,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995116503869398,
|
|
"loss": 6.6172,
|
|
"mean_token_accuracy": 0.12655090987682344,
|
|
"num_tokens": 6386698.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.799907445907593,
|
|
"epoch": 0.315158649472952,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995091294927673,
|
|
"loss": 6.6832,
|
|
"mean_token_accuracy": 0.11689872294664383,
|
|
"num_tokens": 6397237.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.938808870315552,
|
|
"epoch": 0.3156937235807159,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995066021159253,
|
|
"loss": 6.7826,
|
|
"mean_token_accuracy": 0.11724542751908303,
|
|
"num_tokens": 6408266.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.75793423652649,
|
|
"epoch": 0.31622879768847983,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995040682564867,
|
|
"loss": 6.6881,
|
|
"mean_token_accuracy": 0.12444577813148498,
|
|
"num_tokens": 6419563.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.7891706943511965,
|
|
"epoch": 0.31676387179624377,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995015279145247,
|
|
"loss": 6.6566,
|
|
"mean_token_accuracy": 0.12058857157826423,
|
|
"num_tokens": 6430220.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.835130596160889,
|
|
"epoch": 0.3172989459040077,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994989810901126,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.11899991482496261,
|
|
"num_tokens": 6440157.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.804441738128662,
|
|
"epoch": 0.31783402001177163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994964277833239,
|
|
"loss": 6.7116,
|
|
"mean_token_accuracy": 0.12262500971555709,
|
|
"num_tokens": 6449511.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.889899396896363,
|
|
"epoch": 0.31836909411953557,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994938679942324,
|
|
"loss": 6.7037,
|
|
"mean_token_accuracy": 0.11440852656960487,
|
|
"num_tokens": 6460608.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.79391393661499,
|
|
"epoch": 0.3189041682272995,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994913017229121,
|
|
"loss": 6.6872,
|
|
"mean_token_accuracy": 0.12514959052205085,
|
|
"num_tokens": 6472737.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.744311809539795,
|
|
"epoch": 0.31943924233506343,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994887289694371,
|
|
"loss": 6.5779,
|
|
"mean_token_accuracy": 0.12682042494416237,
|
|
"num_tokens": 6482993.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.897027587890625,
|
|
"epoch": 0.3199743164428273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994861497338814,
|
|
"loss": 6.769,
|
|
"mean_token_accuracy": 0.11616470366716385,
|
|
"num_tokens": 6494530.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.82117919921875,
|
|
"epoch": 0.32050939055059124,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994835640163198,
|
|
"loss": 6.6057,
|
|
"mean_token_accuracy": 0.11340584680438041,
|
|
"num_tokens": 6504691.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.7946573257446286,
|
|
"epoch": 0.3210444646583552,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994809718168267,
|
|
"loss": 6.6401,
|
|
"mean_token_accuracy": 0.12243752628564834,
|
|
"num_tokens": 6514924.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3210444646583552,
|
|
"eval_entropy": 6.541231488281825,
|
|
"eval_loss": 6.7393646240234375,
|
|
"eval_mean_token_accuracy": 0.12389561494440844,
|
|
"eval_num_tokens": 6514924.0,
|
|
"eval_runtime": 17.9576,
|
|
"eval_samples_per_second": 1652.726,
|
|
"eval_steps_per_second": 206.598,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 93440,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1414915727523840.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|