48123 lines
1.3 MiB
48123 lines
1.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.372479240806643,
|
|
"eval_steps": 3000,
|
|
"global_step": 24000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742559432983398,
|
|
"epoch": 0.0004942665085013839,
|
|
"grad_norm": 5.34375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7918,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11289.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742565155029297,
|
|
"epoch": 0.0009885330170027679,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7677,
|
|
"mean_token_accuracy": 0.00010660981060937048,
|
|
"num_tokens": 21541.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.74260196685791,
|
|
"epoch": 0.0014827995255041518,
|
|
"grad_norm": 5.28125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7469,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 32257.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742596530914307,
|
|
"epoch": 0.0019770660340055358,
|
|
"grad_norm": 5.09375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7082,
|
|
"mean_token_accuracy": 0.00043735416838899257,
|
|
"num_tokens": 44176.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742553424835204,
|
|
"epoch": 0.0024713325425069197,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6063,
|
|
"mean_token_accuracy": 0.005003847437910736,
|
|
"num_tokens": 56115.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.742230701446534,
|
|
"epoch": 0.0029655990510083037,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4933,
|
|
"mean_token_accuracy": 0.02219230718910694,
|
|
"num_tokens": 68828.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.74111728668213,
|
|
"epoch": 0.0034598655595096876,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3232,
|
|
"mean_token_accuracy": 0.037596833519637586,
|
|
"num_tokens": 80097.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.73831787109375,
|
|
"epoch": 0.0039541320680110716,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1706,
|
|
"mean_token_accuracy": 0.042161832191050054,
|
|
"num_tokens": 91510.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.734669494628907,
|
|
"epoch": 0.004448398576512456,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0532,
|
|
"mean_token_accuracy": 0.04492984525859356,
|
|
"num_tokens": 103443.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.731356620788574,
|
|
"epoch": 0.0049426650850138395,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9944,
|
|
"mean_token_accuracy": 0.04110746793448925,
|
|
"num_tokens": 114629.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.72984676361084,
|
|
"epoch": 0.005436931593515224,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9354,
|
|
"mean_token_accuracy": 0.0402316827327013,
|
|
"num_tokens": 125012.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.72827968597412,
|
|
"epoch": 0.005931198102016607,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.8745,
|
|
"mean_token_accuracy": 0.0415823869407177,
|
|
"num_tokens": 135834.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.726681423187255,
|
|
"epoch": 0.006425464610517992,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.8094,
|
|
"mean_token_accuracy": 0.0378471277654171,
|
|
"num_tokens": 147413.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.725395107269287,
|
|
"epoch": 0.006919731119019375,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7766,
|
|
"mean_token_accuracy": 0.04534405171871185,
|
|
"num_tokens": 158046.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.722041702270507,
|
|
"epoch": 0.00741399762752076,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7003,
|
|
"mean_token_accuracy": 0.04153196755796671,
|
|
"num_tokens": 168564.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.717565536499023,
|
|
"epoch": 0.007908264136022143,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.6649,
|
|
"mean_token_accuracy": 0.040395910106599334,
|
|
"num_tokens": 181168.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.712557983398437,
|
|
"epoch": 0.008402530644523527,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.5927,
|
|
"mean_token_accuracy": 0.040117064118385316,
|
|
"num_tokens": 192666.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.706313228607177,
|
|
"epoch": 0.008896797153024912,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5324,
|
|
"mean_token_accuracy": 0.04307716451585293,
|
|
"num_tokens": 203688.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.696890449523925,
|
|
"epoch": 0.009391063661526295,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.4292,
|
|
"mean_token_accuracy": 0.04244718514382839,
|
|
"num_tokens": 214399.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.68424196243286,
|
|
"epoch": 0.009885330170027679,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4064,
|
|
"mean_token_accuracy": 0.03980784080922604,
|
|
"num_tokens": 227549.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.669907379150391,
|
|
"epoch": 0.010379596678529062,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2501,
|
|
"mean_token_accuracy": 0.05166649520397186,
|
|
"num_tokens": 239612.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.647725677490234,
|
|
"epoch": 0.010873863187030448,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1891,
|
|
"mean_token_accuracy": 0.05595755912363529,
|
|
"num_tokens": 251163.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.614391994476318,
|
|
"epoch": 0.011368129695531831,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0675,
|
|
"mean_token_accuracy": 0.0543642945587635,
|
|
"num_tokens": 263995.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.580703353881836,
|
|
"epoch": 0.011862396204033215,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.0334,
|
|
"mean_token_accuracy": 0.05128365270793438,
|
|
"num_tokens": 275103.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.53465690612793,
|
|
"epoch": 0.012356662712534598,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.9026,
|
|
"mean_token_accuracy": 0.05212775617837906,
|
|
"num_tokens": 286838.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.470762634277344,
|
|
"epoch": 0.012850929221035983,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.8066,
|
|
"mean_token_accuracy": 0.05225841067731381,
|
|
"num_tokens": 298750.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.38624849319458,
|
|
"epoch": 0.013345195729537367,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.6142,
|
|
"mean_token_accuracy": 0.06268712393939495,
|
|
"num_tokens": 310451.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.291066646575928,
|
|
"epoch": 0.01383946223803875,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.5675,
|
|
"mean_token_accuracy": 0.05591914691030979,
|
|
"num_tokens": 321232.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.217416381835937,
|
|
"epoch": 0.014333728746540134,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.426,
|
|
"mean_token_accuracy": 0.06510277166962623,
|
|
"num_tokens": 332531.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.091275501251221,
|
|
"epoch": 0.01482799525504152,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.3371,
|
|
"mean_token_accuracy": 0.060455797240138054,
|
|
"num_tokens": 346002.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.966124248504638,
|
|
"epoch": 0.015322261763542903,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1965,
|
|
"mean_token_accuracy": 0.05812167599797249,
|
|
"num_tokens": 356691.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.774528980255127,
|
|
"epoch": 0.015816528272044286,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.1137,
|
|
"mean_token_accuracy": 0.06779846139252185,
|
|
"num_tokens": 368749.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.564791774749756,
|
|
"epoch": 0.01631079478054567,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9752,
|
|
"mean_token_accuracy": 0.06878971830010414,
|
|
"num_tokens": 379484.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.371025466918946,
|
|
"epoch": 0.016805061289047053,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9252,
|
|
"mean_token_accuracy": 0.065206453576684,
|
|
"num_tokens": 389751.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.126683902740478,
|
|
"epoch": 0.017299327797548437,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.8734,
|
|
"mean_token_accuracy": 0.06619854085147381,
|
|
"num_tokens": 400771.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.916962146759033,
|
|
"epoch": 0.017793594306049824,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.8145,
|
|
"mean_token_accuracy": 0.07182282060384751,
|
|
"num_tokens": 413575.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.716337394714355,
|
|
"epoch": 0.018287860814551207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7284,
|
|
"mean_token_accuracy": 0.07276704236865043,
|
|
"num_tokens": 424825.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.58464298248291,
|
|
"epoch": 0.01878212732305259,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.7373,
|
|
"mean_token_accuracy": 0.07814876064658165,
|
|
"num_tokens": 435610.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.413296604156494,
|
|
"epoch": 0.019276393831553974,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6992,
|
|
"mean_token_accuracy": 0.07458564341068268,
|
|
"num_tokens": 445855.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.39066514968872,
|
|
"epoch": 0.019770660340055358,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5975,
|
|
"mean_token_accuracy": 0.07509246952831745,
|
|
"num_tokens": 456895.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.318842697143555,
|
|
"epoch": 0.02026492684855674,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.6975,
|
|
"mean_token_accuracy": 0.07416085563600064,
|
|
"num_tokens": 467446.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.206272411346436,
|
|
"epoch": 0.020759193357058125,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.6073,
|
|
"mean_token_accuracy": 0.07490024492144584,
|
|
"num_tokens": 478988.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.203931045532226,
|
|
"epoch": 0.02125345986555951,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.6028,
|
|
"mean_token_accuracy": 0.0804927557706833,
|
|
"num_tokens": 491053.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.194980716705322,
|
|
"epoch": 0.021747726374060895,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.6693,
|
|
"mean_token_accuracy": 0.07337137088179588,
|
|
"num_tokens": 502279.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.176432991027832,
|
|
"epoch": 0.02224199288256228,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.5236,
|
|
"mean_token_accuracy": 0.08306471854448319,
|
|
"num_tokens": 513470.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.073592710494996,
|
|
"epoch": 0.022736259391063662,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5779,
|
|
"mean_token_accuracy": 0.07856447473168374,
|
|
"num_tokens": 524380.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.152504539489746,
|
|
"epoch": 0.023230525899565046,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5837,
|
|
"mean_token_accuracy": 0.08571179807186127,
|
|
"num_tokens": 535798.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.032267951965332,
|
|
"epoch": 0.02372479240806643,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.4937,
|
|
"mean_token_accuracy": 0.08659510985016823,
|
|
"num_tokens": 545720.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.007299280166626,
|
|
"epoch": 0.024219058916567813,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5277,
|
|
"mean_token_accuracy": 0.0827151209115982,
|
|
"num_tokens": 557110.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.001366901397706,
|
|
"epoch": 0.024713325425069196,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.4975,
|
|
"mean_token_accuracy": 0.08423097357153893,
|
|
"num_tokens": 568966.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.03173599243164,
|
|
"epoch": 0.02520759193357058,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4969,
|
|
"mean_token_accuracy": 0.08669283166527748,
|
|
"num_tokens": 580441.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.057562732696534,
|
|
"epoch": 0.025701858442071967,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4982,
|
|
"mean_token_accuracy": 0.08434496074914932,
|
|
"num_tokens": 592698.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.953376913070679,
|
|
"epoch": 0.02619612495057335,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4669,
|
|
"mean_token_accuracy": 0.08737746998667717,
|
|
"num_tokens": 604787.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.998782920837402,
|
|
"epoch": 0.026690391459074734,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4532,
|
|
"mean_token_accuracy": 0.08598756566643714,
|
|
"num_tokens": 616445.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.9657186508178714,
|
|
"epoch": 0.027184657967576117,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4802,
|
|
"mean_token_accuracy": 0.08283287510275841,
|
|
"num_tokens": 627723.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.00689115524292,
|
|
"epoch": 0.0276789244760775,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.5189,
|
|
"mean_token_accuracy": 0.08700487017631531,
|
|
"num_tokens": 638987.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.936768245697022,
|
|
"epoch": 0.028173190984578884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.334,
|
|
"mean_token_accuracy": 0.09142324700951576,
|
|
"num_tokens": 650626.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.860474920272827,
|
|
"epoch": 0.028667457493080268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.3572,
|
|
"mean_token_accuracy": 0.09691204503178596,
|
|
"num_tokens": 661911.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.903319931030273,
|
|
"epoch": 0.02916172400158165,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4067,
|
|
"mean_token_accuracy": 0.09089745208621025,
|
|
"num_tokens": 674298.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.882914972305298,
|
|
"epoch": 0.02965599051008304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3443,
|
|
"mean_token_accuracy": 0.0963382288813591,
|
|
"num_tokens": 686000.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.80755648612976,
|
|
"epoch": 0.030150257018584422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.362,
|
|
"mean_token_accuracy": 0.0944715328514576,
|
|
"num_tokens": 698464.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.860896110534668,
|
|
"epoch": 0.030644523527085805,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.379,
|
|
"mean_token_accuracy": 0.09046986699104309,
|
|
"num_tokens": 709702.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.968799591064453,
|
|
"epoch": 0.03113879003558719,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.4846,
|
|
"mean_token_accuracy": 0.0890492059290409,
|
|
"num_tokens": 722234.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.776518249511719,
|
|
"epoch": 0.03163305654408857,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.4068,
|
|
"mean_token_accuracy": 0.0861303061246872,
|
|
"num_tokens": 733001.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.8235656261444095,
|
|
"epoch": 0.03212732305258996,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3732,
|
|
"mean_token_accuracy": 0.09485758617520332,
|
|
"num_tokens": 743315.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.8506021976470945,
|
|
"epoch": 0.03262158956109134,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3153,
|
|
"mean_token_accuracy": 0.09164077565073966,
|
|
"num_tokens": 754386.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.832219028472901,
|
|
"epoch": 0.033115856069592726,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.4069,
|
|
"mean_token_accuracy": 0.09743229635059833,
|
|
"num_tokens": 766504.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.739070034027099,
|
|
"epoch": 0.033610122578094107,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.2425,
|
|
"mean_token_accuracy": 0.10150521248579025,
|
|
"num_tokens": 777039.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.80741925239563,
|
|
"epoch": 0.034104389086595494,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.3291,
|
|
"mean_token_accuracy": 0.09152510985732079,
|
|
"num_tokens": 787890.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.745412302017212,
|
|
"epoch": 0.034598655595096874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.2991,
|
|
"mean_token_accuracy": 0.09431157857179642,
|
|
"num_tokens": 800129.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.7933450698852536,
|
|
"epoch": 0.03509292210359826,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.3748,
|
|
"mean_token_accuracy": 0.08783866837620735,
|
|
"num_tokens": 812517.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.6894533157348635,
|
|
"epoch": 0.03558718861209965,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.2982,
|
|
"mean_token_accuracy": 0.09622510373592377,
|
|
"num_tokens": 824570.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.741975736618042,
|
|
"epoch": 0.03608145512060103,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.2824,
|
|
"mean_token_accuracy": 0.09666576460003853,
|
|
"num_tokens": 836506.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.75258502960205,
|
|
"epoch": 0.036575721629102415,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.3016,
|
|
"mean_token_accuracy": 0.09653399288654327,
|
|
"num_tokens": 846841.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.799630975723266,
|
|
"epoch": 0.037069988137603795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.3364,
|
|
"mean_token_accuracy": 0.10044656544923783,
|
|
"num_tokens": 858770.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.680880880355835,
|
|
"epoch": 0.03756425464610518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.1812,
|
|
"mean_token_accuracy": 0.09969076812267304,
|
|
"num_tokens": 870184.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.6216026782989506,
|
|
"epoch": 0.03805852115460656,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.2248,
|
|
"mean_token_accuracy": 0.10294909402728081,
|
|
"num_tokens": 881843.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.7437238693237305,
|
|
"epoch": 0.03855278766310795,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.2613,
|
|
"mean_token_accuracy": 0.09593532085418702,
|
|
"num_tokens": 893453.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.66199746131897,
|
|
"epoch": 0.03904705417160933,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.3009,
|
|
"mean_token_accuracy": 0.08956974968314171,
|
|
"num_tokens": 904417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.71559739112854,
|
|
"epoch": 0.039541320680110716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.223,
|
|
"mean_token_accuracy": 0.09316879063844681,
|
|
"num_tokens": 915134.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.676138925552368,
|
|
"epoch": 0.0400355871886121,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.2417,
|
|
"mean_token_accuracy": 0.09755214676260948,
|
|
"num_tokens": 926361.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.596137046813965,
|
|
"epoch": 0.04052985369711348,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.1619,
|
|
"mean_token_accuracy": 0.09669081121683121,
|
|
"num_tokens": 937474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.70306715965271,
|
|
"epoch": 0.04102412020561487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.2242,
|
|
"mean_token_accuracy": 0.10178504958748817,
|
|
"num_tokens": 948897.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.578281736373901,
|
|
"epoch": 0.04151838671411625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.2445,
|
|
"mean_token_accuracy": 0.09385722428560257,
|
|
"num_tokens": 960669.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.606976747512817,
|
|
"epoch": 0.04201265322261764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.097,
|
|
"mean_token_accuracy": 0.10118152871727944,
|
|
"num_tokens": 973001.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.5266501903533936,
|
|
"epoch": 0.04250691973111902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.1573,
|
|
"mean_token_accuracy": 0.1002947136759758,
|
|
"num_tokens": 986214.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.537716960906982,
|
|
"epoch": 0.043001186239620404,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.1675,
|
|
"mean_token_accuracy": 0.09322678521275521,
|
|
"num_tokens": 997363.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.530834531784057,
|
|
"epoch": 0.04349545274812179,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.092,
|
|
"mean_token_accuracy": 0.10840804129838943,
|
|
"num_tokens": 1009543.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.578037929534912,
|
|
"epoch": 0.04398971925662317,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.1736,
|
|
"mean_token_accuracy": 0.0948575533926487,
|
|
"num_tokens": 1020561.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.589271831512451,
|
|
"epoch": 0.04448398576512456,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.1256,
|
|
"mean_token_accuracy": 0.09639807492494583,
|
|
"num_tokens": 1032587.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.5890984535217285,
|
|
"epoch": 0.04497825227362594,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.1359,
|
|
"mean_token_accuracy": 0.09905373975634575,
|
|
"num_tokens": 1044249.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.547998476028442,
|
|
"epoch": 0.045472518782127325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.1744,
|
|
"mean_token_accuracy": 0.09762973859906196,
|
|
"num_tokens": 1055415.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.5688958168029785,
|
|
"epoch": 0.045966785290628705,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.1466,
|
|
"mean_token_accuracy": 0.09966595321893693,
|
|
"num_tokens": 1066593.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.529252672195435,
|
|
"epoch": 0.04646105179913009,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.1369,
|
|
"mean_token_accuracy": 0.10283891633152961,
|
|
"num_tokens": 1076966.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.504359388351441,
|
|
"epoch": 0.04695531830763147,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.1676,
|
|
"mean_token_accuracy": 0.09871028363704681,
|
|
"num_tokens": 1089927.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.551082754135132,
|
|
"epoch": 0.04744958481613286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.1255,
|
|
"mean_token_accuracy": 0.09758824929594993,
|
|
"num_tokens": 1101920.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.489306211471558,
|
|
"epoch": 0.047943851324634246,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.1816,
|
|
"mean_token_accuracy": 0.10394024401903153,
|
|
"num_tokens": 1115078.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.6370282649993895,
|
|
"epoch": 0.048438117833135626,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.2542,
|
|
"mean_token_accuracy": 0.09503929167985917,
|
|
"num_tokens": 1127138.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.449513244628906,
|
|
"epoch": 0.04893238434163701,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.0705,
|
|
"mean_token_accuracy": 0.0948334887623787,
|
|
"num_tokens": 1138390.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.407353210449219,
|
|
"epoch": 0.04942665085013839,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.0009,
|
|
"mean_token_accuracy": 0.10578849464654923,
|
|
"num_tokens": 1149124.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.487055921554566,
|
|
"epoch": 0.04992091735863978,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.0787,
|
|
"mean_token_accuracy": 0.10215417668223381,
|
|
"num_tokens": 1161091.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.527550268173218,
|
|
"epoch": 0.05041518386714116,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.062,
|
|
"mean_token_accuracy": 0.10265694484114647,
|
|
"num_tokens": 1171919.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.452037620544433,
|
|
"epoch": 0.05090945037564255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.0832,
|
|
"mean_token_accuracy": 0.10110483095049858,
|
|
"num_tokens": 1183688.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.405346298217774,
|
|
"epoch": 0.051403716884143934,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.012,
|
|
"mean_token_accuracy": 0.0998148925602436,
|
|
"num_tokens": 1195323.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.492317199707031,
|
|
"epoch": 0.051897983392645314,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.1082,
|
|
"mean_token_accuracy": 0.09472725465893746,
|
|
"num_tokens": 1206782.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.3935158252716064,
|
|
"epoch": 0.0523922499011467,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.0087,
|
|
"mean_token_accuracy": 0.10457788184285163,
|
|
"num_tokens": 1218102.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.366737365722656,
|
|
"epoch": 0.05288651640964808,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.979,
|
|
"mean_token_accuracy": 0.10683351457118988,
|
|
"num_tokens": 1230199.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.456813716888428,
|
|
"epoch": 0.05338078291814947,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.1109,
|
|
"mean_token_accuracy": 0.09833906963467598,
|
|
"num_tokens": 1242127.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.489393091201782,
|
|
"epoch": 0.05387504942665085,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.9608,
|
|
"mean_token_accuracy": 0.10372178331017494,
|
|
"num_tokens": 1252329.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.225747203826904,
|
|
"epoch": 0.054369315935152235,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9648,
|
|
"mean_token_accuracy": 0.10731954500079155,
|
|
"num_tokens": 1264832.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.370330858230591,
|
|
"epoch": 0.054863582443653615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.041,
|
|
"mean_token_accuracy": 0.10336996018886566,
|
|
"num_tokens": 1276708.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.453816318511963,
|
|
"epoch": 0.055357848952155,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.9314,
|
|
"mean_token_accuracy": 0.11433103457093238,
|
|
"num_tokens": 1288089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.364833116531372,
|
|
"epoch": 0.05585211546065639,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0866,
|
|
"mean_token_accuracy": 0.09704122841358184,
|
|
"num_tokens": 1299411.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.38861722946167,
|
|
"epoch": 0.05634638196915777,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.0718,
|
|
"mean_token_accuracy": 0.09769185036420822,
|
|
"num_tokens": 1311368.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.383206033706665,
|
|
"epoch": 0.056840648477659156,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9885,
|
|
"mean_token_accuracy": 0.10403251945972443,
|
|
"num_tokens": 1321962.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.367150115966797,
|
|
"epoch": 0.057334914986160536,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.9718,
|
|
"mean_token_accuracy": 0.10916787758469582,
|
|
"num_tokens": 1335150.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.376563596725464,
|
|
"epoch": 0.05782918149466192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.0122,
|
|
"mean_token_accuracy": 0.10337089449167251,
|
|
"num_tokens": 1346986.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.361315155029297,
|
|
"epoch": 0.0583234480031633,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.951,
|
|
"mean_token_accuracy": 0.10719594955444336,
|
|
"num_tokens": 1357820.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.284826040267944,
|
|
"epoch": 0.05881771451166469,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.11087205111980439,
|
|
"num_tokens": 1368269.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.249915885925293,
|
|
"epoch": 0.05931198102016608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9547,
|
|
"mean_token_accuracy": 0.10180922672152519,
|
|
"num_tokens": 1380364.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.395902109146118,
|
|
"epoch": 0.05980624752866746,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.9082,
|
|
"mean_token_accuracy": 0.11050013303756714,
|
|
"num_tokens": 1390667.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.20961561203003,
|
|
"epoch": 0.060300514037168844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8605,
|
|
"mean_token_accuracy": 0.10693677067756653,
|
|
"num_tokens": 1401452.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.270598030090332,
|
|
"epoch": 0.060794780545670224,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.8652,
|
|
"mean_token_accuracy": 0.10748695507645607,
|
|
"num_tokens": 1412947.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.267968559265137,
|
|
"epoch": 0.06128904705417161,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.923,
|
|
"mean_token_accuracy": 0.10039002001285553,
|
|
"num_tokens": 1425123.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.293630933761596,
|
|
"epoch": 0.06178331356267299,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.8859,
|
|
"mean_token_accuracy": 0.10513018518686294,
|
|
"num_tokens": 1436538.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.242138385772705,
|
|
"epoch": 0.06227758007117438,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.9292,
|
|
"mean_token_accuracy": 0.1024887353181839,
|
|
"num_tokens": 1448269.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.26104211807251,
|
|
"epoch": 0.06277184657967576,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.904,
|
|
"mean_token_accuracy": 0.11182300597429276,
|
|
"num_tokens": 1459729.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.269317722320556,
|
|
"epoch": 0.06326611308817714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.9178,
|
|
"mean_token_accuracy": 0.10927679911255836,
|
|
"num_tokens": 1470684.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.160611963272094,
|
|
"epoch": 0.06376037959667853,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.8722,
|
|
"mean_token_accuracy": 0.10590490102767944,
|
|
"num_tokens": 1483571.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.248231744766235,
|
|
"epoch": 0.06425464610517992,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.8625,
|
|
"mean_token_accuracy": 0.113711516559124,
|
|
"num_tokens": 1494671.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.255923461914063,
|
|
"epoch": 0.06474891261368129,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8742,
|
|
"mean_token_accuracy": 0.10942275002598763,
|
|
"num_tokens": 1505435.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.311585712432861,
|
|
"epoch": 0.06524317912218268,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.9542,
|
|
"mean_token_accuracy": 0.10462261438369751,
|
|
"num_tokens": 1518510.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.2363609790802,
|
|
"epoch": 0.06573744563068407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.11201808229088783,
|
|
"num_tokens": 1530218.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.211708068847656,
|
|
"epoch": 0.06623171213918545,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.9092,
|
|
"mean_token_accuracy": 0.10970637276768684,
|
|
"num_tokens": 1542486.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.21020245552063,
|
|
"epoch": 0.06672597864768683,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.9146,
|
|
"mean_token_accuracy": 0.10766631141304969,
|
|
"num_tokens": 1553873.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.245796585083008,
|
|
"epoch": 0.06722024515618821,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8705,
|
|
"mean_token_accuracy": 0.11166855990886689,
|
|
"num_tokens": 1565343.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.190037250518799,
|
|
"epoch": 0.0677145116646896,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.9103,
|
|
"mean_token_accuracy": 0.10737355202436447,
|
|
"num_tokens": 1577061.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.27009220123291,
|
|
"epoch": 0.06820877817319099,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.9156,
|
|
"mean_token_accuracy": 0.10903515294194221,
|
|
"num_tokens": 1588083.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.203428411483765,
|
|
"epoch": 0.06870304468169237,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.856,
|
|
"mean_token_accuracy": 0.10634591579437255,
|
|
"num_tokens": 1599796.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.246427440643311,
|
|
"epoch": 0.06919731119019375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.9223,
|
|
"mean_token_accuracy": 0.10735742151737213,
|
|
"num_tokens": 1611994.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.121251058578491,
|
|
"epoch": 0.06969157769869513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.8412,
|
|
"mean_token_accuracy": 0.10536888688802719,
|
|
"num_tokens": 1623280.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.183412694931031,
|
|
"epoch": 0.07018584420719652,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.9013,
|
|
"mean_token_accuracy": 0.10780779123306275,
|
|
"num_tokens": 1634989.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.263358879089355,
|
|
"epoch": 0.07068011071569791,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.9441,
|
|
"mean_token_accuracy": 0.10218141227960587,
|
|
"num_tokens": 1647042.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.1384925365448,
|
|
"epoch": 0.0711743772241993,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.8193,
|
|
"mean_token_accuracy": 0.11825829073786735,
|
|
"num_tokens": 1659245.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.110760354995728,
|
|
"epoch": 0.07166864373270067,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.1118646964430809,
|
|
"num_tokens": 1670271.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.166925048828125,
|
|
"epoch": 0.07216291024120206,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8701,
|
|
"mean_token_accuracy": 0.10942979305982589,
|
|
"num_tokens": 1682648.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.17819299697876,
|
|
"epoch": 0.07265717674970344,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.8884,
|
|
"mean_token_accuracy": 0.10658517628908157,
|
|
"num_tokens": 1694542.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.1897674083709715,
|
|
"epoch": 0.07315144325820483,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.7792,
|
|
"mean_token_accuracy": 0.1051691822707653,
|
|
"num_tokens": 1705737.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.1092109203338625,
|
|
"epoch": 0.0736457097667062,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.10925951823592187,
|
|
"num_tokens": 1718474.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.171104812622071,
|
|
"epoch": 0.07413997627520759,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.1083482749760151,
|
|
"num_tokens": 1729360.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.082499885559082,
|
|
"epoch": 0.07463424278370898,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.8145,
|
|
"mean_token_accuracy": 0.1140282928943634,
|
|
"num_tokens": 1739654.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.164748859405518,
|
|
"epoch": 0.07512850929221036,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.8316,
|
|
"mean_token_accuracy": 0.1102795235812664,
|
|
"num_tokens": 1752158.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.129274892807007,
|
|
"epoch": 0.07562277580071175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.804,
|
|
"mean_token_accuracy": 0.11611431241035461,
|
|
"num_tokens": 1764545.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.115315723419189,
|
|
"epoch": 0.07611704230921312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.8045,
|
|
"mean_token_accuracy": 0.1117110326886177,
|
|
"num_tokens": 1775422.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.086942100524903,
|
|
"epoch": 0.07661130881771451,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.8269,
|
|
"mean_token_accuracy": 0.10424647778272629,
|
|
"num_tokens": 1787833.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.1043376445770265,
|
|
"epoch": 0.0771055753262159,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6876,
|
|
"mean_token_accuracy": 0.12525334507226943,
|
|
"num_tokens": 1798508.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.1196941375732425,
|
|
"epoch": 0.07759984183471728,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7504,
|
|
"mean_token_accuracy": 0.11390295699238777,
|
|
"num_tokens": 1809873.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.046653699874878,
|
|
"epoch": 0.07809410834321866,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.10968291312456131,
|
|
"num_tokens": 1820876.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.074091911315918,
|
|
"epoch": 0.07858837485172004,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.7882,
|
|
"mean_token_accuracy": 0.10766826942563057,
|
|
"num_tokens": 1833233.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.204562473297119,
|
|
"epoch": 0.07908264136022143,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.8631,
|
|
"mean_token_accuracy": 0.1043733924627304,
|
|
"num_tokens": 1844520.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.992415571212769,
|
|
"epoch": 0.07957690786872282,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7529,
|
|
"mean_token_accuracy": 0.11640457883477211,
|
|
"num_tokens": 1856814.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.083125209808349,
|
|
"epoch": 0.0800711743772242,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7458,
|
|
"mean_token_accuracy": 0.11934995800256729,
|
|
"num_tokens": 1867581.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.114955091476441,
|
|
"epoch": 0.08056544088572558,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.793,
|
|
"mean_token_accuracy": 0.10545687675476074,
|
|
"num_tokens": 1879302.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.047843027114868,
|
|
"epoch": 0.08105970739422697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.7703,
|
|
"mean_token_accuracy": 0.10801751762628556,
|
|
"num_tokens": 1891697.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.011522197723389,
|
|
"epoch": 0.08155397390272835,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6972,
|
|
"mean_token_accuracy": 0.113658956438303,
|
|
"num_tokens": 1903544.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.099178838729858,
|
|
"epoch": 0.08204824041122974,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.7716,
|
|
"mean_token_accuracy": 0.11163810566067696,
|
|
"num_tokens": 1915286.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.956659364700317,
|
|
"epoch": 0.08254250691973111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.6435,
|
|
"mean_token_accuracy": 0.1189879409968853,
|
|
"num_tokens": 1926361.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.089762735366821,
|
|
"epoch": 0.0830367734282325,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.7388,
|
|
"mean_token_accuracy": 0.11271768435835838,
|
|
"num_tokens": 1938540.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.055161714553833,
|
|
"epoch": 0.08353103993673389,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7549,
|
|
"mean_token_accuracy": 0.11166792660951615,
|
|
"num_tokens": 1950532.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.115563917160034,
|
|
"epoch": 0.08402530644523527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.7771,
|
|
"mean_token_accuracy": 0.11082297042012215,
|
|
"num_tokens": 1960899.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.951827669143677,
|
|
"epoch": 0.08451957295373666,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.7352,
|
|
"mean_token_accuracy": 0.11721526905894279,
|
|
"num_tokens": 1972278.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.075967121124267,
|
|
"epoch": 0.08501383946223803,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.753,
|
|
"mean_token_accuracy": 0.11036830991506577,
|
|
"num_tokens": 1985079.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.958264875411987,
|
|
"epoch": 0.08550810597073942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7833,
|
|
"mean_token_accuracy": 0.10577104613184929,
|
|
"num_tokens": 1996467.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.0288783550262455,
|
|
"epoch": 0.08600237247924081,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6732,
|
|
"mean_token_accuracy": 0.11622288599610328,
|
|
"num_tokens": 2007339.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.031373453140259,
|
|
"epoch": 0.0864966389877422,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.6974,
|
|
"mean_token_accuracy": 0.11922055259346961,
|
|
"num_tokens": 2019962.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.015153598785401,
|
|
"epoch": 0.08699090549624358,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.6811,
|
|
"mean_token_accuracy": 0.1218427762389183,
|
|
"num_tokens": 2031251.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.9253716468811035,
|
|
"epoch": 0.08748517200474495,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6908,
|
|
"mean_token_accuracy": 0.11059122309088706,
|
|
"num_tokens": 2042412.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.9423582553863525,
|
|
"epoch": 0.08797943851324634,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.7154,
|
|
"mean_token_accuracy": 0.11710638850927353,
|
|
"num_tokens": 2054423.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.971608352661133,
|
|
"epoch": 0.08847370502174773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6994,
|
|
"mean_token_accuracy": 0.11089581474661828,
|
|
"num_tokens": 2065657.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.033730363845825,
|
|
"epoch": 0.08896797153024912,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.6673,
|
|
"mean_token_accuracy": 0.11892515495419502,
|
|
"num_tokens": 2076305.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.9093526840209964,
|
|
"epoch": 0.08946223803875049,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6538,
|
|
"mean_token_accuracy": 0.11571658477187156,
|
|
"num_tokens": 2087734.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.8397496223449705,
|
|
"epoch": 0.08995650454725188,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.12399489283561707,
|
|
"num_tokens": 2098016.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.953526353836059,
|
|
"epoch": 0.09045077105575326,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7456,
|
|
"mean_token_accuracy": 0.11191561967134475,
|
|
"num_tokens": 2110293.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.92013955116272,
|
|
"epoch": 0.09094503756425465,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.12161664664745331,
|
|
"num_tokens": 2120441.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.89482569694519,
|
|
"epoch": 0.09143930407275604,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.6421,
|
|
"mean_token_accuracy": 0.12238077148795128,
|
|
"num_tokens": 2131520.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.9351709365844725,
|
|
"epoch": 0.09193357058125741,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.6623,
|
|
"mean_token_accuracy": 0.11628105267882347,
|
|
"num_tokens": 2145005.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.952813577651978,
|
|
"epoch": 0.0924278370897588,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.6147,
|
|
"mean_token_accuracy": 0.12266910672187806,
|
|
"num_tokens": 2156608.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.844784832000732,
|
|
"epoch": 0.09292210359826018,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6121,
|
|
"mean_token_accuracy": 0.12510473579168319,
|
|
"num_tokens": 2168341.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.867721843719482,
|
|
"epoch": 0.09341637010676157,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.11190108060836793,
|
|
"num_tokens": 2178704.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.011946821212769,
|
|
"epoch": 0.09391063661526294,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.7787,
|
|
"mean_token_accuracy": 0.1083400510251522,
|
|
"num_tokens": 2190884.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.949655151367187,
|
|
"epoch": 0.09440490312376433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6793,
|
|
"mean_token_accuracy": 0.11808931306004525,
|
|
"num_tokens": 2201822.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.885033130645752,
|
|
"epoch": 0.09489916963226572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.1151963710784912,
|
|
"num_tokens": 2213362.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.988611841201783,
|
|
"epoch": 0.0953934361407671,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6834,
|
|
"mean_token_accuracy": 0.11506200209259987,
|
|
"num_tokens": 2224366.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.796273279190063,
|
|
"epoch": 0.09588770264926849,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.5308,
|
|
"mean_token_accuracy": 0.11869918927550316,
|
|
"num_tokens": 2234645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.887414264678955,
|
|
"epoch": 0.09638196915776986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.12557216882705688,
|
|
"num_tokens": 2245904.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.760451459884644,
|
|
"epoch": 0.09687623566627125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.5608,
|
|
"mean_token_accuracy": 0.11967702507972718,
|
|
"num_tokens": 2257753.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.836030530929565,
|
|
"epoch": 0.09737050217477264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5764,
|
|
"mean_token_accuracy": 0.1251159615814686,
|
|
"num_tokens": 2269009.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.922193813323974,
|
|
"epoch": 0.09786476868327403,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.11580619663000107,
|
|
"num_tokens": 2279840.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.835604095458985,
|
|
"epoch": 0.0983590351917754,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.11514367312192916,
|
|
"num_tokens": 2290577.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.809481859207153,
|
|
"epoch": 0.09885330170027679,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.12064301818609238,
|
|
"num_tokens": 2301341.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.813262176513672,
|
|
"epoch": 0.09934756820877817,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999999982287888,
|
|
"loss": 6.6368,
|
|
"mean_token_accuracy": 0.11775564104318618,
|
|
"num_tokens": 2312505.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.9637086391448975,
|
|
"epoch": 0.09984183471727956,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999910332434,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.11561667025089264,
|
|
"num_tokens": 2323443.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.791029787063598,
|
|
"epoch": 0.10033610122578095,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999783026635,
|
|
"loss": 6.5993,
|
|
"mean_token_accuracy": 0.11769351288676262,
|
|
"num_tokens": 2335686.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.783609867095947,
|
|
"epoch": 0.10083036773428232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999999600370491,
|
|
"loss": 6.5922,
|
|
"mean_token_accuracy": 0.11608155444264412,
|
|
"num_tokens": 2347273.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.764084768295288,
|
|
"epoch": 0.1013246342427837,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999362364008,
|
|
"loss": 6.5001,
|
|
"mean_token_accuracy": 0.13010589852929116,
|
|
"num_tokens": 2358011.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.786945724487305,
|
|
"epoch": 0.1018189007512851,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999069007191,
|
|
"loss": 6.6375,
|
|
"mean_token_accuracy": 0.1150654211640358,
|
|
"num_tokens": 2371390.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.861456680297851,
|
|
"epoch": 0.10231316725978648,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998720300048,
|
|
"loss": 6.5951,
|
|
"mean_token_accuracy": 0.12022169157862664,
|
|
"num_tokens": 2381887.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.88414945602417,
|
|
"epoch": 0.10280743376828787,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999998316242589,
|
|
"loss": 6.535,
|
|
"mean_token_accuracy": 0.12180361151695251,
|
|
"num_tokens": 2393632.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.735341882705688,
|
|
"epoch": 0.10330170027678924,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997856834821,
|
|
"loss": 6.5544,
|
|
"mean_token_accuracy": 0.12011176198720933,
|
|
"num_tokens": 2405686.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.720200252532959,
|
|
"epoch": 0.10379596678529063,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999997342076757,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.11903640404343604,
|
|
"num_tokens": 2417459.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.890789365768432,
|
|
"epoch": 0.10429023329379201,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999996771968408,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.11979348957538605,
|
|
"num_tokens": 2428689.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.733220434188842,
|
|
"epoch": 0.1047844998022934,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999996146509791,
|
|
"loss": 6.5962,
|
|
"mean_token_accuracy": 0.11043051034212112,
|
|
"num_tokens": 2439437.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.875022935867309,
|
|
"epoch": 0.10527876631079477,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999995465700919,
|
|
"loss": 6.5727,
|
|
"mean_token_accuracy": 0.11816314235329628,
|
|
"num_tokens": 2450576.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.892560863494873,
|
|
"epoch": 0.10577303281929616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999994729541809,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.11508011296391488,
|
|
"num_tokens": 2462684.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.847589826583862,
|
|
"epoch": 0.10626729932779755,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999993938032481,
|
|
"loss": 6.5992,
|
|
"mean_token_accuracy": 0.12335227355360985,
|
|
"num_tokens": 2474193.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.71039776802063,
|
|
"epoch": 0.10676156583629894,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999993091172952,
|
|
"loss": 6.5155,
|
|
"mean_token_accuracy": 0.118268733471632,
|
|
"num_tokens": 2486264.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.779750728607178,
|
|
"epoch": 0.10725583234480032,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999992188963245,
|
|
"loss": 6.5201,
|
|
"mean_token_accuracy": 0.12872469574213027,
|
|
"num_tokens": 2497668.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.727497005462647,
|
|
"epoch": 0.1077500988533017,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499999123140338,
|
|
"loss": 6.5714,
|
|
"mean_token_accuracy": 0.11793504282832146,
|
|
"num_tokens": 2509635.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.829061508178711,
|
|
"epoch": 0.10824436536180308,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999990218493382,
|
|
"loss": 6.5694,
|
|
"mean_token_accuracy": 0.11895573884248734,
|
|
"num_tokens": 2521980.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.751840114593506,
|
|
"epoch": 0.10873863187030447,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999989150233276,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.12123857289552689,
|
|
"num_tokens": 2533750.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.78528938293457,
|
|
"epoch": 0.10923289837880586,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999988026623088,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.11473045870661736,
|
|
"num_tokens": 2545620.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.696118307113648,
|
|
"epoch": 0.10972716488730723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999986847662843,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.1327408328652382,
|
|
"num_tokens": 2556463.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.784327554702759,
|
|
"epoch": 0.11022143139580862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999985613352576,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.11819555461406708,
|
|
"num_tokens": 2567396.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.7881745338439945,
|
|
"epoch": 0.11071569790431,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999984323692311,
|
|
"loss": 6.5291,
|
|
"mean_token_accuracy": 0.12449823319911957,
|
|
"num_tokens": 2579208.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.713969278335571,
|
|
"epoch": 0.11120996441281139,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999982978682085,
|
|
"loss": 6.4819,
|
|
"mean_token_accuracy": 0.12787408530712127,
|
|
"num_tokens": 2590940.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.781643867492676,
|
|
"epoch": 0.11170423092131278,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999981578321927,
|
|
"loss": 6.5599,
|
|
"mean_token_accuracy": 0.12885867655277253,
|
|
"num_tokens": 2602491.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.6775916576385494,
|
|
"epoch": 0.11219849742981415,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999980122611874,
|
|
"loss": 6.3952,
|
|
"mean_token_accuracy": 0.13354044929146766,
|
|
"num_tokens": 2612139.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.752026987075806,
|
|
"epoch": 0.11269276393831554,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499997861155196,
|
|
"loss": 6.5509,
|
|
"mean_token_accuracy": 0.12556230872869492,
|
|
"num_tokens": 2624906.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.673003530502319,
|
|
"epoch": 0.11318703044681692,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999977045142223,
|
|
"loss": 6.4808,
|
|
"mean_token_accuracy": 0.1187933087348938,
|
|
"num_tokens": 2636046.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.753292274475098,
|
|
"epoch": 0.11368129695531831,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999975423382703,
|
|
"loss": 6.4753,
|
|
"mean_token_accuracy": 0.12741708233952523,
|
|
"num_tokens": 2645617.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.790705585479737,
|
|
"epoch": 0.11417556346381968,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973746273438,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.122653928399086,
|
|
"num_tokens": 2656780.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.733772039413452,
|
|
"epoch": 0.11466982997232107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997201381447,
|
|
"loss": 6.5012,
|
|
"mean_token_accuracy": 0.12425200417637824,
|
|
"num_tokens": 2668078.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.741680097579956,
|
|
"epoch": 0.11516409648082246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999970226005841,
|
|
"loss": 6.5639,
|
|
"mean_token_accuracy": 0.11674718782305718,
|
|
"num_tokens": 2679049.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.803271245956421,
|
|
"epoch": 0.11565836298932385,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999968382847595,
|
|
"loss": 6.5366,
|
|
"mean_token_accuracy": 0.12377994433045388,
|
|
"num_tokens": 2690165.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.783146047592163,
|
|
"epoch": 0.11615262949782523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966484339778,
|
|
"loss": 6.5556,
|
|
"mean_token_accuracy": 0.12106125354766846,
|
|
"num_tokens": 2701965.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.6661967754364015,
|
|
"epoch": 0.1166468960063266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999964530482437,
|
|
"loss": 6.4637,
|
|
"mean_token_accuracy": 0.12662513479590415,
|
|
"num_tokens": 2713479.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.716840696334839,
|
|
"epoch": 0.11714116251482799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999962521275619,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.1229412630200386,
|
|
"num_tokens": 2725629.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.520010709762573,
|
|
"epoch": 0.11763542902332938,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999960456719374,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.12263003587722779,
|
|
"num_tokens": 2736620.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.698487615585327,
|
|
"epoch": 0.11812969553183077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999958336813753,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.13159746527671815,
|
|
"num_tokens": 2747118.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.5850576877594,
|
|
"epoch": 0.11862396204033215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999956161558807,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.12530086562037468,
|
|
"num_tokens": 2758371.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.637788963317871,
|
|
"epoch": 0.11911822854883353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999953930954591,
|
|
"loss": 6.4311,
|
|
"mean_token_accuracy": 0.12403330877423287,
|
|
"num_tokens": 2770575.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.686907768249512,
|
|
"epoch": 0.11961249505733491,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999951645001159,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12846756651997565,
|
|
"num_tokens": 2783103.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.6527008533477785,
|
|
"epoch": 0.1201067615658363,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999949303698568,
|
|
"loss": 6.516,
|
|
"mean_token_accuracy": 0.12293659523129463,
|
|
"num_tokens": 2796636.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.695577192306518,
|
|
"epoch": 0.12060102807433769,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999946907046875,
|
|
"loss": 6.3694,
|
|
"mean_token_accuracy": 0.13485616445541382,
|
|
"num_tokens": 2807798.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.6003742694854735,
|
|
"epoch": 0.12109529458283906,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999944455046139,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.12794808968901633,
|
|
"num_tokens": 2819255.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.676394367218018,
|
|
"epoch": 0.12158956109134045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499994194769642,
|
|
"loss": 6.4363,
|
|
"mean_token_accuracy": 0.12319996431469918,
|
|
"num_tokens": 2829952.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.776423740386963,
|
|
"epoch": 0.12208382759984183,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499993938499778,
|
|
"loss": 6.5218,
|
|
"mean_token_accuracy": 0.1313498340547085,
|
|
"num_tokens": 2841056.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.614255428314209,
|
|
"epoch": 0.12257809410834322,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999936766950283,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.13403896167874335,
|
|
"num_tokens": 2852045.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.6999880313873295,
|
|
"epoch": 0.12307236061684461,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999934093553992,
|
|
"loss": 6.4759,
|
|
"mean_token_accuracy": 0.1261597417294979,
|
|
"num_tokens": 2863440.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.664808034896851,
|
|
"epoch": 0.12356662712534598,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999931364808972,
|
|
"loss": 6.4951,
|
|
"mean_token_accuracy": 0.12566187903285025,
|
|
"num_tokens": 2874017.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.6710155487060545,
|
|
"epoch": 0.12406089363384737,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999928580715293,
|
|
"loss": 6.4019,
|
|
"mean_token_accuracy": 0.1276327282190323,
|
|
"num_tokens": 2885677.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.632281970977783,
|
|
"epoch": 0.12455516014234876,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499992574127302,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.12587906420230865,
|
|
"num_tokens": 2897825.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.72322564125061,
|
|
"epoch": 0.12504942665085014,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999922846482226,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.11891639679670334,
|
|
"num_tokens": 2909304.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.680528593063355,
|
|
"epoch": 0.12554369315935152,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999919896342981,
|
|
"loss": 6.494,
|
|
"mean_token_accuracy": 0.11919789239764214,
|
|
"num_tokens": 2920918.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.711538314819336,
|
|
"epoch": 0.12603795966785292,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999916890855358,
|
|
"loss": 6.4429,
|
|
"mean_token_accuracy": 0.12809634804725648,
|
|
"num_tokens": 2932294.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.614521741867065,
|
|
"epoch": 0.1265322261763543,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999913830019431,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.13480542078614235,
|
|
"num_tokens": 2943372.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.5310547828674315,
|
|
"epoch": 0.12702649268485566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999910713835272,
|
|
"loss": 6.3364,
|
|
"mean_token_accuracy": 0.12778233140707015,
|
|
"num_tokens": 2953807.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.607894229888916,
|
|
"epoch": 0.12752075919335706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999907542302962,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.13762608990073205,
|
|
"num_tokens": 2964372.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.600684118270874,
|
|
"epoch": 0.12801502570185844,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999904315422577,
|
|
"loss": 6.3847,
|
|
"mean_token_accuracy": 0.13021055534482,
|
|
"num_tokens": 2975537.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.563079786300659,
|
|
"epoch": 0.12850929221035984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999901033194198,
|
|
"loss": 6.3563,
|
|
"mean_token_accuracy": 0.12701485753059388,
|
|
"num_tokens": 2986094.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.685067892074585,
|
|
"epoch": 0.1290035587188612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999897695617904,
|
|
"loss": 6.4705,
|
|
"mean_token_accuracy": 0.12639627903699874,
|
|
"num_tokens": 2996023.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.640681552886963,
|
|
"epoch": 0.12949782522736258,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999894302693778,
|
|
"loss": 6.4669,
|
|
"mean_token_accuracy": 0.12245377749204636,
|
|
"num_tokens": 3007584.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.764276647567749,
|
|
"epoch": 0.12999209173586398,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999890854421902,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.12133662179112434,
|
|
"num_tokens": 3018995.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.470447969436646,
|
|
"epoch": 0.13048635824436536,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999887350802362,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.13123086243867874,
|
|
"num_tokens": 3030576.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.557611608505249,
|
|
"epoch": 0.13098062475286676,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999883791835246,
|
|
"loss": 6.3631,
|
|
"mean_token_accuracy": 0.12982181310653687,
|
|
"num_tokens": 3040765.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.625185441970825,
|
|
"epoch": 0.13147489126136813,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999880177520637,
|
|
"loss": 6.4162,
|
|
"mean_token_accuracy": 0.12189083769917489,
|
|
"num_tokens": 3053912.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.515785074234008,
|
|
"epoch": 0.1319691577698695,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999876507858628,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.12720990628004075,
|
|
"num_tokens": 3065921.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.7070118427276615,
|
|
"epoch": 0.1324634242783709,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999872782849308,
|
|
"loss": 6.4407,
|
|
"mean_token_accuracy": 0.1257806733250618,
|
|
"num_tokens": 3078643.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.503523445129394,
|
|
"epoch": 0.13295769078687228,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999869002492768,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.12997100427746772,
|
|
"num_tokens": 3090300.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.547778797149658,
|
|
"epoch": 0.13345195729537365,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999865166789102,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.13570954278111458,
|
|
"num_tokens": 3102307.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.671496915817261,
|
|
"epoch": 0.13394622380387505,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999861275738404,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.122230763733387,
|
|
"num_tokens": 3113817.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.534291315078735,
|
|
"epoch": 0.13444049031237643,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999857329340769,
|
|
"loss": 6.2984,
|
|
"mean_token_accuracy": 0.1316831812262535,
|
|
"num_tokens": 3124719.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.49489164352417,
|
|
"epoch": 0.13493475682087783,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999853327596295,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.12992627099156379,
|
|
"num_tokens": 3136136.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.607687616348267,
|
|
"epoch": 0.1354290233293792,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499984927050508,
|
|
"loss": 6.3386,
|
|
"mean_token_accuracy": 0.13101759776473046,
|
|
"num_tokens": 3148977.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.594228982925415,
|
|
"epoch": 0.13592328983788057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999845158067223,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.12740953639149666,
|
|
"num_tokens": 3160520.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.579832983016968,
|
|
"epoch": 0.13641755634638197,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999840990282828,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1273616522550583,
|
|
"num_tokens": 3172895.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.562347316741944,
|
|
"epoch": 0.13691182285488335,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999836767151994,
|
|
"loss": 6.3811,
|
|
"mean_token_accuracy": 0.1285211369395256,
|
|
"num_tokens": 3183960.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.513716793060302,
|
|
"epoch": 0.13740608936338475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999832488674827,
|
|
"loss": 6.4157,
|
|
"mean_token_accuracy": 0.12590486258268357,
|
|
"num_tokens": 3194276.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.599906539916992,
|
|
"epoch": 0.13790035587188612,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999828154851432,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.1359431803226471,
|
|
"num_tokens": 3206084.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.534882593154907,
|
|
"epoch": 0.1383946223803875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999823765681915,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.1354965254664421,
|
|
"num_tokens": 3217941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.533507204055786,
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999819321166385,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.13300728499889375,
|
|
"num_tokens": 3229088.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.476707124710083,
|
|
"epoch": 0.13938315539739027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499981482130495,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.13597408458590507,
|
|
"num_tokens": 3240708.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.52806544303894,
|
|
"epoch": 0.13987742190589167,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999810266097721,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.12898992374539375,
|
|
"num_tokens": 3251040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.505051183700561,
|
|
"epoch": 0.14037168841439304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999805655544811,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.13407422080636025,
|
|
"num_tokens": 3262655.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.514699459075928,
|
|
"epoch": 0.14086595492289442,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999800989646333,
|
|
"loss": 6.2762,
|
|
"mean_token_accuracy": 0.1369866333901882,
|
|
"num_tokens": 3273160.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.538471126556397,
|
|
"epoch": 0.14136022143139582,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999796268402401,
|
|
"loss": 6.3008,
|
|
"mean_token_accuracy": 0.129919171333313,
|
|
"num_tokens": 3285932.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.4485719203948975,
|
|
"epoch": 0.1418544879398972,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999791491813132,
|
|
"loss": 6.3325,
|
|
"mean_token_accuracy": 0.12975751757621765,
|
|
"num_tokens": 3298834.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.628458499908447,
|
|
"epoch": 0.1423487544483986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999786659878643,
|
|
"loss": 6.3121,
|
|
"mean_token_accuracy": 0.13101852536201478,
|
|
"num_tokens": 3310473.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.355752944946289,
|
|
"epoch": 0.14284302095689996,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999781772599055,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.1346455655992031,
|
|
"num_tokens": 3322662.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.666700553894043,
|
|
"epoch": 0.14333728746540134,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999776829974484,
|
|
"loss": 6.377,
|
|
"mean_token_accuracy": 0.13617630526423455,
|
|
"num_tokens": 3334321.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.4790514469146725,
|
|
"epoch": 0.14383155397390274,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999771832005055,
|
|
"loss": 6.2639,
|
|
"mean_token_accuracy": 0.12925363183021546,
|
|
"num_tokens": 3345130.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.453184318542481,
|
|
"epoch": 0.1443258204824041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499976677869089,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.13220407143235208,
|
|
"num_tokens": 3355601.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.477377080917359,
|
|
"epoch": 0.14482008699090548,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999761670032115,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.13375383466482163,
|
|
"num_tokens": 3367075.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.511325311660767,
|
|
"epoch": 0.14531435349940688,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999756506028851,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.13651637956500054,
|
|
"num_tokens": 3378888.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.501529884338379,
|
|
"epoch": 0.14580862000790826,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999751286681229,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.13225537091493605,
|
|
"num_tokens": 3390705.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.47571210861206,
|
|
"epoch": 0.14630288651640966,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999746011989376,
|
|
"loss": 6.2827,
|
|
"mean_token_accuracy": 0.1402031034231186,
|
|
"num_tokens": 3401710.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.556623744964599,
|
|
"epoch": 0.14679715302491103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999740681953422,
|
|
"loss": 6.3976,
|
|
"mean_token_accuracy": 0.1264283038675785,
|
|
"num_tokens": 3413467.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.510135364532471,
|
|
"epoch": 0.1472914195334124,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999735296573499,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.1363067075610161,
|
|
"num_tokens": 3425885.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.520489978790283,
|
|
"epoch": 0.1477856860419138,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999729855849738,
|
|
"loss": 6.3524,
|
|
"mean_token_accuracy": 0.1277867116034031,
|
|
"num_tokens": 3437952.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.465743494033814,
|
|
"epoch": 0.14827995255041518,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999724359782274,
|
|
"loss": 6.2184,
|
|
"mean_token_accuracy": 0.14817326366901398,
|
|
"num_tokens": 3449680.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.495955276489258,
|
|
"epoch": 0.14877421905891658,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999718808371241,
|
|
"loss": 6.3814,
|
|
"mean_token_accuracy": 0.1254202604293823,
|
|
"num_tokens": 3460699.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.596548366546631,
|
|
"epoch": 0.14926848556741795,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999713201616776,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.13369383811950683,
|
|
"num_tokens": 3471919.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.353741025924682,
|
|
"epoch": 0.14976275207591933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499970753951902,
|
|
"loss": 6.356,
|
|
"mean_token_accuracy": 0.12923398613929749,
|
|
"num_tokens": 3484110.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.576723194122314,
|
|
"epoch": 0.15025701858442073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999701822078107,
|
|
"loss": 6.265,
|
|
"mean_token_accuracy": 0.1321140117943287,
|
|
"num_tokens": 3496103.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.493707942962646,
|
|
"epoch": 0.1507512850929221,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499969604929418,
|
|
"loss": 6.3409,
|
|
"mean_token_accuracy": 0.13155030012130736,
|
|
"num_tokens": 3507291.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.532199859619141,
|
|
"epoch": 0.1512455516014235,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999690221167382,
|
|
"loss": 6.3266,
|
|
"mean_token_accuracy": 0.1285949692130089,
|
|
"num_tokens": 3519564.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.396489763259888,
|
|
"epoch": 0.15173981810992487,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999684337697855,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.14119874984025954,
|
|
"num_tokens": 3530679.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.489102125167847,
|
|
"epoch": 0.15223408461842625,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999678398885746,
|
|
"loss": 6.2593,
|
|
"mean_token_accuracy": 0.13449762463569642,
|
|
"num_tokens": 3542662.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.484030818939209,
|
|
"epoch": 0.15272835112692765,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999672404731197,
|
|
"loss": 6.3726,
|
|
"mean_token_accuracy": 0.12962616756558418,
|
|
"num_tokens": 3554760.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.430119800567627,
|
|
"epoch": 0.15322261763542902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499966635523436,
|
|
"loss": 6.184,
|
|
"mean_token_accuracy": 0.1408859372138977,
|
|
"num_tokens": 3565604.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.50899305343628,
|
|
"epoch": 0.1537168841439304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999660250395381,
|
|
"loss": 6.3469,
|
|
"mean_token_accuracy": 0.12966826558113098,
|
|
"num_tokens": 3577535.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.513133192062378,
|
|
"epoch": 0.1542111506524318,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499965409021441,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.12810506224632262,
|
|
"num_tokens": 3590458.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.503912401199341,
|
|
"epoch": 0.15470541716093317,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049996478746916,
|
|
"loss": 6.3018,
|
|
"mean_token_accuracy": 0.13346393704414367,
|
|
"num_tokens": 3600916.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.413891839981079,
|
|
"epoch": 0.15519968366943457,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999641603827104,
|
|
"loss": 6.3234,
|
|
"mean_token_accuracy": 0.13152189254760743,
|
|
"num_tokens": 3612794.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.491737747192383,
|
|
"epoch": 0.15569395017793594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999635277621073,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.1417726531624794,
|
|
"num_tokens": 3624186.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.421962738037109,
|
|
"epoch": 0.15618821668643731,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999628896073668,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.13585594519972802,
|
|
"num_tokens": 3636041.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.4938102722167965,
|
|
"epoch": 0.15668248319493872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999622459185042,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.1295533798635006,
|
|
"num_tokens": 3646859.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.432663345336914,
|
|
"epoch": 0.1571767497034401,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999615966955354,
|
|
"loss": 6.1457,
|
|
"mean_token_accuracy": 0.14173236414790152,
|
|
"num_tokens": 3657853.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.514078617095947,
|
|
"epoch": 0.1576710162119415,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999609419384764,
|
|
"loss": 6.2523,
|
|
"mean_token_accuracy": 0.1346098266541958,
|
|
"num_tokens": 3668341.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.446404361724854,
|
|
"epoch": 0.15816528272044286,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999602816473434,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.13876884281635285,
|
|
"num_tokens": 3679020.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.419503450393677,
|
|
"epoch": 0.15865954922894424,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999596158221526,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.14101243168115615,
|
|
"num_tokens": 3691121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.448402786254883,
|
|
"epoch": 0.15915381573744564,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999589444629203,
|
|
"loss": 6.2489,
|
|
"mean_token_accuracy": 0.13868038430809976,
|
|
"num_tokens": 3702584.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.412480592727661,
|
|
"epoch": 0.159648082245947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999582675696631,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.14014509692788124,
|
|
"num_tokens": 3713085.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.4948835372924805,
|
|
"epoch": 0.1601423487544484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999575851423976,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.1277170367538929,
|
|
"num_tokens": 3724318.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.488896036148072,
|
|
"epoch": 0.16063661526294978,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999568971811407,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.14014409109950066,
|
|
"num_tokens": 3734288.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.383061933517456,
|
|
"epoch": 0.16113088177145116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499956203685909,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.1334229089319706,
|
|
"num_tokens": 3744645.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.456633996963501,
|
|
"epoch": 0.16162514827995256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049995550465672,
|
|
"loss": 6.219,
|
|
"mean_token_accuracy": 0.1377868391573429,
|
|
"num_tokens": 3755660.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.372065544128418,
|
|
"epoch": 0.16211941478845393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999548000935906,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.1421402059495449,
|
|
"num_tokens": 3767614.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.441373538970947,
|
|
"epoch": 0.16261368129695533,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999540899965383,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.1364623002707958,
|
|
"num_tokens": 3780750.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.428185367584229,
|
|
"epoch": 0.1631079478054567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999533743655803,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.1284065067768097,
|
|
"num_tokens": 3793195.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.457364511489868,
|
|
"epoch": 0.16360221431395808,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999526532007346,
|
|
"loss": 6.2676,
|
|
"mean_token_accuracy": 0.13861094564199447,
|
|
"num_tokens": 3804256.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.42730746269226,
|
|
"epoch": 0.16409648082245948,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999519265020187,
|
|
"loss": 6.2388,
|
|
"mean_token_accuracy": 0.13844978511333467,
|
|
"num_tokens": 3815403.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.320225238800049,
|
|
"epoch": 0.16459074733096085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999511942694504,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14466449469327927,
|
|
"num_tokens": 3826682.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.43041729927063,
|
|
"epoch": 0.16508501383946222,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999504565030479,
|
|
"loss": 6.1678,
|
|
"mean_token_accuracy": 0.13993233293294907,
|
|
"num_tokens": 3837780.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.429787445068359,
|
|
"epoch": 0.16557928034796363,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999497132028293,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.1318391665816307,
|
|
"num_tokens": 3848782.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.428545904159546,
|
|
"epoch": 0.166073546856465,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999489643688127,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.13959652185440063,
|
|
"num_tokens": 3859220.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.30494270324707,
|
|
"epoch": 0.1665678133649664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999482100010169,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.1421866834163666,
|
|
"num_tokens": 3869794.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.35781421661377,
|
|
"epoch": 0.16706207987346777,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999474500994601,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.13421173691749572,
|
|
"num_tokens": 3881133.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.413172864913941,
|
|
"epoch": 0.16755634638196915,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999466846641611,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.13713917806744574,
|
|
"num_tokens": 3891600.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.333802795410156,
|
|
"epoch": 0.16805061289047055,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999459136951389,
|
|
"loss": 6.2631,
|
|
"mean_token_accuracy": 0.13335662260651587,
|
|
"num_tokens": 3903287.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.439137983322143,
|
|
"epoch": 0.16854487939897192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999451371924123,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.13854067176580429,
|
|
"num_tokens": 3914497.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.338579225540161,
|
|
"epoch": 0.16903914590747332,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999443551560003,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.13935932666063308,
|
|
"num_tokens": 3925536.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.43532075881958,
|
|
"epoch": 0.1695334124159747,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999435675859224,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.14295403137803078,
|
|
"num_tokens": 3936705.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.352819776535034,
|
|
"epoch": 0.17002767892447607,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999427744821977,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.1423388808965683,
|
|
"num_tokens": 3948422.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.321838235855102,
|
|
"epoch": 0.17052194543297747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499941975844846,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.14932032078504562,
|
|
"num_tokens": 3958697.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.3387940406799315,
|
|
"epoch": 0.17101621194147884,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999411716738866,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.13918534070253372,
|
|
"num_tokens": 3970255.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.376590156555176,
|
|
"epoch": 0.17151047844998024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999403619693397,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.1375705450773239,
|
|
"num_tokens": 3980892.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.290405988693237,
|
|
"epoch": 0.17200474495848161,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999395467312249,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.13679868206381798,
|
|
"num_tokens": 3991375.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.445168209075928,
|
|
"epoch": 0.172499011466983,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999387259595623,
|
|
"loss": 6.2982,
|
|
"mean_token_accuracy": 0.13123658969998359,
|
|
"num_tokens": 4003352.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.349807596206665,
|
|
"epoch": 0.1729932779754844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999378996543723,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.13942418098449708,
|
|
"num_tokens": 4014429.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.37531623840332,
|
|
"epoch": 0.17348754448398576,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999370678156749,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.1444903664290905,
|
|
"num_tokens": 4025213.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.307505178451538,
|
|
"epoch": 0.17398181099248716,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999362304434909,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.1425596944987774,
|
|
"num_tokens": 4036244.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.413739204406738,
|
|
"epoch": 0.17447607750098854,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999353875378406,
|
|
"loss": 6.1546,
|
|
"mean_token_accuracy": 0.1389375738799572,
|
|
"num_tokens": 4047944.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.28089075088501,
|
|
"epoch": 0.1749703440094899,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499934539098745,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.14509597718715667,
|
|
"num_tokens": 4058865.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.326784420013428,
|
|
"epoch": 0.1754646105179913,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999336851262247,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.13881123885512353,
|
|
"num_tokens": 4070627.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.431045770645142,
|
|
"epoch": 0.17595887702649268,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999328256203009,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.13756831139326095,
|
|
"num_tokens": 4081406.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.324437522888184,
|
|
"epoch": 0.17645314353499406,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999319605809947,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.12888796105980874,
|
|
"num_tokens": 4092957.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.411680078506469,
|
|
"epoch": 0.17694741004349546,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999310900083274,
|
|
"loss": 6.231,
|
|
"mean_token_accuracy": 0.1384389355778694,
|
|
"num_tokens": 4104381.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.3523437023162845,
|
|
"epoch": 0.17744167655199683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999302139023204,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.14232124909758567,
|
|
"num_tokens": 4117190.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.305995988845825,
|
|
"epoch": 0.17793594306049823,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999293322629951,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.14318788796663284,
|
|
"num_tokens": 4127870.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.298418235778809,
|
|
"epoch": 0.1784302095689996,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999284450903736,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.14193641096353532,
|
|
"num_tokens": 4139240.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.373674917221069,
|
|
"epoch": 0.17892447607750098,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999275523844772,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.14574467837810517,
|
|
"num_tokens": 4149885.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.44624924659729,
|
|
"epoch": 0.17941874258600238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999266541453283,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.13498160094022751,
|
|
"num_tokens": 4161824.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.335614776611328,
|
|
"epoch": 0.17991300909450375,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999257503729487,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.13315987810492516,
|
|
"num_tokens": 4173581.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.3903834342956545,
|
|
"epoch": 0.18040727560300515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999248410673607,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.14748075008392333,
|
|
"num_tokens": 4184843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.380693054199218,
|
|
"epoch": 0.18090154211150652,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999239262285869,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.1320282258093357,
|
|
"num_tokens": 4195016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.386849069595337,
|
|
"epoch": 0.1813958086200079,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999230058566495,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.14474730044603348,
|
|
"num_tokens": 4206798.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.370251035690307,
|
|
"epoch": 0.1818900751285093,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999220799515713,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.13890684843063356,
|
|
"num_tokens": 4218784.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.337589168548584,
|
|
"epoch": 0.18238434163701067,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499921148513375,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.13808465152978897,
|
|
"num_tokens": 4229875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.241511249542237,
|
|
"epoch": 0.18287860814551207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999202115420836,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.1402451813220978,
|
|
"num_tokens": 4241801.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.385967588424682,
|
|
"epoch": 0.18337287465401345,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999192690377201,
|
|
"loss": 6.1187,
|
|
"mean_token_accuracy": 0.1410462327301502,
|
|
"num_tokens": 4253168.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.331370687484741,
|
|
"epoch": 0.18386714116251482,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999183210003076,
|
|
"loss": 6.1497,
|
|
"mean_token_accuracy": 0.13985029086470604,
|
|
"num_tokens": 4264791.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.294579124450683,
|
|
"epoch": 0.18436140767101622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999173674298696,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.14586635753512384,
|
|
"num_tokens": 4275816.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.413454818725586,
|
|
"epoch": 0.1848556741795176,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999164083264294,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.13626813441514968,
|
|
"num_tokens": 4287806.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.289838790893555,
|
|
"epoch": 0.185349940688019,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999154436900108,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.14326421394944192,
|
|
"num_tokens": 4300319.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.346887874603271,
|
|
"epoch": 0.18584420719652037,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999144735206373,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.13601267710328102,
|
|
"num_tokens": 4310987.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.371985960006714,
|
|
"epoch": 0.18633847370502174,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999134978183328,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.14411325454711915,
|
|
"num_tokens": 4322438.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.385655212402344,
|
|
"epoch": 0.18683274021352314,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999125165831215,
|
|
"loss": 6.1898,
|
|
"mean_token_accuracy": 0.1465175122022629,
|
|
"num_tokens": 4333242.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.255407238006592,
|
|
"epoch": 0.1873270067220245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999115298150273,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.14152660295367242,
|
|
"num_tokens": 4343660.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.372375345230102,
|
|
"epoch": 0.1878212732305259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999105375140746,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.14555889666080474,
|
|
"num_tokens": 4353382.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.268469953536988,
|
|
"epoch": 0.1883155397390273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999095396802878,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.13386452049016953,
|
|
"num_tokens": 4364614.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.378190708160401,
|
|
"epoch": 0.18880980624752866,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999085363136913,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.13516660034656525,
|
|
"num_tokens": 4376001.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.323903131484985,
|
|
"epoch": 0.18930407275603006,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049990752741431,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.13419201746582984,
|
|
"num_tokens": 4387083.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.297012424468994,
|
|
"epoch": 0.18979833926453143,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999065129821687,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.141158889234066,
|
|
"num_tokens": 4399977.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.267847394943237,
|
|
"epoch": 0.1902926057730328,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999054930172923,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.14234692901372908,
|
|
"num_tokens": 4411609.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.402806425094605,
|
|
"epoch": 0.1907868722815342,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999044675197058,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.14248162806034087,
|
|
"num_tokens": 4423567.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.22545223236084,
|
|
"epoch": 0.19128113879003558,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999034364894345,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.1415740117430687,
|
|
"num_tokens": 4435410.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.422749614715576,
|
|
"epoch": 0.19177540529853698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999023999265039,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.13967961594462394,
|
|
"num_tokens": 4445279.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.232316732406616,
|
|
"epoch": 0.19226967180703836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999013578309392,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.14595175608992578,
|
|
"num_tokens": 4456017.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.297853326797485,
|
|
"epoch": 0.19276393831553973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999003102027663,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.15286524295806886,
|
|
"num_tokens": 4466759.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.268013620376587,
|
|
"epoch": 0.19325820482404113,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499899257042011,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.14023480713367462,
|
|
"num_tokens": 4478316.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.377132701873779,
|
|
"epoch": 0.1937524713325425,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998981983486988,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.13629069328308105,
|
|
"num_tokens": 4490775.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.301769161224366,
|
|
"epoch": 0.1942467378410439,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998971341228563,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.14630968272686004,
|
|
"num_tokens": 4501622.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.303157186508178,
|
|
"epoch": 0.19474100434954528,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998960643645093,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.1427514761686325,
|
|
"num_tokens": 4512279.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.305225229263305,
|
|
"epoch": 0.19523527085804665,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998949890736841,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.1444181725382805,
|
|
"num_tokens": 4524087.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.310341024398804,
|
|
"epoch": 0.19572953736654805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998939082504075,
|
|
"loss": 6.1019,
|
|
"mean_token_accuracy": 0.14459830969572068,
|
|
"num_tokens": 4534816.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.280261421203614,
|
|
"epoch": 0.19622380387504942,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998928218947057,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.1454021230340004,
|
|
"num_tokens": 4545725.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.377605772018432,
|
|
"epoch": 0.1967180703835508,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998917300066056,
|
|
"loss": 6.1899,
|
|
"mean_token_accuracy": 0.1378871500492096,
|
|
"num_tokens": 4557003.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.222435426712036,
|
|
"epoch": 0.1972123368920522,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998906325861342,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.14017595276236533,
|
|
"num_tokens": 4568768.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.241748237609864,
|
|
"epoch": 0.19770660340055357,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998895296333183,
|
|
"loss": 6.0654,
|
|
"mean_token_accuracy": 0.14961813986301423,
|
|
"num_tokens": 4581116.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.334244871139527,
|
|
"epoch": 0.19820086990905497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499888421148185,
|
|
"loss": 6.145,
|
|
"mean_token_accuracy": 0.14341819882392884,
|
|
"num_tokens": 4592660.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.315072679519654,
|
|
"epoch": 0.19869513641755635,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998873071307617,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.1400900736451149,
|
|
"num_tokens": 4603057.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.237052297592163,
|
|
"epoch": 0.19918940292605772,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998861875810758,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.15424127280712127,
|
|
"num_tokens": 4613546.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.281518363952637,
|
|
"epoch": 0.19968366943455912,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998850624991548,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.14481984600424766,
|
|
"num_tokens": 4624613.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.22469654083252,
|
|
"epoch": 0.2001779359430605,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998839318850263,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.14788607954978944,
|
|
"num_tokens": 4636004.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.255212354660034,
|
|
"epoch": 0.2006722024515619,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998827957387182,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.14652306362986564,
|
|
"num_tokens": 4646450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.283095216751098,
|
|
"epoch": 0.20116646896006327,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998816540602584,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.1446727216243744,
|
|
"num_tokens": 4658928.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.248164463043213,
|
|
"epoch": 0.20166073546856464,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998805068496752,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.14286085069179535,
|
|
"num_tokens": 4670392.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.35498571395874,
|
|
"epoch": 0.20215500197706604,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998793541069964,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.1423612579703331,
|
|
"num_tokens": 4680605.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.207654523849487,
|
|
"epoch": 0.2026492684855674,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998781958322507,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.14874968454241752,
|
|
"num_tokens": 4694250.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.302755451202392,
|
|
"epoch": 0.20314353499406881,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998770320254666,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.1457796052098274,
|
|
"num_tokens": 4705754.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.281993579864502,
|
|
"epoch": 0.2036378015025702,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998758626866725,
|
|
"loss": 6.0476,
|
|
"mean_token_accuracy": 0.1467272847890854,
|
|
"num_tokens": 4716393.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.196063613891601,
|
|
"epoch": 0.20413206801107156,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998746878158973,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.14491303488612176,
|
|
"num_tokens": 4726894.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.244138574600219,
|
|
"epoch": 0.20462633451957296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998735074131699,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.14195707365870475,
|
|
"num_tokens": 4737488.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.279796409606933,
|
|
"epoch": 0.20512060102807433,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998723214785194,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.1365630991756916,
|
|
"num_tokens": 4749131.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.2584418773651125,
|
|
"epoch": 0.20561486753657574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998711300119749,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.1438528060913086,
|
|
"num_tokens": 4760503.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.319554138183594,
|
|
"epoch": 0.2061091340450771,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998699330135656,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.14361703097820283,
|
|
"num_tokens": 4771965.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.23747992515564,
|
|
"epoch": 0.20660340055357848,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998687304833212,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.14026476591825485,
|
|
"num_tokens": 4784215.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.243879270553589,
|
|
"epoch": 0.20709766706207988,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499867522421271,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.1493344783782959,
|
|
"num_tokens": 4796410.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.184952163696289,
|
|
"epoch": 0.20759193357058126,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499866308827445,
|
|
"loss": 6.0151,
|
|
"mean_token_accuracy": 0.15359587073326111,
|
|
"num_tokens": 4806990.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.302822113037109,
|
|
"epoch": 0.20808620007908263,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998650897018729,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.1439187079668045,
|
|
"num_tokens": 4818903.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.244305086135864,
|
|
"epoch": 0.20858046658758403,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998638650445847,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1505424477159977,
|
|
"num_tokens": 4829130.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.217615032196045,
|
|
"epoch": 0.2090747330960854,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998626348556105,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.15414684265851974,
|
|
"num_tokens": 4840424.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.263989543914795,
|
|
"epoch": 0.2095689996045868,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998613991349807,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.14594117775559426,
|
|
"num_tokens": 4851674.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.096542119979858,
|
|
"epoch": 0.21006326611308818,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998601578827255,
|
|
"loss": 5.9601,
|
|
"mean_token_accuracy": 0.15645498782396317,
|
|
"num_tokens": 4863884.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.19989767074585,
|
|
"epoch": 0.21055753262158955,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998589110988755,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.15132073909044266,
|
|
"num_tokens": 4875582.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.274530458450317,
|
|
"epoch": 0.21105179913009095,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998576587834614,
|
|
"loss": 6.0528,
|
|
"mean_token_accuracy": 0.14546677693724633,
|
|
"num_tokens": 4888325.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.172981452941895,
|
|
"epoch": 0.21154606563859232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499856400936514,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.14551248848438264,
|
|
"num_tokens": 4899631.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.245505332946777,
|
|
"epoch": 0.21204033214709372,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998551375580643,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.14277451261878013,
|
|
"num_tokens": 4910954.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.237064695358276,
|
|
"epoch": 0.2125345986555951,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998538686481435,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.14683079421520234,
|
|
"num_tokens": 4921952.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.203374338150025,
|
|
"epoch": 0.21302886516409647,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998525942067824,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.15139593183994293,
|
|
"num_tokens": 4933984.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.283549213409424,
|
|
"epoch": 0.21352313167259787,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998513142340128,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.14827414751052856,
|
|
"num_tokens": 4945926.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.204256439208985,
|
|
"epoch": 0.21401739818109924,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998500287298657,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.15452619791030883,
|
|
"num_tokens": 4958123.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.319782829284668,
|
|
"epoch": 0.21451166468960065,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998487376943733,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.1432581551373005,
|
|
"num_tokens": 4970409.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.231132888793946,
|
|
"epoch": 0.21500593119810202,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499847441127567,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.1420576423406601,
|
|
"num_tokens": 4980429.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.213157796859742,
|
|
"epoch": 0.2155001977066034,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998461390294787,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.14993677660822868,
|
|
"num_tokens": 4991790.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.261713266372681,
|
|
"epoch": 0.2159944642151048,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998448314001405,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.1435249201953411,
|
|
"num_tokens": 5003611.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.302479600906372,
|
|
"epoch": 0.21648873072360617,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998435182395845,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.13771253526210786,
|
|
"num_tokens": 5014824.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.258434915542603,
|
|
"epoch": 0.21698299723210757,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998421995478432,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.14596307873725892,
|
|
"num_tokens": 5026937.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.298146438598633,
|
|
"epoch": 0.21747726374060894,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998408753249489,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.14147113561630248,
|
|
"num_tokens": 5037996.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.2773766040802,
|
|
"epoch": 0.2179715302491103,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998395455709342,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.15115779191255568,
|
|
"num_tokens": 5050944.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.2505774974823,
|
|
"epoch": 0.2184657967576117,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998382102858317,
|
|
"loss": 6.0871,
|
|
"mean_token_accuracy": 0.13831509053707122,
|
|
"num_tokens": 5062129.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.262403440475464,
|
|
"epoch": 0.2189600632661131,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998368694696743,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.1436243861913681,
|
|
"num_tokens": 5073318.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.185823059082031,
|
|
"epoch": 0.21945432977461446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998355231224952,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.14238689020276069,
|
|
"num_tokens": 5084607.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.298590517044067,
|
|
"epoch": 0.21994859628311586,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998341712443273,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.1467602863907814,
|
|
"num_tokens": 5096004.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.199511909484864,
|
|
"epoch": 0.22044286279161723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499832813835204,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.14269362017512321,
|
|
"num_tokens": 5107171.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.184848213195801,
|
|
"epoch": 0.22093712930011863,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998314508951584,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.15424952656030655,
|
|
"num_tokens": 5119249.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.14829421043396,
|
|
"epoch": 0.22143139580862,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998300824242244,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.14679246842861177,
|
|
"num_tokens": 5130798.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.275025987625122,
|
|
"epoch": 0.22192566231712138,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998287084224353,
|
|
"loss": 6.1437,
|
|
"mean_token_accuracy": 0.13429683446884155,
|
|
"num_tokens": 5141376.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.154032039642334,
|
|
"epoch": 0.22241992882562278,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998273288898252,
|
|
"loss": 5.9357,
|
|
"mean_token_accuracy": 0.15065955817699433,
|
|
"num_tokens": 5152888.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.156353521347046,
|
|
"epoch": 0.22291419533412415,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499825943826428,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.14408660531044007,
|
|
"num_tokens": 5165720.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.161768770217895,
|
|
"epoch": 0.22340846184262556,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998245532322776,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.15456337854266167,
|
|
"num_tokens": 5177345.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.202211046218872,
|
|
"epoch": 0.22390272835112693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998231571074083,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.1534419000148773,
|
|
"num_tokens": 5187385.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.170833683013916,
|
|
"epoch": 0.2243969948596283,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998217554518545,
|
|
"loss": 6.0403,
|
|
"mean_token_accuracy": 0.14258744418621064,
|
|
"num_tokens": 5199552.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.200662231445312,
|
|
"epoch": 0.2248912613681297,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998203482656507,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.15123232156038285,
|
|
"num_tokens": 5210316.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.234782314300537,
|
|
"epoch": 0.22538552787663108,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998189355488314,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.14858508333563805,
|
|
"num_tokens": 5221595.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.227956914901734,
|
|
"epoch": 0.22587979438513248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998175173014313,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.14020669236779212,
|
|
"num_tokens": 5232882.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.238587951660156,
|
|
"epoch": 0.22637406089363385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998160935234857,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.14422304853796958,
|
|
"num_tokens": 5244841.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.146130466461182,
|
|
"epoch": 0.22686832740213522,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499814664215029,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.152134919911623,
|
|
"num_tokens": 5256162.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.190051794052124,
|
|
"epoch": 0.22736259391063662,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998132293760968,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.15613968968391417,
|
|
"num_tokens": 5267130.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.0447431087493895,
|
|
"epoch": 0.227856860419138,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998117890067243,
|
|
"loss": 6.0008,
|
|
"mean_token_accuracy": 0.1474076971411705,
|
|
"num_tokens": 5279394.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.172190380096436,
|
|
"epoch": 0.22835112692763937,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998103431069469,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.14816260784864427,
|
|
"num_tokens": 5291068.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.2173741340637205,
|
|
"epoch": 0.22884539343614077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998088916768002,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.15463171005249024,
|
|
"num_tokens": 5300924.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.124597406387329,
|
|
"epoch": 0.22933965994464214,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998074347163199,
|
|
"loss": 5.9419,
|
|
"mean_token_accuracy": 0.15559005588293076,
|
|
"num_tokens": 5311998.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.211737871170044,
|
|
"epoch": 0.22983392645314354,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998059722255418,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.14932580888271332,
|
|
"num_tokens": 5322163.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.127090263366699,
|
|
"epoch": 0.23032819296164492,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998045042045019,
|
|
"loss": 5.981,
|
|
"mean_token_accuracy": 0.15460044890642166,
|
|
"num_tokens": 5331638.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.200595951080322,
|
|
"epoch": 0.2308224594701463,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998030306532363,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15659119933843613,
|
|
"num_tokens": 5342399.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.172941446304321,
|
|
"epoch": 0.2313167259786477,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998015515717813,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.14542844295501708,
|
|
"num_tokens": 5353481.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.180023050308227,
|
|
"epoch": 0.23181099248714906,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998000669601733,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.1496099278330803,
|
|
"num_tokens": 5365167.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.114148902893066,
|
|
"epoch": 0.23230525899565047,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997985768184488,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.14984080642461778,
|
|
"num_tokens": 5375809.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.076729488372803,
|
|
"epoch": 0.23279952550415184,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997970811466443,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.15644187480211258,
|
|
"num_tokens": 5387372.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.341212034225464,
|
|
"epoch": 0.2332937920126532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997955799447969,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.14222865626215936,
|
|
"num_tokens": 5399210.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.121503829956055,
|
|
"epoch": 0.2337880585211546,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997940732129432,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.14460844695568084,
|
|
"num_tokens": 5410969.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.139842796325683,
|
|
"epoch": 0.23428232502965599,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997925609511205,
|
|
"loss": 5.9347,
|
|
"mean_token_accuracy": 0.15759174525737762,
|
|
"num_tokens": 5422569.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.168006563186646,
|
|
"epoch": 0.2347765915381574,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997910431593659,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.15459632575511933,
|
|
"num_tokens": 5434592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.1388246536254885,
|
|
"epoch": 0.23527085804665876,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997895198377168,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.15070839375257492,
|
|
"num_tokens": 5446525.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.147398662567139,
|
|
"epoch": 0.23576512455516013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997879909862105,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.14832279682159424,
|
|
"num_tokens": 5457327.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.24454779624939,
|
|
"epoch": 0.23625939106366153,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499786456604885,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.14286630377173423,
|
|
"num_tokens": 5468533.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.117534255981445,
|
|
"epoch": 0.2367536575721629,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997849166937776,
|
|
"loss": 5.9146,
|
|
"mean_token_accuracy": 0.14934935867786409,
|
|
"num_tokens": 5480652.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.200796270370484,
|
|
"epoch": 0.2372479240806643,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997833712529265,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.14828556329011916,
|
|
"num_tokens": 5491446.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.11882472038269,
|
|
"epoch": 0.23774219058916568,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997818202823695,
|
|
"loss": 5.9543,
|
|
"mean_token_accuracy": 0.1541999250650406,
|
|
"num_tokens": 5502886.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.157952308654785,
|
|
"epoch": 0.23823645709766705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997802637821449,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.14664816558361055,
|
|
"num_tokens": 5514305.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.153297376632691,
|
|
"epoch": 0.23873072360616845,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997787017522909,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.16202860027551652,
|
|
"num_tokens": 5525913.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.031432867050171,
|
|
"epoch": 0.23922499011466983,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997771341928459,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.15993187874555587,
|
|
"num_tokens": 5537069.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.132914733886719,
|
|
"epoch": 0.2397192566231712,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997755611038487,
|
|
"loss": 6.0155,
|
|
"mean_token_accuracy": 0.1475693963468075,
|
|
"num_tokens": 5547988.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.177093124389648,
|
|
"epoch": 0.2402135231316726,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997739824853378,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.14507206082344054,
|
|
"num_tokens": 5560400.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.125483798980713,
|
|
"epoch": 0.24070778964017397,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997723983373519,
|
|
"loss": 5.9408,
|
|
"mean_token_accuracy": 0.1547750160098076,
|
|
"num_tokens": 5572291.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.23362283706665,
|
|
"epoch": 0.24120205614867538,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997708086599303,
|
|
"loss": 5.9657,
|
|
"mean_token_accuracy": 0.14544104561209678,
|
|
"num_tokens": 5583583.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.20045838356018,
|
|
"epoch": 0.24169632265717675,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997692134531119,
|
|
"loss": 5.9888,
|
|
"mean_token_accuracy": 0.1482198178768158,
|
|
"num_tokens": 5595499.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.0919482707977295,
|
|
"epoch": 0.24219058916567812,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499767612716936,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.1550483450293541,
|
|
"num_tokens": 5606745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.092108058929443,
|
|
"epoch": 0.24268485567417952,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997660064514419,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.15098343044519424,
|
|
"num_tokens": 5618226.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.259077262878418,
|
|
"epoch": 0.2431791221826809,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997643946566691,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.14846471548080445,
|
|
"num_tokens": 5628941.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.092586326599121,
|
|
"epoch": 0.2436733886911823,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997627773326574,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.1619025096297264,
|
|
"num_tokens": 5641077.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.1263285160064695,
|
|
"epoch": 0.24416765519968367,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997611544794465,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14339257180690765,
|
|
"num_tokens": 5652156.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.257670974731445,
|
|
"epoch": 0.24466192170818504,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997595260970764,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.14745921045541763,
|
|
"num_tokens": 5663988.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.131538438796997,
|
|
"epoch": 0.24515618821668644,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499757892185587,
|
|
"loss": 5.9627,
|
|
"mean_token_accuracy": 0.14847193360328675,
|
|
"num_tokens": 5676302.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.159386014938354,
|
|
"epoch": 0.24565045472518782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997562527450187,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.15123492628335952,
|
|
"num_tokens": 5686686.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.16356930732727,
|
|
"epoch": 0.24614472123368922,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997546077754116,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.16507403403520585,
|
|
"num_tokens": 5698379.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.121092033386231,
|
|
"epoch": 0.2466389877421906,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997529572768063,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.154787477850914,
|
|
"num_tokens": 5708891.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.0729203701019285,
|
|
"epoch": 0.24713325425069196,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997513012492434,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.1536966696381569,
|
|
"num_tokens": 5720326.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.153505516052246,
|
|
"epoch": 0.24762752075919336,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997496396927636,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.15583585798740388,
|
|
"num_tokens": 5731121.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.155553531646729,
|
|
"epoch": 0.24812178726769474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997479726074077,
|
|
"loss": 5.93,
|
|
"mean_token_accuracy": 0.15216445177793503,
|
|
"num_tokens": 5741637.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.1915891647338865,
|
|
"epoch": 0.24861605377619614,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499746299993217,
|
|
"loss": 5.9735,
|
|
"mean_token_accuracy": 0.15114908963441848,
|
|
"num_tokens": 5752659.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.094469976425171,
|
|
"epoch": 0.2491103202846975,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997446218502324,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15155530497431755,
|
|
"num_tokens": 5763829.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.132277250289917,
|
|
"epoch": 0.24960458679319888,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997429381784952,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.14910133332014083,
|
|
"num_tokens": 5775848.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.120943069458008,
|
|
"epoch": 0.2500988533017003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997412489780469,
|
|
"loss": 5.9612,
|
|
"mean_token_accuracy": 0.15950672328472137,
|
|
"num_tokens": 5786595.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.140192317962646,
|
|
"epoch": 0.25059311981020166,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499739554248929,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.16149618923664094,
|
|
"num_tokens": 5797841.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.0338222026824955,
|
|
"epoch": 0.25108738631870303,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997378539911832,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.15623045712709427,
|
|
"num_tokens": 5809106.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.107133483886718,
|
|
"epoch": 0.2515816528272044,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997361482048513,
|
|
"loss": 5.8885,
|
|
"mean_token_accuracy": 0.15565961226820946,
|
|
"num_tokens": 5820316.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.121990442276001,
|
|
"epoch": 0.25207591933570583,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997344368899753,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.14788583666086197,
|
|
"num_tokens": 5833137.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.175726079940796,
|
|
"epoch": 0.2525701858442072,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997327200465972,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.15318210422992706,
|
|
"num_tokens": 5844088.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.133507585525512,
|
|
"epoch": 0.2530644523527086,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997309976747594,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.15268272608518602,
|
|
"num_tokens": 5854546.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.149356508255005,
|
|
"epoch": 0.25355871886120995,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997292697745042,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.1569249227643013,
|
|
"num_tokens": 5865326.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.136588287353516,
|
|
"epoch": 0.2540529853697113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997275363458741,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.15652241110801696,
|
|
"num_tokens": 5876487.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.0281952857971195,
|
|
"epoch": 0.25454725187821275,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997257973889118,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.14910998791456223,
|
|
"num_tokens": 5887846.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.157446002960205,
|
|
"epoch": 0.25504151838671413,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997240529036599,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.15892206728458405,
|
|
"num_tokens": 5898572.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.071728754043579,
|
|
"epoch": 0.2555357848952155,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997223028901615,
|
|
"loss": 5.9449,
|
|
"mean_token_accuracy": 0.15322234779596328,
|
|
"num_tokens": 5908927.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.124873542785645,
|
|
"epoch": 0.2560300514037169,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997205473484596,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.1580432742834091,
|
|
"num_tokens": 5919807.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.10838508605957,
|
|
"epoch": 0.25652431791221825,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997187862785974,
|
|
"loss": 5.9259,
|
|
"mean_token_accuracy": 0.15537415742874144,
|
|
"num_tokens": 5931160.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.13609881401062,
|
|
"epoch": 0.2570185844207197,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997170196806181,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.14711610227823257,
|
|
"num_tokens": 5943694.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.120221710205078,
|
|
"epoch": 0.25751285092922105,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997152475545652,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.15604913979768753,
|
|
"num_tokens": 5954543.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.046738481521606,
|
|
"epoch": 0.2580071174377224,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997134699004825,
|
|
"loss": 5.9358,
|
|
"mean_token_accuracy": 0.15628221184015273,
|
|
"num_tokens": 5965080.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.095473432540894,
|
|
"epoch": 0.2585013839462238,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997116867184136,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.14930862933397293,
|
|
"num_tokens": 5975314.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.180641603469849,
|
|
"epoch": 0.25899565045472517,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997098980084022,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.15294832438230516,
|
|
"num_tokens": 5985927.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.087760400772095,
|
|
"epoch": 0.2594899169632266,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997081037704926,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.15042607337236405,
|
|
"num_tokens": 5997311.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.086427164077759,
|
|
"epoch": 0.25998418347172797,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997063040047288,
|
|
"loss": 5.9843,
|
|
"mean_token_accuracy": 0.1468744695186615,
|
|
"num_tokens": 6008595.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.178718137741089,
|
|
"epoch": 0.26047844998022934,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997044987111548,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.1546178936958313,
|
|
"num_tokens": 6019055.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.0701744079589846,
|
|
"epoch": 0.2609727164887307,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997026878898155,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.14548355862498283,
|
|
"num_tokens": 6030029.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.153164005279541,
|
|
"epoch": 0.2614669829972321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997008715407552,
|
|
"loss": 5.9902,
|
|
"mean_token_accuracy": 0.1496541254222393,
|
|
"num_tokens": 6041495.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.143697834014892,
|
|
"epoch": 0.2619612495057335,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996990496640185,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.15100248157978058,
|
|
"num_tokens": 6052307.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.028233671188355,
|
|
"epoch": 0.2624555160142349,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996972222596505,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.15583381801843643,
|
|
"num_tokens": 6062550.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.0477863311767575,
|
|
"epoch": 0.26294978252273626,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996953893276958,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.14674556404352188,
|
|
"num_tokens": 6074450.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.078070211410522,
|
|
"epoch": 0.26344404903123764,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996935508681997,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.1591618239879608,
|
|
"num_tokens": 6085749.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.09918999671936,
|
|
"epoch": 0.263938315539739,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996917068812075,
|
|
"loss": 5.8488,
|
|
"mean_token_accuracy": 0.15992971658706664,
|
|
"num_tokens": 6096438.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.059639120101929,
|
|
"epoch": 0.26443258204824044,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996898573667643,
|
|
"loss": 5.9086,
|
|
"mean_token_accuracy": 0.14664011746644973,
|
|
"num_tokens": 6108386.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.083099842071533,
|
|
"epoch": 0.2649268485567418,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996880023249158,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.16396086513996125,
|
|
"num_tokens": 6118771.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.0931103229522705,
|
|
"epoch": 0.2654211150652432,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996861417557076,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.15202439576387405,
|
|
"num_tokens": 6130718.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.067891788482666,
|
|
"epoch": 0.26591538157374456,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996842756591855,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.15080306231975554,
|
|
"num_tokens": 6142086.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.042020416259765,
|
|
"epoch": 0.26640964808224593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996824040353953,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.1560404196381569,
|
|
"num_tokens": 6153857.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.241527795791626,
|
|
"epoch": 0.2669039145907473,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996805268843832,
|
|
"loss": 6.0421,
|
|
"mean_token_accuracy": 0.14912690445780755,
|
|
"num_tokens": 6166796.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.072644186019898,
|
|
"epoch": 0.26739818109924873,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996786442061952,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.15616288185119628,
|
|
"num_tokens": 6178046.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.0524310111999515,
|
|
"epoch": 0.2678924476077501,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996767560008777,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.1550481289625168,
|
|
"num_tokens": 6190455.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.06898980140686,
|
|
"epoch": 0.2683867141162515,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996748622684771,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.1622350811958313,
|
|
"num_tokens": 6201659.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.995411539077759,
|
|
"epoch": 0.26888098062475285,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996729630090401,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.14895097762346268,
|
|
"num_tokens": 6213870.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.167082738876343,
|
|
"epoch": 0.2693752471332542,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996710582226133,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.1600447803735733,
|
|
"num_tokens": 6224237.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.082718801498413,
|
|
"epoch": 0.26986951364175565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996691479092437,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.15194753110408782,
|
|
"num_tokens": 6235868.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.102431201934815,
|
|
"epoch": 0.270363780150257,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996672320689782,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.14958198070526124,
|
|
"num_tokens": 6247994.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.958840847015381,
|
|
"epoch": 0.2708580466587584,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996653107018638,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.16383833289146424,
|
|
"num_tokens": 6259654.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.046971559524536,
|
|
"epoch": 0.2713523131672598,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499663383807948,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.1581733912229538,
|
|
"num_tokens": 6270582.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.1495075702667235,
|
|
"epoch": 0.27184657967576115,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996614513872781,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.1616063266992569,
|
|
"num_tokens": 6281088.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.113773393630981,
|
|
"epoch": 0.2723408461842626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996595134399017,
|
|
"loss": 6.0061,
|
|
"mean_token_accuracy": 0.1472685419023037,
|
|
"num_tokens": 6292920.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.09270396232605,
|
|
"epoch": 0.27283511269276395,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996575699658664,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.1566832423210144,
|
|
"num_tokens": 6304980.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.006596946716309,
|
|
"epoch": 0.2733293792012653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996556209652199,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.1554800748825073,
|
|
"num_tokens": 6316175.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.153335475921631,
|
|
"epoch": 0.2738236457097667,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996536664380104,
|
|
"loss": 5.9069,
|
|
"mean_token_accuracy": 0.1567239671945572,
|
|
"num_tokens": 6327590.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.017695617675781,
|
|
"epoch": 0.27431791221826807,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996517063842859,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.15392989069223403,
|
|
"num_tokens": 6339066.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.086386060714721,
|
|
"epoch": 0.2748121787267695,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996497408040944,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.15775285810232162,
|
|
"num_tokens": 6349485.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.981375408172608,
|
|
"epoch": 0.27530644523527087,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996477696974845,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.15953710824251174,
|
|
"num_tokens": 6360775.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.034738063812256,
|
|
"epoch": 0.27580071174377224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996457930645046,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.15122711658477783,
|
|
"num_tokens": 6371645.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.013451719284058,
|
|
"epoch": 0.2762949782522736,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996438109052034,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.15728358179330826,
|
|
"num_tokens": 6383877.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.08137354850769,
|
|
"epoch": 0.276789244760775,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996418232196296,
|
|
"loss": 5.9411,
|
|
"mean_token_accuracy": 0.1478685200214386,
|
|
"num_tokens": 6394488.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.082438802719116,
|
|
"epoch": 0.2772835112692764,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996398300078321,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.1562285304069519,
|
|
"num_tokens": 6404948.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.112468290328979,
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996378312698598,
|
|
"loss": 5.8919,
|
|
"mean_token_accuracy": 0.15620481222867966,
|
|
"num_tokens": 6416273.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.089010572433471,
|
|
"epoch": 0.27827204428627916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996358270057622,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.15275675654411316,
|
|
"num_tokens": 6427091.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.05656418800354,
|
|
"epoch": 0.27876631079478054,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996338172155883,
|
|
"loss": 5.8618,
|
|
"mean_token_accuracy": 0.15593931525945665,
|
|
"num_tokens": 6438254.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.018289232254029,
|
|
"epoch": 0.2792605773032819,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996318018993876,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.15474870353937148,
|
|
"num_tokens": 6450618.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.027504634857178,
|
|
"epoch": 0.27975484381178334,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996297810572098,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.1601539134979248,
|
|
"num_tokens": 6462467.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.017673635482788,
|
|
"epoch": 0.2802491103202847,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996277546891045,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.1652624100446701,
|
|
"num_tokens": 6474206.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.056855010986328,
|
|
"epoch": 0.2807433768287861,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996257227951216,
|
|
"loss": 5.9084,
|
|
"mean_token_accuracy": 0.15035663545131683,
|
|
"num_tokens": 6486405.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.039477729797364,
|
|
"epoch": 0.28123764333728746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499623685375311,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.15469448566436766,
|
|
"num_tokens": 6496949.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.027335119247437,
|
|
"epoch": 0.28173190984578883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499621642429723,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.16200096756219864,
|
|
"num_tokens": 6508913.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.040955018997193,
|
|
"epoch": 0.28222617635429026,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996195939584078,
|
|
"loss": 5.8639,
|
|
"mean_token_accuracy": 0.1561881922185421,
|
|
"num_tokens": 6519837.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.054210805892945,
|
|
"epoch": 0.28272044286279163,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996175399614156,
|
|
"loss": 5.8126,
|
|
"mean_token_accuracy": 0.1579636812210083,
|
|
"num_tokens": 6531409.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.995057392120361,
|
|
"epoch": 0.283214709371293,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996154804387972,
|
|
"loss": 5.8556,
|
|
"mean_token_accuracy": 0.15890285670757293,
|
|
"num_tokens": 6543433.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.053872203826904,
|
|
"epoch": 0.2837089758797944,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499613415390603,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.151950404047966,
|
|
"num_tokens": 6554511.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.0932821273803714,
|
|
"epoch": 0.28420324238829575,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499611344816884,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.1596566081047058,
|
|
"num_tokens": 6564591.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.049549293518067,
|
|
"epoch": 0.2846975088967972,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499609268717691,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.15844885110855103,
|
|
"num_tokens": 6575684.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.073301649093628,
|
|
"epoch": 0.28519177540529855,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996071870930753,
|
|
"loss": 5.9619,
|
|
"mean_token_accuracy": 0.15451340526342391,
|
|
"num_tokens": 6588504.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.963142967224121,
|
|
"epoch": 0.2856860419137999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996050999430878,
|
|
"loss": 5.7836,
|
|
"mean_token_accuracy": 0.15867630690336226,
|
|
"num_tokens": 6599969.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.050960683822632,
|
|
"epoch": 0.2861803084223013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996030072677802,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.163725782930851,
|
|
"num_tokens": 6611430.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.036673974990845,
|
|
"epoch": 0.2866745749308027,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996009090672037,
|
|
"loss": 5.8447,
|
|
"mean_token_accuracy": 0.15628752261400222,
|
|
"num_tokens": 6623247.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.034439992904663,
|
|
"epoch": 0.28716884143930405,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995988053414098,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.15123033076524733,
|
|
"num_tokens": 6635508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.039534950256348,
|
|
"epoch": 0.2876631079478055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995966960904506,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.15228607207536698,
|
|
"num_tokens": 6646020.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.089818906784058,
|
|
"epoch": 0.28815737445630685,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995945813143778,
|
|
"loss": 5.9051,
|
|
"mean_token_accuracy": 0.14688372910022734,
|
|
"num_tokens": 6658194.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.052178907394409,
|
|
"epoch": 0.2886516409648082,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995924610132435,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.15363554805517196,
|
|
"num_tokens": 6670582.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.036479187011719,
|
|
"epoch": 0.2891459074733096,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995903351870998,
|
|
"loss": 5.8224,
|
|
"mean_token_accuracy": 0.1569667100906372,
|
|
"num_tokens": 6680836.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.112790536880493,
|
|
"epoch": 0.28964017398181097,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499588203835999,
|
|
"loss": 5.9134,
|
|
"mean_token_accuracy": 0.14992318898439408,
|
|
"num_tokens": 6693045.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.067016649246216,
|
|
"epoch": 0.2901344404903124,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995860669599935,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.1490854561328888,
|
|
"num_tokens": 6704006.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.941438627243042,
|
|
"epoch": 0.29062870699881377,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499583924559136,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.15538810789585114,
|
|
"num_tokens": 6717027.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.075238943099976,
|
|
"epoch": 0.29112297350731514,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499581776633479,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.1584622010588646,
|
|
"num_tokens": 6728107.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.981333208084107,
|
|
"epoch": 0.2916172400158165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995796231830756,
|
|
"loss": 5.8421,
|
|
"mean_token_accuracy": 0.15783749520778656,
|
|
"num_tokens": 6738628.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.984621667861939,
|
|
"epoch": 0.2921115065243179,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995774642079786,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.1646315023303032,
|
|
"num_tokens": 6749416.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.985525369644165,
|
|
"epoch": 0.2926057730328193,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499575299708241,
|
|
"loss": 5.8929,
|
|
"mean_token_accuracy": 0.1488107793033123,
|
|
"num_tokens": 6761663.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.097906303405762,
|
|
"epoch": 0.2931000395413207,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995731296839163,
|
|
"loss": 5.8395,
|
|
"mean_token_accuracy": 0.15889886170625686,
|
|
"num_tokens": 6773557.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.906320524215698,
|
|
"epoch": 0.29359430604982206,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995709541350578,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.16536967307329178,
|
|
"num_tokens": 6782832.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.064802503585815,
|
|
"epoch": 0.29408857255832344,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499568773061719,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.15133094489574433,
|
|
"num_tokens": 6795165.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.07623519897461,
|
|
"epoch": 0.2945828390668248,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995665864639534,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.15480878055095673,
|
|
"num_tokens": 6807054.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.915165376663208,
|
|
"epoch": 0.29507710557532624,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995643943418149,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.16479281187057496,
|
|
"num_tokens": 6817681.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.030046367645264,
|
|
"epoch": 0.2955713720838276,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995621966953576,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.15873999148607254,
|
|
"num_tokens": 6829387.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.994547605514526,
|
|
"epoch": 0.296065638592329,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995599935246355,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.15944462567567824,
|
|
"num_tokens": 6842023.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.006680917739868,
|
|
"epoch": 0.29655990510083036,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995577848297026,
|
|
"loss": 5.8521,
|
|
"mean_token_accuracy": 0.1528011903166771,
|
|
"num_tokens": 6853189.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29655990510083036,
|
|
"eval_entropy": 5.838898362913988,
|
|
"eval_loss": 5.886573314666748,
|
|
"eval_mean_token_accuracy": 0.16203675489657332,
|
|
"eval_num_tokens": 6853189.0,
|
|
"eval_runtime": 20.7287,
|
|
"eval_samples_per_second": 1568.503,
|
|
"eval_steps_per_second": 196.105,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.084212350845337,
|
|
"epoch": 0.29705417160933173,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995555706106134,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.1488155320286751,
|
|
"num_tokens": 6864338.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.997887516021729,
|
|
"epoch": 0.29754843811783316,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995533508674223,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.16026814579963683,
|
|
"num_tokens": 6875409.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.001093864440918,
|
|
"epoch": 0.29804270462633453,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995511256001839,
|
|
"loss": 5.8172,
|
|
"mean_token_accuracy": 0.16170514672994613,
|
|
"num_tokens": 6885757.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.015048027038574,
|
|
"epoch": 0.2985369711348359,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499548894808953,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.1570695921778679,
|
|
"num_tokens": 6896440.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.0726926803588865,
|
|
"epoch": 0.2990312376433373,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995466584937846,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.1561363235116005,
|
|
"num_tokens": 6907319.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.034220218658447,
|
|
"epoch": 0.29952550415183865,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995444166547333,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.15464108437299728,
|
|
"num_tokens": 6918683.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.9634346008300785,
|
|
"epoch": 0.3000197706603401,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995421692918547,
|
|
"loss": 5.8091,
|
|
"mean_token_accuracy": 0.15337479412555693,
|
|
"num_tokens": 6929974.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.0475657939910885,
|
|
"epoch": 0.30051403716884145,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995399164052038,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.15774545818567276,
|
|
"num_tokens": 6941213.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.0742419242858885,
|
|
"epoch": 0.3010083036773428,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995376579948362,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.15712235271930694,
|
|
"num_tokens": 6952880.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.066303396224976,
|
|
"epoch": 0.3015025701858442,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995353940608074,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.15944461822509765,
|
|
"num_tokens": 6964344.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.925079202651977,
|
|
"epoch": 0.30199683669434557,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499533124603173,
|
|
"loss": 5.8007,
|
|
"mean_token_accuracy": 0.1586202546954155,
|
|
"num_tokens": 6976042.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.026428174972534,
|
|
"epoch": 0.302491103202847,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499530849621989,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.16500493586063386,
|
|
"num_tokens": 6988137.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.921867370605469,
|
|
"epoch": 0.3029853697113484,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995285691173111,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15778796151280403,
|
|
"num_tokens": 6999858.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.067946720123291,
|
|
"epoch": 0.30347963621984975,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995262830891957,
|
|
"loss": 5.8567,
|
|
"mean_token_accuracy": 0.1585906222462654,
|
|
"num_tokens": 7012756.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.023791694641114,
|
|
"epoch": 0.3039739027283511,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995239915376988,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.1543585553765297,
|
|
"num_tokens": 7024769.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.019925165176391,
|
|
"epoch": 0.3044681692368525,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995216944628769,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14953593611717225,
|
|
"num_tokens": 7035422.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.966122579574585,
|
|
"epoch": 0.3049624357453539,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995193918647865,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.16542816460132598,
|
|
"num_tokens": 7046923.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.064773893356323,
|
|
"epoch": 0.3054567022538553,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995170837434844,
|
|
"loss": 5.835,
|
|
"mean_token_accuracy": 0.15419175177812577,
|
|
"num_tokens": 7058241.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.946009635925293,
|
|
"epoch": 0.30595096876235667,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995147700990269,
|
|
"loss": 5.8536,
|
|
"mean_token_accuracy": 0.15725975334644318,
|
|
"num_tokens": 7070028.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.053697729110718,
|
|
"epoch": 0.30644523527085804,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995124509314714,
|
|
"loss": 5.843,
|
|
"mean_token_accuracy": 0.1565923348069191,
|
|
"num_tokens": 7082641.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.01456732749939,
|
|
"epoch": 0.3069395017793594,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995101262408748,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.15755832195281982,
|
|
"num_tokens": 7094462.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.96401424407959,
|
|
"epoch": 0.3074337682878608,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995077960272943,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.15858004838228226,
|
|
"num_tokens": 7106598.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.959226036071778,
|
|
"epoch": 0.3079280347963622,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995054602907871,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.15864774882793425,
|
|
"num_tokens": 7117006.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.91728892326355,
|
|
"epoch": 0.3084223013048636,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995031190314107,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.1534339338541031,
|
|
"num_tokens": 7128071.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.038468742370606,
|
|
"epoch": 0.30891656781336496,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995007722492228,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.15981683135032654,
|
|
"num_tokens": 7139896.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.941322183609008,
|
|
"epoch": 0.30941083432186633,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994984199442811,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.16602752953767777,
|
|
"num_tokens": 7151479.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.075007772445678,
|
|
"epoch": 0.3099051008303677,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994960621166434,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.1607074946165085,
|
|
"num_tokens": 7162942.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.900337553024292,
|
|
"epoch": 0.31039936733886914,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994936987663678,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.17076555639505386,
|
|
"num_tokens": 7174572.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.006263065338135,
|
|
"epoch": 0.3108936338473705,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994913298935124,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.15694652497768402,
|
|
"num_tokens": 7186352.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.027054071426392,
|
|
"epoch": 0.3113879003558719,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994889554981353,
|
|
"loss": 5.8046,
|
|
"mean_token_accuracy": 0.15830225646495819,
|
|
"num_tokens": 7197849.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.930756330490112,
|
|
"epoch": 0.31188216686437326,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994865755802953,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.16295457482337952,
|
|
"num_tokens": 7207897.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.050958681106567,
|
|
"epoch": 0.31237643337287463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994841901400505,
|
|
"loss": 5.8943,
|
|
"mean_token_accuracy": 0.15915813744068147,
|
|
"num_tokens": 7219148.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.136546277999878,
|
|
"epoch": 0.31287069988137606,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994817991774599,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.1445558950304985,
|
|
"num_tokens": 7230690.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.0489771366119385,
|
|
"epoch": 0.31336496638987743,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994794026925822,
|
|
"loss": 5.8088,
|
|
"mean_token_accuracy": 0.1555367588996887,
|
|
"num_tokens": 7240935.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.9755167961120605,
|
|
"epoch": 0.3138592328983788,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994770006854763,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.1574193097651005,
|
|
"num_tokens": 7253345.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.117976140975952,
|
|
"epoch": 0.3143534994068802,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994745931562015,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1560059294104576,
|
|
"num_tokens": 7265355.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.841166162490845,
|
|
"epoch": 0.31484776591538155,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994721801048168,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.16469242423772812,
|
|
"num_tokens": 7277355.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.000030755996704,
|
|
"epoch": 0.315342032423883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994697615313817,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.15941714942455293,
|
|
"num_tokens": 7288754.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.082979965209961,
|
|
"epoch": 0.31583629893238435,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994673374359556,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.15342381596565247,
|
|
"num_tokens": 7301158.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.9652362823486325,
|
|
"epoch": 0.3163305654408857,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994649078185982,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.1522575005888939,
|
|
"num_tokens": 7314420.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.985113191604614,
|
|
"epoch": 0.3168248319493871,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004994624726793693,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.15395023226737975,
|
|
"num_tokens": 7325459.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.024287176132202,
|
|
"epoch": 0.31731909845788847,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994600320183286,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.1591726526618004,
|
|
"num_tokens": 7336016.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.913967657089233,
|
|
"epoch": 0.3178133649663899,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994575858355364,
|
|
"loss": 5.7501,
|
|
"mean_token_accuracy": 0.163642817735672,
|
|
"num_tokens": 7346716.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.081499481201172,
|
|
"epoch": 0.3183076314748913,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994551341310526,
|
|
"loss": 5.8756,
|
|
"mean_token_accuracy": 0.15766478031873704,
|
|
"num_tokens": 7357246.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.9896539688110355,
|
|
"epoch": 0.31880189798339265,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994526769049379,
|
|
"loss": 5.8908,
|
|
"mean_token_accuracy": 0.14943311512470245,
|
|
"num_tokens": 7369173.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.064849996566773,
|
|
"epoch": 0.319296164491894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994502141572524,
|
|
"loss": 5.8934,
|
|
"mean_token_accuracy": 0.14667481258511544,
|
|
"num_tokens": 7381118.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.995628929138183,
|
|
"epoch": 0.3197904310003954,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994477458880568,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.16845426261425017,
|
|
"num_tokens": 7391874.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.9674286365509035,
|
|
"epoch": 0.3202846975088968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994452720974119,
|
|
"loss": 5.8193,
|
|
"mean_token_accuracy": 0.16485921144485474,
|
|
"num_tokens": 7403474.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.999954891204834,
|
|
"epoch": 0.3207789640173982,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994427927853785,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.16761064678430557,
|
|
"num_tokens": 7415173.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.933607673645019,
|
|
"epoch": 0.32127323052589957,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994403079520175,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.16161210387945174,
|
|
"num_tokens": 7426965.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.983630275726318,
|
|
"epoch": 0.32176749703440094,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994378175973902,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1643822655081749,
|
|
"num_tokens": 7438162.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.964900636672974,
|
|
"epoch": 0.3222617635429023,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994353217215577,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.1570591390132904,
|
|
"num_tokens": 7450241.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.0549173831939695,
|
|
"epoch": 0.32275603005140374,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994328203245814,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.15149068981409072,
|
|
"num_tokens": 7462236.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.991492128372192,
|
|
"epoch": 0.3232502965599051,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994303134065231,
|
|
"loss": 5.8109,
|
|
"mean_token_accuracy": 0.15657777860760688,
|
|
"num_tokens": 7472811.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.953076362609863,
|
|
"epoch": 0.3237445630684065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994278009674442,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.17091321498155593,
|
|
"num_tokens": 7484837.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.976023769378662,
|
|
"epoch": 0.32423882957690786,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994252830074064,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.15214902013540268,
|
|
"num_tokens": 7496712.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.9532591819763185,
|
|
"epoch": 0.32473309608540923,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499422759526472,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.15640552788972856,
|
|
"num_tokens": 7508014.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.006920337677002,
|
|
"epoch": 0.32522736259391066,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994202305247029,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.15756394267082213,
|
|
"num_tokens": 7519466.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.092730522155762,
|
|
"epoch": 0.32572162910241204,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994176960021613,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.15043263658881187,
|
|
"num_tokens": 7531661.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.011136770248413,
|
|
"epoch": 0.3262158956109134,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994151559589095,
|
|
"loss": 5.8126,
|
|
"mean_token_accuracy": 0.15739361941814423,
|
|
"num_tokens": 7544096.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.966448974609375,
|
|
"epoch": 0.3267101621194148,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994126103950101,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.15891228914260863,
|
|
"num_tokens": 7556022.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.001350831985474,
|
|
"epoch": 0.32720442862791616,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994100593105257,
|
|
"loss": 5.7715,
|
|
"mean_token_accuracy": 0.16757655888795853,
|
|
"num_tokens": 7567399.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.9018275260925295,
|
|
"epoch": 0.3276986951364176,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994075027055189,
|
|
"loss": 5.8052,
|
|
"mean_token_accuracy": 0.16109628975391388,
|
|
"num_tokens": 7580673.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.0015599727630615,
|
|
"epoch": 0.32819296164491896,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994049405800529,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.15706816017627717,
|
|
"num_tokens": 7591799.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.0001458644866945,
|
|
"epoch": 0.32868722815342033,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994023729341904,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.15964777916669845,
|
|
"num_tokens": 7603663.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.934050226211548,
|
|
"epoch": 0.3291814946619217,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993997997679949,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.1650229200720787,
|
|
"num_tokens": 7615651.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.850442028045654,
|
|
"epoch": 0.3296757611704231,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993972210815292,
|
|
"loss": 5.7733,
|
|
"mean_token_accuracy": 0.16448295265436172,
|
|
"num_tokens": 7628033.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.106792783737182,
|
|
"epoch": 0.33017002767892445,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993946368748573,
|
|
"loss": 5.8938,
|
|
"mean_token_accuracy": 0.15707466006278992,
|
|
"num_tokens": 7640227.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.990322303771973,
|
|
"epoch": 0.3306642941874259,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993920471480424,
|
|
"loss": 5.7874,
|
|
"mean_token_accuracy": 0.1599864438176155,
|
|
"num_tokens": 7651684.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.992852735519409,
|
|
"epoch": 0.33115856069592725,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993894519011484,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1593676432967186,
|
|
"num_tokens": 7662721.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.983349990844727,
|
|
"epoch": 0.3316528272044286,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993868511342391,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16285967379808425,
|
|
"num_tokens": 7674060.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.922141075134277,
|
|
"epoch": 0.33214709371293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993842448473783,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.16841071248054504,
|
|
"num_tokens": 7685054.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.9582678318023685,
|
|
"epoch": 0.33264136022143137,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993816330406304,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.15618079006671906,
|
|
"num_tokens": 7696554.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.990711975097656,
|
|
"epoch": 0.3331356267299328,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993790157140595,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.15978904366493224,
|
|
"num_tokens": 7707000.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.0205179214477536,
|
|
"epoch": 0.33362989323843417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993763928677299,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.16219552308321,
|
|
"num_tokens": 7718898.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.975991106033325,
|
|
"epoch": 0.33412415974693555,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993737645017064,
|
|
"loss": 5.838,
|
|
"mean_token_accuracy": 0.15772839039564132,
|
|
"num_tokens": 7730493.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.923499536514282,
|
|
"epoch": 0.3346184262554369,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993711306160534,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.1578788787126541,
|
|
"num_tokens": 7742177.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.978937292098999,
|
|
"epoch": 0.3351126927639383,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993684912108358,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.16342742890119552,
|
|
"num_tokens": 7753386.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.9103271484375,
|
|
"epoch": 0.3356069592724397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993658462861184,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.16263284534215927,
|
|
"num_tokens": 7764259.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.9659192085266115,
|
|
"epoch": 0.3361012257809411,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993631958419666,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.1682667076587677,
|
|
"num_tokens": 7775853.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.945500326156616,
|
|
"epoch": 0.33659549228944247,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993605398784451,
|
|
"loss": 5.8374,
|
|
"mean_token_accuracy": 0.15530660152435302,
|
|
"num_tokens": 7787116.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.046633911132813,
|
|
"epoch": 0.33708975879794384,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993578783956198,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.15285939276218413,
|
|
"num_tokens": 7799666.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.977567195892334,
|
|
"epoch": 0.3375840253064452,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993552113935557,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.16652155816555023,
|
|
"num_tokens": 7812454.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.960903215408325,
|
|
"epoch": 0.33807829181494664,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993525388723186,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.15966083854436874,
|
|
"num_tokens": 7824427.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.984457540512085,
|
|
"epoch": 0.338572558323448,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993498608319742,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.16384893357753755,
|
|
"num_tokens": 7835382.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.932029294967651,
|
|
"epoch": 0.3390668248319494,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993471772725886,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.17235663235187532,
|
|
"num_tokens": 7846618.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.924665880203247,
|
|
"epoch": 0.33956109134045076,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993444881942274,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.16130691021680832,
|
|
"num_tokens": 7859160.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.8683253765106205,
|
|
"epoch": 0.34005535784895213,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993417935969572,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.1602069690823555,
|
|
"num_tokens": 7870628.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.023205184936524,
|
|
"epoch": 0.34054962435745356,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499339093480844,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.1631205275654793,
|
|
"num_tokens": 7883016.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.954569149017334,
|
|
"epoch": 0.34104389086595494,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993363878459542,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.15368073135614396,
|
|
"num_tokens": 7895940.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.957338905334472,
|
|
"epoch": 0.3415381573744563,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993336766923546,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.15807777494192124,
|
|
"num_tokens": 7907920.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.994265747070313,
|
|
"epoch": 0.3420324238829577,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993309600201117,
|
|
"loss": 5.8035,
|
|
"mean_token_accuracy": 0.16190102994441985,
|
|
"num_tokens": 7920181.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.9474118709564205,
|
|
"epoch": 0.34252669039145905,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993282378292923,
|
|
"loss": 5.7755,
|
|
"mean_token_accuracy": 0.1690393105149269,
|
|
"num_tokens": 7931135.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.96035213470459,
|
|
"epoch": 0.3430209568999605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993255101199635,
|
|
"loss": 5.7411,
|
|
"mean_token_accuracy": 0.16467749774456025,
|
|
"num_tokens": 7941002.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.978878927230835,
|
|
"epoch": 0.34351522340846186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993227768921924,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.1669140040874481,
|
|
"num_tokens": 7950393.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.915142822265625,
|
|
"epoch": 0.34400948991696323,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993200381460461,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.16538604199886323,
|
|
"num_tokens": 7961468.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.8853638648986815,
|
|
"epoch": 0.3445037564254646,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993172938815922,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.1773862972855568,
|
|
"num_tokens": 7973783.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.884685754776001,
|
|
"epoch": 0.344998022933966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993145440988979,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.16831784844398498,
|
|
"num_tokens": 7984099.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.006422710418701,
|
|
"epoch": 0.3454922894424674,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993117887980311,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.1570899724960327,
|
|
"num_tokens": 7995115.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.938472509384155,
|
|
"epoch": 0.3459865559509688,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993090279790596,
|
|
"loss": 5.7549,
|
|
"mean_token_accuracy": 0.16229426264762878,
|
|
"num_tokens": 8006103.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.8403284549713135,
|
|
"epoch": 0.34648082245947015,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499306261642051,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.15982834249734879,
|
|
"num_tokens": 8018228.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.949107980728149,
|
|
"epoch": 0.3469750889679715,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993034897870737,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.16040400564670562,
|
|
"num_tokens": 8029808.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.904809379577637,
|
|
"epoch": 0.3474693554764729,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993007124141958,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.15806748270988463,
|
|
"num_tokens": 8041136.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.961758375167847,
|
|
"epoch": 0.3479636219849743,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992979295234854,
|
|
"loss": 5.8112,
|
|
"mean_token_accuracy": 0.15807072520256044,
|
|
"num_tokens": 8053013.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.986888790130616,
|
|
"epoch": 0.3484578884934757,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004992951411150112,
|
|
"loss": 5.7934,
|
|
"mean_token_accuracy": 0.16370038390159608,
|
|
"num_tokens": 8065139.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.906422662734985,
|
|
"epoch": 0.34895215500197707,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992923471888418,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.1711960718035698,
|
|
"num_tokens": 8075719.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.937537574768067,
|
|
"epoch": 0.34944642151047844,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992895477450459,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.16310322284698486,
|
|
"num_tokens": 8087821.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.891085863113403,
|
|
"epoch": 0.3499406880189798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992867427836923,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.16491053253412247,
|
|
"num_tokens": 8099861.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.05497784614563,
|
|
"epoch": 0.3504349545274812,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992839323048501,
|
|
"loss": 5.9043,
|
|
"mean_token_accuracy": 0.1527191035449505,
|
|
"num_tokens": 8111671.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.090972948074341,
|
|
"epoch": 0.3509292210359826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992811163085882,
|
|
"loss": 5.852,
|
|
"mean_token_accuracy": 0.15342505127191544,
|
|
"num_tokens": 8123569.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.987070226669312,
|
|
"epoch": 0.351423487544484,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992782947949761,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.15805700719356536,
|
|
"num_tokens": 8135621.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.903195428848266,
|
|
"epoch": 0.35191775405298537,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992754677640831,
|
|
"loss": 5.7147,
|
|
"mean_token_accuracy": 0.16510182321071626,
|
|
"num_tokens": 8147012.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.971565055847168,
|
|
"epoch": 0.35241202056148674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992726352159789,
|
|
"loss": 5.7032,
|
|
"mean_token_accuracy": 0.16711681187152863,
|
|
"num_tokens": 8158686.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.921085596084595,
|
|
"epoch": 0.3529062870699881,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992697971507331,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.168816876411438,
|
|
"num_tokens": 8170188.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.903818559646607,
|
|
"epoch": 0.35340055357848954,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992669535684155,
|
|
"loss": 5.779,
|
|
"mean_token_accuracy": 0.1621542379260063,
|
|
"num_tokens": 8182467.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.023322820663452,
|
|
"epoch": 0.3538948200869909,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992641044690959,
|
|
"loss": 5.8818,
|
|
"mean_token_accuracy": 0.1577792763710022,
|
|
"num_tokens": 8193433.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.934952306747436,
|
|
"epoch": 0.3543890865954923,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992612498528447,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.1658499911427498,
|
|
"num_tokens": 8204220.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.828398132324219,
|
|
"epoch": 0.35488335310399366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992583897197319,
|
|
"loss": 5.6841,
|
|
"mean_token_accuracy": 0.17446459233760833,
|
|
"num_tokens": 8214203.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.018448543548584,
|
|
"epoch": 0.35537761961249503,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992555240698279,
|
|
"loss": 5.8262,
|
|
"mean_token_accuracy": 0.1579638361930847,
|
|
"num_tokens": 8225143.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.982320880889892,
|
|
"epoch": 0.35587188612099646,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992526529032032,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.16971834599971772,
|
|
"num_tokens": 8237715.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.860608386993408,
|
|
"epoch": 0.35636615262949783,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992497762199285,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.16622899174690248,
|
|
"num_tokens": 8249645.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.949036455154419,
|
|
"epoch": 0.3568604191379992,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992468940200745,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.1648137539625168,
|
|
"num_tokens": 8260624.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.970369958877564,
|
|
"epoch": 0.3573546856465006,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992440063037121,
|
|
"loss": 5.8078,
|
|
"mean_token_accuracy": 0.16165586411952973,
|
|
"num_tokens": 8272526.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.85641655921936,
|
|
"epoch": 0.35784895215500195,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992411130709124,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.16460638791322707,
|
|
"num_tokens": 8284270.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.034624099731445,
|
|
"epoch": 0.3583432186635034,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992382143217466,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.16384400129318238,
|
|
"num_tokens": 8296407.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.897780036926269,
|
|
"epoch": 0.35883748517200476,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992353100562858,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.17074024528265,
|
|
"num_tokens": 8307695.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.851276445388794,
|
|
"epoch": 0.35933175168050613,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992324002746016,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.16381751298904418,
|
|
"num_tokens": 8319458.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.8534314155578615,
|
|
"epoch": 0.3598260181890075,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992294849767656,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.1727339133620262,
|
|
"num_tokens": 8330284.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.955981206893921,
|
|
"epoch": 0.3603202846975089,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992265641628495,
|
|
"loss": 5.7445,
|
|
"mean_token_accuracy": 0.16239794641733168,
|
|
"num_tokens": 8343622.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.90520133972168,
|
|
"epoch": 0.3608145512060103,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992236378329252,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.16424720287322997,
|
|
"num_tokens": 8354079.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.9196117401123045,
|
|
"epoch": 0.3613088177145117,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992207059870645,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.1665163055062294,
|
|
"num_tokens": 8364876.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.96867995262146,
|
|
"epoch": 0.36180308422301305,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992177686253396,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.17012346237897874,
|
|
"num_tokens": 8375095.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.867181015014649,
|
|
"epoch": 0.3622973507315144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499214825747823,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.16863478869199752,
|
|
"num_tokens": 8385934.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.895959329605103,
|
|
"epoch": 0.3627916172400158,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992118773545868,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.1754315674304962,
|
|
"num_tokens": 8397018.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.8759214878082275,
|
|
"epoch": 0.3632858837485172,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992089234457036,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.17084360122680664,
|
|
"num_tokens": 8406668.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.957876110076905,
|
|
"epoch": 0.3637801502570186,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992059640212461,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.16381780356168746,
|
|
"num_tokens": 8417471.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.9014252662658695,
|
|
"epoch": 0.36427441676551997,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004992029990812872,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.15887220278382302,
|
|
"num_tokens": 8430073.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.959695863723755,
|
|
"epoch": 0.36476868327402134,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992000286258997,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.15926548838615417,
|
|
"num_tokens": 8442573.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.989988708496094,
|
|
"epoch": 0.3652629497825227,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991970526551567,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.16171564161777496,
|
|
"num_tokens": 8453920.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.919428443908691,
|
|
"epoch": 0.36575721629102415,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991940711691314,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.1626737430691719,
|
|
"num_tokens": 8466652.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.965742731094361,
|
|
"epoch": 0.3662514827995255,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991910841678972,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.16027045547962188,
|
|
"num_tokens": 8480203.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.894874143600464,
|
|
"epoch": 0.3667457493080269,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991880916515275,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.15868055671453477,
|
|
"num_tokens": 8491396.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.984350538253784,
|
|
"epoch": 0.36724001581652826,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499185093620096,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1644155576825142,
|
|
"num_tokens": 8501838.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.835333776473999,
|
|
"epoch": 0.36773428232502964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991820900736765,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.1708022579550743,
|
|
"num_tokens": 8512113.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.903925180435181,
|
|
"epoch": 0.36822854883353107,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991790810123427,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.16471227556467055,
|
|
"num_tokens": 8523888.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.873724317550659,
|
|
"epoch": 0.36872281534203244,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991760664361688,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.1763386145234108,
|
|
"num_tokens": 8536078.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.917610549926758,
|
|
"epoch": 0.3692170818505338,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991730463452288,
|
|
"loss": 5.7365,
|
|
"mean_token_accuracy": 0.15684023201465608,
|
|
"num_tokens": 8547131.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.8698803901672365,
|
|
"epoch": 0.3697113483590352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991700207395971,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.1780976265668869,
|
|
"num_tokens": 8557269.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.956096744537353,
|
|
"epoch": 0.37020561486753656,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991669896193482,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.15648694485425949,
|
|
"num_tokens": 8569193.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.880059432983399,
|
|
"epoch": 0.370699881376038,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991639529845565,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.16808689683675765,
|
|
"num_tokens": 8580888.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.89161524772644,
|
|
"epoch": 0.37119414788453936,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991609108352968,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.16513347923755645,
|
|
"num_tokens": 8591868.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.909579420089722,
|
|
"epoch": 0.37168841439304073,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991578631716438,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.16595157831907273,
|
|
"num_tokens": 8602338.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.941970682144165,
|
|
"epoch": 0.3721826809015421,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991548099936727,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.173343163728714,
|
|
"num_tokens": 8611698.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.856791067123413,
|
|
"epoch": 0.3726769474100435,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991517513014585,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.1660086154937744,
|
|
"num_tokens": 8623537.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.841311836242676,
|
|
"epoch": 0.37317121391854485,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991486870950765,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.1621934913098812,
|
|
"num_tokens": 8634678.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.882809162139893,
|
|
"epoch": 0.3736654804270463,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991456173746021,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.16786129027605057,
|
|
"num_tokens": 8646207.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.001916694641113,
|
|
"epoch": 0.37415974693554765,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991425421401105,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.1641547426581383,
|
|
"num_tokens": 8657069.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.807131099700928,
|
|
"epoch": 0.374654013444049,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991394613916777,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.1740735113620758,
|
|
"num_tokens": 8668296.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.855770206451416,
|
|
"epoch": 0.3751482799525504,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991363751293795,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.16410524398088455,
|
|
"num_tokens": 8680626.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.886316013336182,
|
|
"epoch": 0.3756425464610518,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991332833532915,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.17040918320417403,
|
|
"num_tokens": 8691571.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.851473236083985,
|
|
"epoch": 0.3761368129695532,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049913018606349,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.17158605754375458,
|
|
"num_tokens": 8703262.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.95896167755127,
|
|
"epoch": 0.3766310794780546,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991270832600512,
|
|
"loss": 5.7957,
|
|
"mean_token_accuracy": 0.15546323359012604,
|
|
"num_tokens": 8714799.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.970942783355713,
|
|
"epoch": 0.37712534598655595,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991239749430514,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.16242330521345139,
|
|
"num_tokens": 8726417.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.813585662841797,
|
|
"epoch": 0.3776196124950573,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499120861112567,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.17116913944482803,
|
|
"num_tokens": 8738572.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.012410116195679,
|
|
"epoch": 0.3781138790035587,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991177417686747,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.15966544151306153,
|
|
"num_tokens": 8750557.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.920189714431762,
|
|
"epoch": 0.3786081455120601,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991146169114511,
|
|
"loss": 5.6061,
|
|
"mean_token_accuracy": 0.16634851098060607,
|
|
"num_tokens": 8761921.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.795895385742187,
|
|
"epoch": 0.3791024120205615,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991114865409732,
|
|
"loss": 5.6987,
|
|
"mean_token_accuracy": 0.16617852002382277,
|
|
"num_tokens": 8772705.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.9335143089294435,
|
|
"epoch": 0.37959667852906287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499108350657318,
|
|
"loss": 5.7191,
|
|
"mean_token_accuracy": 0.16396770179271697,
|
|
"num_tokens": 8783563.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.827181816101074,
|
|
"epoch": 0.38009094503756424,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991052092605627,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.17345058768987656,
|
|
"num_tokens": 8794171.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.871563816070557,
|
|
"epoch": 0.3805852115460656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991020623507842,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.16282366067171097,
|
|
"num_tokens": 8806487.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.900928640365601,
|
|
"epoch": 0.38107947805456704,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004990989099280604,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.16446596533060073,
|
|
"num_tokens": 8817819.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.923869180679321,
|
|
"epoch": 0.3815737445630684,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990957519924686,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.16552813053131105,
|
|
"num_tokens": 8828485.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.869322299957275,
|
|
"epoch": 0.3820680110715698,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990925885440865,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.1641053080558777,
|
|
"num_tokens": 8840179.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.883348655700684,
|
|
"epoch": 0.38256227758007116,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990894195829921,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.17041839957237243,
|
|
"num_tokens": 8851813.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.874509334564209,
|
|
"epoch": 0.38305654408857254,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990862451092631,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.16271054595708848,
|
|
"num_tokens": 8863072.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.908667039871216,
|
|
"epoch": 0.38355081059707397,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990830651229776,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.16601400971412658,
|
|
"num_tokens": 8873510.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.83857684135437,
|
|
"epoch": 0.38404507710557534,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990798796242142,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16807291507720948,
|
|
"num_tokens": 8884296.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.888775205612182,
|
|
"epoch": 0.3845393436140767,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990766886130508,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.17192094773054123,
|
|
"num_tokens": 8894208.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.020419263839722,
|
|
"epoch": 0.3850336101225781,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990734920895662,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.15748704373836517,
|
|
"num_tokens": 8905703.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.877511692047119,
|
|
"epoch": 0.38552787663107946,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990702900538388,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.16876436471939088,
|
|
"num_tokens": 8918077.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.776277256011963,
|
|
"epoch": 0.3860221431395809,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990670825059477,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.165885029733181,
|
|
"num_tokens": 8930240.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.9259237289428714,
|
|
"epoch": 0.38651640964808226,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990638694459715,
|
|
"loss": 5.6923,
|
|
"mean_token_accuracy": 0.17438057214021682,
|
|
"num_tokens": 8941421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.886525201797485,
|
|
"epoch": 0.38701067615658363,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990606508739893,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.1625737339258194,
|
|
"num_tokens": 8952296.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.887601089477539,
|
|
"epoch": 0.387504942665085,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990574267900804,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.16023652553558348,
|
|
"num_tokens": 8963167.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.860787200927734,
|
|
"epoch": 0.3879992091735864,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990541971943241,
|
|
"loss": 5.6944,
|
|
"mean_token_accuracy": 0.16610553562641145,
|
|
"num_tokens": 8974405.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.813625812530518,
|
|
"epoch": 0.3884934756820878,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990509620867997,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17485980838537216,
|
|
"num_tokens": 8986012.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.794552993774414,
|
|
"epoch": 0.3889877421905892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990477214675868,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.1692924752831459,
|
|
"num_tokens": 8996759.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.887366104125976,
|
|
"epoch": 0.38948200869909055,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990444753367653,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.16604164093732834,
|
|
"num_tokens": 9007215.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.832546091079712,
|
|
"epoch": 0.3899762752075919,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990412236944149,
|
|
"loss": 5.6156,
|
|
"mean_token_accuracy": 0.18009421676397325,
|
|
"num_tokens": 9018281.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.932539606094361,
|
|
"epoch": 0.3904705417160933,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990379665406157,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.16505084782838822,
|
|
"num_tokens": 9029312.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.949569416046143,
|
|
"epoch": 0.39096480822459473,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990347038754477,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.1618492618203163,
|
|
"num_tokens": 9040273.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.916225481033325,
|
|
"epoch": 0.3914590747330961,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990314356989912,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.16216366291046141,
|
|
"num_tokens": 9052571.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.783906412124634,
|
|
"epoch": 0.3919533412415975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990281620113268,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.16567644774913787,
|
|
"num_tokens": 9063531.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.918298578262329,
|
|
"epoch": 0.39244760775009885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990248828125347,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.1612454503774643,
|
|
"num_tokens": 9075404.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.828043699264526,
|
|
"epoch": 0.3929418742586002,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990215981026958,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.16850079447031022,
|
|
"num_tokens": 9086570.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.859482908248902,
|
|
"epoch": 0.3934361407671016,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990183078818908,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.17108299285173417,
|
|
"num_tokens": 9097993.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.892006063461304,
|
|
"epoch": 0.393930407275603,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990150121502007,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.1727806583046913,
|
|
"num_tokens": 9108783.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.804200029373169,
|
|
"epoch": 0.3944246737841044,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990117109077066,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.1658673793077469,
|
|
"num_tokens": 9120039.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.9291599750518795,
|
|
"epoch": 0.39491894029260577,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990084041544895,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.17073300033807753,
|
|
"num_tokens": 9131543.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.854316997528076,
|
|
"epoch": 0.39541320680110714,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499005091890631,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.16651399731636046,
|
|
"num_tokens": 9142968.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.838335704803467,
|
|
"epoch": 0.3959074733096085,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004990017741162125,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.16216625273227692,
|
|
"num_tokens": 9155705.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.960814714431763,
|
|
"epoch": 0.39640173981810994,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989984508313156,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.15642520487308503,
|
|
"num_tokens": 9167575.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.833995151519775,
|
|
"epoch": 0.3968960063266113,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498995122036022,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1676729664206505,
|
|
"num_tokens": 9178493.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.956012725830078,
|
|
"epoch": 0.3973902728351127,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989917877304138,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.1605817899107933,
|
|
"num_tokens": 9189677.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.868053340911866,
|
|
"epoch": 0.39788453934361406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989884479145727,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.17071904242038727,
|
|
"num_tokens": 9199179.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.88495979309082,
|
|
"epoch": 0.39837880585211544,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989851025885812,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.16467752456665039,
|
|
"num_tokens": 9210689.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.871729373931885,
|
|
"epoch": 0.39887307236061686,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989817517525212,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.1702873781323433,
|
|
"num_tokens": 9221710.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.912847375869751,
|
|
"epoch": 0.39936733886911824,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989783954064755,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.16328861117362975,
|
|
"num_tokens": 9234079.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.854098844528198,
|
|
"epoch": 0.3998616053776196,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989750335505265,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.16908831596374513,
|
|
"num_tokens": 9245050.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.98025598526001,
|
|
"epoch": 0.400355871886121,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989716661847571,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.16286372840404512,
|
|
"num_tokens": 9256455.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.82414436340332,
|
|
"epoch": 0.40085013839462236,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989682933092497,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1701007068157196,
|
|
"num_tokens": 9267722.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.808041715621949,
|
|
"epoch": 0.4013444049031238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989649149240877,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.16336237341165544,
|
|
"num_tokens": 9277533.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.926660394668579,
|
|
"epoch": 0.40183867141162516,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000498961531029354,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.1723726972937584,
|
|
"num_tokens": 9290052.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.907356834411621,
|
|
"epoch": 0.40233293792012653,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498958141625132,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.16776670813560485,
|
|
"num_tokens": 9302201.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.887616729736328,
|
|
"epoch": 0.4028272044286279,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989547467115047,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.15944056063890458,
|
|
"num_tokens": 9313215.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.9510393142700195,
|
|
"epoch": 0.4033214709371293,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989513462885561,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.155883726477623,
|
|
"num_tokens": 9324098.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.978319501876831,
|
|
"epoch": 0.4038157374456307,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004989479403563696,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1646607756614685,
|
|
"num_tokens": 9336048.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.8422708988189695,
|
|
"epoch": 0.4043100039541321,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989445289150289,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.16654919385910033,
|
|
"num_tokens": 9347723.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.829070520401001,
|
|
"epoch": 0.40480427046263345,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004989411119646183,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.16050561815500258,
|
|
"num_tokens": 9360588.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.922001028060913,
|
|
"epoch": 0.4052985369711348,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989376895052214,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.16239948570728302,
|
|
"num_tokens": 9371798.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.878776121139526,
|
|
"epoch": 0.4057928034796362,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989342615369226,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.1724824145436287,
|
|
"num_tokens": 9382421.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.878492259979248,
|
|
"epoch": 0.40628706998813763,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989308280598063,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.1707899510860443,
|
|
"num_tokens": 9392832.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.794064044952393,
|
|
"epoch": 0.406781336496639,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004989273890739569,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.16852443814277648,
|
|
"num_tokens": 9405309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.773290777206421,
|
|
"epoch": 0.4072756030051404,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498923944579459,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.1808168187737465,
|
|
"num_tokens": 9416707.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.88574185371399,
|
|
"epoch": 0.40776986951364175,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989204945763972,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.1645051822066307,
|
|
"num_tokens": 9427684.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.875238704681396,
|
|
"epoch": 0.4082641360221431,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989170390648567,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1686164915561676,
|
|
"num_tokens": 9439073.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.833017063140869,
|
|
"epoch": 0.40875840253064455,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989135780449222,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.1716807648539543,
|
|
"num_tokens": 9450266.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.776205968856812,
|
|
"epoch": 0.4092526690391459,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989101115166789,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.17508271783590318,
|
|
"num_tokens": 9462662.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.8494264602661135,
|
|
"epoch": 0.4097469355476473,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989066394802122,
|
|
"loss": 5.6922,
|
|
"mean_token_accuracy": 0.1669348806142807,
|
|
"num_tokens": 9474338.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.889415454864502,
|
|
"epoch": 0.41024120205614867,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989031619356074,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.17034045308828355,
|
|
"num_tokens": 9486353.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.844692850112915,
|
|
"epoch": 0.41073546856465004,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049889967888295,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.16728283166885377,
|
|
"num_tokens": 9497464.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.854997682571411,
|
|
"epoch": 0.41122973507315147,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988961903223258,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.17531556785106658,
|
|
"num_tokens": 9508037.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.7995391368865965,
|
|
"epoch": 0.41172400158165284,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988926962538207,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.17245213091373443,
|
|
"num_tokens": 9518653.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.82932858467102,
|
|
"epoch": 0.4122182680901542,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988891966775204,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.17256172150373458,
|
|
"num_tokens": 9529225.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.87958402633667,
|
|
"epoch": 0.4127125345986556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988856915935112,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.16461459249258042,
|
|
"num_tokens": 9541010.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.78000111579895,
|
|
"epoch": 0.41320680110715696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988821810018791,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.16528748869895935,
|
|
"num_tokens": 9552061.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.9790253162384035,
|
|
"epoch": 0.41370106761565834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988786649027108,
|
|
"loss": 5.7987,
|
|
"mean_token_accuracy": 0.15660196989774705,
|
|
"num_tokens": 9563970.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.864908266067505,
|
|
"epoch": 0.41419533412415976,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988751432960926,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.17485955953598023,
|
|
"num_tokens": 9575381.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.86647777557373,
|
|
"epoch": 0.41468960063266114,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988716161821111,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.17472680807113647,
|
|
"num_tokens": 9586821.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.876406335830689,
|
|
"epoch": 0.4151838671411625,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004988680835608531,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.16150547564029694,
|
|
"num_tokens": 9599580.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.784275007247925,
|
|
"epoch": 0.4156781336496639,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988645454324055,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.16584365963935851,
|
|
"num_tokens": 9611495.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.936398077011108,
|
|
"epoch": 0.41617240015816526,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988610017968554,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.17303829044103622,
|
|
"num_tokens": 9623713.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.818154144287109,
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988574526542899,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.1765165865421295,
|
|
"num_tokens": 9633922.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.824317121505738,
|
|
"epoch": 0.41716093317516806,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988538980047963,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.16559439152479172,
|
|
"num_tokens": 9645641.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.841555404663086,
|
|
"epoch": 0.41765519968366943,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988503378484622,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.17398539781570435,
|
|
"num_tokens": 9656927.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.814691019058228,
|
|
"epoch": 0.4181494661921708,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498846772185375,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1729745402932167,
|
|
"num_tokens": 9669148.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.893791246414184,
|
|
"epoch": 0.4186437327006722,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988432010156224,
|
|
"loss": 5.7396,
|
|
"mean_token_accuracy": 0.15868683755397797,
|
|
"num_tokens": 9680620.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.925040054321289,
|
|
"epoch": 0.4191379992091736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988396243392924,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.16457130312919616,
|
|
"num_tokens": 9690984.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.835089540481567,
|
|
"epoch": 0.419632265717675,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498836042156473,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.17159282118082048,
|
|
"num_tokens": 9701561.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.884567213058472,
|
|
"epoch": 0.42012653222617635,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988324544672521,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.1672545090317726,
|
|
"num_tokens": 9712780.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.868431282043457,
|
|
"epoch": 0.4206207987346777,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988288612717182,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.16327356547117233,
|
|
"num_tokens": 9724547.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.844528484344482,
|
|
"epoch": 0.4211150652431791,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988252625699594,
|
|
"loss": 5.6823,
|
|
"mean_token_accuracy": 0.16297900527715684,
|
|
"num_tokens": 9736897.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.867266893386841,
|
|
"epoch": 0.4216093317516805,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988216583620647,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.17023655623197556,
|
|
"num_tokens": 9748214.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.869999837875366,
|
|
"epoch": 0.4221035982601819,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988180486481223,
|
|
"loss": 5.6769,
|
|
"mean_token_accuracy": 0.17015081495046616,
|
|
"num_tokens": 9759602.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.8174549579620365,
|
|
"epoch": 0.4225978647686833,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988144334282211,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.17117137610912322,
|
|
"num_tokens": 9771645.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.859453535079956,
|
|
"epoch": 0.42309213127718465,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988108127024503,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.16911172568798066,
|
|
"num_tokens": 9783504.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.893519067764283,
|
|
"epoch": 0.423586397785686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988071864708987,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.16314952075481415,
|
|
"num_tokens": 9795572.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.836259841918945,
|
|
"epoch": 0.42408066429418745,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988035547336555,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.1675659477710724,
|
|
"num_tokens": 9806398.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.779581737518311,
|
|
"epoch": 0.4245749308026888,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987999174908104,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.1663268983364105,
|
|
"num_tokens": 9817171.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.922465467453003,
|
|
"epoch": 0.4250691973111902,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987962747424524,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.16931165456771852,
|
|
"num_tokens": 9827535.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.815274333953857,
|
|
"epoch": 0.42556346381969157,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987926264886713,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.17092007547616958,
|
|
"num_tokens": 9839619.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.857655954360962,
|
|
"epoch": 0.42605773032819294,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498788972729557,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.16871783286333084,
|
|
"num_tokens": 9850100.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.928799676895141,
|
|
"epoch": 0.42655199683669437,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987853134651992,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.15432474240660668,
|
|
"num_tokens": 9862228.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.837745666503906,
|
|
"epoch": 0.42704626334519574,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498781648695688,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.17573820501565934,
|
|
"num_tokens": 9873080.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.808217191696167,
|
|
"epoch": 0.4275405298536971,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987779784211135,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.16612853109836578,
|
|
"num_tokens": 9884735.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.865272378921508,
|
|
"epoch": 0.4280347963621985,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498774302641566,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.16833435297012328,
|
|
"num_tokens": 9895018.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.842509174346924,
|
|
"epoch": 0.42852906287069986,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987706213571359,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.17211945354938507,
|
|
"num_tokens": 9906838.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.889233684539795,
|
|
"epoch": 0.4290233293792013,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987669345679139,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.16429460048675537,
|
|
"num_tokens": 9919556.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.859847974777222,
|
|
"epoch": 0.42951759588770266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987632422739904,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.16938609331846238,
|
|
"num_tokens": 9929783.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.787507438659668,
|
|
"epoch": 0.43001186239620404,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987595444754567,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.17016697227954863,
|
|
"num_tokens": 9940894.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.81076602935791,
|
|
"epoch": 0.4305061289047054,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004987558411724032,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.1788248375058174,
|
|
"num_tokens": 9951973.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.868822050094605,
|
|
"epoch": 0.4310003954132068,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987521323649215,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.16563129425048828,
|
|
"num_tokens": 9963304.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.841874361038208,
|
|
"epoch": 0.4314946619217082,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987484180531026,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.17026820480823518,
|
|
"num_tokens": 9973981.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.889091730117798,
|
|
"epoch": 0.4319889284302096,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987446982370379,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.16372227519750596,
|
|
"num_tokens": 9986461.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.871285724639892,
|
|
"epoch": 0.43248319493871096,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498740972916819,
|
|
"loss": 5.6439,
|
|
"mean_token_accuracy": 0.16812467724084854,
|
|
"num_tokens": 9997973.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.843570899963379,
|
|
"epoch": 0.43297746144721233,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987372420925373,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.16844396740198136,
|
|
"num_tokens": 10009572.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.805202341079712,
|
|
"epoch": 0.4334717279557137,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987335057642847,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.1798780858516693,
|
|
"num_tokens": 10020437.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.822914123535156,
|
|
"epoch": 0.43396599446421513,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004987297639321533,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.1684048891067505,
|
|
"num_tokens": 10031827.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.822333097457886,
|
|
"epoch": 0.4344602609727165,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987260165962349,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.16710660308599473,
|
|
"num_tokens": 10043833.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.837571001052856,
|
|
"epoch": 0.4349545274812179,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987222637566218,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.17188626825809478,
|
|
"num_tokens": 10054645.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.769827222824096,
|
|
"epoch": 0.43544879398971925,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987185054134064,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.16493925750255584,
|
|
"num_tokens": 10065178.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.826924991607666,
|
|
"epoch": 0.4359430604982206,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000498714741566681,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.17811701595783233,
|
|
"num_tokens": 10076701.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.780032110214234,
|
|
"epoch": 0.436437327006722,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987109722165383,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.1700105130672455,
|
|
"num_tokens": 10087959.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.880767917633056,
|
|
"epoch": 0.4369315935152234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987071973630708,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.16818706542253495,
|
|
"num_tokens": 10099463.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.803549814224243,
|
|
"epoch": 0.4374258600237248,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987034170063717,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.1695466473698616,
|
|
"num_tokens": 10111384.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.801593875885009,
|
|
"epoch": 0.4379201265322262,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986996311465338,
|
|
"loss": 5.6118,
|
|
"mean_token_accuracy": 0.17462965697050095,
|
|
"num_tokens": 10121838.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.847334098815918,
|
|
"epoch": 0.43841439304072755,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986958397836503,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.1757386162877083,
|
|
"num_tokens": 10132225.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.764697647094726,
|
|
"epoch": 0.4389086595492289,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986920429178144,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.16869834214448928,
|
|
"num_tokens": 10143114.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.858071994781494,
|
|
"epoch": 0.43940292605773035,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986882405491195,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.15645925253629683,
|
|
"num_tokens": 10155057.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.825079345703125,
|
|
"epoch": 0.4398971925662317,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986844326776593,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.1803316131234169,
|
|
"num_tokens": 10166816.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.74500150680542,
|
|
"epoch": 0.4403914590747331,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986806193035272,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.18103527575731276,
|
|
"num_tokens": 10179433.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.826761674880982,
|
|
"epoch": 0.44088572558323447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986768004268173,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.17316691279411317,
|
|
"num_tokens": 10190784.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.801952075958252,
|
|
"epoch": 0.44137999209173584,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986729760476234,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.16593633741140365,
|
|
"num_tokens": 10201941.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.82014422416687,
|
|
"epoch": 0.44187425860023727,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986691461660394,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.1733821839094162,
|
|
"num_tokens": 10214029.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.777339315414428,
|
|
"epoch": 0.44236852510873864,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986653107821599,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.1750914230942726,
|
|
"num_tokens": 10225585.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.764943027496338,
|
|
"epoch": 0.44286279161724,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004986614698960789,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.17808845043182372,
|
|
"num_tokens": 10237753.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.887031602859497,
|
|
"epoch": 0.4433570581257414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986576235078913,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.1615597724914551,
|
|
"num_tokens": 10251522.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.887323236465454,
|
|
"epoch": 0.44385132463424276,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986537716176912,
|
|
"loss": 5.5271,
|
|
"mean_token_accuracy": 0.17930984050035476,
|
|
"num_tokens": 10263319.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.712326526641846,
|
|
"epoch": 0.4443455911427442,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986499142255738,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.16989955455064773,
|
|
"num_tokens": 10274899.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.838864421844482,
|
|
"epoch": 0.44483985765124556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986460513316338,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.17787883430719376,
|
|
"num_tokens": 10286110.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.809325695037842,
|
|
"epoch": 0.44533412415974694,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986421829359662,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.16746099144220353,
|
|
"num_tokens": 10298870.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.820289134979248,
|
|
"epoch": 0.4458283906682483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986383090386661,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.16782621592283248,
|
|
"num_tokens": 10310326.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.8581438064575195,
|
|
"epoch": 0.4463226571767497,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498634429639829,
|
|
"loss": 5.5542,
|
|
"mean_token_accuracy": 0.17202099561691284,
|
|
"num_tokens": 10320899.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.825332593917847,
|
|
"epoch": 0.4468169236852511,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986305447395502,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.17592785209417344,
|
|
"num_tokens": 10331669.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.816992092132568,
|
|
"epoch": 0.4473111901937525,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986266543379254,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.17180951982736586,
|
|
"num_tokens": 10343120.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.797379636764527,
|
|
"epoch": 0.44780545670225386,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986227584350501,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.17498999536037446,
|
|
"num_tokens": 10354806.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.858649969100952,
|
|
"epoch": 0.44829972321075523,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986188570310203,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.17178542762994767,
|
|
"num_tokens": 10366453.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.873257064819336,
|
|
"epoch": 0.4487939897192566,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986149501259319,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.16281179934740067,
|
|
"num_tokens": 10378095.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.739948797225952,
|
|
"epoch": 0.44928825622775803,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986110377198812,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.17470115125179292,
|
|
"num_tokens": 10389620.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.882530689239502,
|
|
"epoch": 0.4497825227362594,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498607119812964,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.16568560302257537,
|
|
"num_tokens": 10400166.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.857796144485474,
|
|
"epoch": 0.4502767892447608,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986031964052772,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.1668781518936157,
|
|
"num_tokens": 10411116.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.778992223739624,
|
|
"epoch": 0.45077105575326215,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985992674969169,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.16282664388418197,
|
|
"num_tokens": 10423484.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.844914436340332,
|
|
"epoch": 0.4512653222617635,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985953330879801,
|
|
"loss": 5.6905,
|
|
"mean_token_accuracy": 0.1586763396859169,
|
|
"num_tokens": 10435636.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.848702239990234,
|
|
"epoch": 0.45175958877026495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985913931785633,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.17407121509313583,
|
|
"num_tokens": 10447586.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.762767887115478,
|
|
"epoch": 0.4522538552787663,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985874477687636,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.16698419600725173,
|
|
"num_tokens": 10460678.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.831792402267456,
|
|
"epoch": 0.4527481217872677,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985834968586779,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.1700241297483444,
|
|
"num_tokens": 10472738.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.835088634490967,
|
|
"epoch": 0.45324238829576907,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985795404484037,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.17453843653202056,
|
|
"num_tokens": 10483716.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.850312614440918,
|
|
"epoch": 0.45373665480427045,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985755785380379,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.16620276123285294,
|
|
"num_tokens": 10495287.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.794805860519409,
|
|
"epoch": 0.4542309213127719,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985716111276781,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.1721417114138603,
|
|
"num_tokens": 10506332.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.857477140426636,
|
|
"epoch": 0.45472518782127325,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985676382174223,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.16736275106668472,
|
|
"num_tokens": 10517574.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.8186877250671385,
|
|
"epoch": 0.4552194543297746,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985636598073677,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.17843152284622193,
|
|
"num_tokens": 10528998.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.789574527740479,
|
|
"epoch": 0.455713720838276,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985596758976125,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15976811945438385,
|
|
"num_tokens": 10539669.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.796797466278076,
|
|
"epoch": 0.45620798734677737,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985556864882545,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.17045630514621735,
|
|
"num_tokens": 10550005.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.758793020248413,
|
|
"epoch": 0.45670225385527874,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498551691579392,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1709605410695076,
|
|
"num_tokens": 10561122.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.835131645202637,
|
|
"epoch": 0.45719652036378017,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985476911711232,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.1706647038459778,
|
|
"num_tokens": 10572081.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.716209506988525,
|
|
"epoch": 0.45769078687228154,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985436852635465,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.18031772524118422,
|
|
"num_tokens": 10582297.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.866713285446167,
|
|
"epoch": 0.4581850533807829,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985396738567604,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.16463931947946547,
|
|
"num_tokens": 10593161.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.830714082717895,
|
|
"epoch": 0.4586793198892843,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985356569508638,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.17743647396564483,
|
|
"num_tokens": 10603900.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.7970226287841795,
|
|
"epoch": 0.45917358639778566,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985316345459551,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.1742269366979599,
|
|
"num_tokens": 10614946.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.833553075790405,
|
|
"epoch": 0.4596678529062871,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985276066421338,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.16616080701351166,
|
|
"num_tokens": 10625073.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.859928894042969,
|
|
"epoch": 0.46016211941478846,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985235732394986,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.16246279031038285,
|
|
"num_tokens": 10636942.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.88986988067627,
|
|
"epoch": 0.46065638592328984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985195343381487,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.16346882283687592,
|
|
"num_tokens": 10647608.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.906115961074829,
|
|
"epoch": 0.4611506524317912,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004985154899381837,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.16399595737457276,
|
|
"num_tokens": 10659532.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.830447673797607,
|
|
"epoch": 0.4616449189402926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985114400397029,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.17186745554208754,
|
|
"num_tokens": 10670342.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.846805810928345,
|
|
"epoch": 0.462139185448794,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985073846428061,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.16922882795333863,
|
|
"num_tokens": 10682984.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.81272177696228,
|
|
"epoch": 0.4626334519572954,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004985033237475929,
|
|
"loss": 5.6571,
|
|
"mean_token_accuracy": 0.16456034183502197,
|
|
"num_tokens": 10694235.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.869851016998291,
|
|
"epoch": 0.46312771846579676,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984992573541633,
|
|
"loss": 5.6675,
|
|
"mean_token_accuracy": 0.16956137716770173,
|
|
"num_tokens": 10704508.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.717702198028564,
|
|
"epoch": 0.46362198497429813,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004984951854626173,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17722870260477067,
|
|
"num_tokens": 10716927.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.770853900909424,
|
|
"epoch": 0.4641162514827995,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004984911080730551,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.17649805545806885,
|
|
"num_tokens": 10728396.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.8329957008361815,
|
|
"epoch": 0.46461051799130093,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984870251855769,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.17403971701860427,
|
|
"num_tokens": 10739001.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.846718072891235,
|
|
"epoch": 0.4651047844998023,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984829368002831,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.17142556011676788,
|
|
"num_tokens": 10748768.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.830345964431762,
|
|
"epoch": 0.4655990510083037,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984788429172745,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.1713384658098221,
|
|
"num_tokens": 10760582.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.788267183303833,
|
|
"epoch": 0.46609331751680505,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004984747435366517,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.1783460333943367,
|
|
"num_tokens": 10772537.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.8207924365997314,
|
|
"epoch": 0.4665875840253064,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984706386585156,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.1830333173274994,
|
|
"num_tokens": 10783740.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.793240213394165,
|
|
"epoch": 0.46708185053380785,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498466528282967,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.17064726650714873,
|
|
"num_tokens": 10794793.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.866763877868652,
|
|
"epoch": 0.4675761170423092,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984624124101072,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.17204025834798814,
|
|
"num_tokens": 10805944.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.824394655227661,
|
|
"epoch": 0.4680703835508106,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984582910400374,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.16792816668748856,
|
|
"num_tokens": 10818362.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.7967041015625,
|
|
"epoch": 0.46856465005931197,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498454164172859,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.17585522532463074,
|
|
"num_tokens": 10831306.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.778382873535156,
|
|
"epoch": 0.46905891656781334,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984500318086733,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.170336352288723,
|
|
"num_tokens": 10841671.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.7844038009643555,
|
|
"epoch": 0.4695531830763148,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984458939475824,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.17546041458845138,
|
|
"num_tokens": 10852754.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.811524963378906,
|
|
"epoch": 0.47004744958481615,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984417505896877,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.17046928852796556,
|
|
"num_tokens": 10864812.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.803496170043945,
|
|
"epoch": 0.4705417160933175,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984376017350913,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.17111281156539918,
|
|
"num_tokens": 10875967.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.790186262130737,
|
|
"epoch": 0.4710359826018189,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004984334473838953,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.17373200058937072,
|
|
"num_tokens": 10889575.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.820612001419067,
|
|
"epoch": 0.47153024911032027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984292875362018,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.1711822271347046,
|
|
"num_tokens": 10900751.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.854453992843628,
|
|
"epoch": 0.4720245156188217,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984251221921131,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.17048616111278533,
|
|
"num_tokens": 10912618.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.797359228134155,
|
|
"epoch": 0.47251878212732307,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984209513517317,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.16904376298189164,
|
|
"num_tokens": 10925286.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.824411010742187,
|
|
"epoch": 0.47301304863582444,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984167750151603,
|
|
"loss": 5.5834,
|
|
"mean_token_accuracy": 0.1733615979552269,
|
|
"num_tokens": 10936033.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.806764793395996,
|
|
"epoch": 0.4735073151443258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984125931825018,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.1778370752930641,
|
|
"num_tokens": 10947055.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.810790061950684,
|
|
"epoch": 0.4740015816528272,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984084058538585,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.16869567036628724,
|
|
"num_tokens": 10957468.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.83496503829956,
|
|
"epoch": 0.4744958481613286,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984042130293339,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.17087534070014954,
|
|
"num_tokens": 10970273.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.864707565307617,
|
|
"epoch": 0.47499011466983,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004984000147090311,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.1655959367752075,
|
|
"num_tokens": 10981842.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.832684135437011,
|
|
"epoch": 0.47548438117833136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983958108930531,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.1743028372526169,
|
|
"num_tokens": 10993615.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.792374134063721,
|
|
"epoch": 0.47597864768683273,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983916015815036,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.16958209425210952,
|
|
"num_tokens": 11004451.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.859997797012329,
|
|
"epoch": 0.4764729141953341,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498387386774486,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.16668929606676103,
|
|
"num_tokens": 11014834.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.74824743270874,
|
|
"epoch": 0.4769671807038355,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000498383166472104,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.17305494248867034,
|
|
"num_tokens": 11026116.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.7953392505645756,
|
|
"epoch": 0.4774614472123369,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983789406744615,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.17153684049844742,
|
|
"num_tokens": 11038780.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.897364330291748,
|
|
"epoch": 0.4779557137208383,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983747093816625,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.17048557847738266,
|
|
"num_tokens": 11049824.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.761606454849243,
|
|
"epoch": 0.47844998022933966,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983704725938108,
|
|
"loss": 5.5351,
|
|
"mean_token_accuracy": 0.1786967322230339,
|
|
"num_tokens": 11060863.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.732560920715332,
|
|
"epoch": 0.47894424673784103,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498366230311011,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.17488910108804703,
|
|
"num_tokens": 11072533.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.747886800765992,
|
|
"epoch": 0.4794385132463424,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983619825333671,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.17575133293867112,
|
|
"num_tokens": 11083627.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.860506629943847,
|
|
"epoch": 0.47993277975484383,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983577292609839,
|
|
"loss": 5.7019,
|
|
"mean_token_accuracy": 0.1633409082889557,
|
|
"num_tokens": 11096421.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.758524656295776,
|
|
"epoch": 0.4804270462633452,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983534704939659,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16786952167749405,
|
|
"num_tokens": 11109053.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.763889265060425,
|
|
"epoch": 0.4809213127718466,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983492062324179,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.1796043336391449,
|
|
"num_tokens": 11120431.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.772010707855225,
|
|
"epoch": 0.48141557928034795,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983449364764447,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.17402093708515168,
|
|
"num_tokens": 11132767.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.7384312629699705,
|
|
"epoch": 0.4819098457888493,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983406612261514,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.17281497567892073,
|
|
"num_tokens": 11144508.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.754504060745239,
|
|
"epoch": 0.48240411229735075,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983363804816433,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.17433478832244872,
|
|
"num_tokens": 11156905.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.790156269073487,
|
|
"epoch": 0.4828983788058521,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983320942430256,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.1798376262187958,
|
|
"num_tokens": 11169383.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.767265319824219,
|
|
"epoch": 0.4833926453143535,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983278025104036,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.1851058930158615,
|
|
"num_tokens": 11179795.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.776008224487304,
|
|
"epoch": 0.48388691182285487,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498323505283883,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.166591776907444,
|
|
"num_tokens": 11190783.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.878120708465576,
|
|
"epoch": 0.48438117833135624,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983192025635698,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.16896193027496337,
|
|
"num_tokens": 11203000.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.807617330551148,
|
|
"epoch": 0.48487544483985767,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983148943495693,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.16904626190662383,
|
|
"num_tokens": 11213721.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.807488822937012,
|
|
"epoch": 0.48536971134835905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983105806419878,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1656417280435562,
|
|
"num_tokens": 11224490.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.816106748580933,
|
|
"epoch": 0.4858639778568604,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004983062614409314,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.1777344286441803,
|
|
"num_tokens": 11235022.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.793050861358642,
|
|
"epoch": 0.4863582443653618,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983019367465064,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.16975762099027633,
|
|
"num_tokens": 11247485.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.753307914733886,
|
|
"epoch": 0.48685251087386316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498297606558819,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.18103411495685579,
|
|
"num_tokens": 11258488.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.752778434753418,
|
|
"epoch": 0.4873467773823646,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004982932708779759,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.17985471934080124,
|
|
"num_tokens": 11270786.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.886114311218262,
|
|
"epoch": 0.48784104389086597,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982889297040836,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.1702333375811577,
|
|
"num_tokens": 11282434.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.779879140853882,
|
|
"epoch": 0.48833531039936734,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982845830372491,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.17203909456729888,
|
|
"num_tokens": 11292406.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.893464851379394,
|
|
"epoch": 0.4888295769078687,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982802308775791,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.16397708654403687,
|
|
"num_tokens": 11304491.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.8376823425292965,
|
|
"epoch": 0.4893238434163701,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498275873225181,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.16995202153921127,
|
|
"num_tokens": 11317038.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.7879523754119875,
|
|
"epoch": 0.4898181099248715,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004982715100801616,
|
|
"loss": 5.6255,
|
|
"mean_token_accuracy": 0.17164080440998078,
|
|
"num_tokens": 11329354.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.823068714141845,
|
|
"epoch": 0.4903123764333729,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982671414426285,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17055580019950867,
|
|
"num_tokens": 11340508.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.75929479598999,
|
|
"epoch": 0.49080664294187426,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982627673126889,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.17654407620429993,
|
|
"num_tokens": 11352608.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.774344491958618,
|
|
"epoch": 0.49130090945037563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982583876904508,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.174379463493824,
|
|
"num_tokens": 11364089.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.7411417961120605,
|
|
"epoch": 0.491795175958877,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982540025760217,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.17841892540454865,
|
|
"num_tokens": 11375521.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.75401611328125,
|
|
"epoch": 0.49228944246737844,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004982496119695094,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.17747943848371506,
|
|
"num_tokens": 11387721.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.8155148983001705,
|
|
"epoch": 0.4927837089758798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498245215871022,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.17238590121269226,
|
|
"num_tokens": 11398688.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.775302314758301,
|
|
"epoch": 0.4932779754843812,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982408142806678,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.1715422198176384,
|
|
"num_tokens": 11410420.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.730592966079712,
|
|
"epoch": 0.49377224199288255,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982364071985549,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.1779486283659935,
|
|
"num_tokens": 11420521.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.839930009841919,
|
|
"epoch": 0.4942665085013839,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982319946247917,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.16767350286245347,
|
|
"num_tokens": 11432550.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.845134305953979,
|
|
"epoch": 0.49476077500988536,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982275765594869,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.16987244784832,
|
|
"num_tokens": 11444602.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.698256492614746,
|
|
"epoch": 0.49525504151838673,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982231530027489,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.1847676157951355,
|
|
"num_tokens": 11456187.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.73066554069519,
|
|
"epoch": 0.4957493080268881,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004982187239546868,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.17178757935762407,
|
|
"num_tokens": 11468615.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.82112340927124,
|
|
"epoch": 0.4962435745353895,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982142894154095,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.17167694121599197,
|
|
"num_tokens": 11480865.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.835798645019532,
|
|
"epoch": 0.49673784104389085,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498209849385026,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.16441622376441956,
|
|
"num_tokens": 11492590.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.828628826141357,
|
|
"epoch": 0.4972321075523923,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982054038636456,
|
|
"loss": 5.5994,
|
|
"mean_token_accuracy": 0.1767118379473686,
|
|
"num_tokens": 11503481.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.75640377998352,
|
|
"epoch": 0.49772637406089365,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004982009528513776,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.1742475911974907,
|
|
"num_tokens": 11515083.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.744735908508301,
|
|
"epoch": 0.498220640569395,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981964963483316,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.16762128323316575,
|
|
"num_tokens": 11527923.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.806128787994385,
|
|
"epoch": 0.4987149070778964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981920343546171,
|
|
"loss": 5.6242,
|
|
"mean_token_accuracy": 0.17232828587293625,
|
|
"num_tokens": 11539456.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.8579912185668945,
|
|
"epoch": 0.49920917358639777,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498187566870344,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.17905319184064866,
|
|
"num_tokens": 11550809.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.844864320755005,
|
|
"epoch": 0.49970344009489914,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981830938956221,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.1694789245724678,
|
|
"num_tokens": 11562545.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.684816217422485,
|
|
"epoch": 0.5001977066034006,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981786154305615,
|
|
"loss": 5.5496,
|
|
"mean_token_accuracy": 0.1772656634449959,
|
|
"num_tokens": 11574479.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.833620500564575,
|
|
"epoch": 0.500691973111902,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981741314752722,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.1810210108757019,
|
|
"num_tokens": 11583942.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.795402908325196,
|
|
"epoch": 0.5011862396204033,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981696420298647,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.1765076547861099,
|
|
"num_tokens": 11596745.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.678934144973755,
|
|
"epoch": 0.5016805061289047,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004981651470944495,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.18235170245170593,
|
|
"num_tokens": 11608950.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.705907011032105,
|
|
"epoch": 0.5021747726374061,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498160646669137,
|
|
"loss": 5.6211,
|
|
"mean_token_accuracy": 0.1725287452340126,
|
|
"num_tokens": 11619996.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.7708536148071286,
|
|
"epoch": 0.5026690391459074,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981561407540379,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.179334656894207,
|
|
"num_tokens": 11632167.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.74412727355957,
|
|
"epoch": 0.5031633056544088,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981516293492632,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.17766835987567903,
|
|
"num_tokens": 11643722.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.741613960266113,
|
|
"epoch": 0.5036575721629103,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981471124549237,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.18306994438171387,
|
|
"num_tokens": 11654890.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.780077838897705,
|
|
"epoch": 0.5041518386714117,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981425900711308,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1708131328225136,
|
|
"num_tokens": 11665485.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.757856941223144,
|
|
"epoch": 0.504646105179913,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981380621979954,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.1807607591152191,
|
|
"num_tokens": 11676145.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.746283102035522,
|
|
"epoch": 0.5051403716884144,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981335288356291,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17166837453842163,
|
|
"num_tokens": 11687777.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.780774974822998,
|
|
"epoch": 0.5056346381969158,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004981289899841434,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.17905764877796174,
|
|
"num_tokens": 11699703.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.799895524978638,
|
|
"epoch": 0.5061289047054172,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981244456436499,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.16529887765645981,
|
|
"num_tokens": 11711632.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.838253498077393,
|
|
"epoch": 0.5066231712139185,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004981198958142604,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.17375699877738954,
|
|
"num_tokens": 11723763.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.781112957000732,
|
|
"epoch": 0.5071174377224199,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004981153404960869,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.169736647605896,
|
|
"num_tokens": 11736061.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.7520177364349365,
|
|
"epoch": 0.5076117042309213,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981107796892414,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.17034420669078826,
|
|
"num_tokens": 11749342.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.83673939704895,
|
|
"epoch": 0.5081059707394227,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981062133938361,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.17624873220920562,
|
|
"num_tokens": 11760441.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.691654300689697,
|
|
"epoch": 0.508600237247924,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981016416099834,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.1785828486084938,
|
|
"num_tokens": 11772191.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.839021492004394,
|
|
"epoch": 0.5090945037564255,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980970643377956,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.16388301253318788,
|
|
"num_tokens": 11786347.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.824480104446411,
|
|
"epoch": 0.5095887702649269,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980924815773855,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.17841615229845048,
|
|
"num_tokens": 11797741.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.7572705268859865,
|
|
"epoch": 0.5100830367734283,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980878933288657,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.16382424384355546,
|
|
"num_tokens": 11809728.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.790679597854615,
|
|
"epoch": 0.5105773032819296,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498083299592349,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.16833973973989486,
|
|
"num_tokens": 11822000.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.793793964385986,
|
|
"epoch": 0.511071569790431,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980787003679486,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.17131773084402085,
|
|
"num_tokens": 11834059.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.663825464248657,
|
|
"epoch": 0.5115658362989324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980740956557776,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.18564523011446,
|
|
"num_tokens": 11844001.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.726988124847412,
|
|
"epoch": 0.5120601028074337,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004980694854559493,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.17274706214666366,
|
|
"num_tokens": 11855991.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.838094997406006,
|
|
"epoch": 0.5125543693159351,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498064869768577,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.18166578263044358,
|
|
"num_tokens": 11867975.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.738130235671997,
|
|
"epoch": 0.5130486358244365,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980602485937743,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.17443735152482986,
|
|
"num_tokens": 11880034.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.822977781295776,
|
|
"epoch": 0.5135429023329379,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980556219316549,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.17538013756275178,
|
|
"num_tokens": 11891490.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.8056519508361815,
|
|
"epoch": 0.5140371688414394,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980509897823326,
|
|
"loss": 5.5061,
|
|
"mean_token_accuracy": 0.1805155858397484,
|
|
"num_tokens": 11902988.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.771095228195191,
|
|
"epoch": 0.5145314353499407,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980463521459212,
|
|
"loss": 5.5572,
|
|
"mean_token_accuracy": 0.17159489244222642,
|
|
"num_tokens": 11915088.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.744380903244019,
|
|
"epoch": 0.5150257018584421,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980417090225351,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1802521362900734,
|
|
"num_tokens": 11926789.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.84690670967102,
|
|
"epoch": 0.5155199683669435,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980370604122883,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.17123763561248778,
|
|
"num_tokens": 11938876.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.80683331489563,
|
|
"epoch": 0.5160142348754448,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980324063152952,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.17346588969230653,
|
|
"num_tokens": 11950099.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.814678430557251,
|
|
"epoch": 0.5165085013839462,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980277467316704,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.1707424610853195,
|
|
"num_tokens": 11962585.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.7683158874511715,
|
|
"epoch": 0.5170027678924476,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980230816615282,
|
|
"loss": 5.5503,
|
|
"mean_token_accuracy": 0.17995088100433348,
|
|
"num_tokens": 11972579.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.750294351577759,
|
|
"epoch": 0.517497034400949,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980184111049837,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.1822764351963997,
|
|
"num_tokens": 11983337.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.768231058120728,
|
|
"epoch": 0.5179913009094503,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980137350621518,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.17121624797582627,
|
|
"num_tokens": 11995086.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.806021642684937,
|
|
"epoch": 0.5184855674179517,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004980090535331473,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.17547132670879365,
|
|
"num_tokens": 12007814.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.683626890182495,
|
|
"epoch": 0.5189798339264532,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004980043665180857,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.1842152625322342,
|
|
"num_tokens": 12020714.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.758127641677857,
|
|
"epoch": 0.5194741004349546,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979996740170819,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.17521584779024124,
|
|
"num_tokens": 12031994.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.808197927474976,
|
|
"epoch": 0.5199683669434559,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979949760302515,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.17272645235061646,
|
|
"num_tokens": 12042887.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.782262372970581,
|
|
"epoch": 0.5204626334519573,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979902725577101,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.177044178545475,
|
|
"num_tokens": 12054426.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.756087017059326,
|
|
"epoch": 0.5209568999604587,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979855635995735,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.17331088930368424,
|
|
"num_tokens": 12066360.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.85052261352539,
|
|
"epoch": 0.5214511664689601,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004979808491559573,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.16670458763837814,
|
|
"num_tokens": 12076651.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.771056127548218,
|
|
"epoch": 0.5219454329774614,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004979761292269778,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.17414287924766542,
|
|
"num_tokens": 12087522.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.761127662658692,
|
|
"epoch": 0.5224396994859628,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004979714038127508,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.17948328703641891,
|
|
"num_tokens": 12097999.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.718210601806641,
|
|
"epoch": 0.5229339659944642,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979666729133927,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.1711346134543419,
|
|
"num_tokens": 12108080.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.881346368789673,
|
|
"epoch": 0.5234282325029656,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979619365290199,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.15981903672218323,
|
|
"num_tokens": 12122705.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.837782144546509,
|
|
"epoch": 0.523922499011467,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979571946597488,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.17717295587062837,
|
|
"num_tokens": 12134000.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.725484991073609,
|
|
"epoch": 0.5244167655199684,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979524473056961,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.17184950709342955,
|
|
"num_tokens": 12144825.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.820409774780273,
|
|
"epoch": 0.5249110320284698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979476944669787,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.1701199322938919,
|
|
"num_tokens": 12156590.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.804708576202392,
|
|
"epoch": 0.5254052985369712,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979429361437134,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.18055262863636018,
|
|
"num_tokens": 12167478.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.747417736053467,
|
|
"epoch": 0.5258995650454725,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979381723360173,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.17926698178052902,
|
|
"num_tokens": 12178728.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.686006307601929,
|
|
"epoch": 0.5263938315539739,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979334030440076,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.17048746943473816,
|
|
"num_tokens": 12190061.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.760270595550537,
|
|
"epoch": 0.5268880980624753,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979286282678015,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.17671838849782945,
|
|
"num_tokens": 12200867.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.807965469360352,
|
|
"epoch": 0.5273823645709766,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004979238480075166,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.17594483196735383,
|
|
"num_tokens": 12212681.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.717815256118774,
|
|
"epoch": 0.527876631079478,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979190622632705,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.1718001186847687,
|
|
"num_tokens": 12224279.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.644581842422485,
|
|
"epoch": 0.5283708975879794,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979142710351809,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.19358813017606735,
|
|
"num_tokens": 12235754.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.827294206619262,
|
|
"epoch": 0.5288651640964809,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979094743233656,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.17078588604927064,
|
|
"num_tokens": 12246014.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.72751259803772,
|
|
"epoch": 0.5293594306049823,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979046721279426,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.1794961079955101,
|
|
"num_tokens": 12257519.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.747145128250122,
|
|
"epoch": 0.5298536971134836,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004978998644490302,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.17280252277851105,
|
|
"num_tokens": 12269806.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.7658251285552975,
|
|
"epoch": 0.530347963621985,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004978950512867465,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.17104875147342682,
|
|
"num_tokens": 12281612.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.753850746154785,
|
|
"epoch": 0.5308422301304864,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978902326412099,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.17531534731388093,
|
|
"num_tokens": 12293022.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.773637151718139,
|
|
"epoch": 0.5313364966389877,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497885408512539,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.17462725639343263,
|
|
"num_tokens": 12304414.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.884887838363648,
|
|
"epoch": 0.5318307631474891,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978805789008526,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.16161142140626908,
|
|
"num_tokens": 12315618.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.784448099136353,
|
|
"epoch": 0.5323250296559905,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978757438062692,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.18568605333566665,
|
|
"num_tokens": 12328026.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.714285135269165,
|
|
"epoch": 0.5328192961644919,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978709032289081,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.17499915808439254,
|
|
"num_tokens": 12339441.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.8693047046661375,
|
|
"epoch": 0.5333135626729932,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978660571688881,
|
|
"loss": 5.5846,
|
|
"mean_token_accuracy": 0.17316054701805114,
|
|
"num_tokens": 12351005.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.7560142993927,
|
|
"epoch": 0.5338078291814946,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978612056263286,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.1801098331809044,
|
|
"num_tokens": 12363147.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.758735609054566,
|
|
"epoch": 0.5343020956899961,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978563486013488,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.17649147361516954,
|
|
"num_tokens": 12373446.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.721365737915039,
|
|
"epoch": 0.5347963621984975,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978514860940683,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.1789020672440529,
|
|
"num_tokens": 12384591.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.714781665802002,
|
|
"epoch": 0.5352906287069988,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978466181046067,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.17836556285619737,
|
|
"num_tokens": 12396117.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.737146425247192,
|
|
"epoch": 0.5357848952155002,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978417446330837,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.18124449849128724,
|
|
"num_tokens": 12407400.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.733011627197266,
|
|
"epoch": 0.5362791617240016,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004978368656796191,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.18468766957521437,
|
|
"num_tokens": 12417629.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.679784297943115,
|
|
"epoch": 0.536773428232503,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978319812443331,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.18626576960086821,
|
|
"num_tokens": 12428522.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.778678750991821,
|
|
"epoch": 0.5372676947410043,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978270913273458,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.1696370154619217,
|
|
"num_tokens": 12440390.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.722135162353515,
|
|
"epoch": 0.5377619612495057,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978221959287775,
|
|
"loss": 5.4891,
|
|
"mean_token_accuracy": 0.1793165847659111,
|
|
"num_tokens": 12451846.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.736186552047729,
|
|
"epoch": 0.5382562277580071,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978172950487486,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.18181947022676467,
|
|
"num_tokens": 12462051.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.72767391204834,
|
|
"epoch": 0.5387504942665085,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978123886873797,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.18565606623888015,
|
|
"num_tokens": 12472730.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.714382457733154,
|
|
"epoch": 0.5392447607750099,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978074768447915,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.18636564016342164,
|
|
"num_tokens": 12482719.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.759675645828247,
|
|
"epoch": 0.5397390272835113,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978025595211048,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.178179569542408,
|
|
"num_tokens": 12492659.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.803636932373047,
|
|
"epoch": 0.5402332937920127,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004977976367164404,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.18235886394977568,
|
|
"num_tokens": 12504381.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.713931465148926,
|
|
"epoch": 0.540727560300514,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977927084309198,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.19028392285108567,
|
|
"num_tokens": 12515041.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.778231859207153,
|
|
"epoch": 0.5412218268090154,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977877746646639,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.17734709233045579,
|
|
"num_tokens": 12526313.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.78344693183899,
|
|
"epoch": 0.5417160933175168,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977828354177941,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.16407859474420547,
|
|
"num_tokens": 12538268.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.80599570274353,
|
|
"epoch": 0.5422103598260182,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004977778906904321,
|
|
"loss": 5.5419,
|
|
"mean_token_accuracy": 0.17868427336215972,
|
|
"num_tokens": 12548365.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.8335600852966305,
|
|
"epoch": 0.5427046263345195,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004977729404826995,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.16520809680223464,
|
|
"num_tokens": 12560652.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.7249761581420895,
|
|
"epoch": 0.5431988928430209,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004977679847947179,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.17777654379606248,
|
|
"num_tokens": 12572079.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.692812252044678,
|
|
"epoch": 0.5436931593515223,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977630236266093,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.18401208221912385,
|
|
"num_tokens": 12582601.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.757671642303467,
|
|
"epoch": 0.5441874258600238,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977580569784958,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.17192913889884948,
|
|
"num_tokens": 12595176.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.774952411651611,
|
|
"epoch": 0.5446816923685251,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977530848504994,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.17247545272111892,
|
|
"num_tokens": 12608161.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.733337450027466,
|
|
"epoch": 0.5451759588770265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977481072427427,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.17189727872610092,
|
|
"num_tokens": 12620109.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.800567626953125,
|
|
"epoch": 0.5456702253855279,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497743124155348,
|
|
"loss": 5.5808,
|
|
"mean_token_accuracy": 0.17410012185573578,
|
|
"num_tokens": 12630339.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.743124771118164,
|
|
"epoch": 0.5461644918940293,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977381355884379,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.17426336109638213,
|
|
"num_tokens": 12642101.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.830995035171509,
|
|
"epoch": 0.5466587584025306,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977331415421351,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.16365431249141693,
|
|
"num_tokens": 12655436.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.704841995239258,
|
|
"epoch": 0.547153024911032,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977281420165624,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.18484551161527635,
|
|
"num_tokens": 12667100.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.728894424438477,
|
|
"epoch": 0.5476472914195334,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497723137011843,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.1720960780978203,
|
|
"num_tokens": 12678788.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.749471235275268,
|
|
"epoch": 0.5481415579280348,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004977181265280997,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.18557162582874298,
|
|
"num_tokens": 12690980.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.806805658340454,
|
|
"epoch": 0.5486358244365361,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497713110565456,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.1691083773970604,
|
|
"num_tokens": 12702642.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.682715511322021,
|
|
"epoch": 0.5491300909450376,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977080891240352,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.1857164591550827,
|
|
"num_tokens": 12712750.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.676763010025025,
|
|
"epoch": 0.549624357453539,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497703062203961,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.1835971713066101,
|
|
"num_tokens": 12724464.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.707128715515137,
|
|
"epoch": 0.5501186239620404,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976980298053567,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.17907305359840392,
|
|
"num_tokens": 12735419.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.786734914779663,
|
|
"epoch": 0.5506128904705417,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976929919283465,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.17892698645591737,
|
|
"num_tokens": 12746279.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.759409761428833,
|
|
"epoch": 0.5511071569790431,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004976879485730541,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.17511751651763915,
|
|
"num_tokens": 12758107.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.74146876335144,
|
|
"epoch": 0.5516014234875445,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976828997396036,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.18297296315431594,
|
|
"num_tokens": 12769354.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.758933639526367,
|
|
"epoch": 0.5520956899960459,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976778454281193,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.17354206144809722,
|
|
"num_tokens": 12780926.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.787692737579346,
|
|
"epoch": 0.5525899565045472,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976727856387253,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.17749321311712266,
|
|
"num_tokens": 12792423.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.695298957824707,
|
|
"epoch": 0.5530842230130486,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004976677203715464,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.1868865191936493,
|
|
"num_tokens": 12803688.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.6502316951751705,
|
|
"epoch": 0.55357848952155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497662649626707,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.18135617524385453,
|
|
"num_tokens": 12814617.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.69397349357605,
|
|
"epoch": 0.5540727560300513,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004976575734043318,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.17544914335012435,
|
|
"num_tokens": 12826027.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.719434452056885,
|
|
"epoch": 0.5545670225385528,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976524917045457,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.1705397292971611,
|
|
"num_tokens": 12837454.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.689467716217041,
|
|
"epoch": 0.5550612890470542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497647404527474,
|
|
"loss": 5.4336,
|
|
"mean_token_accuracy": 0.17773413360118867,
|
|
"num_tokens": 12848550.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.722694396972656,
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976423118732413,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.1816477209329605,
|
|
"num_tokens": 12858270.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.654467916488647,
|
|
"epoch": 0.556049822064057,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976372137419733,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.1788386359810829,
|
|
"num_tokens": 12869507.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.737163782119751,
|
|
"epoch": 0.5565440885725583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004976321101337954,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.18255448937416077,
|
|
"num_tokens": 12880097.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.667933368682862,
|
|
"epoch": 0.5570383550810597,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497627001048833,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.1818331375718117,
|
|
"num_tokens": 12891302.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.656579065322876,
|
|
"epoch": 0.5575326215895611,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004976218864872118,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.1905026078224182,
|
|
"num_tokens": 12903950.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.692523384094239,
|
|
"epoch": 0.5580268880980624,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976167664490576,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.17595995217561722,
|
|
"num_tokens": 12915713.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.690003156661987,
|
|
"epoch": 0.5585211546065638,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976116409344966,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.1829339236021042,
|
|
"num_tokens": 12926655.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.695260763168335,
|
|
"epoch": 0.5590154211150652,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004976065099436546,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.18093121349811553,
|
|
"num_tokens": 12938144.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.7835081100463865,
|
|
"epoch": 0.5595096876235667,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004976013734766579,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.17341161221265794,
|
|
"num_tokens": 12950486.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.676397037506104,
|
|
"epoch": 0.560003954132068,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497596231533633,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.19318064153194428,
|
|
"num_tokens": 12960966.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.62633786201477,
|
|
"epoch": 0.5604982206405694,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000497591084114706,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.17677472084760665,
|
|
"num_tokens": 12971960.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.742179298400879,
|
|
"epoch": 0.5609924871490708,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497585931220004,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.17461706101894378,
|
|
"num_tokens": 12984186.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.698014545440674,
|
|
"epoch": 0.5614867536575722,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975807728496535,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.19021368771791458,
|
|
"num_tokens": 12994205.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.76334228515625,
|
|
"epoch": 0.5619810201660735,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004975756090037815,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.17858278900384902,
|
|
"num_tokens": 13006143.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.787828063964843,
|
|
"epoch": 0.5624752866745749,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000497570439682515,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1784708470106125,
|
|
"num_tokens": 13017849.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.556822872161865,
|
|
"epoch": 0.5629695531830763,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497565264885981,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.18541548997163773,
|
|
"num_tokens": 13030301.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.736711740493774,
|
|
"epoch": 0.5634638196915777,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004975600846143072,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.18181895613670349,
|
|
"num_tokens": 13040229.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.723695230484009,
|
|
"epoch": 0.563958086200079,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004975548988676206,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.184915491938591,
|
|
"num_tokens": 13050752.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.724451875686645,
|
|
"epoch": 0.5644523527085805,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975497076460491,
|
|
"loss": 5.6137,
|
|
"mean_token_accuracy": 0.16811935752630233,
|
|
"num_tokens": 13062003.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.731402015686035,
|
|
"epoch": 0.5649466192170819,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975445109497202,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.16912083178758622,
|
|
"num_tokens": 13073746.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.8177405834198,
|
|
"epoch": 0.5654408857255833,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004975393087787617,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.16762364655733109,
|
|
"num_tokens": 13086068.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.747670316696167,
|
|
"epoch": 0.5659351522340846,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004975341011333019,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.17420125305652617,
|
|
"num_tokens": 13097078.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.71416392326355,
|
|
"epoch": 0.566429418742586,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004975288880134685,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.17938829362392425,
|
|
"num_tokens": 13108450.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.715784931182862,
|
|
"epoch": 0.5669236852510874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975236694193901,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.17660179734230042,
|
|
"num_tokens": 13120216.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.715113353729248,
|
|
"epoch": 0.5674179517595888,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004975184453511948,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.17144474685192107,
|
|
"num_tokens": 13131214.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.777291917800904,
|
|
"epoch": 0.5679122182680901,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975132158090112,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.1721394255757332,
|
|
"num_tokens": 13143792.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.686273527145386,
|
|
"epoch": 0.5684064847765915,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497507980792968,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.17619652599096297,
|
|
"num_tokens": 13156022.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.732636404037476,
|
|
"epoch": 0.5689007512850929,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497502740303194,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.1848985359072685,
|
|
"num_tokens": 13167374.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.702525520324707,
|
|
"epoch": 0.5693950177935944,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497497494339818,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.18368844240903853,
|
|
"num_tokens": 13177662.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.71856722831726,
|
|
"epoch": 0.5698892843020957,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974922429029692,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.1769362986087799,
|
|
"num_tokens": 13188375.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.725184345245362,
|
|
"epoch": 0.5703835508105971,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974869859927767,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.1829233556985855,
|
|
"num_tokens": 13198988.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.75066499710083,
|
|
"epoch": 0.5708778173190985,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974817236093697,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.1693466141819954,
|
|
"num_tokens": 13210699.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.63893141746521,
|
|
"epoch": 0.5713720838275999,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974764557528779,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.18506574779748916,
|
|
"num_tokens": 13221925.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.719260883331299,
|
|
"epoch": 0.5718663503361012,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974711824234308,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.17589188367128372,
|
|
"num_tokens": 13233278.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.768571138381958,
|
|
"epoch": 0.5723606168446026,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497465903621158,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.17983630001544954,
|
|
"num_tokens": 13245423.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.738625240325928,
|
|
"epoch": 0.572854883353104,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974606193461895,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.18063973784446716,
|
|
"num_tokens": 13256312.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.735036182403564,
|
|
"epoch": 0.5733491498616053,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004974553295986553,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.17640191316604614,
|
|
"num_tokens": 13268158.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.740165710449219,
|
|
"epoch": 0.5738434163701067,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004974500343786854,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.18072212785482406,
|
|
"num_tokens": 13279625.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.749358749389648,
|
|
"epoch": 0.5743376828786081,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004974447336864102,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.17794628590345382,
|
|
"num_tokens": 13291967.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.602593231201172,
|
|
"epoch": 0.5748319493871096,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049743942752196,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.19058725386857986,
|
|
"num_tokens": 13303641.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.683610582351685,
|
|
"epoch": 0.575326215895611,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974341158854654,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.1757155492901802,
|
|
"num_tokens": 13314754.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.693660020828247,
|
|
"epoch": 0.5758204824041123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974287987770571,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.17383753061294555,
|
|
"num_tokens": 13325574.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.7115068435668945,
|
|
"epoch": 0.5763147489126137,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974234761968658,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.18795131742954255,
|
|
"num_tokens": 13335946.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.728109359741211,
|
|
"epoch": 0.5768090154211151,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004974181481450224,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.18762592375278472,
|
|
"num_tokens": 13347812.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.65715970993042,
|
|
"epoch": 0.5773032819296164,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004974128146216581,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.179990316927433,
|
|
"num_tokens": 13358492.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.792056941986084,
|
|
"epoch": 0.5777975484381178,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974074756269042,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.17083921730518342,
|
|
"num_tokens": 13370465.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.757367944717407,
|
|
"epoch": 0.5782918149466192,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004974021311608917,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.18890322297811507,
|
|
"num_tokens": 13382328.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.696540975570679,
|
|
"epoch": 0.5787860814551206,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973967812237523,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.17575131952762604,
|
|
"num_tokens": 13393439.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.700885200500489,
|
|
"epoch": 0.5792803479636219,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973914258156177,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.17841797769069673,
|
|
"num_tokens": 13404778.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.7527289390563965,
|
|
"epoch": 0.5797746144721234,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004973860649366195,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.18216743618249892,
|
|
"num_tokens": 13417031.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.719571590423584,
|
|
"epoch": 0.5802688809806248,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004973806985868895,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.18248441964387893,
|
|
"num_tokens": 13428030.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.7111420154571535,
|
|
"epoch": 0.5807631474891262,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973753267665599,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.18524419367313386,
|
|
"num_tokens": 13438934.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.714941215515137,
|
|
"epoch": 0.5812574139976275,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973699494757627,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.17472849637269974,
|
|
"num_tokens": 13450542.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.673115491867065,
|
|
"epoch": 0.5817516805061289,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004973645667146302,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.18238535523414612,
|
|
"num_tokens": 13462382.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.741902160644531,
|
|
"epoch": 0.5822459470146303,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973591784832949,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.17877876311540603,
|
|
"num_tokens": 13473852.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.752352094650268,
|
|
"epoch": 0.5827402135231317,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004973537847818894,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.176455520093441,
|
|
"num_tokens": 13485763.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.6837280750274655,
|
|
"epoch": 0.583234480031633,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004973483856105462,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.17691107243299484,
|
|
"num_tokens": 13498154.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.812195873260498,
|
|
"epoch": 0.5837287465401344,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004973429809693983,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.17449950724840163,
|
|
"num_tokens": 13510563.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.851145839691162,
|
|
"epoch": 0.5842230130486358,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004973375708585785,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.1754000350832939,
|
|
"num_tokens": 13521987.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.73386697769165,
|
|
"epoch": 0.5847172795571373,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973321552782201,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.17520942091941832,
|
|
"num_tokens": 13534075.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.754039716720581,
|
|
"epoch": 0.5852115460656386,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000497326734228456,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.16962009221315383,
|
|
"num_tokens": 13546201.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.766037034988403,
|
|
"epoch": 0.58570581257414,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973213077094199,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.18465032577514648,
|
|
"num_tokens": 13556985.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.782201862335205,
|
|
"epoch": 0.5862000790826414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973158757212451,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.18101984709501268,
|
|
"num_tokens": 13568617.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.699190378189087,
|
|
"epoch": 0.5866943455911428,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973104382640652,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.18187535405158997,
|
|
"num_tokens": 13581326.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.667532730102539,
|
|
"epoch": 0.5871886120996441,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973049953380141,
|
|
"loss": 5.4649,
|
|
"mean_token_accuracy": 0.17698167711496354,
|
|
"num_tokens": 13591776.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.793080759048462,
|
|
"epoch": 0.5876828786081455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972995469432256,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.17576271593570708,
|
|
"num_tokens": 13603475.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.731459617614746,
|
|
"epoch": 0.5881771451166469,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972940930798338,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.17928755432367324,
|
|
"num_tokens": 13615348.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.633429050445557,
|
|
"epoch": 0.5886714116251482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972886337479727,
|
|
"loss": 5.3704,
|
|
"mean_token_accuracy": 0.18748244941234588,
|
|
"num_tokens": 13625982.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.74733533859253,
|
|
"epoch": 0.5891656781336496,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972831689477768,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.17600917518138887,
|
|
"num_tokens": 13637203.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.699123191833496,
|
|
"epoch": 0.5896599446421511,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004972776986793806,
|
|
"loss": 5.4367,
|
|
"mean_token_accuracy": 0.1801018312573433,
|
|
"num_tokens": 13648880.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.731894826889038,
|
|
"epoch": 0.5901542111506525,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972722229429184,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1764528974890709,
|
|
"num_tokens": 13660266.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.8591515064239506,
|
|
"epoch": 0.5906484776591538,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000497266741738525,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.1685237005352974,
|
|
"num_tokens": 13672063.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.797526502609253,
|
|
"epoch": 0.5911427441676552,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972612550663353,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.18678943663835526,
|
|
"num_tokens": 13683379.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.670707130432129,
|
|
"epoch": 0.5916370106761566,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004972557629264842,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.1874980717897415,
|
|
"num_tokens": 13694512.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.649473810195923,
|
|
"epoch": 0.592131277184658,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972502653191069,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.1757025897502899,
|
|
"num_tokens": 13705642.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.607302522659301,
|
|
"epoch": 0.5926255436931593,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972447622443387,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.19193902164697646,
|
|
"num_tokens": 13717367.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.68580436706543,
|
|
"epoch": 0.5931198102016607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972392537023147,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.18161719143390656,
|
|
"num_tokens": 13728577.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5931198102016607,
|
|
"eval_entropy": 5.543885540229075,
|
|
"eval_loss": 5.5077314376831055,
|
|
"eval_mean_token_accuracy": 0.18510187076356577,
|
|
"eval_num_tokens": 13728577.0,
|
|
"eval_runtime": 20.3407,
|
|
"eval_samples_per_second": 1598.419,
|
|
"eval_steps_per_second": 199.845,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.693338632583618,
|
|
"epoch": 0.5936140767101621,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004972337396931707,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.17748550027608873,
|
|
"num_tokens": 13739016.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.71715931892395,
|
|
"epoch": 0.5941083432186635,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972282202170421,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.17308816090226173,
|
|
"num_tokens": 13749971.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.751609849929809,
|
|
"epoch": 0.5946026097271648,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497222695274065,
|
|
"loss": 5.5131,
|
|
"mean_token_accuracy": 0.17564282119274138,
|
|
"num_tokens": 13760927.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.713732385635376,
|
|
"epoch": 0.5950968762356663,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972171648643749,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.17753133326768875,
|
|
"num_tokens": 13772725.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.656687498092651,
|
|
"epoch": 0.5955911427441677,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004972116289881082,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.18235348165035248,
|
|
"num_tokens": 13783427.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.675543308258057,
|
|
"epoch": 0.5960854092526691,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497206087645401,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.1879747837781906,
|
|
"num_tokens": 13794045.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.708596134185791,
|
|
"epoch": 0.5965796757611704,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972005408363894,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.18292929530143737,
|
|
"num_tokens": 13805629.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.68604793548584,
|
|
"epoch": 0.5970739422696718,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971949885612102,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.17549283504486085,
|
|
"num_tokens": 13817526.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.755584383010865,
|
|
"epoch": 0.5975682087781732,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971894308199997,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.18744254857301712,
|
|
"num_tokens": 13828553.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.711791324615478,
|
|
"epoch": 0.5980624752866746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971838676128947,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.18320010602474213,
|
|
"num_tokens": 13840323.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.6459356307983395,
|
|
"epoch": 0.5985567417951759,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004971782989400323,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.18255051523447036,
|
|
"num_tokens": 13853524.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.678977108001709,
|
|
"epoch": 0.5990510083036773,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004971727248015491,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.17558186650276184,
|
|
"num_tokens": 13864462.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.720080327987671,
|
|
"epoch": 0.5995452748121787,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971671451975823,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.1817041128873825,
|
|
"num_tokens": 13876615.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.739533758163452,
|
|
"epoch": 0.6000395413206802,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971615601282695,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.17829847931861878,
|
|
"num_tokens": 13887652.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.691545486450195,
|
|
"epoch": 0.6005338078291815,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004971559695937477,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.18535303324460983,
|
|
"num_tokens": 13898961.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.772193145751953,
|
|
"epoch": 0.6010280743376829,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971503735941547,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.18379769772291182,
|
|
"num_tokens": 13909904.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.781509637832642,
|
|
"epoch": 0.6015223408461843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497144772129628,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.1743398889899254,
|
|
"num_tokens": 13921376.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.669444561004639,
|
|
"epoch": 0.6020166073546857,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971391652003054,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.18568859994411469,
|
|
"num_tokens": 13932925.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.6786703109741214,
|
|
"epoch": 0.602510873863187,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497133552806325,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.18331165611743927,
|
|
"num_tokens": 13945010.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.706253242492676,
|
|
"epoch": 0.6030051403716884,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004971279349478245,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.16978354305028914,
|
|
"num_tokens": 13957710.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.6717077732086185,
|
|
"epoch": 0.6034994068801898,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004971223116249424,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.19802093803882598,
|
|
"num_tokens": 13967819.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.81233229637146,
|
|
"epoch": 0.6039936733886911,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971166828378172,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.16502135545015334,
|
|
"num_tokens": 13980342.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.7933876514434814,
|
|
"epoch": 0.6044879398971925,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000497111048586587,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17665462493896483,
|
|
"num_tokens": 13990370.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.74040117263794,
|
|
"epoch": 0.604982206405694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971054088713905,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.18113837242126465,
|
|
"num_tokens": 14001761.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.712833499908447,
|
|
"epoch": 0.6054764729141954,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970997636923665,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.17608647644519806,
|
|
"num_tokens": 14012980.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.735250759124756,
|
|
"epoch": 0.6059707394226967,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000497094113049654,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.1825260877609253,
|
|
"num_tokens": 14023609.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.718038272857666,
|
|
"epoch": 0.6064650059311981,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970884569433917,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.17623211890459062,
|
|
"num_tokens": 14036052.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.63355860710144,
|
|
"epoch": 0.6069592724396995,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000497082795373719,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.18857624679803847,
|
|
"num_tokens": 14047932.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.746037721633911,
|
|
"epoch": 0.6074535389482009,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970771283407749,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.1831844449043274,
|
|
"num_tokens": 14059674.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.774702501296997,
|
|
"epoch": 0.6079478054567022,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004970714558446992,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.17914710342884063,
|
|
"num_tokens": 14070753.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.706883811950684,
|
|
"epoch": 0.6084420719652036,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970657778856312,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.17967574745416642,
|
|
"num_tokens": 14083565.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.806309461593628,
|
|
"epoch": 0.608936338473705,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004970600944637106,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.1718636840581894,
|
|
"num_tokens": 14095008.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.6775635242462155,
|
|
"epoch": 0.6094306049822064,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004970544055790772,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.18482159674167634,
|
|
"num_tokens": 14106586.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.585059976577758,
|
|
"epoch": 0.6099248714907078,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497048711231871,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.18798351436853408,
|
|
"num_tokens": 14117778.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.679389190673828,
|
|
"epoch": 0.6104191379992092,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970430114222319,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.18183008581399918,
|
|
"num_tokens": 14129644.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.634195613861084,
|
|
"epoch": 0.6109134045077106,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970373061503005,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.18722597807645797,
|
|
"num_tokens": 14141230.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.713296222686767,
|
|
"epoch": 0.611407671016212,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970315954162169,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.1784057155251503,
|
|
"num_tokens": 14151622.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.786626958847046,
|
|
"epoch": 0.6119019375247133,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970258792201214,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.18192349523305892,
|
|
"num_tokens": 14163641.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.71040678024292,
|
|
"epoch": 0.6123962040332147,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000497020157562155,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.1838184729218483,
|
|
"num_tokens": 14175154.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.720538473129272,
|
|
"epoch": 0.6128904705417161,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970144304424582,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.18366681635379792,
|
|
"num_tokens": 14185472.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.685149717330932,
|
|
"epoch": 0.6133847370502175,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000497008697861172,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.1842101126909256,
|
|
"num_tokens": 14196992.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.6781305313110355,
|
|
"epoch": 0.6138790035587188,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970029598184375,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.17972283512353898,
|
|
"num_tokens": 14207732.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.831124305725098,
|
|
"epoch": 0.6143732700672202,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969972163143956,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.16833030581474304,
|
|
"num_tokens": 14219164.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.7736307144165036,
|
|
"epoch": 0.6148675365757216,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004969914673491878,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.1713523432612419,
|
|
"num_tokens": 14231687.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.731515979766845,
|
|
"epoch": 0.6153618030842231,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969857129229555,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1838352233171463,
|
|
"num_tokens": 14243099.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.7796424388885494,
|
|
"epoch": 0.6158560695927244,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969799530358402,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.17443785965442657,
|
|
"num_tokens": 14255835.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.639222145080566,
|
|
"epoch": 0.6163503361012258,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004969741876879835,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17747138887643815,
|
|
"num_tokens": 14266661.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.714282703399658,
|
|
"epoch": 0.6168446026097272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969684168795275,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.18221446871757507,
|
|
"num_tokens": 14278474.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.743070602416992,
|
|
"epoch": 0.6173388691182286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004969626406106139,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.17949046045541764,
|
|
"num_tokens": 14289516.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.6380690574646,
|
|
"epoch": 0.6178331356267299,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969568588813851,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.18283882290124892,
|
|
"num_tokens": 14301312.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.769012975692749,
|
|
"epoch": 0.6183274021352313,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004969510716919829,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.18169225454330445,
|
|
"num_tokens": 14312009.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.668433618545532,
|
|
"epoch": 0.6188216686437327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049694527904255,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.18407995700836183,
|
|
"num_tokens": 14322754.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.659542465209961,
|
|
"epoch": 0.619315935152234,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004969394809332287,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.18018449544906617,
|
|
"num_tokens": 14333939.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.687064218521118,
|
|
"epoch": 0.6198102016607354,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969336773641619,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18374679684638978,
|
|
"num_tokens": 14345987.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.765881681442261,
|
|
"epoch": 0.6203044681692369,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969278683354921,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1718706965446472,
|
|
"num_tokens": 14356974.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.717262840270996,
|
|
"epoch": 0.6207987346777383,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969220538473625,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.1765012577176094,
|
|
"num_tokens": 14368175.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.707417917251587,
|
|
"epoch": 0.6212930011862396,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969162338999157,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.17327929586172103,
|
|
"num_tokens": 14379067.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.778901672363281,
|
|
"epoch": 0.621787267694741,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969104084932953,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.17797669619321824,
|
|
"num_tokens": 14390483.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.703991556167603,
|
|
"epoch": 0.6222815342032424,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969045776276443,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.1764296755194664,
|
|
"num_tokens": 14402757.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.662689924240112,
|
|
"epoch": 0.6227758007117438,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004968987413031063,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.18288048207759858,
|
|
"num_tokens": 14413829.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.7220807552337645,
|
|
"epoch": 0.6232700672202451,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968928995198249,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.17076856046915054,
|
|
"num_tokens": 14425165.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.812552976608276,
|
|
"epoch": 0.6237643337287465,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968870522779437,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.1804996207356453,
|
|
"num_tokens": 14436264.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.6658447265625,
|
|
"epoch": 0.6242586002372479,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004968811995776066,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1808133065700531,
|
|
"num_tokens": 14447384.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.754222202301025,
|
|
"epoch": 0.6247528667457493,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004968753414189576,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.17646001577377318,
|
|
"num_tokens": 14460013.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.7590904712677,
|
|
"epoch": 0.6252471332542507,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968694778021408,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.18161038011312486,
|
|
"num_tokens": 14472452.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.69494857788086,
|
|
"epoch": 0.6257413997627521,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968636087273003,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.17987588793039322,
|
|
"num_tokens": 14484487.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.7048008918762205,
|
|
"epoch": 0.6262356662712535,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004968577341945806,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.1903366833925247,
|
|
"num_tokens": 14496043.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.676010608673096,
|
|
"epoch": 0.6267299327797549,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968518542041264,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.17935250848531722,
|
|
"num_tokens": 14508089.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.800727367401123,
|
|
"epoch": 0.6272241992882562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496845968756082,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.17207197695970536,
|
|
"num_tokens": 14519480.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.7255082607269285,
|
|
"epoch": 0.6277184657967576,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968400778505925,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.1843769818544388,
|
|
"num_tokens": 14531214.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.761374855041504,
|
|
"epoch": 0.628212732305259,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004968341814878025,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.18138425350189208,
|
|
"num_tokens": 14544118.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.763683319091797,
|
|
"epoch": 0.6287069988137604,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968282796678573,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.17990829646587372,
|
|
"num_tokens": 14555545.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.653489446640014,
|
|
"epoch": 0.6292012653222617,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000496822372390902,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.18334181904792785,
|
|
"num_tokens": 14567157.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.627438592910766,
|
|
"epoch": 0.6296955318307631,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496816459657082,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.18774764686822892,
|
|
"num_tokens": 14577074.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.747024059295654,
|
|
"epoch": 0.6301897983392646,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968105414665426,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.18496745675802231,
|
|
"num_tokens": 14589133.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.678619337081909,
|
|
"epoch": 0.630684064847766,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968046178194295,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.18086182624101638,
|
|
"num_tokens": 14600985.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.662907648086548,
|
|
"epoch": 0.6311783313562673,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967986887158884,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.18445221483707427,
|
|
"num_tokens": 14612163.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.732915449142456,
|
|
"epoch": 0.6316725978647687,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004967927541560651,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.18310444355010985,
|
|
"num_tokens": 14623045.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.775830936431885,
|
|
"epoch": 0.6321668643732701,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967868141401056,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.1803148493170738,
|
|
"num_tokens": 14634696.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.78247389793396,
|
|
"epoch": 0.6326611308817714,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967808686681562,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.17738671898841857,
|
|
"num_tokens": 14645589.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.73599271774292,
|
|
"epoch": 0.6331553973902728,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967749177403629,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.18212483525276185,
|
|
"num_tokens": 14657199.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.7224438190460205,
|
|
"epoch": 0.6336496638987742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967689613568723,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.18070882707834243,
|
|
"num_tokens": 14668767.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.653053569793701,
|
|
"epoch": 0.6341439304072756,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004967629995178309,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.1870437741279602,
|
|
"num_tokens": 14680860.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.60442328453064,
|
|
"epoch": 0.6346381969157769,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967570322233852,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.1859385684132576,
|
|
"num_tokens": 14692134.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.683021068572998,
|
|
"epoch": 0.6351324634242784,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967510594736822,
|
|
"loss": 5.4587,
|
|
"mean_token_accuracy": 0.1802861988544464,
|
|
"num_tokens": 14703323.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.679267406463623,
|
|
"epoch": 0.6356267299327798,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967450812688686,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.18792552798986434,
|
|
"num_tokens": 14714453.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.706775379180908,
|
|
"epoch": 0.6361209964412812,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967390976090917,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.1811143323779106,
|
|
"num_tokens": 14726562.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.642064619064331,
|
|
"epoch": 0.6366152629497825,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967331084944986,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19146147221326829,
|
|
"num_tokens": 14738054.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.668184995651245,
|
|
"epoch": 0.6371095294582839,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967271139252365,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.18423206657171248,
|
|
"num_tokens": 14749037.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.684755325317383,
|
|
"epoch": 0.6376037959667853,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967211139014531,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.18072779774665831,
|
|
"num_tokens": 14759667.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.665920972824097,
|
|
"epoch": 0.6380980624752867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496715108423296,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.18640340119600296,
|
|
"num_tokens": 14770866.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.716802549362183,
|
|
"epoch": 0.638592328983788,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967090974909127,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.1808260887861252,
|
|
"num_tokens": 14783095.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.71856918334961,
|
|
"epoch": 0.6390865954922894,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967030811044512,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1751694679260254,
|
|
"num_tokens": 14794046.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.6662344455719,
|
|
"epoch": 0.6395808620007908,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966970592640596,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1810481920838356,
|
|
"num_tokens": 14807295.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.67359619140625,
|
|
"epoch": 0.6400751285092922,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966910319698859,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.1912796750664711,
|
|
"num_tokens": 14819109.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.696849727630616,
|
|
"epoch": 0.6405693950177936,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966849992220784,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.18482088297605515,
|
|
"num_tokens": 14830719.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.688433980941772,
|
|
"epoch": 0.641063661526295,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966789610207856,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.17849323749542237,
|
|
"num_tokens": 14843392.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.730852794647217,
|
|
"epoch": 0.6415579280347964,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966729173661559,
|
|
"loss": 5.3745,
|
|
"mean_token_accuracy": 0.18784392029047012,
|
|
"num_tokens": 14855745.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.741331386566162,
|
|
"epoch": 0.6420521945432978,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000496666868258338,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.17939966768026352,
|
|
"num_tokens": 14868053.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.6654657363891605,
|
|
"epoch": 0.6425464610517991,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004966608136974809,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18736762702465057,
|
|
"num_tokens": 14880095.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.7884503364562985,
|
|
"epoch": 0.6430407275603005,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966547536837333,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.1772681400179863,
|
|
"num_tokens": 14891013.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.722235155105591,
|
|
"epoch": 0.6435349940688019,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966486882172444,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.18554937839508057,
|
|
"num_tokens": 14901875.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.681920337677002,
|
|
"epoch": 0.6440292605773033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966426172981634,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.18451722115278243,
|
|
"num_tokens": 14912620.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.644273138046264,
|
|
"epoch": 0.6445235270858046,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966365409266396,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.1952839434146881,
|
|
"num_tokens": 14923128.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.694646263122559,
|
|
"epoch": 0.645017793594306,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966304591028225,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.18826288729906082,
|
|
"num_tokens": 14933621.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.612667226791382,
|
|
"epoch": 0.6455120601028075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966243718268617,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.18682371973991393,
|
|
"num_tokens": 14943292.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.661767244338989,
|
|
"epoch": 0.6460063266113089,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496618279098907,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.17924872636795045,
|
|
"num_tokens": 14953998.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.72789740562439,
|
|
"epoch": 0.6465005931198102,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004966121809191083,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.17934831082820893,
|
|
"num_tokens": 14965430.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.682815170288086,
|
|
"epoch": 0.6469948596283116,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004966060772876156,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.18645986020565034,
|
|
"num_tokens": 14977124.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.679669809341431,
|
|
"epoch": 0.647489126136813,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004965999682045788,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.18724352568387986,
|
|
"num_tokens": 14987069.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.549817800521851,
|
|
"epoch": 0.6479833926453143,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965938536701486,
|
|
"loss": 5.4502,
|
|
"mean_token_accuracy": 0.19603352546691893,
|
|
"num_tokens": 14997919.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.698160219192505,
|
|
"epoch": 0.6484776591538157,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965877336844752,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.18569322377443315,
|
|
"num_tokens": 15010042.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.714714622497558,
|
|
"epoch": 0.6489719256623171,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965816082477091,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.1896207496523857,
|
|
"num_tokens": 15021166.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.712548923492432,
|
|
"epoch": 0.6494661921708185,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965754773600011,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.18120106011629106,
|
|
"num_tokens": 15032182.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.693567943572998,
|
|
"epoch": 0.6499604586793198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496569341021502,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.1808716431260109,
|
|
"num_tokens": 15043054.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.583023166656494,
|
|
"epoch": 0.6504547251878213,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004965631992323628,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.1918557107448578,
|
|
"num_tokens": 15055462.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.669038772583008,
|
|
"epoch": 0.6509489916963227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965570519927345,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.1815560758113861,
|
|
"num_tokens": 15066849.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.655196714401245,
|
|
"epoch": 0.6514432582048241,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965508993027682,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.18373749703168868,
|
|
"num_tokens": 15078388.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.70443549156189,
|
|
"epoch": 0.6519375247133254,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004965447411626156,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.1772635281085968,
|
|
"num_tokens": 15090474.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.754064655303955,
|
|
"epoch": 0.6524317912218268,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965385775724279,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.18001952916383743,
|
|
"num_tokens": 15101104.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.692561197280884,
|
|
"epoch": 0.6529260577303282,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004965324085323569,
|
|
"loss": 5.4468,
|
|
"mean_token_accuracy": 0.1817217543721199,
|
|
"num_tokens": 15112036.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.763051605224609,
|
|
"epoch": 0.6534203242388296,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965262340425541,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1677619531750679,
|
|
"num_tokens": 15124913.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.76483302116394,
|
|
"epoch": 0.6539145907473309,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965200541031717,
|
|
"loss": 5.4783,
|
|
"mean_token_accuracy": 0.183321450650692,
|
|
"num_tokens": 15135555.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.733474779129028,
|
|
"epoch": 0.6544088572558323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965138687143616,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.1743663564324379,
|
|
"num_tokens": 15146646.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.72074818611145,
|
|
"epoch": 0.6549031237643337,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965076778762759,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1807381883263588,
|
|
"num_tokens": 15157101.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.7268517971038815,
|
|
"epoch": 0.6553973902728352,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004965014815890671,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.18116676807403564,
|
|
"num_tokens": 15169645.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.694109916687012,
|
|
"epoch": 0.6558916567813365,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004964952798528874,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.1830903097987175,
|
|
"num_tokens": 15181018.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.657157897949219,
|
|
"epoch": 0.6563859232898379,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004964890726678894,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.1775732085108757,
|
|
"num_tokens": 15191880.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.610965061187744,
|
|
"epoch": 0.6568801897983393,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004964828600342259,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.18650533705949784,
|
|
"num_tokens": 15203886.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.650919437408447,
|
|
"epoch": 0.6573744563068407,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964766419520497,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.1918613001704216,
|
|
"num_tokens": 15215837.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.725353145599366,
|
|
"epoch": 0.657868722815342,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004964704184215138,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.17489349395036696,
|
|
"num_tokens": 15226833.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.705512523651123,
|
|
"epoch": 0.6583629893238434,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004964641894427712,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.17734523564577104,
|
|
"num_tokens": 15239312.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.673008966445923,
|
|
"epoch": 0.6588572558323448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964579550159752,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.1783429428935051,
|
|
"num_tokens": 15250348.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.684113836288452,
|
|
"epoch": 0.6593515223408462,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964517151412791,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.18892684876918792,
|
|
"num_tokens": 15261445.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.699908685684204,
|
|
"epoch": 0.6598457888493475,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964454698188364,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.18405035734176636,
|
|
"num_tokens": 15271606.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.6878753185272215,
|
|
"epoch": 0.6603400553578489,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496439219048801,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.1803918570280075,
|
|
"num_tokens": 15283690.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.638463973999023,
|
|
"epoch": 0.6608343218663504,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004964329628313263,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.1880164697766304,
|
|
"num_tokens": 15294792.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.757958173751831,
|
|
"epoch": 0.6613285883748518,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964267011665664,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.17849235981702805,
|
|
"num_tokens": 15305636.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.705075693130493,
|
|
"epoch": 0.6618228548833531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964204340546753,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.18019956052303315,
|
|
"num_tokens": 15316495.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.686946821212769,
|
|
"epoch": 0.6623171213918545,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964141614958071,
|
|
"loss": 5.4207,
|
|
"mean_token_accuracy": 0.1857387065887451,
|
|
"num_tokens": 15328246.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.73296275138855,
|
|
"epoch": 0.6628113879003559,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004964078834901163,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.18510466516017915,
|
|
"num_tokens": 15339229.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.669465160369873,
|
|
"epoch": 0.6633056544088572,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496401600037757,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.1813725098967552,
|
|
"num_tokens": 15350591.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.705862951278687,
|
|
"epoch": 0.6637999209173586,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963953111388842,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.17732539474964143,
|
|
"num_tokens": 15363726.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.677817535400391,
|
|
"epoch": 0.66429418742586,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963890167936524,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.1843595862388611,
|
|
"num_tokens": 15375569.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.709108495712281,
|
|
"epoch": 0.6647884539343614,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004963827170022164,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.16931309849023818,
|
|
"num_tokens": 15387323.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.669873046875,
|
|
"epoch": 0.6652827204428627,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004963764117647311,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.18145694583654404,
|
|
"num_tokens": 15397912.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.589202356338501,
|
|
"epoch": 0.6657769869513642,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963701010813519,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.20091821402311325,
|
|
"num_tokens": 15409469.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.6283924102783205,
|
|
"epoch": 0.6662712534598656,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004963637849522338,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.18584844768047332,
|
|
"num_tokens": 15419681.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.706773376464843,
|
|
"epoch": 0.666765519968367,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004963574633775323,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.1782970607280731,
|
|
"num_tokens": 15431237.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.719655752182007,
|
|
"epoch": 0.6672597864768683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004963511363574027,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.17875704169273376,
|
|
"num_tokens": 15442366.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.709488773345948,
|
|
"epoch": 0.6677540529853697,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963448038920009,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.1814780816435814,
|
|
"num_tokens": 15453121.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.659934949874878,
|
|
"epoch": 0.6682483194938711,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963384659814827,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.18677566051483155,
|
|
"num_tokens": 15463489.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.6461833953857425,
|
|
"epoch": 0.6687425860023725,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004963321226260038,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.17960599809885025,
|
|
"num_tokens": 15475217.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.665601205825806,
|
|
"epoch": 0.6692368525108738,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963257738257203,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.1814910888671875,
|
|
"num_tokens": 15485844.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.667984580993652,
|
|
"epoch": 0.6697311190193752,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004963194195807886,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.18200096637010574,
|
|
"num_tokens": 15496835.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.6734765529632565,
|
|
"epoch": 0.6702253855278766,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963130598913646,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.1851516157388687,
|
|
"num_tokens": 15508087.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.764274644851684,
|
|
"epoch": 0.6707196520363781,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004963066947576051,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1808246150612831,
|
|
"num_tokens": 15519596.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.690254163742066,
|
|
"epoch": 0.6712139185448794,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963003241796666,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.17773212790489196,
|
|
"num_tokens": 15530830.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.654678916931152,
|
|
"epoch": 0.6717081850533808,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962939481577059,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.1938735544681549,
|
|
"num_tokens": 15543195.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.7092162609100345,
|
|
"epoch": 0.6722024515618822,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962875666918796,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.18274641782045364,
|
|
"num_tokens": 15554465.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.616643476486206,
|
|
"epoch": 0.6726967180703836,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962811797823448,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.1812501907348633,
|
|
"num_tokens": 15566016.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.737135314941407,
|
|
"epoch": 0.6731909845788849,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004962747874292588,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.17539905160665512,
|
|
"num_tokens": 15576843.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.699502229690552,
|
|
"epoch": 0.6736852510873863,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004962683896327786,
|
|
"loss": 5.4387,
|
|
"mean_token_accuracy": 0.18047475665807725,
|
|
"num_tokens": 15588390.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.728416013717651,
|
|
"epoch": 0.6741795175958877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962619863930616,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.1804381787776947,
|
|
"num_tokens": 15600270.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.728389406204224,
|
|
"epoch": 0.674673784104389,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962555777102656,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.18523539155721663,
|
|
"num_tokens": 15611617.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.642977905273438,
|
|
"epoch": 0.6751680506128904,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496249163584548,
|
|
"loss": 5.4547,
|
|
"mean_token_accuracy": 0.1856302410364151,
|
|
"num_tokens": 15622128.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.7459893226623535,
|
|
"epoch": 0.6756623171213919,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962427440160665,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.17632827013731003,
|
|
"num_tokens": 15635250.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.799910354614258,
|
|
"epoch": 0.6761565836298933,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004962363190049794,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.17796835601329802,
|
|
"num_tokens": 15646535.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.697930431365966,
|
|
"epoch": 0.6766508501383947,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962298885514444,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.18419041037559508,
|
|
"num_tokens": 15658399.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.688305950164795,
|
|
"epoch": 0.677145116646896,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962234526556199,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.18858383893966674,
|
|
"num_tokens": 15669321.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.68391375541687,
|
|
"epoch": 0.6776393831553974,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496217011317664,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.18412790149450303,
|
|
"num_tokens": 15681666.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.601411294937134,
|
|
"epoch": 0.6781336496638988,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004962105645377354,
|
|
"loss": 5.3855,
|
|
"mean_token_accuracy": 0.18707387149333954,
|
|
"num_tokens": 15693432.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.693903207778931,
|
|
"epoch": 0.6786279161724001,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004962041123159926,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.1900697097182274,
|
|
"num_tokens": 15705151.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.663706636428833,
|
|
"epoch": 0.6791221826809015,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961976546525943,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.18783595263957978,
|
|
"num_tokens": 15716549.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.701740694046021,
|
|
"epoch": 0.6796164491894029,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961911915476994,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.18121766448020935,
|
|
"num_tokens": 15727499.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.651185655593872,
|
|
"epoch": 0.6801107156979043,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004961847230014668,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.1849137842655182,
|
|
"num_tokens": 15739196.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.671923065185547,
|
|
"epoch": 0.6806049822064056,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004961782490140558,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18903211653232574,
|
|
"num_tokens": 15750890.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.662531900405884,
|
|
"epoch": 0.6810992487149071,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961717695856256,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.1925715312361717,
|
|
"num_tokens": 15762366.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.617862510681152,
|
|
"epoch": 0.6815935152234085,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004961652847163354,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.18369491398334503,
|
|
"num_tokens": 15773962.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.641139554977417,
|
|
"epoch": 0.6820877817319099,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000496158794406345,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.1957280844449997,
|
|
"num_tokens": 15784563.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.650210762023926,
|
|
"epoch": 0.6825820482404112,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961522986558139,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.1822483003139496,
|
|
"num_tokens": 15796461.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.6847318649292,
|
|
"epoch": 0.6830763147489126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496145797464902,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.17998380810022355,
|
|
"num_tokens": 15807303.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.626545524597168,
|
|
"epoch": 0.683570581257414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961392908337691,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.19580137580633164,
|
|
"num_tokens": 15818964.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.659780597686767,
|
|
"epoch": 0.6840648477659154,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004961327787625754,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.1796172648668289,
|
|
"num_tokens": 15831181.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.649292850494385,
|
|
"epoch": 0.6845591142744167,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496126261251481,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.18648644983768464,
|
|
"num_tokens": 15842442.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.708519363403321,
|
|
"epoch": 0.6850533807829181,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961197383006463,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.18111221343278885,
|
|
"num_tokens": 15854755.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.565923118591309,
|
|
"epoch": 0.6855476472914195,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961132099102316,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.19061403423547746,
|
|
"num_tokens": 15866300.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.643864345550537,
|
|
"epoch": 0.686041913799921,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961066760803978,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.19204534143209456,
|
|
"num_tokens": 15877165.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.722785520553589,
|
|
"epoch": 0.6865361803084223,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004961001368113054,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.17978667616844177,
|
|
"num_tokens": 15888893.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.6792816638946535,
|
|
"epoch": 0.6870304468169237,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004960935921031153,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.18164823651313783,
|
|
"num_tokens": 15899994.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.578463697433472,
|
|
"epoch": 0.6875247133254251,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960870419559887,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.1927930772304535,
|
|
"num_tokens": 15911330.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.645543813705444,
|
|
"epoch": 0.6880189798339265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960804863700864,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.19140509217977525,
|
|
"num_tokens": 15922397.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.668138217926026,
|
|
"epoch": 0.6885132463424278,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960739253455699,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.18389109820127486,
|
|
"num_tokens": 15934628.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.627578592300415,
|
|
"epoch": 0.6890075128509292,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960673588826005,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.18917313814163209,
|
|
"num_tokens": 15946599.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.694380283355713,
|
|
"epoch": 0.6895017793594306,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004960607869813398,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.18457768559455873,
|
|
"num_tokens": 15957402.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.700537586212159,
|
|
"epoch": 0.689996045867932,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004960542096419494,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.18641959130764008,
|
|
"num_tokens": 15968091.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.6515697002410885,
|
|
"epoch": 0.6904903123764333,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960476268645912,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.18348170667886735,
|
|
"num_tokens": 15980809.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.681520938873291,
|
|
"epoch": 0.6909845788849348,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004960410386494271,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.1831069767475128,
|
|
"num_tokens": 15992701.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.77148928642273,
|
|
"epoch": 0.6914788453934362,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960344449966191,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.17651577144861222,
|
|
"num_tokens": 16005871.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.763817024230957,
|
|
"epoch": 0.6919731119019376,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004960278459063296,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.17383982986211777,
|
|
"num_tokens": 16018126.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.660416507720948,
|
|
"epoch": 0.6924673784104389,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960212413787206,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.18668118119239807,
|
|
"num_tokens": 16028694.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.609909439086914,
|
|
"epoch": 0.6929616449189403,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496014631413955,
|
|
"loss": 5.4636,
|
|
"mean_token_accuracy": 0.1778472289443016,
|
|
"num_tokens": 16040354.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.6946430683135985,
|
|
"epoch": 0.6934559114274417,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004960080160121951,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18865488320589066,
|
|
"num_tokens": 16051713.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.695664024353027,
|
|
"epoch": 0.693950177935943,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004960013951736036,
|
|
"loss": 5.4765,
|
|
"mean_token_accuracy": 0.17734843641519546,
|
|
"num_tokens": 16064737.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.65210599899292,
|
|
"epoch": 0.6944444444444444,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959947688983436,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.18901321440935134,
|
|
"num_tokens": 16075515.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.674917221069336,
|
|
"epoch": 0.6949387109529458,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004959881371865779,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.18163476139307022,
|
|
"num_tokens": 16088702.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.660607814788818,
|
|
"epoch": 0.6954329774614472,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959815000384699,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.18652654588222503,
|
|
"num_tokens": 16101122.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.707927942276001,
|
|
"epoch": 0.6959272439699487,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004959748574541826,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.18145518451929094,
|
|
"num_tokens": 16112817.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.687083339691162,
|
|
"epoch": 0.69642151047845,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959682094338795,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.1754821315407753,
|
|
"num_tokens": 16124827.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.652220296859741,
|
|
"epoch": 0.6969157769869514,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004959615559777243,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.18845241516828537,
|
|
"num_tokens": 16136940.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.713035345077515,
|
|
"epoch": 0.6974100434954528,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959548970858805,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.18737876713275908,
|
|
"num_tokens": 16147541.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.636923933029175,
|
|
"epoch": 0.6979043100039541,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004959482327585119,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.17895619124174117,
|
|
"num_tokens": 16157626.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.645445966720581,
|
|
"epoch": 0.6983985765124555,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004959415629957824,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.1890865683555603,
|
|
"num_tokens": 16168494.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.677611780166626,
|
|
"epoch": 0.6988928430209569,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004959348877978563,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18335221856832504,
|
|
"num_tokens": 16180749.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.677210569381714,
|
|
"epoch": 0.6993871095294583,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004959282071648977,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.18475838452577592,
|
|
"num_tokens": 16193204.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.656859493255615,
|
|
"epoch": 0.6998813760379596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495921521097071,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.1933037355542183,
|
|
"num_tokens": 16204303.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.654446697235107,
|
|
"epoch": 0.700375642546461,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959148295945405,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.19118872731924058,
|
|
"num_tokens": 16215261.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.654616737365723,
|
|
"epoch": 0.7008699090549624,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004959081326574708,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.1869739294052124,
|
|
"num_tokens": 16226973.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.537435150146484,
|
|
"epoch": 0.7013641755634639,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004959014302860271,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.2000797674059868,
|
|
"num_tokens": 16239152.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.671125364303589,
|
|
"epoch": 0.7018584420719652,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004958947224803737,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.18841296285390854,
|
|
"num_tokens": 16251884.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.682699298858642,
|
|
"epoch": 0.7023527085804666,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958880092406759,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.17482409477233887,
|
|
"num_tokens": 16262497.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.6305183410644535,
|
|
"epoch": 0.702846975088968,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958812905670988,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.1892905205488205,
|
|
"num_tokens": 16274624.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.746497869491577,
|
|
"epoch": 0.7033412415974694,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958745664598077,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.1858081564307213,
|
|
"num_tokens": 16286096.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.634428548812866,
|
|
"epoch": 0.7038355081059707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004958678369189679,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.19181613475084305,
|
|
"num_tokens": 16297853.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.649743986129761,
|
|
"epoch": 0.7043297746144721,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958611019447452,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.18137550055980683,
|
|
"num_tokens": 16310708.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.701823949813843,
|
|
"epoch": 0.7048240411229735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004958543615373051,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.1839786797761917,
|
|
"num_tokens": 16321216.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.64765739440918,
|
|
"epoch": 0.7053183076314749,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004958476156968134,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.19156715869903565,
|
|
"num_tokens": 16331982.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.653167867660523,
|
|
"epoch": 0.7058125741399762,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495840864423436,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.18317919969558716,
|
|
"num_tokens": 16343001.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.750587844848633,
|
|
"epoch": 0.7063068406484777,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004958341077173392,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.1854384422302246,
|
|
"num_tokens": 16355519.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.678952312469482,
|
|
"epoch": 0.7068011071569791,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004958273455786892,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.18318860083818436,
|
|
"num_tokens": 16366342.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.694130849838257,
|
|
"epoch": 0.7072953736654805,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004958205780076521,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.17927791625261308,
|
|
"num_tokens": 16378395.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.663529253005981,
|
|
"epoch": 0.7077896401739818,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004958138050043945,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.18564121425151825,
|
|
"num_tokens": 16388946.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.578586578369141,
|
|
"epoch": 0.7082839066824832,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004958070265690831,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.18518381416797638,
|
|
"num_tokens": 16399824.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.747214651107788,
|
|
"epoch": 0.7087781731909846,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958002427018845,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.17862845510244368,
|
|
"num_tokens": 16411932.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.6991194725036625,
|
|
"epoch": 0.709272439699486,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957934534029658,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.18126825988292694,
|
|
"num_tokens": 16423634.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.715042686462402,
|
|
"epoch": 0.7097667062079873,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957866586724938,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.18193342089653014,
|
|
"num_tokens": 16434700.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.74013319015503,
|
|
"epoch": 0.7102609727164887,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004957798585106359,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.18293837904930116,
|
|
"num_tokens": 16445829.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.5745384216308596,
|
|
"epoch": 0.7107552392249901,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495773052917559,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.19844848811626434,
|
|
"num_tokens": 16456352.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.635031843185425,
|
|
"epoch": 0.7112495057334915,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004957662418934309,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18821563422679902,
|
|
"num_tokens": 16467542.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.602718019485474,
|
|
"epoch": 0.7117437722419929,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957594254384189,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.20144389420747758,
|
|
"num_tokens": 16478614.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.653006887435913,
|
|
"epoch": 0.7122380387504943,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957526035526908,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.18989845663309096,
|
|
"num_tokens": 16489929.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.755248165130615,
|
|
"epoch": 0.7127323052589957,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004957457762364146,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.17849240005016326,
|
|
"num_tokens": 16502532.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.733708286285401,
|
|
"epoch": 0.713226571767497,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957389434897578,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.18215182721614837,
|
|
"num_tokens": 16513805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.694751405715943,
|
|
"epoch": 0.7137208382759984,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957321053128889,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.1830164983868599,
|
|
"num_tokens": 16525189.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.696434402465821,
|
|
"epoch": 0.7142151047844998,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004957252617059759,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.1788410171866417,
|
|
"num_tokens": 16538246.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.734514427185059,
|
|
"epoch": 0.7147093712930012,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957184126691873,
|
|
"loss": 5.4521,
|
|
"mean_token_accuracy": 0.1796474426984787,
|
|
"num_tokens": 16550036.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.660345840454101,
|
|
"epoch": 0.7152036378015025,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957115582026915,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.19144424200057983,
|
|
"num_tokens": 16562262.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.669035863876343,
|
|
"epoch": 0.7156979043100039,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000495704698306657,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.19261749237775802,
|
|
"num_tokens": 16574213.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.683400344848633,
|
|
"epoch": 0.7161921708185054,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004956978329812528,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.18806204646825792,
|
|
"num_tokens": 16586063.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.686618185043335,
|
|
"epoch": 0.7166864373270068,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004956909622266476,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.17914970964193344,
|
|
"num_tokens": 16598014.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.707431745529175,
|
|
"epoch": 0.7171807038355081,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956840860430104,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.19171763509511947,
|
|
"num_tokens": 16609128.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.623238468170166,
|
|
"epoch": 0.7176749703440095,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004956772044305106,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.19043963104486467,
|
|
"num_tokens": 16620095.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.6551319599151615,
|
|
"epoch": 0.7181692368525109,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004956703173893173,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.18289692848920822,
|
|
"num_tokens": 16630919.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.679590797424316,
|
|
"epoch": 0.7186635033610123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956634249196001,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.1806553363800049,
|
|
"num_tokens": 16642111.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.74385437965393,
|
|
"epoch": 0.7191577698695136,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004956565270215282,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.17933779656887056,
|
|
"num_tokens": 16654805.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.736494064331055,
|
|
"epoch": 0.719652036378015,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956496236952716,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.17921999394893645,
|
|
"num_tokens": 16664735.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.67899374961853,
|
|
"epoch": 0.7201463028865164,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495642714941,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.1852945253252983,
|
|
"num_tokens": 16676163.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.774364233016968,
|
|
"epoch": 0.7206405693950177,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004956358007588834,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.17558194547891617,
|
|
"num_tokens": 16689683.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.756363868713379,
|
|
"epoch": 0.7211348359035191,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004956288811490919,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.17679381519556045,
|
|
"num_tokens": 16702193.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.596215677261353,
|
|
"epoch": 0.7216291024120206,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956219561117955,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.20026921778917312,
|
|
"num_tokens": 16713489.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.609003162384033,
|
|
"epoch": 0.722123368920522,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000495615025647165,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.18067056834697723,
|
|
"num_tokens": 16725103.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.646150684356689,
|
|
"epoch": 0.7226176354290234,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956080897553705,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.18291271924972535,
|
|
"num_tokens": 16737056.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.66698989868164,
|
|
"epoch": 0.7231119019375247,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004956011484365829,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.19922607094049455,
|
|
"num_tokens": 16747347.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.63881483078003,
|
|
"epoch": 0.7236061684460261,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955942016909728,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.19549122154712678,
|
|
"num_tokens": 16758738.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.659709072113037,
|
|
"epoch": 0.7241004349545275,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495587249518711,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.1806495487689972,
|
|
"num_tokens": 16770867.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.689478921890259,
|
|
"epoch": 0.7245947014630288,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004955802919199687,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.1905299812555313,
|
|
"num_tokens": 16781537.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.677388429641724,
|
|
"epoch": 0.7250889679715302,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495573328894917,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.184035524725914,
|
|
"num_tokens": 16792250.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.620421934127807,
|
|
"epoch": 0.7255832344800316,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004955663604437272,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.1843078002333641,
|
|
"num_tokens": 16803673.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.6805750846862795,
|
|
"epoch": 0.726077500988533,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004955593865665707,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.18508365750312805,
|
|
"num_tokens": 16815484.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.691528081893921,
|
|
"epoch": 0.7265717674970344,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000495552407263619,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.18326476812362671,
|
|
"num_tokens": 16827097.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.721248006820678,
|
|
"epoch": 0.7270660340055358,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004955454225350441,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.1852470189332962,
|
|
"num_tokens": 16838235.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.6892084121704105,
|
|
"epoch": 0.7275603005140372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004955384323810174,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.18810428380966188,
|
|
"num_tokens": 16847831.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.702212142944336,
|
|
"epoch": 0.7280545670225386,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000495531436801711,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.18493885099887847,
|
|
"num_tokens": 16859607.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.753056144714355,
|
|
"epoch": 0.7285488335310399,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004955244357972972,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.17905111014842987,
|
|
"num_tokens": 16869787.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.626278877258301,
|
|
"epoch": 0.7290431000395413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000495517429367948,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19048488289117813,
|
|
"num_tokens": 16880819.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.71539158821106,
|
|
"epoch": 0.7295373665480427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004955104175138358,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.18184176683425904,
|
|
"num_tokens": 16893247.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.689558982849121,
|
|
"epoch": 0.7300316330565441,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955034002351332,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18559390902519227,
|
|
"num_tokens": 16904469.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.6558443069458,
|
|
"epoch": 0.7305258995650454,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004954963775320127,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.17719829380512236,
|
|
"num_tokens": 16918433.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.694541168212891,
|
|
"epoch": 0.7310201660735468,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495489349404647,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.17820830643177032,
|
|
"num_tokens": 16930905.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.734336233139038,
|
|
"epoch": 0.7315144325820483,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004954823158532093,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17735820710659028,
|
|
"num_tokens": 16943461.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.63409914970398,
|
|
"epoch": 0.7320086990905497,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954752768778723,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.18278694599866868,
|
|
"num_tokens": 16955539.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.670486307144165,
|
|
"epoch": 0.732502965599051,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954682324788093,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.17866645008325577,
|
|
"num_tokens": 16967508.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.652829694747925,
|
|
"epoch": 0.7329972321075524,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954611826561935,
|
|
"loss": 5.3545,
|
|
"mean_token_accuracy": 0.18973411619663239,
|
|
"num_tokens": 16979033.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.6304679870605465,
|
|
"epoch": 0.7334914986160538,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004954541274101985,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.19321956485509872,
|
|
"num_tokens": 16991874.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.73438401222229,
|
|
"epoch": 0.7339857651245552,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954470667409978,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.18036859035491942,
|
|
"num_tokens": 17003160.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.654939031600952,
|
|
"epoch": 0.7344800316330565,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000495440000648765,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.18651044368743896,
|
|
"num_tokens": 17014043.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.679742813110352,
|
|
"epoch": 0.7349742981415579,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954329291336739,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.1880825787782669,
|
|
"num_tokens": 17025117.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.660619735717773,
|
|
"epoch": 0.7354685646500593,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954258521958988,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.18671616166830063,
|
|
"num_tokens": 17037366.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.70739483833313,
|
|
"epoch": 0.7359628311585606,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954187698356133,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18276374340057372,
|
|
"num_tokens": 17050683.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.5868124008178714,
|
|
"epoch": 0.7364570976670621,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954116820529921,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.19585615694522857,
|
|
"num_tokens": 17062403.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.65182785987854,
|
|
"epoch": 0.7369513641755635,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954045888482091,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.19099604934453965,
|
|
"num_tokens": 17072688.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.6631995677948,
|
|
"epoch": 0.7374456306840649,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004953974902214391,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1912774920463562,
|
|
"num_tokens": 17084118.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.664176034927368,
|
|
"epoch": 0.7379398971925663,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953903861728567,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18769233971834182,
|
|
"num_tokens": 17095600.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.803557062149048,
|
|
"epoch": 0.7384341637010676,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004953832767026365,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.18064996600151062,
|
|
"num_tokens": 17107934.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.742346906661988,
|
|
"epoch": 0.738928430209569,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953761618109535,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.18403366953134537,
|
|
"num_tokens": 17119578.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.659234714508057,
|
|
"epoch": 0.7394226967180704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953690414979828,
|
|
"loss": 5.4486,
|
|
"mean_token_accuracy": 0.17846433073282242,
|
|
"num_tokens": 17129928.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.692962598800659,
|
|
"epoch": 0.7399169632265717,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004953619157638995,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.18141815960407257,
|
|
"num_tokens": 17141149.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.634675598144531,
|
|
"epoch": 0.7404112297350731,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953547846088789,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.18541015982627868,
|
|
"num_tokens": 17152577.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.642905759811401,
|
|
"epoch": 0.7409054962435745,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004953476480330964,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.18487662076950073,
|
|
"num_tokens": 17163997.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.635993385314942,
|
|
"epoch": 0.741399762752076,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004953405060367276,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1913245663046837,
|
|
"num_tokens": 17175317.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.558791065216065,
|
|
"epoch": 0.7418940292605773,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004953333586199481,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.1898777738213539,
|
|
"num_tokens": 17185615.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.712562322616577,
|
|
"epoch": 0.7423882957690787,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004953262057829338,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.17779784202575682,
|
|
"num_tokens": 17198160.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.71424126625061,
|
|
"epoch": 0.7428825622775801,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953190475258607,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.1871979668736458,
|
|
"num_tokens": 17209652.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.681139039993286,
|
|
"epoch": 0.7433768287860815,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004953118838489049,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.183564230799675,
|
|
"num_tokens": 17220832.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.644816732406616,
|
|
"epoch": 0.7438710952945828,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953047147522424,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.1867297887802124,
|
|
"num_tokens": 17231952.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.5916526317596436,
|
|
"epoch": 0.7443653618030842,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952975402360499,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.19042591601610184,
|
|
"num_tokens": 17242705.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.7398519039154055,
|
|
"epoch": 0.7448596283115856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004952903603005037,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.17742991149425508,
|
|
"num_tokens": 17253946.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.707596158981323,
|
|
"epoch": 0.745353894820087,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004952831749457804,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.19042180627584457,
|
|
"num_tokens": 17265732.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.643588733673096,
|
|
"epoch": 0.7458481613285883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004952759841720569,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.19260530769824982,
|
|
"num_tokens": 17277154.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.69439206123352,
|
|
"epoch": 0.7463424278370897,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004952687879795101,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.1851677566766739,
|
|
"num_tokens": 17288179.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.6562920093536375,
|
|
"epoch": 0.7468366943455912,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004952615863683167,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.189335697889328,
|
|
"num_tokens": 17299435.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.525950908660889,
|
|
"epoch": 0.7473309608540926,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004952543793386543,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.2058229401707649,
|
|
"num_tokens": 17309442.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.715339136123657,
|
|
"epoch": 0.7478252273625939,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004952471668906999,
|
|
"loss": 5.4208,
|
|
"mean_token_accuracy": 0.1828790307044983,
|
|
"num_tokens": 17322072.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.651614856719971,
|
|
"epoch": 0.7483194938710953,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004952399490246311,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.18749946355819702,
|
|
"num_tokens": 17333458.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.626357316970825,
|
|
"epoch": 0.7488137603795967,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004952327257406253,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.18851567655801774,
|
|
"num_tokens": 17344319.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.7104216575622555,
|
|
"epoch": 0.749308026888098,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004952254970388603,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.18660738319158554,
|
|
"num_tokens": 17357016.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.590426397323609,
|
|
"epoch": 0.7498022933965994,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000495218262919514,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.19457150101661683,
|
|
"num_tokens": 17368574.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.589792156219483,
|
|
"epoch": 0.7502965599051008,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004952110233827642,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.19795868545770645,
|
|
"num_tokens": 17379858.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.693734884262085,
|
|
"epoch": 0.7507908264136022,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004952037784287891,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.18673142343759536,
|
|
"num_tokens": 17391543.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.684725666046143,
|
|
"epoch": 0.7512850929221035,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951965280577668,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.18937657475471498,
|
|
"num_tokens": 17403193.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.697777366638183,
|
|
"epoch": 0.751779359430605,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004951892722698759,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.1847672641277313,
|
|
"num_tokens": 17415866.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.613073396682739,
|
|
"epoch": 0.7522736259391064,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004951820110652946,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.18801401406526566,
|
|
"num_tokens": 17427880.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.650252342224121,
|
|
"epoch": 0.7527678924476078,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004951747444442017,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.18859250843524933,
|
|
"num_tokens": 17440295.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.654036188125611,
|
|
"epoch": 0.7532621589561092,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004951674724067759,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.18445403277873992,
|
|
"num_tokens": 17451636.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.690109729766846,
|
|
"epoch": 0.7537564254646105,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951601949531962,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.18781063109636306,
|
|
"num_tokens": 17464376.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.661364555358887,
|
|
"epoch": 0.7542506919731119,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951529120836416,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.1877681091427803,
|
|
"num_tokens": 17475098.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.559615898132324,
|
|
"epoch": 0.7547449584816133,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004951456237982911,
|
|
"loss": 5.3135,
|
|
"mean_token_accuracy": 0.1875964432954788,
|
|
"num_tokens": 17486176.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.614330673217774,
|
|
"epoch": 0.7552392249901146,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951383300973242,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.19070686846971513,
|
|
"num_tokens": 17498386.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.6752747058868405,
|
|
"epoch": 0.755733491498616,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004951310309809201,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.18466150015592575,
|
|
"num_tokens": 17510409.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.647143459320068,
|
|
"epoch": 0.7562277580071174,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004951237264492585,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18571873009204865,
|
|
"num_tokens": 17521803.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.6209554195404055,
|
|
"epoch": 0.7567220245156189,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004951164165025192,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.18765482753515245,
|
|
"num_tokens": 17532974.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.684657382965088,
|
|
"epoch": 0.7572162910241202,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951091011408818,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.1874500870704651,
|
|
"num_tokens": 17544309.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.641847133636475,
|
|
"epoch": 0.7577105575326216,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004951017803645264,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.19300690591335296,
|
|
"num_tokens": 17555395.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.623783922195434,
|
|
"epoch": 0.758204824041123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495094454173633,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.18821680992841722,
|
|
"num_tokens": 17567434.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.705420303344726,
|
|
"epoch": 0.7586990905496244,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004950871225683819,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.18236252963542937,
|
|
"num_tokens": 17578381.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.634431171417236,
|
|
"epoch": 0.7591933570581257,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004950797855489535,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.18885243833065032,
|
|
"num_tokens": 17589732.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.689999294281006,
|
|
"epoch": 0.7596876235666271,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950724431155283,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.18844882100820542,
|
|
"num_tokens": 17601092.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.6386909008026125,
|
|
"epoch": 0.7601818900751285,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004950650952682867,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.18836773484945296,
|
|
"num_tokens": 17613268.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.663677787780761,
|
|
"epoch": 0.7606761565836299,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950577420074098,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.18444576859474182,
|
|
"num_tokens": 17623500.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.686369800567627,
|
|
"epoch": 0.7611704230921312,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004950503833330781,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.17894016355276107,
|
|
"num_tokens": 17636151.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.675409030914307,
|
|
"epoch": 0.7616646896006327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950430192454729,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.17720431983470916,
|
|
"num_tokens": 17648392.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.672790813446045,
|
|
"epoch": 0.7621589561091341,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004950356497447754,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18612737208604813,
|
|
"num_tokens": 17659777.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.694863367080688,
|
|
"epoch": 0.7626532226176355,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004950282748311666,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18029696643352508,
|
|
"num_tokens": 17671986.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.656952524185181,
|
|
"epoch": 0.7631474891261368,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950208945048283,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.19005147516727447,
|
|
"num_tokens": 17683740.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.652459192276001,
|
|
"epoch": 0.7636417556346382,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950135087659417,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.18499477207660675,
|
|
"num_tokens": 17696034.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.661531734466553,
|
|
"epoch": 0.7641360221431396,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004950061176146887,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.1886142760515213,
|
|
"num_tokens": 17707783.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.632096576690674,
|
|
"epoch": 0.764630288651641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949987210512511,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.18884276300668718,
|
|
"num_tokens": 17718127.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.677348661422729,
|
|
"epoch": 0.7651245551601423,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004949913190758109,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1795927718281746,
|
|
"num_tokens": 17729798.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.6840489387512205,
|
|
"epoch": 0.7656188216686437,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004949839116885499,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.18357911854982376,
|
|
"num_tokens": 17741989.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.648376083374023,
|
|
"epoch": 0.7661130881771451,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004949764988896508,
|
|
"loss": 5.4056,
|
|
"mean_token_accuracy": 0.18787432014942168,
|
|
"num_tokens": 17753737.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.596786546707153,
|
|
"epoch": 0.7666073546856464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949690806792955,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1968316003680229,
|
|
"num_tokens": 17764158.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.680300617218018,
|
|
"epoch": 0.7671016211941479,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004949616570576668,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.1885527640581131,
|
|
"num_tokens": 17775878.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.650046873092651,
|
|
"epoch": 0.7675958877026493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004949542280249473,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.1919610396027565,
|
|
"num_tokens": 17786107.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.618096351623535,
|
|
"epoch": 0.7680901542111507,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004949467935813196,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1877329871058464,
|
|
"num_tokens": 17798470.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.6560972213745115,
|
|
"epoch": 0.768584420719652,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004949393537269666,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.1861312359571457,
|
|
"num_tokens": 17811125.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.6340124130249025,
|
|
"epoch": 0.7690786872281534,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004949319084620714,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.19185607135295868,
|
|
"num_tokens": 17821535.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.710686779022216,
|
|
"epoch": 0.7695729537366548,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494924457786817,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.18006813228130342,
|
|
"num_tokens": 17833493.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.75515193939209,
|
|
"epoch": 0.7700672202451562,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949170017013871,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.18286254703998567,
|
|
"num_tokens": 17844705.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.700857877731323,
|
|
"epoch": 0.7705614867536575,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004949095402059646,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.18440821766853333,
|
|
"num_tokens": 17856088.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.734563112258911,
|
|
"epoch": 0.7710557532621589,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004949020733007334,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.1825122967362404,
|
|
"num_tokens": 17867602.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.735884046554565,
|
|
"epoch": 0.7715500197706603,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000494894600985877,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.1801721751689911,
|
|
"num_tokens": 17880487.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.687494564056396,
|
|
"epoch": 0.7720442862791618,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004948871232615794,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18796298503875733,
|
|
"num_tokens": 17891690.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.725475549697876,
|
|
"epoch": 0.7725385527876631,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004948796401280244,
|
|
"loss": 5.4484,
|
|
"mean_token_accuracy": 0.17923469990491867,
|
|
"num_tokens": 17903165.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.676923418045044,
|
|
"epoch": 0.7730328192961645,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004948721515853962,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.1925194516777992,
|
|
"num_tokens": 17914492.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.690169191360473,
|
|
"epoch": 0.7735270858046659,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004948646576338789,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.17486454397439957,
|
|
"num_tokens": 17926231.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.604264497756958,
|
|
"epoch": 0.7740213523131673,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000494857158273657,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.1902058318257332,
|
|
"num_tokens": 17937167.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.644855165481568,
|
|
"epoch": 0.7745156188216686,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004948496535049148,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.18402523845434188,
|
|
"num_tokens": 17948939.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.670464086532593,
|
|
"epoch": 0.77500988533017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494842143327837,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.20334178060293198,
|
|
"num_tokens": 17959250.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.6042379379272464,
|
|
"epoch": 0.7755041518386714,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004948346277426084,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18002065718173982,
|
|
"num_tokens": 17970191.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.698566579818726,
|
|
"epoch": 0.7759984183471728,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494827106749414,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.18793852031230926,
|
|
"num_tokens": 17982114.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.799722337722779,
|
|
"epoch": 0.7764926848556741,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948195803484385,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18278124928474426,
|
|
"num_tokens": 17994066.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.620365715026855,
|
|
"epoch": 0.7769869513641756,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948120485398673,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.1864301308989525,
|
|
"num_tokens": 18005406.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.635767650604248,
|
|
"epoch": 0.777481217872677,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004948045113238856,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.1857351467013359,
|
|
"num_tokens": 18016773.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.705584764480591,
|
|
"epoch": 0.7779754843811784,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004947969687006787,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.18227917850017547,
|
|
"num_tokens": 18028682.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.6915607929229735,
|
|
"epoch": 0.7784697508896797,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004947894206704324,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18589052706956863,
|
|
"num_tokens": 18039525.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.652793121337891,
|
|
"epoch": 0.7789640173981811,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004947818672333323,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.18564853221178054,
|
|
"num_tokens": 18049918.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.734889125823974,
|
|
"epoch": 0.7794582839066825,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000494774308389564,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.17997895628213884,
|
|
"num_tokens": 18061019.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.667730093002319,
|
|
"epoch": 0.7799525504151839,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004947667441393138,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.190121528506279,
|
|
"num_tokens": 18072123.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.631020641326904,
|
|
"epoch": 0.7804468169236852,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004947591744827674,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.18434544503688813,
|
|
"num_tokens": 18083354.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.758954620361328,
|
|
"epoch": 0.7809410834321866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947515994201113,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.1783450126647949,
|
|
"num_tokens": 18094188.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.68081693649292,
|
|
"epoch": 0.781435349940688,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004947440189515318,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.18587932586669922,
|
|
"num_tokens": 18106198.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.668081760406494,
|
|
"epoch": 0.7819296164491895,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004947364330772154,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.1908632695674896,
|
|
"num_tokens": 18117137.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.6121697425842285,
|
|
"epoch": 0.7824238829576908,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947288417973486,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.1813672661781311,
|
|
"num_tokens": 18127341.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.680874872207641,
|
|
"epoch": 0.7829181494661922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947212451121182,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.18717844635248185,
|
|
"num_tokens": 18138333.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.736912250518799,
|
|
"epoch": 0.7834124159746936,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000494713643021711,
|
|
"loss": 5.6047,
|
|
"mean_token_accuracy": 0.1727058097720146,
|
|
"num_tokens": 18150961.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.747749853134155,
|
|
"epoch": 0.783906682483195,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004947060355263142,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.1867763638496399,
|
|
"num_tokens": 18162604.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.650860834121704,
|
|
"epoch": 0.7844009489916963,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004946984226261149,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.186197167634964,
|
|
"num_tokens": 18174202.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.709315061569214,
|
|
"epoch": 0.7848952155001977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946908043213001,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.18151017129421235,
|
|
"num_tokens": 18185942.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.680483102798462,
|
|
"epoch": 0.7853894820086991,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946831806120576,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1878525972366333,
|
|
"num_tokens": 18198897.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.636187314987183,
|
|
"epoch": 0.7858837485172004,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946755514985748,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.19495179057121276,
|
|
"num_tokens": 18211439.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.574185180664062,
|
|
"epoch": 0.7863780150257018,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004946679169810392,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.19399549663066865,
|
|
"num_tokens": 18221864.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.661316442489624,
|
|
"epoch": 0.7868722815342032,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494660277059639,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.1834837704896927,
|
|
"num_tokens": 18234005.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.641396713256836,
|
|
"epoch": 0.7873665480427047,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946526317345617,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.191530941426754,
|
|
"num_tokens": 18246804.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.644958782196045,
|
|
"epoch": 0.787860814551206,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004946449810059957,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.19076861441135406,
|
|
"num_tokens": 18259192.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.679888200759888,
|
|
"epoch": 0.7883550810597074,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004946373248741289,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18994068652391433,
|
|
"num_tokens": 18271073.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.651530361175537,
|
|
"epoch": 0.7888493475682088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049462966333915,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.1886462688446045,
|
|
"num_tokens": 18281650.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.665188026428223,
|
|
"epoch": 0.7893436140767102,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946219964012473,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.18682026714086533,
|
|
"num_tokens": 18292217.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.645196723937988,
|
|
"epoch": 0.7898378805852115,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004946143240606095,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.19166507869958876,
|
|
"num_tokens": 18305210.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.6403951168060305,
|
|
"epoch": 0.7903321470937129,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946066463174251,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.19262539297342302,
|
|
"num_tokens": 18316418.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.558445596694947,
|
|
"epoch": 0.7908264136022143,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945989631718831,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.19246632903814315,
|
|
"num_tokens": 18328637.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.647032308578491,
|
|
"epoch": 0.7913206801107157,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004945912746241727,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.1939465433359146,
|
|
"num_tokens": 18340292.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.6033656120300295,
|
|
"epoch": 0.791814946619217,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945835806744828,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.19372644424438476,
|
|
"num_tokens": 18350784.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.702573823928833,
|
|
"epoch": 0.7923092131277185,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004945758813230028,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.182921838760376,
|
|
"num_tokens": 18363147.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.706137704849243,
|
|
"epoch": 0.7928034796362199,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000494568176569922,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18668553978204727,
|
|
"num_tokens": 18374152.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.62548828125,
|
|
"epoch": 0.7932977461447213,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049456046641543,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.19460718631744384,
|
|
"num_tokens": 18385321.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.665828895568848,
|
|
"epoch": 0.7937920126532226,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945527508597165,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18383132070302963,
|
|
"num_tokens": 18397072.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.6188959121704105,
|
|
"epoch": 0.794286279161724,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945450299029713,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.18940794765949248,
|
|
"num_tokens": 18408172.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.651398515701294,
|
|
"epoch": 0.7947805456702254,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004945373035453842,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.19606102257966995,
|
|
"num_tokens": 18419350.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.631956243515015,
|
|
"epoch": 0.7952748121787268,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945295717871454,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18574828803539276,
|
|
"num_tokens": 18430907.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.672289752960205,
|
|
"epoch": 0.7957690786872281,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945218346284451,
|
|
"loss": 5.3493,
|
|
"mean_token_accuracy": 0.1913642480969429,
|
|
"num_tokens": 18441167.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.6557718276977536,
|
|
"epoch": 0.7962633451957295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945140920694736,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.19807880222797394,
|
|
"num_tokens": 18452025.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.67685546875,
|
|
"epoch": 0.7967576117042309,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004945063441104214,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.17122341692447662,
|
|
"num_tokens": 18464305.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.654890537261963,
|
|
"epoch": 0.7972518782127324,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004944985907514791,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.18807248324155806,
|
|
"num_tokens": 18476217.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.736039495468139,
|
|
"epoch": 0.7977461447212337,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004944908319928372,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.1839275300502777,
|
|
"num_tokens": 18486967.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.67571382522583,
|
|
"epoch": 0.7982404112297351,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944830678346871,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.18242959231138228,
|
|
"num_tokens": 18498918.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.63468108177185,
|
|
"epoch": 0.7987346777382365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944752982772194,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.19296954274177552,
|
|
"num_tokens": 18509424.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.581369543075562,
|
|
"epoch": 0.7992289442467378,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004944675233206252,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.19389283806085586,
|
|
"num_tokens": 18520444.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.606768465042114,
|
|
"epoch": 0.7997232107552392,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000494459742965096,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.19006512463092803,
|
|
"num_tokens": 18531874.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.740726375579834,
|
|
"epoch": 0.8002174772637406,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494451957210823,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.1826380893588066,
|
|
"num_tokens": 18542492.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.749100589752198,
|
|
"epoch": 0.800711743772242,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004944441660579979,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.177557510137558,
|
|
"num_tokens": 18554477.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.633746767044068,
|
|
"epoch": 0.8012060102807433,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004944363695068121,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.1938049763441086,
|
|
"num_tokens": 18565416.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.649519681930542,
|
|
"epoch": 0.8017002767892447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004944285675574576,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.19163744747638703,
|
|
"num_tokens": 18575949.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.626943635940552,
|
|
"epoch": 0.8021945432977462,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004944207602101265,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.1850971981883049,
|
|
"num_tokens": 18588177.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.642237997055053,
|
|
"epoch": 0.8026888098062476,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004944129474650104,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.18568051755428314,
|
|
"num_tokens": 18599112.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.5302375793457035,
|
|
"epoch": 0.803183076314749,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000494405129322302,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.19962379783391954,
|
|
"num_tokens": 18610432.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.663758420944214,
|
|
"epoch": 0.8036773428232503,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004943973057821931,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.1833953693509102,
|
|
"num_tokens": 18621739.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.680219650268555,
|
|
"epoch": 0.8041716093317517,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943894768448768,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.19260417222976683,
|
|
"num_tokens": 18631983.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.6862352848052975,
|
|
"epoch": 0.8046658758402531,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000494381642510545,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.17927457243204117,
|
|
"num_tokens": 18643507.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.7087085247039795,
|
|
"epoch": 0.8051601423487544,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943738027793909,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.18695662617683412,
|
|
"num_tokens": 18654516.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.69820761680603,
|
|
"epoch": 0.8056544088572558,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004943659576516072,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.18055962175130844,
|
|
"num_tokens": 18666855.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.671946907043457,
|
|
"epoch": 0.8061486753657572,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004943581071273869,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.1805286005139351,
|
|
"num_tokens": 18679105.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.698519659042359,
|
|
"epoch": 0.8066429418742586,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004943502512069232,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.1906839370727539,
|
|
"num_tokens": 18691349.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.750455522537232,
|
|
"epoch": 0.8071372083827599,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943423898904092,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.18375960737466812,
|
|
"num_tokens": 18703773.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.706942796707153,
|
|
"epoch": 0.8076314748912614,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004943345231780385,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.18648601621389388,
|
|
"num_tokens": 18715281.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.662128543853759,
|
|
"epoch": 0.8081257413997628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943266510700043,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.19051504135131836,
|
|
"num_tokens": 18726446.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.574031162261963,
|
|
"epoch": 0.8086200079082642,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943187735665007,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.2042323023080826,
|
|
"num_tokens": 18737348.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.6237263679504395,
|
|
"epoch": 0.8091142744167655,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004943108906677211,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.19175722897052766,
|
|
"num_tokens": 18748921.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.64940390586853,
|
|
"epoch": 0.8096085409252669,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004943030023738595,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.19513626247644425,
|
|
"num_tokens": 18761252.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.643872547149658,
|
|
"epoch": 0.8101028074337683,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004942951086851102,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.18811838924884797,
|
|
"num_tokens": 18772915.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.632459449768066,
|
|
"epoch": 0.8105970739422697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004942872096016671,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.1934368595480919,
|
|
"num_tokens": 18783533.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.623964548110962,
|
|
"epoch": 0.811091340450771,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942793051237247,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18667526841163634,
|
|
"num_tokens": 18795068.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.704107761383057,
|
|
"epoch": 0.8115856069592724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942713952514773,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.17669492065906525,
|
|
"num_tokens": 18808105.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.671244192123413,
|
|
"epoch": 0.8120798734677738,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004942634799851196,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18254307061433792,
|
|
"num_tokens": 18819275.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.6933129787445065,
|
|
"epoch": 0.8125741399762753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942555593248463,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19309946447610854,
|
|
"num_tokens": 18828535.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.63012318611145,
|
|
"epoch": 0.8130684064847766,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004942476332708522,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.1880142495036125,
|
|
"num_tokens": 18839983.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.619532632827759,
|
|
"epoch": 0.813562672993278,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004942397018233322,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.18770268112421035,
|
|
"num_tokens": 18851875.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.621423578262329,
|
|
"epoch": 0.8140569395017794,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004942317649824816,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.18783365488052367,
|
|
"num_tokens": 18863629.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.647859239578247,
|
|
"epoch": 0.8145512060102807,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004942238227484956,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.19434317499399184,
|
|
"num_tokens": 18875660.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.656901836395264,
|
|
"epoch": 0.8150454725187821,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004942158751215696,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18389780670404435,
|
|
"num_tokens": 18887140.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.61653413772583,
|
|
"epoch": 0.8155397390272835,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004942079221018989,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.18758510798215866,
|
|
"num_tokens": 18899386.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.730333232879639,
|
|
"epoch": 0.8160340055357849,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004941999636896795,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.17575519382953644,
|
|
"num_tokens": 18911187.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.662143564224243,
|
|
"epoch": 0.8165282720442862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941919998851068,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1871063530445099,
|
|
"num_tokens": 18922522.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.538512277603149,
|
|
"epoch": 0.8170225385527876,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941840306883771,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19285360276699065,
|
|
"num_tokens": 18932689.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.706580305099488,
|
|
"epoch": 0.8175168050612891,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004941760560996861,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.1789873644709587,
|
|
"num_tokens": 18944296.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.7018084049224855,
|
|
"epoch": 0.8180110715697905,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004941680761192302,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.18427854031324387,
|
|
"num_tokens": 18955449.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.7311506271362305,
|
|
"epoch": 0.8185053380782918,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004941600907472055,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.18190620988607406,
|
|
"num_tokens": 18969065.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.679945564270019,
|
|
"epoch": 0.8189996045867932,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941520999838088,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.18917620927095413,
|
|
"num_tokens": 18979801.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.686408424377442,
|
|
"epoch": 0.8194938710952946,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941441038292363,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.18298430889844894,
|
|
"num_tokens": 18990795.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.710878992080689,
|
|
"epoch": 0.819988137603796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004941361022836847,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.18471910208463668,
|
|
"num_tokens": 19002318.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.650199365615845,
|
|
"epoch": 0.8204824041122973,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004941280953473513,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.19438256621360778,
|
|
"num_tokens": 19014977.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.697762298583984,
|
|
"epoch": 0.8209766706207987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004941200830204325,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.18394842445850373,
|
|
"num_tokens": 19026081.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.6803977489471436,
|
|
"epoch": 0.8214709371293001,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941120653031256,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.1822434276342392,
|
|
"num_tokens": 19037694.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.619025754928589,
|
|
"epoch": 0.8219652036378015,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004941040421956282,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.19455636739730836,
|
|
"num_tokens": 19048344.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.722106456756592,
|
|
"epoch": 0.8224594701463029,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004940960136981372,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.1871915876865387,
|
|
"num_tokens": 19060213.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.606636047363281,
|
|
"epoch": 0.8229537366548043,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004940879798108503,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.19717976301908494,
|
|
"num_tokens": 19070881.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.5907165050506595,
|
|
"epoch": 0.8234480031633057,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004940799405339651,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.1917427361011505,
|
|
"num_tokens": 19082206.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.587018775939941,
|
|
"epoch": 0.8239422696718071,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940718958676794,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.193899068236351,
|
|
"num_tokens": 19094014.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.690460920333862,
|
|
"epoch": 0.8244365361803084,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494063845812191,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.1972723424434662,
|
|
"num_tokens": 19106859.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.587282657623291,
|
|
"epoch": 0.8249308026888098,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940557903676981,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.18980784267187117,
|
|
"num_tokens": 19118296.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.666278123855591,
|
|
"epoch": 0.8254250691973112,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004940477295343988,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.1907990410923958,
|
|
"num_tokens": 19130212.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.605793571472168,
|
|
"epoch": 0.8259193357058126,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004940396633124912,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.20178446620702745,
|
|
"num_tokens": 19140798.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.691914510726929,
|
|
"epoch": 0.8264136022143139,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004940315917021742,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.18535835891962052,
|
|
"num_tokens": 19151875.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.742526245117188,
|
|
"epoch": 0.8269078687228153,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004940235147036457,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17392984479665757,
|
|
"num_tokens": 19164532.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.665090608596802,
|
|
"epoch": 0.8274021352313167,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000494015432317105,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.18460462540388106,
|
|
"num_tokens": 19176828.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.572837066650391,
|
|
"epoch": 0.8278964017398182,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004940073445427506,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.2020925760269165,
|
|
"num_tokens": 19188118.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.62059473991394,
|
|
"epoch": 0.8283906682483195,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004939992513807816,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.18436657041311263,
|
|
"num_tokens": 19201009.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.63350772857666,
|
|
"epoch": 0.8288849347568209,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004939911528313971,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.1860504150390625,
|
|
"num_tokens": 19212747.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.690491580963135,
|
|
"epoch": 0.8293792012653223,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000493983048894796,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.18318575620651245,
|
|
"num_tokens": 19224043.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.652051591873169,
|
|
"epoch": 0.8298734677738236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939749395711782,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.19014801383018493,
|
|
"num_tokens": 19235475.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.719591093063355,
|
|
"epoch": 0.830367734282325,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939668248607428,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.18801588863134383,
|
|
"num_tokens": 19247208.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.619096803665161,
|
|
"epoch": 0.8308620007908264,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004939587047636896,
|
|
"loss": 5.3513,
|
|
"mean_token_accuracy": 0.18398840725421906,
|
|
"num_tokens": 19260172.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.644792604446411,
|
|
"epoch": 0.8313562672993278,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939505792802182,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.18869961947202682,
|
|
"num_tokens": 19271173.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.674806785583496,
|
|
"epoch": 0.8318505338078291,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939424484105287,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.19194461554288864,
|
|
"num_tokens": 19282693.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.679836702346802,
|
|
"epoch": 0.8323448003163305,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004939343121548209,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.17997315227985383,
|
|
"num_tokens": 19293883.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.564936923980713,
|
|
"epoch": 0.832839066824832,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939261705132951,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1949543133378029,
|
|
"num_tokens": 19304530.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.5415472984313965,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004939180234861516,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.19091598093509674,
|
|
"num_tokens": 19315765.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.666932535171509,
|
|
"epoch": 0.8338275998418347,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939098710735906,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.1927936092019081,
|
|
"num_tokens": 19328484.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.615507936477661,
|
|
"epoch": 0.8343218663503361,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004939017132758129,
|
|
"loss": 5.3052,
|
|
"mean_token_accuracy": 0.1889285370707512,
|
|
"num_tokens": 19340594.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.724935531616211,
|
|
"epoch": 0.8348161328588375,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004938935500930192,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.18532176017761232,
|
|
"num_tokens": 19351105.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.6668126583099365,
|
|
"epoch": 0.8353103993673389,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004938853815254101,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.19699563682079316,
|
|
"num_tokens": 19361619.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.6400025367736815,
|
|
"epoch": 0.8358046658758402,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004938772075731867,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.18332935124635696,
|
|
"num_tokens": 19374251.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.7364896774292,
|
|
"epoch": 0.8362989323843416,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004938690282365499,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.1773327350616455,
|
|
"num_tokens": 19386300.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.659038972854614,
|
|
"epoch": 0.836793198892843,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004938608435157012,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1898784428834915,
|
|
"num_tokens": 19397082.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.610478067398072,
|
|
"epoch": 0.8372874654013444,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004938526534108417,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.18632503896951674,
|
|
"num_tokens": 19409123.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.542996788024903,
|
|
"epoch": 0.8377817319098458,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938444579221732,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.2029905751347542,
|
|
"num_tokens": 19419854.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.636118745803833,
|
|
"epoch": 0.8382759984183472,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004938362570498969,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.18787182122468948,
|
|
"num_tokens": 19430825.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.623866319656372,
|
|
"epoch": 0.8387702649268486,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938280507942146,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1818978264927864,
|
|
"num_tokens": 19442617.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.721683168411255,
|
|
"epoch": 0.83926453143535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938198391553285,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.18268522769212722,
|
|
"num_tokens": 19453911.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.6255655765533445,
|
|
"epoch": 0.8397587979438513,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004938116221334404,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.18966425955295563,
|
|
"num_tokens": 19464837.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.574881935119629,
|
|
"epoch": 0.8402530644523527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938033997287524,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.19560590088367463,
|
|
"num_tokens": 19477067.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.5759570598602295,
|
|
"epoch": 0.8407473309608541,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937951719414668,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.1896255925297737,
|
|
"num_tokens": 19489442.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.618827962875367,
|
|
"epoch": 0.8412415974693555,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004937869387717861,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18787578344345093,
|
|
"num_tokens": 19501197.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.6528948783874515,
|
|
"epoch": 0.8417358639778568,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004937787002199127,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.19116035848855972,
|
|
"num_tokens": 19513311.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.735564565658569,
|
|
"epoch": 0.8422301304863582,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004937704562860493,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.17906060963869094,
|
|
"num_tokens": 19525643.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.566340589523316,
|
|
"epoch": 0.8427243969948597,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004937622069703988,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.1952924534678459,
|
|
"num_tokens": 19537478.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.652986860275268,
|
|
"epoch": 0.843218663503361,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004937539522731641,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.19262114465236663,
|
|
"num_tokens": 19549370.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.677238416671753,
|
|
"epoch": 0.8437129300118624,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937456921945482,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.19591226130723954,
|
|
"num_tokens": 19561793.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.5420262813568115,
|
|
"epoch": 0.8442071965203638,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004937374267347543,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.20097958892583848,
|
|
"num_tokens": 19573603.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.625102758407593,
|
|
"epoch": 0.8447014630288652,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937291558939858,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.18257204294204712,
|
|
"num_tokens": 19584848.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.616266870498658,
|
|
"epoch": 0.8451957295373665,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004937208796724461,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.18870454728603364,
|
|
"num_tokens": 19594965.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.628319978713989,
|
|
"epoch": 0.8456899960458679,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004937125980703389,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.20184896290302276,
|
|
"num_tokens": 19607347.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.6301665782928465,
|
|
"epoch": 0.8461842625543693,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004937043110878678,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.19272432029247283,
|
|
"num_tokens": 19618614.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.630640888214112,
|
|
"epoch": 0.8466785290628707,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004936960187252367,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.1898093119263649,
|
|
"num_tokens": 19630409.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.614495325088501,
|
|
"epoch": 0.847172795571372,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004936877209826497,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.1860443025827408,
|
|
"num_tokens": 19642183.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.610469961166382,
|
|
"epoch": 0.8476670620798734,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004936794178603108,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.19837487488985062,
|
|
"num_tokens": 19653846.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.647045516967774,
|
|
"epoch": 0.8481613285883749,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004936711093584242,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.19066232144832612,
|
|
"num_tokens": 19664183.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.651234722137451,
|
|
"epoch": 0.8486555950968763,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004936627954771945,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.18965909034013748,
|
|
"num_tokens": 19675863.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.608486032485962,
|
|
"epoch": 0.8491498616053776,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004936544762168261,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.19289756417274476,
|
|
"num_tokens": 19688410.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.639685392379761,
|
|
"epoch": 0.849644128113879,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936461515775237,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.18706392198801042,
|
|
"num_tokens": 19698849.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.712615442276001,
|
|
"epoch": 0.8501383946223804,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000493637821559492,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.1762271672487259,
|
|
"num_tokens": 19710761.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.630744504928589,
|
|
"epoch": 0.8506326611308818,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004936294861629358,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18898882120847701,
|
|
"num_tokens": 19722530.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.624499034881592,
|
|
"epoch": 0.8511269276393831,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936211453880606,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1893622949719429,
|
|
"num_tokens": 19733352.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.662234544754028,
|
|
"epoch": 0.8516211941478845,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004936127992350712,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.19108893424272538,
|
|
"num_tokens": 19745071.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.621189308166504,
|
|
"epoch": 0.8521154606563859,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004936044477041729,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.1932872161269188,
|
|
"num_tokens": 19756039.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.670988082885742,
|
|
"epoch": 0.8526097271648873,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935960907955715,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.17891822755336761,
|
|
"num_tokens": 19768728.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.61225266456604,
|
|
"epoch": 0.8531039936733887,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935877285094722,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.18423692137002945,
|
|
"num_tokens": 19780010.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.65412220954895,
|
|
"epoch": 0.8535982601818901,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493579360846081,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.19768353402614594,
|
|
"num_tokens": 19790082.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.6661571025848385,
|
|
"epoch": 0.8540925266903915,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935709878056034,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1892878919839859,
|
|
"num_tokens": 19801702.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.661633682250977,
|
|
"epoch": 0.8545867931988929,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004935626093882457,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.18570428043603898,
|
|
"num_tokens": 19812173.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.629301738739014,
|
|
"epoch": 0.8550810597073942,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493554225594214,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.19773084670305252,
|
|
"num_tokens": 19823286.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.693342828750611,
|
|
"epoch": 0.8555753262158956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004935458364237143,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.190741828083992,
|
|
"num_tokens": 19834472.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.665266036987305,
|
|
"epoch": 0.856069592724397,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004935374418769532,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.1872141808271408,
|
|
"num_tokens": 19845073.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.66392297744751,
|
|
"epoch": 0.8565638592328984,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004935290419541371,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1858500674366951,
|
|
"num_tokens": 19856762.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.625785779953003,
|
|
"epoch": 0.8570581257413997,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004935206366554726,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.19144676774740219,
|
|
"num_tokens": 19867358.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.615385293960571,
|
|
"epoch": 0.8575523922499011,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935122259811667,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.19447528421878815,
|
|
"num_tokens": 19878527.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.697225570678711,
|
|
"epoch": 0.8580466587584026,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493503809931426,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.18498689234256743,
|
|
"num_tokens": 19889680.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.655039262771607,
|
|
"epoch": 0.858540925266904,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004934953885064577,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.19361486732959748,
|
|
"num_tokens": 19900569.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.588249015808105,
|
|
"epoch": 0.8590351917754053,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000493486961706469,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19664759039878846,
|
|
"num_tokens": 19912537.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.6815883159637455,
|
|
"epoch": 0.8595294582839067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934785295316672,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1965631663799286,
|
|
"num_tokens": 19923931.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.705501413345337,
|
|
"epoch": 0.8600237247924081,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004934700919822596,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.1823534056544304,
|
|
"num_tokens": 19933956.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.559091186523437,
|
|
"epoch": 0.8605179913009094,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004934616490584538,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.19276793003082277,
|
|
"num_tokens": 19945603.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.677602958679199,
|
|
"epoch": 0.8610122578094108,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934532007604577,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.19237906038761138,
|
|
"num_tokens": 19956358.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.61974778175354,
|
|
"epoch": 0.8615065243179122,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004934447470884788,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.19488293677568436,
|
|
"num_tokens": 19967856.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.60012845993042,
|
|
"epoch": 0.8620007908264136,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004934362880427253,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.19039387553930281,
|
|
"num_tokens": 19979323.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.699257898330688,
|
|
"epoch": 0.8624950573349149,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004934278236234052,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.18056602478027345,
|
|
"num_tokens": 19991543.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.683034086227417,
|
|
"epoch": 0.8629893238434164,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004934193538307268,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.18849651515483856,
|
|
"num_tokens": 20003621.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.568985176086426,
|
|
"epoch": 0.8634835903519178,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004934108786648983,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.183358895778656,
|
|
"num_tokens": 20015183.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.660060453414917,
|
|
"epoch": 0.8639778568604192,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004934023981261285,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.18640766888856888,
|
|
"num_tokens": 20026735.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.624735355377197,
|
|
"epoch": 0.8644721233689205,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933939122146256,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.19271255731582643,
|
|
"num_tokens": 20037410.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.548708438873291,
|
|
"epoch": 0.8649663898774219,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004933854209305987,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.1923980250954628,
|
|
"num_tokens": 20048972.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.699293947219848,
|
|
"epoch": 0.8654606563859233,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004933769242742566,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.1967056706547737,
|
|
"num_tokens": 20059667.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.625824689865112,
|
|
"epoch": 0.8659549228944247,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004933684222458082,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.19832002818584443,
|
|
"num_tokens": 20070612.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.567928647994995,
|
|
"epoch": 0.866449189402926,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933599148454628,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1937839835882187,
|
|
"num_tokens": 20081445.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.684582853317261,
|
|
"epoch": 0.8669434559114274,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004933514020734296,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.18456608355045317,
|
|
"num_tokens": 20094414.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.60057487487793,
|
|
"epoch": 0.8674377224199288,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004933428839299181,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.2031479448080063,
|
|
"num_tokens": 20106793.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.58985481262207,
|
|
"epoch": 0.8679319889284303,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004933343604151376,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1928417980670929,
|
|
"num_tokens": 20118582.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.627998208999633,
|
|
"epoch": 0.8684262554369316,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004933258315292982,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.19237957745790482,
|
|
"num_tokens": 20130548.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.654617643356323,
|
|
"epoch": 0.868920521945433,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004933172972726094,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.18313205391168594,
|
|
"num_tokens": 20141821.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.6661763191223145,
|
|
"epoch": 0.8694147884539344,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004933087576452811,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.19099952578544616,
|
|
"num_tokens": 20152071.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.650398826599121,
|
|
"epoch": 0.8699090549624358,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004933002126475235,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.19017913490533828,
|
|
"num_tokens": 20163780.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.583788204193115,
|
|
"epoch": 0.8704033214709371,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004932916622795468,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1903591126203537,
|
|
"num_tokens": 20175477.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.574006128311157,
|
|
"epoch": 0.8708975879794385,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004932831065415614,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.1951898828148842,
|
|
"num_tokens": 20189452.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.6863140106201175,
|
|
"epoch": 0.8713918544879399,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932745454337778,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.19187350273132325,
|
|
"num_tokens": 20201250.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.577649307250977,
|
|
"epoch": 0.8718861209964412,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004932659789564065,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19492629766464234,
|
|
"num_tokens": 20212394.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.632228708267212,
|
|
"epoch": 0.8723803875049426,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004932574071096581,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.19227567315101624,
|
|
"num_tokens": 20223262.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.622003507614136,
|
|
"epoch": 0.872874654013444,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004932488298937437,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.19351560920476912,
|
|
"num_tokens": 20234088.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.559382677078247,
|
|
"epoch": 0.8733689205219455,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932402473088743,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.19630859941244125,
|
|
"num_tokens": 20245373.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.683034801483155,
|
|
"epoch": 0.8738631870304469,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004932316593552609,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.19051172584295273,
|
|
"num_tokens": 20255824.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.575156927108765,
|
|
"epoch": 0.8743574535389482,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004932230660331148,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.20189533531665801,
|
|
"num_tokens": 20266576.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.6922413349151615,
|
|
"epoch": 0.8748517200474496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932144673426475,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.1854723498225212,
|
|
"num_tokens": 20277874.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.6022850513458256,
|
|
"epoch": 0.875345986555951,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004932058632840705,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19467467963695526,
|
|
"num_tokens": 20288403.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.716291666030884,
|
|
"epoch": 0.8758402530644523,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931972538575952,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.18976085782051086,
|
|
"num_tokens": 20299564.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.626631450653076,
|
|
"epoch": 0.8763345195729537,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931886390634338,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.19307836890220642,
|
|
"num_tokens": 20312208.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.586365795135498,
|
|
"epoch": 0.8768287860814551,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000493180018901798,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.19199634343385696,
|
|
"num_tokens": 20323486.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.6254486560821535,
|
|
"epoch": 0.8773230525899565,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004931713933728997,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18812766075134277,
|
|
"num_tokens": 20335806.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.627936792373657,
|
|
"epoch": 0.8778173190984578,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931627624769515,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.19559958428144456,
|
|
"num_tokens": 20347216.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.668179130554199,
|
|
"epoch": 0.8783115856069593,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931541262141653,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.18359874337911605,
|
|
"num_tokens": 20358938.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.646789169311523,
|
|
"epoch": 0.8788058521154607,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004931454845847539,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.1863119438290596,
|
|
"num_tokens": 20370742.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.533660078048706,
|
|
"epoch": 0.8793001186239621,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004931368375889298,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19917842149734497,
|
|
"num_tokens": 20382100.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.696718072891235,
|
|
"epoch": 0.8797943851324634,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004931281852269054,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1852152332663536,
|
|
"num_tokens": 20393348.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.6462465763092045,
|
|
"epoch": 0.8802886516409648,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493119527498894,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.20135423094034194,
|
|
"num_tokens": 20403471.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.575044918060303,
|
|
"epoch": 0.8807829181494662,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931108644051084,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.20270061641931533,
|
|
"num_tokens": 20415146.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.665388345718384,
|
|
"epoch": 0.8812771846579676,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004931021959457617,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.18896603733301162,
|
|
"num_tokens": 20425857.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.627101469039917,
|
|
"epoch": 0.8817714511664689,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000493093522121067,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.1786689355969429,
|
|
"num_tokens": 20437987.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.605519247055054,
|
|
"epoch": 0.8822657176749703,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004930848429312379,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.19142666608095169,
|
|
"num_tokens": 20449079.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.672420835494995,
|
|
"epoch": 0.8827599841834717,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930761583764879,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.18534404784440994,
|
|
"num_tokens": 20461032.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.713896703720093,
|
|
"epoch": 0.8832542506919732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930674684570306,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.19122811704874038,
|
|
"num_tokens": 20471825.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.683028793334961,
|
|
"epoch": 0.8837485172004745,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004930587731730796,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.1945595845580101,
|
|
"num_tokens": 20483329.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.636679983139038,
|
|
"epoch": 0.8842427837089759,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000493050072524849,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.18361458033323289,
|
|
"num_tokens": 20494537.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.578615140914917,
|
|
"epoch": 0.8847370502174773,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004930413665125528,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19713531881570817,
|
|
"num_tokens": 20506205.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.645243167877197,
|
|
"epoch": 0.8852313167259787,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004930326551364052,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.1907733276486397,
|
|
"num_tokens": 20517447.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.6713865280151365,
|
|
"epoch": 0.88572558323448,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004930239383966204,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.1947559803724289,
|
|
"num_tokens": 20529435.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.6489564895629885,
|
|
"epoch": 0.8862198497429814,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004930152162934128,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.20294218361377717,
|
|
"num_tokens": 20540151.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.6032298564910885,
|
|
"epoch": 0.8867141162514828,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004930064888269973,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18443470895290376,
|
|
"num_tokens": 20552355.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.689976978302002,
|
|
"epoch": 0.8872083827599841,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004929977559975881,
|
|
"loss": 5.3484,
|
|
"mean_token_accuracy": 0.1876038894057274,
|
|
"num_tokens": 20562129.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.640780973434448,
|
|
"epoch": 0.8877026492684855,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004929890178054004,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.19223759919404984,
|
|
"num_tokens": 20573232.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.617765665054321,
|
|
"epoch": 0.888196915776987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929802742506491,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.19902599602937698,
|
|
"num_tokens": 20582986.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.674885368347168,
|
|
"epoch": 0.8886911822854884,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004929715253335492,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.19323651790618895,
|
|
"num_tokens": 20593619.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.583137464523316,
|
|
"epoch": 0.8891854487939898,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004929627710543159,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.1936362475156784,
|
|
"num_tokens": 20604748.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.6882861137390135,
|
|
"epoch": 0.8896797153024911,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929540114131647,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.1791296437382698,
|
|
"num_tokens": 20615915.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8896797153024911,
|
|
"eval_entropy": 5.47890327331618,
|
|
"eval_loss": 5.328938007354736,
|
|
"eval_mean_token_accuracy": 0.1972782794913096,
|
|
"eval_num_tokens": 20615915.0,
|
|
"eval_runtime": 20.5309,
|
|
"eval_samples_per_second": 1583.616,
|
|
"eval_steps_per_second": 197.995,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.608039999008179,
|
|
"epoch": 0.8901739818109925,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004929452464103109,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.1942211478948593,
|
|
"num_tokens": 20627127.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.661704063415527,
|
|
"epoch": 0.8906682483194939,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004929364760459704,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.18934856355190277,
|
|
"num_tokens": 20638568.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.576007986068726,
|
|
"epoch": 0.8911625148279952,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004929277003203586,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.19965030401945114,
|
|
"num_tokens": 20650803.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.635476875305176,
|
|
"epoch": 0.8916567813364966,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929189192336916,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.1840985432267189,
|
|
"num_tokens": 20663021.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.609073114395142,
|
|
"epoch": 0.892151047844998,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004929101327861854,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.1931273505091667,
|
|
"num_tokens": 20675144.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.641273498535156,
|
|
"epoch": 0.8926453143534994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929013409780562,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19299022108316422,
|
|
"num_tokens": 20685941.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.580771636962891,
|
|
"epoch": 0.8931395808620007,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004928925438095202,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.18719339221715928,
|
|
"num_tokens": 20696996.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.625216817855835,
|
|
"epoch": 0.8936338473705022,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004928837412807938,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.19271886795759202,
|
|
"num_tokens": 20708571.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.645078134536743,
|
|
"epoch": 0.8941281138790036,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004928749333920935,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.19714017659425737,
|
|
"num_tokens": 20719816.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.629637002944946,
|
|
"epoch": 0.894622380387505,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000492866120143636,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.19270482361316682,
|
|
"num_tokens": 20731540.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.6221473693847654,
|
|
"epoch": 0.8951166468960063,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004928573015356382,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.1948941543698311,
|
|
"num_tokens": 20742949.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.633759689331055,
|
|
"epoch": 0.8956109134045077,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004928484775683171,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.1925402268767357,
|
|
"num_tokens": 20752840.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.667916584014892,
|
|
"epoch": 0.8961051799130091,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004928396482418895,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18978545665740967,
|
|
"num_tokens": 20763772.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.62776551246643,
|
|
"epoch": 0.8965994464215105,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004928308135565728,
|
|
"loss": 5.2931,
|
|
"mean_token_accuracy": 0.19508009254932404,
|
|
"num_tokens": 20775815.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.6546248435974125,
|
|
"epoch": 0.8970937129300118,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004928219735125843,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.1867268294095993,
|
|
"num_tokens": 20787307.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.662793922424316,
|
|
"epoch": 0.8975879794385132,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004928131281101415,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18566095530986787,
|
|
"num_tokens": 20798910.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.719676733016968,
|
|
"epoch": 0.8980822459470146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000492804277349462,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.18229461908340455,
|
|
"num_tokens": 20808628.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.623229169845581,
|
|
"epoch": 0.8985765124555161,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004927954212307634,
|
|
"loss": 5.2484,
|
|
"mean_token_accuracy": 0.19233248829841615,
|
|
"num_tokens": 20820117.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.579427194595337,
|
|
"epoch": 0.8990707789640174,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927865597542637,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.20122673958539963,
|
|
"num_tokens": 20830859.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.6382408618927,
|
|
"epoch": 0.8995650454725188,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004927776929201807,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.1934790790081024,
|
|
"num_tokens": 20843016.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.603344392776489,
|
|
"epoch": 0.9000593119810202,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927688207287328,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.19735045433044435,
|
|
"num_tokens": 20854873.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.689843273162841,
|
|
"epoch": 0.9005535784895216,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004927599431801381,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.19032826274633408,
|
|
"num_tokens": 20866756.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.617052984237671,
|
|
"epoch": 0.9010478449980229,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000492751060274615,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.2041651874780655,
|
|
"num_tokens": 20878859.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.6377472400665285,
|
|
"epoch": 0.9015421115065243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004927421720123821,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.19372290670871734,
|
|
"num_tokens": 20889188.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.5876377582550045,
|
|
"epoch": 0.9020363780150257,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004927332783936579,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19304563254117965,
|
|
"num_tokens": 20900318.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.596222019195556,
|
|
"epoch": 0.902530644523527,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004927243794186614,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18640169203281404,
|
|
"num_tokens": 20912384.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.637099075317383,
|
|
"epoch": 0.9030249110320284,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004927154750876112,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.1945919066667557,
|
|
"num_tokens": 20923002.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.692681837081909,
|
|
"epoch": 0.9035191775405299,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004927065654007268,
|
|
"loss": 5.4231,
|
|
"mean_token_accuracy": 0.18299901187419892,
|
|
"num_tokens": 20934235.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.5883252143859865,
|
|
"epoch": 0.9040134440490313,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004926976503582269,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18882970362901688,
|
|
"num_tokens": 20946788.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.636935806274414,
|
|
"epoch": 0.9045077105575327,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492688729960331,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19535788744688035,
|
|
"num_tokens": 20958963.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.6738831996917725,
|
|
"epoch": 0.905001977066034,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004926798042072587,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.1906489074230194,
|
|
"num_tokens": 20969630.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.59778790473938,
|
|
"epoch": 0.9054962435745354,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004926708730992294,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19406097680330275,
|
|
"num_tokens": 20980489.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.64363317489624,
|
|
"epoch": 0.9059905100830368,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004926619366364629,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.1919349417090416,
|
|
"num_tokens": 20992199.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.676075553894043,
|
|
"epoch": 0.9064847765915381,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492652994819179,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.1892781972885132,
|
|
"num_tokens": 21003680.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.608012962341308,
|
|
"epoch": 0.9069790431000395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004926440476475975,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.20041443407535553,
|
|
"num_tokens": 21014191.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.5886283874511715,
|
|
"epoch": 0.9074733096085409,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004926350951219388,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19715968370437623,
|
|
"num_tokens": 21025692.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.615425872802734,
|
|
"epoch": 0.9079675761170423,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000492626137242423,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.19887588173151016,
|
|
"num_tokens": 21036643.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.651152896881103,
|
|
"epoch": 0.9084618426255437,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004926171740092704,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.18680619597434997,
|
|
"num_tokens": 21047509.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.610640954971314,
|
|
"epoch": 0.9089561091340451,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004926082054227016,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.19079017788171768,
|
|
"num_tokens": 21059854.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.628097820281982,
|
|
"epoch": 0.9094503756425465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004925992314829372,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19790041148662568,
|
|
"num_tokens": 21069926.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.684758615493775,
|
|
"epoch": 0.9099446421510479,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000492590252190198,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18842111229896547,
|
|
"num_tokens": 21081580.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.592061471939087,
|
|
"epoch": 0.9104389086595492,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004925812675447047,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19864101707935333,
|
|
"num_tokens": 21092510.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.593926811218262,
|
|
"epoch": 0.9109331751680506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004925722775466785,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.19563381373882294,
|
|
"num_tokens": 21103995.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.585638093948364,
|
|
"epoch": 0.911427441676552,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004925632821963406,
|
|
"loss": 5.3134,
|
|
"mean_token_accuracy": 0.1955977663397789,
|
|
"num_tokens": 21114949.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.577049303054809,
|
|
"epoch": 0.9119217081850534,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004925542814939121,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.2003214254975319,
|
|
"num_tokens": 21125810.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.6128781795501705,
|
|
"epoch": 0.9124159746935547,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004925452754396146,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.1855644091963768,
|
|
"num_tokens": 21137728.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.598874044418335,
|
|
"epoch": 0.9129102412020561,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004925362640336696,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19423135221004487,
|
|
"num_tokens": 21149249.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.603559255599976,
|
|
"epoch": 0.9134045077105575,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004925272472762987,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.18429987132549286,
|
|
"num_tokens": 21162338.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.558680629730224,
|
|
"epoch": 0.913898774219059,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004925182251677238,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.2053635001182556,
|
|
"num_tokens": 21172953.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.584990072250366,
|
|
"epoch": 0.9143930407275603,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004925091977081668,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.19499597698450089,
|
|
"num_tokens": 21183835.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.551011085510254,
|
|
"epoch": 0.9148873072360617,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004925001648978498,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.19924670606851577,
|
|
"num_tokens": 21195392.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.737870788574218,
|
|
"epoch": 0.9153815737445631,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492491126736995,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.18362648338079451,
|
|
"num_tokens": 21207213.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.68385534286499,
|
|
"epoch": 0.9158758402530645,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004924820832258248,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.1934768319129944,
|
|
"num_tokens": 21218843.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.57321605682373,
|
|
"epoch": 0.9163701067615658,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004924730343645614,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1911016121506691,
|
|
"num_tokens": 21229596.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.667065525054932,
|
|
"epoch": 0.9168643732700672,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004924639801534278,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.1913779318332672,
|
|
"num_tokens": 21240040.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.679235315322876,
|
|
"epoch": 0.9173586397785686,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004924549205926465,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.18306160867214202,
|
|
"num_tokens": 21252046.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.6912134170532225,
|
|
"epoch": 0.91785290628707,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004924458556824405,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.1818564310669899,
|
|
"num_tokens": 21263720.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.66510329246521,
|
|
"epoch": 0.9183471727955713,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004924367854230326,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.18773467242717742,
|
|
"num_tokens": 21275751.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.60714054107666,
|
|
"epoch": 0.9188414393040728,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004924277098146461,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.19376610368490219,
|
|
"num_tokens": 21287081.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.591529417037964,
|
|
"epoch": 0.9193357058125742,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924186288575043,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.1956242397427559,
|
|
"num_tokens": 21298007.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.689355087280274,
|
|
"epoch": 0.9198299723210756,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004924095425518304,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.18748197108507156,
|
|
"num_tokens": 21309416.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.5772706985473635,
|
|
"epoch": 0.9203242388295769,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492400450897848,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.19434358030557633,
|
|
"num_tokens": 21321129.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.605843257904053,
|
|
"epoch": 0.9208185053380783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004923913538957809,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19848465770483018,
|
|
"num_tokens": 21331706.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.628567028045654,
|
|
"epoch": 0.9213127718465797,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004923822515458526,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.19570659399032592,
|
|
"num_tokens": 21343738.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.602812242507935,
|
|
"epoch": 0.921807038355081,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004923731438482873,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.19304077476263046,
|
|
"num_tokens": 21354714.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.672587156295776,
|
|
"epoch": 0.9223013048635824,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004923640308033088,
|
|
"loss": 5.3346,
|
|
"mean_token_accuracy": 0.1851639434695244,
|
|
"num_tokens": 21365947.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.729375123977661,
|
|
"epoch": 0.9227955713720838,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923549124111416,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.18300598561763765,
|
|
"num_tokens": 21376729.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.612264728546142,
|
|
"epoch": 0.9232898378805852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923457886720098,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.20023103058338165,
|
|
"num_tokens": 21388017.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.570937442779541,
|
|
"epoch": 0.9237841043890866,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004923366595861378,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.20207480043172837,
|
|
"num_tokens": 21399566.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.644844961166382,
|
|
"epoch": 0.924278370897588,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004923275251537503,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1912105306982994,
|
|
"num_tokens": 21410276.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.602874231338501,
|
|
"epoch": 0.9247726374060894,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000492318385375072,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.19977347403764725,
|
|
"num_tokens": 21421090.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.591992282867432,
|
|
"epoch": 0.9252669039145908,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923092402503277,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19554599225521088,
|
|
"num_tokens": 21431057.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.597142171859741,
|
|
"epoch": 0.9257611704230921,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004923000897797423,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.1854785606265068,
|
|
"num_tokens": 21443849.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.704565191268921,
|
|
"epoch": 0.9262554369315935,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004922909339635411,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18549126982688904,
|
|
"num_tokens": 21454824.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.6667567729949955,
|
|
"epoch": 0.9267497034400949,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004922817728019492,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.19091322273015976,
|
|
"num_tokens": 21466082.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.577264308929443,
|
|
"epoch": 0.9272439699485963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922726062951918,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.19171712994575502,
|
|
"num_tokens": 21477805.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.6575517654418945,
|
|
"epoch": 0.9277382364570976,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922634344434948,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.18642699718475342,
|
|
"num_tokens": 21490014.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.615246772766113,
|
|
"epoch": 0.928232502965599,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004922542572470835,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.1938742831349373,
|
|
"num_tokens": 21501713.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.536674118041992,
|
|
"epoch": 0.9287267694741005,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004922450747061837,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19749983549118041,
|
|
"num_tokens": 21513258.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.609413528442383,
|
|
"epoch": 0.9292210359826019,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004922358868210214,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1925557628273964,
|
|
"num_tokens": 21526259.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.584788465499878,
|
|
"epoch": 0.9297153024911032,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004922266935918227,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.19477527886629104,
|
|
"num_tokens": 21539144.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.673647069931031,
|
|
"epoch": 0.9302095689996046,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004922174950188136,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.18334164917469026,
|
|
"num_tokens": 21550550.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.604119157791137,
|
|
"epoch": 0.930703835508106,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004922082911022204,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.19387674778699876,
|
|
"num_tokens": 21562491.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.57192096710205,
|
|
"epoch": 0.9311981020166074,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004921990818422694,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18991569876670839,
|
|
"num_tokens": 21573679.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.642074489593506,
|
|
"epoch": 0.9316923685251087,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004921898672391874,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.19252065271139146,
|
|
"num_tokens": 21585491.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.643537187576294,
|
|
"epoch": 0.9321866350336101,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004921806472932011,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.19361097663640975,
|
|
"num_tokens": 21598302.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.548214673995972,
|
|
"epoch": 0.9326809015421115,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004921714220045371,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.19482027143239974,
|
|
"num_tokens": 21608442.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.64955849647522,
|
|
"epoch": 0.9331751680506128,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004921621913734223,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.19053839892148972,
|
|
"num_tokens": 21619594.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.69784140586853,
|
|
"epoch": 0.9336694345591142,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921529554000841,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1914744883775711,
|
|
"num_tokens": 21631065.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.561979198455811,
|
|
"epoch": 0.9341637010676157,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004921437140847493,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.19402305036783218,
|
|
"num_tokens": 21640949.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.760262727737427,
|
|
"epoch": 0.9346579675761171,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921344674276456,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.18913189619779586,
|
|
"num_tokens": 21651189.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.7121833801269535,
|
|
"epoch": 0.9351522340846185,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004921252154290003,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.18299551159143448,
|
|
"num_tokens": 21662790.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.626903104782104,
|
|
"epoch": 0.9356465005931198,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492115958089041,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.1882074698805809,
|
|
"num_tokens": 21674980.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.652727651596069,
|
|
"epoch": 0.9361407671016212,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921066954079955,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.1957204207777977,
|
|
"num_tokens": 21687721.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.662063074111939,
|
|
"epoch": 0.9366350336101226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004920974273860915,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.18004003465175628,
|
|
"num_tokens": 21699522.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.616191768646241,
|
|
"epoch": 0.9371293001186239,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004920881540235572,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.19853858798742294,
|
|
"num_tokens": 21709972.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.553194618225097,
|
|
"epoch": 0.9376235666271253,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004920788753206205,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.19493181705474855,
|
|
"num_tokens": 21722172.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.596704435348511,
|
|
"epoch": 0.9381178331356267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049206959127751,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.19186157286167144,
|
|
"num_tokens": 21734314.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.63874249458313,
|
|
"epoch": 0.9386120996441281,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004920603018944537,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.1962213173508644,
|
|
"num_tokens": 21744031.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.630405330657959,
|
|
"epoch": 0.9391063661526295,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920510071716803,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.19808519929647445,
|
|
"num_tokens": 21755653.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.674383592605591,
|
|
"epoch": 0.9396006326611309,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004920417071094186,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.18645153492689132,
|
|
"num_tokens": 21768513.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.6544403553009035,
|
|
"epoch": 0.9400948991696323,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004920324017078971,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.18442377597093582,
|
|
"num_tokens": 21780857.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.579956436157227,
|
|
"epoch": 0.9405891656781337,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492023090967345,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.20063927620649338,
|
|
"num_tokens": 21792514.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.630829238891602,
|
|
"epoch": 0.941083432186635,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492013774887991,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.19309911578893663,
|
|
"num_tokens": 21803154.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.634845209121704,
|
|
"epoch": 0.9415776986951364,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920044534700645,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.18889188021421432,
|
|
"num_tokens": 21814439.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.629956912994385,
|
|
"epoch": 0.9420719652036378,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004919951267137949,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.19965579360723495,
|
|
"num_tokens": 21826870.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.6650889873504635,
|
|
"epoch": 0.9425662317121392,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004919857946194114,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.19790223240852356,
|
|
"num_tokens": 21837627.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.607153797149659,
|
|
"epoch": 0.9430604982206405,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919764571871438,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.19002410322427749,
|
|
"num_tokens": 21848891.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.676448154449463,
|
|
"epoch": 0.9435547647291419,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004919671144172216,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.1898767203092575,
|
|
"num_tokens": 21860094.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.58936619758606,
|
|
"epoch": 0.9440490312376434,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004919577663098748,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.194608274102211,
|
|
"num_tokens": 21870881.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.560912370681763,
|
|
"epoch": 0.9445432977461448,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004919484128653333,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.19403542578220367,
|
|
"num_tokens": 21882825.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.662732362747192,
|
|
"epoch": 0.9450375642546461,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004919390540838271,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.18788367360830308,
|
|
"num_tokens": 21894952.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.651932430267334,
|
|
"epoch": 0.9455318307631475,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004919296899655866,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.1855970874428749,
|
|
"num_tokens": 21906893.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.643131875991822,
|
|
"epoch": 0.9460260972716489,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491920320510842,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.19035353362560273,
|
|
"num_tokens": 21918571.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.601896953582764,
|
|
"epoch": 0.9465203637801503,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004919109457198239,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1949240520596504,
|
|
"num_tokens": 21929488.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.5939172267913815,
|
|
"epoch": 0.9470146302886516,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004919015655927629,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.1913357272744179,
|
|
"num_tokens": 21940368.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.636135387420654,
|
|
"epoch": 0.947508896797153,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918921801298897,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.19131146520376205,
|
|
"num_tokens": 21951171.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.673929071426391,
|
|
"epoch": 0.9480031633056544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004918827893314353,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.19988007247447967,
|
|
"num_tokens": 21962312.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.668216514587402,
|
|
"epoch": 0.9484974298141557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918733931976305,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.19467929303646087,
|
|
"num_tokens": 21971994.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.680405378341675,
|
|
"epoch": 0.9489916963226572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004918639917287067,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.18573708683252335,
|
|
"num_tokens": 21983084.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.67577052116394,
|
|
"epoch": 0.9494859628311586,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004918545849248951,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.18384079337120057,
|
|
"num_tokens": 21995005.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.561293649673462,
|
|
"epoch": 0.94998022933966,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000491845172786427,
|
|
"loss": 5.2932,
|
|
"mean_token_accuracy": 0.1960711047053337,
|
|
"num_tokens": 22006377.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.612299299240112,
|
|
"epoch": 0.9504744958481613,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918357553135339,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18998344093561173,
|
|
"num_tokens": 22019663.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.755678939819336,
|
|
"epoch": 0.9509687623566627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918263325064476,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.18709334582090378,
|
|
"num_tokens": 22030646.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.647117233276367,
|
|
"epoch": 0.9514630288651641,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004918169043654,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.19839103370904923,
|
|
"num_tokens": 22043563.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.597343301773071,
|
|
"epoch": 0.9519572953736655,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004918074708906229,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19743698388338088,
|
|
"num_tokens": 22055224.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.621808052062988,
|
|
"epoch": 0.9524515618821668,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004917980320823483,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18741225749254226,
|
|
"num_tokens": 22067445.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.627112531661988,
|
|
"epoch": 0.9529458283906682,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004917885879408085,
|
|
"loss": 5.2642,
|
|
"mean_token_accuracy": 0.1959032729268074,
|
|
"num_tokens": 22078565.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.5303792476654055,
|
|
"epoch": 0.9534400948991696,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004917791384662359,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.2047170639038086,
|
|
"num_tokens": 22088658.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.581570816040039,
|
|
"epoch": 0.953934361407671,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004917696836588628,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.1871662840247154,
|
|
"num_tokens": 22100747.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.56132493019104,
|
|
"epoch": 0.9544286279161724,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004917602235189218,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.19224132001399993,
|
|
"num_tokens": 22113559.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.719173574447632,
|
|
"epoch": 0.9549228944246738,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004917507580466457,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.1880786120891571,
|
|
"num_tokens": 22124678.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.628768110275269,
|
|
"epoch": 0.9554171609331752,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004917412872422674,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.19654264450073242,
|
|
"num_tokens": 22136462.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.594167852401734,
|
|
"epoch": 0.9559114274416766,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004917318111060198,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.1990877091884613,
|
|
"num_tokens": 22149101.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.610759210586548,
|
|
"epoch": 0.9564056939501779,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491722329638136,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.1942766711115837,
|
|
"num_tokens": 22159574.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.644517946243286,
|
|
"epoch": 0.9568999604586793,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004917128428388492,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.19246622622013093,
|
|
"num_tokens": 22172308.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.613810300827026,
|
|
"epoch": 0.9573942269671807,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004917033507083929,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.18665868043899536,
|
|
"num_tokens": 22183714.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.5523786544799805,
|
|
"epoch": 0.9578884934756821,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004916938532470006,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.1981526121497154,
|
|
"num_tokens": 22194785.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.635073041915893,
|
|
"epoch": 0.9583827599841834,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004916843504549058,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.19318872094154357,
|
|
"num_tokens": 22205998.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.644573450088501,
|
|
"epoch": 0.9588770264926848,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004916748423323424,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.19198890924453735,
|
|
"num_tokens": 22216114.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.603600311279297,
|
|
"epoch": 0.9593712930011863,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004916653288795443,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.20045812726020812,
|
|
"num_tokens": 22226793.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.645380735397339,
|
|
"epoch": 0.9598655595096877,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004916558100967455,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1936730772256851,
|
|
"num_tokens": 22237444.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.610105514526367,
|
|
"epoch": 0.960359826018189,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004916462859841801,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.19395934790372849,
|
|
"num_tokens": 22250704.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.620257472991943,
|
|
"epoch": 0.9608540925266904,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004916367565420826,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.1955851584672928,
|
|
"num_tokens": 22264533.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.698529243469238,
|
|
"epoch": 0.9613483590351918,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916272217706871,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.1913663163781166,
|
|
"num_tokens": 22276510.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.689091062545776,
|
|
"epoch": 0.9618426255436932,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916176816702284,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.18925074338912964,
|
|
"num_tokens": 22288634.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.693050241470337,
|
|
"epoch": 0.9623368920521945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004916081362409411,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.18890800178050995,
|
|
"num_tokens": 22299781.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.568251609802246,
|
|
"epoch": 0.9628311585606959,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049159858548306,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20119997560977937,
|
|
"num_tokens": 22310666.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.659449911117553,
|
|
"epoch": 0.9633254250691973,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915890293968202,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.18602459132671356,
|
|
"num_tokens": 22322811.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.66870346069336,
|
|
"epoch": 0.9638196915776986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004915794679824567,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.1833906427025795,
|
|
"num_tokens": 22335017.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.587030363082886,
|
|
"epoch": 0.9643139580862001,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915699012402047,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19727257192134856,
|
|
"num_tokens": 22346250.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.632735729217529,
|
|
"epoch": 0.9648082245947015,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004915603291702995,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.1907932013273239,
|
|
"num_tokens": 22357436.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.617962598800659,
|
|
"epoch": 0.9653024911032029,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004915507517729765,
|
|
"loss": 5.2443,
|
|
"mean_token_accuracy": 0.19969998449087142,
|
|
"num_tokens": 22368312.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.644787311553955,
|
|
"epoch": 0.9657967576117042,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915411690484715,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.19088573455810548,
|
|
"num_tokens": 22378659.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.621055364608765,
|
|
"epoch": 0.9662910241202056,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915315809970202,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19066745191812515,
|
|
"num_tokens": 22390642.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.682119226455688,
|
|
"epoch": 0.966785290628707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915219876188583,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.1840744897723198,
|
|
"num_tokens": 22402484.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.640901899337768,
|
|
"epoch": 0.9672795571372084,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915123889142221,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19494434148073198,
|
|
"num_tokens": 22413315.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.623419761657715,
|
|
"epoch": 0.9677738236457097,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004915027848833472,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.18624964654445647,
|
|
"num_tokens": 22425123.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.6225732326507565,
|
|
"epoch": 0.9682680901542111,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004914931755264705,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.19590737521648408,
|
|
"num_tokens": 22436437.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.639229583740234,
|
|
"epoch": 0.9687623566627125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000491483560843828,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.2007865935564041,
|
|
"num_tokens": 22446677.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.560932874679565,
|
|
"epoch": 0.969256623171214,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004914739408356563,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.19748343378305436,
|
|
"num_tokens": 22457597.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.670977163314819,
|
|
"epoch": 0.9697508896797153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004914643155021921,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.19744355827569962,
|
|
"num_tokens": 22469715.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.6480104446411135,
|
|
"epoch": 0.9702451561882167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914546848436722,
|
|
"loss": 5.311,
|
|
"mean_token_accuracy": 0.1916728511452675,
|
|
"num_tokens": 22479840.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.5793132305145265,
|
|
"epoch": 0.9707394226967181,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004914450488603334,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.1986646518111229,
|
|
"num_tokens": 22491017.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.636435270309448,
|
|
"epoch": 0.9712336892052195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004914354075524129,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19888969659805297,
|
|
"num_tokens": 22502308.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.500595664978027,
|
|
"epoch": 0.9717279557137208,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004914257609201477,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.20340583026409148,
|
|
"num_tokens": 22513090.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.593112897872925,
|
|
"epoch": 0.9722222222222222,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004914161089637752,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.19923784583806992,
|
|
"num_tokens": 22523391.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.61227388381958,
|
|
"epoch": 0.9727164887307236,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004914064516835329,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.203101547062397,
|
|
"num_tokens": 22536038.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.61104736328125,
|
|
"epoch": 0.973210755239225,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913967890796583,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.1981385678052902,
|
|
"num_tokens": 22546897.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.599612712860107,
|
|
"epoch": 0.9737050217477263,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004913871211523891,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.19291321337223052,
|
|
"num_tokens": 22558240.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.602342844009399,
|
|
"epoch": 0.9741992882562278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004913774479019633,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.1954142212867737,
|
|
"num_tokens": 22570540.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.670391416549682,
|
|
"epoch": 0.9746935547647292,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913677693286185,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.1852197229862213,
|
|
"num_tokens": 22582657.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.7341156005859375,
|
|
"epoch": 0.9751878212732306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004913580854325932,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.19256402552127838,
|
|
"num_tokens": 22593445.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.620249462127686,
|
|
"epoch": 0.9756820877817319,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004913483962141253,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.1965990960597992,
|
|
"num_tokens": 22604631.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.5677050113677975,
|
|
"epoch": 0.9761763542902333,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004913387016734533,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.19343892782926558,
|
|
"num_tokens": 22615130.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.589069271087647,
|
|
"epoch": 0.9766706207987347,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004913290018108157,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19410673528909683,
|
|
"num_tokens": 22627372.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.683375072479248,
|
|
"epoch": 0.977164887307236,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004913192966264511,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.1924360066652298,
|
|
"num_tokens": 22640354.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.677717018127441,
|
|
"epoch": 0.9776591538157374,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913095861205982,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.18949446380138396,
|
|
"num_tokens": 22651717.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.691273498535156,
|
|
"epoch": 0.9781534203242388,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004912998702934961,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.18768298327922822,
|
|
"num_tokens": 22663334.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.662432718276977,
|
|
"epoch": 0.9786476868327402,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004912901491453835,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.19687706381082534,
|
|
"num_tokens": 22675894.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.522920179367065,
|
|
"epoch": 0.9791419533412415,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004912804226764997,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.205456380546093,
|
|
"num_tokens": 22687861.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.636275720596314,
|
|
"epoch": 0.979636219849743,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004912706908870838,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19504302740097046,
|
|
"num_tokens": 22698346.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.6292554378509525,
|
|
"epoch": 0.9801304863582444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004912609537773755,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.18624177128076552,
|
|
"num_tokens": 22710665.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.641499662399292,
|
|
"epoch": 0.9806247528667458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912512113476142,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.2029682219028473,
|
|
"num_tokens": 22720989.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.585738229751587,
|
|
"epoch": 0.9811190193752471,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004912414635980395,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19947191178798676,
|
|
"num_tokens": 22732265.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.591073656082154,
|
|
"epoch": 0.9816132858837485,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004912317105288912,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.19825671017169952,
|
|
"num_tokens": 22742435.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.551272344589234,
|
|
"epoch": 0.9821075523922499,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004912219521404094,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.1958669289946556,
|
|
"num_tokens": 22753750.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.653229665756226,
|
|
"epoch": 0.9826018189007513,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000491212188432834,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.19283485859632493,
|
|
"num_tokens": 22765549.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.6413239479064945,
|
|
"epoch": 0.9830960854092526,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004912024194064052,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18766363263130187,
|
|
"num_tokens": 22777882.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.700936794281006,
|
|
"epoch": 0.983590351917754,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004911926450613633,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18520065844058992,
|
|
"num_tokens": 22789671.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.63926887512207,
|
|
"epoch": 0.9840846184262554,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004911828653979488,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.18694156110286714,
|
|
"num_tokens": 22801330.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.620159912109375,
|
|
"epoch": 0.9845788849347569,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004911730804164024,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.18854619711637496,
|
|
"num_tokens": 22813998.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.630801439285278,
|
|
"epoch": 0.9850731514432582,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004911632901169645,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.19400959312915803,
|
|
"num_tokens": 22825048.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.540067911148071,
|
|
"epoch": 0.9855674179517596,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004911534944998762,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.19872192144393921,
|
|
"num_tokens": 22835450.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.588812398910522,
|
|
"epoch": 0.986061684460261,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004911436935653785,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.19831462055444718,
|
|
"num_tokens": 22847320.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.633582639694214,
|
|
"epoch": 0.9865559509687624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004911338873137122,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.20011822432279586,
|
|
"num_tokens": 22857676.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.538009405136108,
|
|
"epoch": 0.9870502174772637,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000491124075745119,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.1993396669626236,
|
|
"num_tokens": 22869767.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.63607702255249,
|
|
"epoch": 0.9875444839857651,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004911142588598399,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.1940407007932663,
|
|
"num_tokens": 22880096.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.679059743881226,
|
|
"epoch": 0.9880387504942665,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004911044366581165,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19356839060783387,
|
|
"num_tokens": 22892436.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.643694686889648,
|
|
"epoch": 0.9885330170027679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004910946091401903,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.19104681611061097,
|
|
"num_tokens": 22904641.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.603832197189331,
|
|
"epoch": 0.9890272835112692,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004910847763063033,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.2031159982085228,
|
|
"num_tokens": 22915372.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.66643443107605,
|
|
"epoch": 0.9895215500197707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004910749381566973,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.18446232229471207,
|
|
"num_tokens": 22926583.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.631104850769043,
|
|
"epoch": 0.9900158165282721,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910650946916143,
|
|
"loss": 5.2241,
|
|
"mean_token_accuracy": 0.19322517961263658,
|
|
"num_tokens": 22938103.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.585657596588135,
|
|
"epoch": 0.9905100830367735,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910552459112964,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.1936303660273552,
|
|
"num_tokens": 22949475.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.638175821304321,
|
|
"epoch": 0.9910043495452748,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004910453918159861,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19244821071624757,
|
|
"num_tokens": 22961404.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.607744884490967,
|
|
"epoch": 0.9914986160537762,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004910355324059255,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19262792319059371,
|
|
"num_tokens": 22973009.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.633600568771362,
|
|
"epoch": 0.9919928825622776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004910256676813572,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.1948724642395973,
|
|
"num_tokens": 22985104.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.616547441482544,
|
|
"epoch": 0.992487149070779,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004910157976425241,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.19048827290534973,
|
|
"num_tokens": 22997133.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.591722106933593,
|
|
"epoch": 0.9929814155792803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004910059222896689,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.19974204003810883,
|
|
"num_tokens": 23007621.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.668904113769531,
|
|
"epoch": 0.9934756820877817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909960416230344,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.18902715295553207,
|
|
"num_tokens": 23018254.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.634682703018188,
|
|
"epoch": 0.9939699485962831,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004909861556428638,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.19833352118730546,
|
|
"num_tokens": 23030733.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.55250244140625,
|
|
"epoch": 0.9944642151047846,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004909762643494003,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.19251906424760817,
|
|
"num_tokens": 23043086.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.711132621765136,
|
|
"epoch": 0.9949584816132859,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004909663677428872,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.18608732968568803,
|
|
"num_tokens": 23055281.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.595179414749145,
|
|
"epoch": 0.9954527481217873,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004909564658235678,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.19430323392152787,
|
|
"num_tokens": 23067332.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.593054342269897,
|
|
"epoch": 0.9959470146302887,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000490946558591686,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19264515042304992,
|
|
"num_tokens": 23079278.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.626236009597778,
|
|
"epoch": 0.99644128113879,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004909366460474852,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.19360380321741105,
|
|
"num_tokens": 23092177.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.534682416915894,
|
|
"epoch": 0.9969355476472914,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004909267281912095,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.19558467268943786,
|
|
"num_tokens": 23103249.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.642769050598145,
|
|
"epoch": 0.9974298141557928,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909168050231029,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.20087829679250718,
|
|
"num_tokens": 23113821.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.660932922363282,
|
|
"epoch": 0.9979240806642942,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004909068765434093,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.19209800511598588,
|
|
"num_tokens": 23124819.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.599535608291626,
|
|
"epoch": 0.9984183471727955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490896942752373,
|
|
"loss": 5.3086,
|
|
"mean_token_accuracy": 0.19286416471004486,
|
|
"num_tokens": 23135590.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.655676651000976,
|
|
"epoch": 0.9989126136812969,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004908870036502384,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.19640028327703477,
|
|
"num_tokens": 23147290.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.683337879180908,
|
|
"epoch": 0.9994068801897983,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004908770592372501,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.1957457184791565,
|
|
"num_tokens": 23158276.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.601388072967529,
|
|
"epoch": 0.9999011466982998,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004908671095136526,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.19549649953842163,
|
|
"num_tokens": 23169174.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.6100077629089355,
|
|
"epoch": 1.0003954132068011,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004908571544796908,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.19631705582141876,
|
|
"num_tokens": 23180377.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.632832956314087,
|
|
"epoch": 1.0008896797153024,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004908471941356094,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.2003858655691147,
|
|
"num_tokens": 23191158.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.654829835891723,
|
|
"epoch": 1.001383946223804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004908372284816537,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.20165897458791732,
|
|
"num_tokens": 23201956.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.594053077697754,
|
|
"epoch": 1.0018782127323052,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004908272575180685,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.19583955705165862,
|
|
"num_tokens": 23213449.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.6795391082763675,
|
|
"epoch": 1.0023724792408066,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004908172812450993,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.1900208815932274,
|
|
"num_tokens": 23226514.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.6067225456237795,
|
|
"epoch": 1.0028667457493081,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004908072996629917,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.19555890709161758,
|
|
"num_tokens": 23239322.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.627415370941162,
|
|
"epoch": 1.0033610122578094,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004907973127719909,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.19606511145830155,
|
|
"num_tokens": 23250990.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.61159496307373,
|
|
"epoch": 1.0038552787663109,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004907873205723427,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.188396155834198,
|
|
"num_tokens": 23261630.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.646563959121704,
|
|
"epoch": 1.0043495452748121,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000490777323064293,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.19345839321613312,
|
|
"num_tokens": 23272823.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.514635515213013,
|
|
"epoch": 1.0048438117833136,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004907673202480876,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.22162040919065476,
|
|
"num_tokens": 23282827.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.577254724502564,
|
|
"epoch": 1.0053380782918149,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004907573121239727,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.19773707687854766,
|
|
"num_tokens": 23295359.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.637523794174195,
|
|
"epoch": 1.0058323448003164,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907472986921945,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.2024553045630455,
|
|
"num_tokens": 23305932.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.5606465339660645,
|
|
"epoch": 1.0063266113088176,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907372799529992,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.19294115006923676,
|
|
"num_tokens": 23317856.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.588295841217041,
|
|
"epoch": 1.006820877817319,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004907272559066334,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.20991285741329194,
|
|
"num_tokens": 23328071.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.58222074508667,
|
|
"epoch": 1.0073151443258206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004907172265533436,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19638827741146087,
|
|
"num_tokens": 23339601.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.644859504699707,
|
|
"epoch": 1.0078094108343219,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004907071918933766,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.1973765879869461,
|
|
"num_tokens": 23351672.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.668191289901733,
|
|
"epoch": 1.0083036773428233,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906971519269793,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19607312530279158,
|
|
"num_tokens": 23361684.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.531037521362305,
|
|
"epoch": 1.0087979438513246,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004906871066543984,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.1975875973701477,
|
|
"num_tokens": 23373969.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.675751686096191,
|
|
"epoch": 1.009292210359826,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004906770560758813,
|
|
"loss": 5.2363,
|
|
"mean_token_accuracy": 0.18354198038578035,
|
|
"num_tokens": 23384747.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.6887959957122805,
|
|
"epoch": 1.0097864768683273,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004906670001916752,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19636847078800201,
|
|
"num_tokens": 23395900.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.619274044036866,
|
|
"epoch": 1.0102807433768288,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004906569390020274,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.19952213168144226,
|
|
"num_tokens": 23408912.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.606116819381714,
|
|
"epoch": 1.01077500988533,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004906468725071855,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.2012458026409149,
|
|
"num_tokens": 23419042.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.6188249588012695,
|
|
"epoch": 1.0112692763938316,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000490636800707397,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.19930345565080643,
|
|
"num_tokens": 23430861.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.701479864120484,
|
|
"epoch": 1.0117635429023328,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004906267236029099,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18746026307344438,
|
|
"num_tokens": 23443489.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.602195072174072,
|
|
"epoch": 1.0122578094108343,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004906166411939718,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19687227606773378,
|
|
"num_tokens": 23454327.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.554819965362549,
|
|
"epoch": 1.0127520759193358,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004906065534808309,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.2068428263068199,
|
|
"num_tokens": 23466684.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.595309782028198,
|
|
"epoch": 1.013246342427837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905964604637353,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.20004372745752336,
|
|
"num_tokens": 23478347.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.593182468414307,
|
|
"epoch": 1.0137406089363385,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004905863621429334,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20330906361341478,
|
|
"num_tokens": 23489588.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.550411128997803,
|
|
"epoch": 1.0142348754448398,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004905762585186735,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.20081121176481248,
|
|
"num_tokens": 23501347.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.660239887237549,
|
|
"epoch": 1.0147291419533413,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004905661495912042,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1940949246287346,
|
|
"num_tokens": 23513036.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.575650691986084,
|
|
"epoch": 1.0152234084618426,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004905560353607742,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.20131876319646835,
|
|
"num_tokens": 23524166.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.595976495742798,
|
|
"epoch": 1.015717674970344,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004905459158276323,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.19659801125526427,
|
|
"num_tokens": 23536638.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.615958309173584,
|
|
"epoch": 1.0162119414788453,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004905357909920275,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19983913749456406,
|
|
"num_tokens": 23548567.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.605298328399658,
|
|
"epoch": 1.0167062079873468,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905256608542086,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20143326818943025,
|
|
"num_tokens": 23560108.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.591742372512817,
|
|
"epoch": 1.0172004744958483,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905155254144251,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.203885780274868,
|
|
"num_tokens": 23571542.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.534454488754273,
|
|
"epoch": 1.0176947410043495,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905053846729263,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.20065390169620514,
|
|
"num_tokens": 23582200.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.639520168304443,
|
|
"epoch": 1.018189007512851,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004904952386299616,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19528298825025558,
|
|
"num_tokens": 23594530.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.588271617889404,
|
|
"epoch": 1.0186832740213523,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904850872857805,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.2131606474518776,
|
|
"num_tokens": 23605697.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.618853902816772,
|
|
"epoch": 1.0191775405298538,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000490474930640633,
|
|
"loss": 5.2399,
|
|
"mean_token_accuracy": 0.1965971902012825,
|
|
"num_tokens": 23615730.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.566145706176758,
|
|
"epoch": 1.019671807038355,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904647686947687,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.20490238815546036,
|
|
"num_tokens": 23627242.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.5099633693695065,
|
|
"epoch": 1.0201660735468565,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904546014484376,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.20741736739873887,
|
|
"num_tokens": 23639450.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.589915180206299,
|
|
"epoch": 1.0206603400553578,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004904444289018898,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.2016470402479172,
|
|
"num_tokens": 23651154.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.63874831199646,
|
|
"epoch": 1.0211546065638593,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004904342510553758,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.1933414399623871,
|
|
"num_tokens": 23663996.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.625178718566895,
|
|
"epoch": 1.0216488730723605,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004904240679091458,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.19972514361143112,
|
|
"num_tokens": 23676270.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.663323974609375,
|
|
"epoch": 1.022143139580862,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904138794634502,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.1995392084121704,
|
|
"num_tokens": 23687483.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.643520069122315,
|
|
"epoch": 1.0226374060893635,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004904036857185398,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.195101498067379,
|
|
"num_tokens": 23697956.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.597309541702271,
|
|
"epoch": 1.0231316725978647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903934866746653,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.2016719549894333,
|
|
"num_tokens": 23709029.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.599404954910279,
|
|
"epoch": 1.0236259391063662,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004903832823320777,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.2061514213681221,
|
|
"num_tokens": 23719792.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.598851919174194,
|
|
"epoch": 1.0241202056148675,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903730726910278,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.1986728236079216,
|
|
"num_tokens": 23730201.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.559210872650146,
|
|
"epoch": 1.024614472123369,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000490362857751767,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.2023387923836708,
|
|
"num_tokens": 23741743.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.614955711364746,
|
|
"epoch": 1.0251087386318702,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004903526375145465,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20339439064264297,
|
|
"num_tokens": 23753879.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.597322940826416,
|
|
"epoch": 1.0256030051403717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004903424119796176,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.1919170618057251,
|
|
"num_tokens": 23765062.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.607200002670288,
|
|
"epoch": 1.026097271648873,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903321811472321,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.20121922791004182,
|
|
"num_tokens": 23777261.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.636020612716675,
|
|
"epoch": 1.0265915381573745,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004903219450176413,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19775684773921967,
|
|
"num_tokens": 23789247.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.583631610870361,
|
|
"epoch": 1.0270858046658757,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903117035910975,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.2014937534928322,
|
|
"num_tokens": 23798981.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.619787216186523,
|
|
"epoch": 1.0275800711743772,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004903014568678523,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.19623916298151017,
|
|
"num_tokens": 23810856.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.6564538955688475,
|
|
"epoch": 1.0280743376828787,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004902912048481579,
|
|
"loss": 5.2302,
|
|
"mean_token_accuracy": 0.19382828772068023,
|
|
"num_tokens": 23821544.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.598402595520019,
|
|
"epoch": 1.02856860419138,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004902809475322664,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.19486696869134904,
|
|
"num_tokens": 23831972.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.6284221649169925,
|
|
"epoch": 1.0290628706998814,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004902706849204302,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20296854823827742,
|
|
"num_tokens": 23843451.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.6014739036560055,
|
|
"epoch": 1.0295571372083827,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004902604170129017,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.19674879163503647,
|
|
"num_tokens": 23854060.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.678252506256103,
|
|
"epoch": 1.0300514037168842,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004902501438099337,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19259535819292067,
|
|
"num_tokens": 23865722.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.655801010131836,
|
|
"epoch": 1.0305456702253855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004902398653117787,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.19363904297351836,
|
|
"num_tokens": 23875888.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.618904638290405,
|
|
"epoch": 1.031039936733887,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004902295815186896,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.19405853599309922,
|
|
"num_tokens": 23887816.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.642099857330322,
|
|
"epoch": 1.0315342032423882,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004902192924309193,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.1990288257598877,
|
|
"num_tokens": 23900468.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.6218345165252686,
|
|
"epoch": 1.0320284697508897,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004902089980487211,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19757075756788253,
|
|
"num_tokens": 23912086.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.593123865127564,
|
|
"epoch": 1.032522736259391,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004901986983723483,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19984557926654817,
|
|
"num_tokens": 23923262.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.5935694694519045,
|
|
"epoch": 1.0330170027678924,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000490188393402054,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.20233773440122604,
|
|
"num_tokens": 23934660.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.571173286437988,
|
|
"epoch": 1.033511269276394,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004901780831380919,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.20368053168058395,
|
|
"num_tokens": 23945822.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.578071260452271,
|
|
"epoch": 1.0340055357848952,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004901677675807155,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19720763415098191,
|
|
"num_tokens": 23957312.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.647917366027832,
|
|
"epoch": 1.0344998022933967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004901574467301786,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.19453432112932206,
|
|
"num_tokens": 23968477.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.566391468048096,
|
|
"epoch": 1.034994068801898,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901471205867353,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20114147365093232,
|
|
"num_tokens": 23979041.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.614834356307983,
|
|
"epoch": 1.0354883353103994,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004901367891506393,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.19947662353515624,
|
|
"num_tokens": 23990947.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.624517583847046,
|
|
"epoch": 1.0359826018189007,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000490126452422145,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.20279881954193116,
|
|
"num_tokens": 24001652.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.666518020629883,
|
|
"epoch": 1.0364768683274022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901161104015066,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.19167366176843642,
|
|
"num_tokens": 24012707.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.5180035591125485,
|
|
"epoch": 1.0369711348359034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004901057630889784,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.20800597071647645,
|
|
"num_tokens": 24024136.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.6054497241973875,
|
|
"epoch": 1.037465401344405,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004900954104848152,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.20203883051872254,
|
|
"num_tokens": 24035586.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.648937511444092,
|
|
"epoch": 1.0379596678529064,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004900850525892714,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.203294974565506,
|
|
"num_tokens": 24045338.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.643433666229248,
|
|
"epoch": 1.0384539343614076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000490074689402602,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.18898199796676635,
|
|
"num_tokens": 24056898.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.512799406051636,
|
|
"epoch": 1.0389482008699091,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900643209250619,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.20767101049423217,
|
|
"num_tokens": 24068998.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.568370723724366,
|
|
"epoch": 1.0394424673784104,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900539471569061,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.1978091925382614,
|
|
"num_tokens": 24080301.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.634547996520996,
|
|
"epoch": 1.0399367338869119,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049004356809839,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.19516054093837737,
|
|
"num_tokens": 24092601.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.682157135009765,
|
|
"epoch": 1.0404310003954131,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900331837497686,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.18680672645568847,
|
|
"num_tokens": 24105621.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.598519897460937,
|
|
"epoch": 1.0409252669039146,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004900227941112976,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.2127085879445076,
|
|
"num_tokens": 24117926.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.597533416748047,
|
|
"epoch": 1.0414195334124159,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004900123991832323,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.195573154091835,
|
|
"num_tokens": 24129119.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.526741075515747,
|
|
"epoch": 1.0419137999209174,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004900019989658288,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19209674149751663,
|
|
"num_tokens": 24141726.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.708407402038574,
|
|
"epoch": 1.0424080664294189,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004899915934593427,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19950339049100876,
|
|
"num_tokens": 24152912.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.690528154373169,
|
|
"epoch": 1.0429023329379201,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004899811826640302,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19273905754089354,
|
|
"num_tokens": 24163602.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.604873085021973,
|
|
"epoch": 1.0433965994464216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004899707665801471,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.1992226794362068,
|
|
"num_tokens": 24175904.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.567919158935547,
|
|
"epoch": 1.0438908659549229,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004899603452079499,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.19423959255218506,
|
|
"num_tokens": 24186438.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.589591121673584,
|
|
"epoch": 1.0443851324634243,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899499185476948,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.19069302678108216,
|
|
"num_tokens": 24198357.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.729695463180542,
|
|
"epoch": 1.0448793989719256,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004899394865996383,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.191837902367115,
|
|
"num_tokens": 24211257.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.7230571746826175,
|
|
"epoch": 1.045373665480427,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899290493640371,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.18740485459566117,
|
|
"num_tokens": 24223189.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.581752443313599,
|
|
"epoch": 1.0458679319889284,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004899186068411481,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.19531538039445878,
|
|
"num_tokens": 24234701.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.6230936527252195,
|
|
"epoch": 1.0463621984974298,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899081590312278,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.19982028901576995,
|
|
"num_tokens": 24245562.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.646186780929566,
|
|
"epoch": 1.046856465005931,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004898977059345336,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.19387844651937486,
|
|
"num_tokens": 24256479.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.632402229309082,
|
|
"epoch": 1.0473507315144326,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004898872475513225,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.18917266875505448,
|
|
"num_tokens": 24266900.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.673963165283203,
|
|
"epoch": 1.047844998022934,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004898767838818517,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.18993811160326005,
|
|
"num_tokens": 24278915.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.592510175704956,
|
|
"epoch": 1.0483392645314353,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004898663149263787,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.20620992332696914,
|
|
"num_tokens": 24289584.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.5979828357696535,
|
|
"epoch": 1.0488335310399368,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898558406851611,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.20248962789773942,
|
|
"num_tokens": 24300922.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.584086132049561,
|
|
"epoch": 1.049327797548438,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004898453611584564,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.19852738231420516,
|
|
"num_tokens": 24311238.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.566949558258057,
|
|
"epoch": 1.0498220640569396,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898348763465226,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.204348823428154,
|
|
"num_tokens": 24322417.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.592318773269653,
|
|
"epoch": 1.0503163305654408,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004898243862496173,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.2061009556055069,
|
|
"num_tokens": 24332751.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.66185736656189,
|
|
"epoch": 1.0508105970739423,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898138908679989,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.18801855593919753,
|
|
"num_tokens": 24345082.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.633440017700195,
|
|
"epoch": 1.0513048635824436,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004898033902019255,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.19885159134864808,
|
|
"num_tokens": 24355863.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.718380928039551,
|
|
"epoch": 1.051799130090945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004897928842516553,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.18917883187532425,
|
|
"num_tokens": 24367763.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.612067222595215,
|
|
"epoch": 1.0522933965994463,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004897823730174468,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.1921558752655983,
|
|
"num_tokens": 24378943.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.6442042827606205,
|
|
"epoch": 1.0527876631079478,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004897718564995587,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.197923643887043,
|
|
"num_tokens": 24389508.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.574830436706543,
|
|
"epoch": 1.0532819296164493,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004897613346982495,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20271708816289902,
|
|
"num_tokens": 24400710.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.528800773620605,
|
|
"epoch": 1.0537761961249505,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897508076137783,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.1976326122879982,
|
|
"num_tokens": 24412854.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.623622035980224,
|
|
"epoch": 1.054270462633452,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004897402752464037,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.19712448120117188,
|
|
"num_tokens": 24423212.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.6668150424957275,
|
|
"epoch": 1.0547647291419533,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004897297375963852,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.20134411454200746,
|
|
"num_tokens": 24436091.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.582789087295533,
|
|
"epoch": 1.0552589956504548,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004897191946639819,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.20405897200107576,
|
|
"num_tokens": 24448499.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.653404092788696,
|
|
"epoch": 1.055753262158956,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004897086464494529,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.18825308680534364,
|
|
"num_tokens": 24460732.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.597353219985962,
|
|
"epoch": 1.0562475286674575,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004896980929530579,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.20154686272144318,
|
|
"num_tokens": 24472460.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.61302809715271,
|
|
"epoch": 1.0567417951759588,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004896875341750567,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20296552032232285,
|
|
"num_tokens": 24483820.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.565239286422729,
|
|
"epoch": 1.0572360616844603,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004896769701157087,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.20751295536756514,
|
|
"num_tokens": 24495775.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.553544902801514,
|
|
"epoch": 1.0577303281929615,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000489666400775274,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.2052976295351982,
|
|
"num_tokens": 24505589.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.579530334472656,
|
|
"epoch": 1.058224594701463,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896558261540125,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.20085039883852004,
|
|
"num_tokens": 24515988.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.537688064575195,
|
|
"epoch": 1.0587188612099645,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004896452462521844,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.20575835704803466,
|
|
"num_tokens": 24528273.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.684996509552002,
|
|
"epoch": 1.0592131277184658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004896346610700498,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.19887850880622865,
|
|
"num_tokens": 24539014.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.5847328186035154,
|
|
"epoch": 1.0597073942269672,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004896240706078694,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.20032164603471755,
|
|
"num_tokens": 24550210.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.550443267822265,
|
|
"epoch": 1.0602016607354685,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004896134748659036,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.20644821971654892,
|
|
"num_tokens": 24560934.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.596108627319336,
|
|
"epoch": 1.06069592724397,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000489602873844413,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.19550950676202775,
|
|
"num_tokens": 24572274.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.613519334793091,
|
|
"epoch": 1.0611901937524713,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004895922675436583,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19638487547636033,
|
|
"num_tokens": 24583950.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.583965873718261,
|
|
"epoch": 1.0616844602609727,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004895816559639006,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.2041704386472702,
|
|
"num_tokens": 24597058.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.493352699279785,
|
|
"epoch": 1.062178726769474,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004895710391054008,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.2144222930073738,
|
|
"num_tokens": 24608604.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.619201612472534,
|
|
"epoch": 1.0626729932779755,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895604169684203,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19471661895513534,
|
|
"num_tokens": 24619707.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.667275333404541,
|
|
"epoch": 1.063167259786477,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004895497895532202,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.19414396584033966,
|
|
"num_tokens": 24629579.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.5603422164917,
|
|
"epoch": 1.0636615262949782,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895391568600619,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18896328657865524,
|
|
"num_tokens": 24641358.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.569506645202637,
|
|
"epoch": 1.0641557928034797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895285188892071,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.20016748160123826,
|
|
"num_tokens": 24652293.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.6454822540283205,
|
|
"epoch": 1.064650059311981,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895178756409175,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19783279448747634,
|
|
"num_tokens": 24663370.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.649098014831543,
|
|
"epoch": 1.0651443258204825,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004895072271154548,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.19361262172460555,
|
|
"num_tokens": 24675037.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.616843271255493,
|
|
"epoch": 1.0656385923289837,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004894965733130812,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.19610688835382462,
|
|
"num_tokens": 24685680.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.52163667678833,
|
|
"epoch": 1.0661328588374852,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004894859142340585,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.20336120426654816,
|
|
"num_tokens": 24697831.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.6424743175506595,
|
|
"epoch": 1.0666271253459865,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894752498786491,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19906843602657318,
|
|
"num_tokens": 24710226.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.641970443725586,
|
|
"epoch": 1.067121391854488,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004894645802471152,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.20488873422145842,
|
|
"num_tokens": 24721743.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.576434469223022,
|
|
"epoch": 1.0676156583629894,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004894539053397194,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.19224703460931777,
|
|
"num_tokens": 24733804.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.59564471244812,
|
|
"epoch": 1.0681099248714907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894432251567242,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.21002655029296874,
|
|
"num_tokens": 24745285.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.622626399993896,
|
|
"epoch": 1.0686041913799922,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004894325396983925,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.19623009562492372,
|
|
"num_tokens": 24756069.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.544876050949097,
|
|
"epoch": 1.0690984578884934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004894218489649869,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.2041807159781456,
|
|
"num_tokens": 24766935.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.612660980224609,
|
|
"epoch": 1.069592724396995,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894111529567707,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.1997630402445793,
|
|
"num_tokens": 24777642.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.594942378997803,
|
|
"epoch": 1.0700869909054962,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004894004516740069,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.20537441372871398,
|
|
"num_tokens": 24788110.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.660078048706055,
|
|
"epoch": 1.0705812574139977,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893897451169586,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19300525337457658,
|
|
"num_tokens": 24799976.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.653074645996094,
|
|
"epoch": 1.071075523922499,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893790332858893,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.1971150279045105,
|
|
"num_tokens": 24811131.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.625109720230102,
|
|
"epoch": 1.0715697904310004,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004893683161810626,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.19663408994674683,
|
|
"num_tokens": 24822137.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.536339139938354,
|
|
"epoch": 1.0720640569395017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893575938027421,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.20709992498159407,
|
|
"num_tokens": 24832369.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.609955501556397,
|
|
"epoch": 1.0725583234480032,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004893468661511914,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.20163075774908065,
|
|
"num_tokens": 24843351.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.733151578903199,
|
|
"epoch": 1.0730525899565047,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004893361332266746,
|
|
"loss": 5.3056,
|
|
"mean_token_accuracy": 0.19099195152521134,
|
|
"num_tokens": 24855019.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.561675786972046,
|
|
"epoch": 1.073546856465006,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004893253950294557,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.196122644841671,
|
|
"num_tokens": 24866224.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.589101648330688,
|
|
"epoch": 1.0740411229735074,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004893146515597989,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.2096235290169716,
|
|
"num_tokens": 24876995.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.638453674316406,
|
|
"epoch": 1.0745353894820087,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004893039028179683,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.1939111828804016,
|
|
"num_tokens": 24887846.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.63774528503418,
|
|
"epoch": 1.0750296559905101,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892931488042285,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.18875517547130585,
|
|
"num_tokens": 24899221.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.657603216171265,
|
|
"epoch": 1.0755239224990114,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000489282389518844,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.1954587608575821,
|
|
"num_tokens": 24912103.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.694338798522949,
|
|
"epoch": 1.076018189007513,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004892716249620795,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.19037206023931502,
|
|
"num_tokens": 24925465.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.635915899276734,
|
|
"epoch": 1.0765124555160142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892608551341997,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.20088418275117875,
|
|
"num_tokens": 24935136.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.5566919326782225,
|
|
"epoch": 1.0770067220245156,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004892500800354697,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.1929467126727104,
|
|
"num_tokens": 24946845.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.54016146659851,
|
|
"epoch": 1.077500988533017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004892392996661544,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.19988464266061784,
|
|
"num_tokens": 24958337.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.6197408676147464,
|
|
"epoch": 1.0779952550415184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004892285140265192,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1911612018942833,
|
|
"num_tokens": 24969505.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.666508960723877,
|
|
"epoch": 1.0784895215500199,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004892177231168292,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.19795316755771636,
|
|
"num_tokens": 24981577.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.659940147399903,
|
|
"epoch": 1.0789837880585211,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004892069269373502,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.19884584844112396,
|
|
"num_tokens": 24992758.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.621998834609985,
|
|
"epoch": 1.0794780545670226,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004891961254883474,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.20227978527545928,
|
|
"num_tokens": 25003057.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.5721417427062985,
|
|
"epoch": 1.0799723210755239,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004891853187700867,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.19908509403467178,
|
|
"num_tokens": 25014900.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.565425062179566,
|
|
"epoch": 1.0804665875840254,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004891745067828339,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.2113812357187271,
|
|
"num_tokens": 25026313.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.644254541397094,
|
|
"epoch": 1.0809608540925266,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891636895268551,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.1985420987010002,
|
|
"num_tokens": 25037014.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.6650491714477536,
|
|
"epoch": 1.081455120601028,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004891528670024162,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.2007567435503006,
|
|
"num_tokens": 25048051.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.55631799697876,
|
|
"epoch": 1.0819493871095294,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004891420392097837,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.2099177733063698,
|
|
"num_tokens": 25057825.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.556065225601197,
|
|
"epoch": 1.0824436536180309,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004891312061492236,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.2023647114634514,
|
|
"num_tokens": 25067702.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.605633068084717,
|
|
"epoch": 1.0829379201265321,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004891203678210027,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20347417891025543,
|
|
"num_tokens": 25078246.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.550473403930664,
|
|
"epoch": 1.0834321866350336,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004891095242253876,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19707193374633789,
|
|
"num_tokens": 25089267.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.669507026672363,
|
|
"epoch": 1.083926453143535,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004890986753626449,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.19486370980739592,
|
|
"num_tokens": 25101392.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.640515422821045,
|
|
"epoch": 1.0844207196520363,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004890878212330418,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.19567573070526123,
|
|
"num_tokens": 25113309.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.523593378067017,
|
|
"epoch": 1.0849149861605378,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004890769618368448,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.21330609172582626,
|
|
"num_tokens": 25124803.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.589742422103882,
|
|
"epoch": 1.085409252669039,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004890660971743215,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.1990187555551529,
|
|
"num_tokens": 25136443.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.6681482791900635,
|
|
"epoch": 1.0859035191775406,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004890552272457389,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1939637392759323,
|
|
"num_tokens": 25147128.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.576626396179199,
|
|
"epoch": 1.0863977856860418,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004890443520513645,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.19955306351184846,
|
|
"num_tokens": 25159420.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.5714414596557615,
|
|
"epoch": 1.0868920521945433,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004890334715914659,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.20374392122030258,
|
|
"num_tokens": 25171624.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.583699083328247,
|
|
"epoch": 1.0873863187030446,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004890225858663106,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.20949340611696243,
|
|
"num_tokens": 25181610.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.588444662094116,
|
|
"epoch": 1.087880585211546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004890116948761666,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.20562160164117813,
|
|
"num_tokens": 25191852.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.651496553421021,
|
|
"epoch": 1.0883748517200476,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004890007986213018,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.18907185196876525,
|
|
"num_tokens": 25204240.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.525005674362182,
|
|
"epoch": 1.0888691182285488,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004889898971019838,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.20219947695732116,
|
|
"num_tokens": 25215512.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.596926307678222,
|
|
"epoch": 1.0893633847370503,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004889789903184815,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.19566643387079238,
|
|
"num_tokens": 25227903.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.643597555160523,
|
|
"epoch": 1.0898576512455516,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004889680782710626,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20368800014257432,
|
|
"num_tokens": 25240204.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.56477952003479,
|
|
"epoch": 1.090351917754053,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004889571609599958,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.2046202763915062,
|
|
"num_tokens": 25251978.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.586012840270996,
|
|
"epoch": 1.0908461842625543,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004889462383855498,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.20550966411828994,
|
|
"num_tokens": 25262496.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.60785756111145,
|
|
"epoch": 1.0913404507710558,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000488935310547993,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.2000531330704689,
|
|
"num_tokens": 25272814.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.61498122215271,
|
|
"epoch": 1.091834717279557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004889243774475945,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.19977964758872985,
|
|
"num_tokens": 25283749.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.540952396392822,
|
|
"epoch": 1.0923289837880585,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000488913439084623,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.2034799799323082,
|
|
"num_tokens": 25295993.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.58284330368042,
|
|
"epoch": 1.09282325029656,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004889024954593477,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.19914669245481492,
|
|
"num_tokens": 25309011.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.620150566101074,
|
|
"epoch": 1.0933175168050613,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000488891546572038,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.20043754130601882,
|
|
"num_tokens": 25320901.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.595513916015625,
|
|
"epoch": 1.0938117833135628,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000488880592422963,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.2071356639266014,
|
|
"num_tokens": 25333042.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.571773481369019,
|
|
"epoch": 1.094306049822064,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004888696330123921,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.20200786888599395,
|
|
"num_tokens": 25346413.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.611135101318359,
|
|
"epoch": 1.0948003163305655,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004888586683405952,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.19944217354059218,
|
|
"num_tokens": 25358104.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.596868515014648,
|
|
"epoch": 1.0952945828390668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004888476984078419,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.19834440648555757,
|
|
"num_tokens": 25369485.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.655099105834961,
|
|
"epoch": 1.0957888493475683,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000488836723214402,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.19397983700037003,
|
|
"num_tokens": 25380349.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.622129201889038,
|
|
"epoch": 1.0962831158560695,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004888257427605456,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19255951195955276,
|
|
"num_tokens": 25393042.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.708660697937011,
|
|
"epoch": 1.096777382364571,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004888147570465426,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.1964405283331871,
|
|
"num_tokens": 25404470.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.565913677215576,
|
|
"epoch": 1.0972716488730723,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004888037660726635,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.20731250196695328,
|
|
"num_tokens": 25415397.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.645141553878784,
|
|
"epoch": 1.0977659153815738,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004887927698391786,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.18996219336986542,
|
|
"num_tokens": 25427409.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.610153436660767,
|
|
"epoch": 1.0982601818900752,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004887817683463583,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.20068458020687102,
|
|
"num_tokens": 25438063.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.58707709312439,
|
|
"epoch": 1.0987544483985765,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004887707615944734,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20992284417152404,
|
|
"num_tokens": 25449242.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.638928365707398,
|
|
"epoch": 1.099248714907078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004887597495837946,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.20158472955226897,
|
|
"num_tokens": 25461434.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.558602237701416,
|
|
"epoch": 1.0997429814155792,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887487323145929,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20621996223926545,
|
|
"num_tokens": 25472035.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.640863275527954,
|
|
"epoch": 1.1002372479240807,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000488737709787139,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.19716196954250337,
|
|
"num_tokens": 25483143.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.639927196502685,
|
|
"epoch": 1.100731514432582,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004887266820017044,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.18816036432981492,
|
|
"num_tokens": 25496873.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.60790319442749,
|
|
"epoch": 1.1012257809410835,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004887156489585603,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.20172854959964753,
|
|
"num_tokens": 25508661.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.692026042938233,
|
|
"epoch": 1.1017200474495847,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000488704610657978,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.19025227129459382,
|
|
"num_tokens": 25520789.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.545534276962281,
|
|
"epoch": 1.1022143139580862,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004886935671002293,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.21081394404172898,
|
|
"num_tokens": 25531131.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.647500371932983,
|
|
"epoch": 1.1027085804665875,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004886825182855855,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.191609226167202,
|
|
"num_tokens": 25543803.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.652146434783935,
|
|
"epoch": 1.103202846975089,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004886714642143188,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20513637810945512,
|
|
"num_tokens": 25553588.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.593723440170288,
|
|
"epoch": 1.1036971134835905,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004886604048867007,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.20126118510961533,
|
|
"num_tokens": 25566175.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.639891624450684,
|
|
"epoch": 1.1041913799920917,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004886493403030035,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.19249668717384338,
|
|
"num_tokens": 25578033.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.58329586982727,
|
|
"epoch": 1.1046856465005932,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004886382704634996,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.20333057194948195,
|
|
"num_tokens": 25588759.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.545940637588501,
|
|
"epoch": 1.1051799130090945,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004886271953684609,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.205940081179142,
|
|
"num_tokens": 25599200.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.570791435241699,
|
|
"epoch": 1.105674179517596,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004886161150181602,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.20087509453296662,
|
|
"num_tokens": 25610279.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.554993772506714,
|
|
"epoch": 1.1061684460260972,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004886050294128698,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.20424916297197343,
|
|
"num_tokens": 25622062.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.6129734992980955,
|
|
"epoch": 1.1066627125345987,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004885939385528628,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.19783098250627518,
|
|
"num_tokens": 25633451.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.544128036499023,
|
|
"epoch": 1.1071569790431,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004885828424384114,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.20746660530567168,
|
|
"num_tokens": 25644537.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.57102255821228,
|
|
"epoch": 1.1076512455516014,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004885717410697892,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.19861021041870117,
|
|
"num_tokens": 25655570.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.707389211654663,
|
|
"epoch": 1.1081455120601027,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000488560634447269,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.18938837051391602,
|
|
"num_tokens": 25669470.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.630181837081909,
|
|
"epoch": 1.1086397785686042,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000488549522571124,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.19894858151674272,
|
|
"num_tokens": 25682347.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.6691876411437985,
|
|
"epoch": 1.1091340450771057,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004885384054416276,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.19145484268665314,
|
|
"num_tokens": 25694038.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.593998432159424,
|
|
"epoch": 1.109628311585607,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004885272830590534,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.20883855670690538,
|
|
"num_tokens": 25705850.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.575067806243896,
|
|
"epoch": 1.1101225780941084,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885161554236748,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.20403964221477508,
|
|
"num_tokens": 25716294.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.568801021575927,
|
|
"epoch": 1.1106168446026097,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004885050225357657,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.20878512114286424,
|
|
"num_tokens": 25727367.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.710361957550049,
|
|
"epoch": 1.1111111111111112,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004884938843955999,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.1868166446685791,
|
|
"num_tokens": 25738352.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.532423973083496,
|
|
"epoch": 1.1116053776196124,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004884827410034515,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.21203147172927855,
|
|
"num_tokens": 25749940.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.602033901214599,
|
|
"epoch": 1.112099644128114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004884715923595945,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.19205178171396256,
|
|
"num_tokens": 25761251.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.6186737537384035,
|
|
"epoch": 1.1125939106366152,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004884604384643032,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.19850173592567444,
|
|
"num_tokens": 25772382.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.552934026718139,
|
|
"epoch": 1.1130881771451167,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000488449279317852,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.20429897606372832,
|
|
"num_tokens": 25784960.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.629480266571045,
|
|
"epoch": 1.113582443653618,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004884381149205154,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.1951213926076889,
|
|
"num_tokens": 25796644.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.601596975326538,
|
|
"epoch": 1.1140767101621194,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004884269452725681,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.20162205398082733,
|
|
"num_tokens": 25807712.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.64228081703186,
|
|
"epoch": 1.1145709766706209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884157703742848,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20367183089256286,
|
|
"num_tokens": 25817944.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.540275144577026,
|
|
"epoch": 1.1150652431791221,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004884045902259405,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.2066369414329529,
|
|
"num_tokens": 25830801.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.557745456695557,
|
|
"epoch": 1.1155595096876236,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883934048278102,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19736449122428895,
|
|
"num_tokens": 25843877.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.612047529220581,
|
|
"epoch": 1.116053776196125,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004883822141801689,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.2047475978732109,
|
|
"num_tokens": 25853763.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.660339212417602,
|
|
"epoch": 1.1165480427046264,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004883710182832921,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.1922273263335228,
|
|
"num_tokens": 25864759.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.690654945373535,
|
|
"epoch": 1.1170423092131276,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004883598171374552,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18838510662317276,
|
|
"num_tokens": 25877325.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.598295593261719,
|
|
"epoch": 1.1175365757216291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004883486107429337,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.20322973430156707,
|
|
"num_tokens": 25889308.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.570185136795044,
|
|
"epoch": 1.1180308422301304,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004883373991000031,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.19732243269681932,
|
|
"num_tokens": 25901721.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.6874839782714846,
|
|
"epoch": 1.1185251087386319,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883261822089395,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.1956360951066017,
|
|
"num_tokens": 25912399.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.571163463592529,
|
|
"epoch": 1.1190193752471334,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883149600700188,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.20984721034765244,
|
|
"num_tokens": 25923560.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.6397301197052006,
|
|
"epoch": 1.1195136417556346,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004883037326835169,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.2001958519220352,
|
|
"num_tokens": 25933408.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.6041769027709964,
|
|
"epoch": 1.120007908264136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004882925000497101,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.19686995893716813,
|
|
"num_tokens": 25944492.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.5810133934021,
|
|
"epoch": 1.1205021747726374,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004882812621688747,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.2053610309958458,
|
|
"num_tokens": 25956439.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.585991334915161,
|
|
"epoch": 1.1209964412811388,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004882700190412873,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19325564205646514,
|
|
"num_tokens": 25968765.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.609309339523316,
|
|
"epoch": 1.12149070778964,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004882587706672242,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.19817647635936736,
|
|
"num_tokens": 25981300.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.61623477935791,
|
|
"epoch": 1.1219849742981416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004882475170469622,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.2071049228310585,
|
|
"num_tokens": 25991655.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.58967695236206,
|
|
"epoch": 1.1224792408066429,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004882362581807783,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.20514735728502273,
|
|
"num_tokens": 26002989.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.550833034515381,
|
|
"epoch": 1.1229735073151443,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004882249940689494,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.2068599134683609,
|
|
"num_tokens": 26013807.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.695304489135742,
|
|
"epoch": 1.1234677738236458,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048821372471175245,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.19761935323476792,
|
|
"num_tokens": 26027099.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.652538633346557,
|
|
"epoch": 1.123962040332147,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048820245010946486,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.19648411124944687,
|
|
"num_tokens": 26039046.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.527272796630859,
|
|
"epoch": 1.1244563068406486,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004881911702623639,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21236271560192108,
|
|
"num_tokens": 26049763.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.525219249725342,
|
|
"epoch": 1.1249505733491498,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004881798851707271,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.2024916708469391,
|
|
"num_tokens": 26062227.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.5266149044036865,
|
|
"epoch": 1.1254448398576513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048816859483483214,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.2034767359495163,
|
|
"num_tokens": 26074019.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.69959864616394,
|
|
"epoch": 1.1259391063661526,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048815729925495656,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19384338557720185,
|
|
"num_tokens": 26086169.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.603618812561035,
|
|
"epoch": 1.126433372874654,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048814599843137837,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.19195906668901444,
|
|
"num_tokens": 26097677.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.499852514266967,
|
|
"epoch": 1.1269276393831553,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004881346923643755,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.20891562551259996,
|
|
"num_tokens": 26108825.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.629191637039185,
|
|
"epoch": 1.1274219058916568,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004881233810542263,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19421287328004838,
|
|
"num_tokens": 26120274.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.602230501174927,
|
|
"epoch": 1.127916172400158,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048811206450120875,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.2055575057864189,
|
|
"num_tokens": 26131964.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.630838680267334,
|
|
"epoch": 1.1284104389086596,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004881007427056013,
|
|
"loss": 5.2046,
|
|
"mean_token_accuracy": 0.19535789489746094,
|
|
"num_tokens": 26143308.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.6695550918579105,
|
|
"epoch": 1.128904705417161,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004880894156676826,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19100353866815567,
|
|
"num_tokens": 26153951.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.60924973487854,
|
|
"epoch": 1.1293989719256623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004880780833877312,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.20742035657167435,
|
|
"num_tokens": 26165951.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.580791664123535,
|
|
"epoch": 1.1298932384341638,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004880667458660259,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.1946610689163208,
|
|
"num_tokens": 26176751.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.629481077194214,
|
|
"epoch": 1.130387504942665,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004880554031028456,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.1927572399377823,
|
|
"num_tokens": 26187682.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.683337879180908,
|
|
"epoch": 1.1308817714511665,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048804405509846933,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.19814158976078033,
|
|
"num_tokens": 26198960.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.553512954711914,
|
|
"epoch": 1.1313760379596678,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004880327018531762,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.1977383866906166,
|
|
"num_tokens": 26210198.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.609118843078614,
|
|
"epoch": 1.1318703044681693,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048802134336724566,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.2031602993607521,
|
|
"num_tokens": 26220817.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.576944732666016,
|
|
"epoch": 1.1323645709766705,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048800997964095687,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20851015746593476,
|
|
"num_tokens": 26233657.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.580789995193482,
|
|
"epoch": 1.132858837485172,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004879986106745897,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.2004464715719223,
|
|
"num_tokens": 26245566.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.608809328079223,
|
|
"epoch": 1.1333531039936733,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048798723646842357,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.2103253111243248,
|
|
"num_tokens": 26256717.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.611515522003174,
|
|
"epoch": 1.1338473705021748,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004879758570227384,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.19773997217416764,
|
|
"num_tokens": 26267926.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.582551765441894,
|
|
"epoch": 1.1343416370106763,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048796447233781406,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.19708593040704728,
|
|
"num_tokens": 26278666.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.60650486946106,
|
|
"epoch": 1.1348359035191775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004879530824139308,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20267072767019273,
|
|
"num_tokens": 26289961.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.589709043502808,
|
|
"epoch": 1.135330170027679,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048794168725136854,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19654595106840134,
|
|
"num_tokens": 26301245.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.6204798221588135,
|
|
"epoch": 1.1358244365361803,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004879302868504078,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.19338615536689757,
|
|
"num_tokens": 26312598.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.720840120315552,
|
|
"epoch": 1.1363187030446817,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004879188812113289,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.20111506730318068,
|
|
"num_tokens": 26324300.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.570767974853515,
|
|
"epoch": 1.136812969553183,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004879074703344125,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.19834372997283936,
|
|
"num_tokens": 26335789.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.5793274402618405,
|
|
"epoch": 1.1373072360616845,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004878960542199394,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.19730139821767806,
|
|
"num_tokens": 26347336.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.656808757781983,
|
|
"epoch": 1.1378015025701858,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048788463286819037,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.2024213269352913,
|
|
"num_tokens": 26358176.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.55414605140686,
|
|
"epoch": 1.1382957690786872,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004878732062794462,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.19850924015045165,
|
|
"num_tokens": 26368915.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.594301843643189,
|
|
"epoch": 1.1387900355871885,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048786177445398816,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.19778390675783158,
|
|
"num_tokens": 26381687.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.646654272079468,
|
|
"epoch": 1.13928430209569,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004878503373920975,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.19569268822669983,
|
|
"num_tokens": 26394289.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.608573150634766,
|
|
"epoch": 1.1397785686041915,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004878388950940555,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.20786156356334687,
|
|
"num_tokens": 26405743.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.6764817237854,
|
|
"epoch": 1.1402728351126927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048782744756014365,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.18656122982501983,
|
|
"num_tokens": 26417255.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.682086658477783,
|
|
"epoch": 1.1407671016211942,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004878159947906436,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19522271901369095,
|
|
"num_tokens": 26428992.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.593657445907593,
|
|
"epoch": 1.1412613681296955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487804536785837,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.2081797391176224,
|
|
"num_tokens": 26440375.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.583353424072266,
|
|
"epoch": 1.141755634638197,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048779307354600586,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.19794875085353852,
|
|
"num_tokens": 26452253.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.6686248779296875,
|
|
"epoch": 1.1422499011466982,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048778160507143204,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19715603590011596,
|
|
"num_tokens": 26463766.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.642669153213501,
|
|
"epoch": 1.1427441676551997,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004877701313623978,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.19412551671266556,
|
|
"num_tokens": 26475869.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.6445270538330075,
|
|
"epoch": 1.1432384341637012,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004877586524191852,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.19723747819662094,
|
|
"num_tokens": 26487142.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.580124187469482,
|
|
"epoch": 1.1437327006722025,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004877471682420768,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2061804324388504,
|
|
"num_tokens": 26499019.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.569995498657226,
|
|
"epoch": 1.1442269671807037,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004877356788313551,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.20974014103412628,
|
|
"num_tokens": 26510060.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.548111152648926,
|
|
"epoch": 1.1447212336892052,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004877241841873027,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.204905404150486,
|
|
"num_tokens": 26520723.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.563028955459595,
|
|
"epoch": 1.1452155001977067,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004877126843102023,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20420341491699218,
|
|
"num_tokens": 26532545.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.565567207336426,
|
|
"epoch": 1.145709766706208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048770117920033697,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.2123001843690872,
|
|
"num_tokens": 26542993.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.564682960510254,
|
|
"epoch": 1.1462040332147094,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004876896688579895,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.20572238117456437,
|
|
"num_tokens": 26554658.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.629250621795654,
|
|
"epoch": 1.1466982997232107,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004876781532834433,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.2058918759226799,
|
|
"num_tokens": 26565925.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.597628784179688,
|
|
"epoch": 1.1471925662317122,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004876666324769815,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20127459168434142,
|
|
"num_tokens": 26577045.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.590678405761719,
|
|
"epoch": 1.1476868327402134,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004876551064388875,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.19435011148452758,
|
|
"num_tokens": 26587773.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.661182546615601,
|
|
"epoch": 1.148181099248715,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048764357516944485,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.2018751546740532,
|
|
"num_tokens": 26597861.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.6584696769714355,
|
|
"epoch": 1.1486753657572164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048763203866893735,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.19973020106554032,
|
|
"num_tokens": 26607695.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.625906753540039,
|
|
"epoch": 1.1491696322657177,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048762049693764866,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.18958619236946106,
|
|
"num_tokens": 26619845.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.661731863021851,
|
|
"epoch": 1.1496638987742192,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048760894997586284,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.2008199065923691,
|
|
"num_tokens": 26630279.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.543630838394165,
|
|
"epoch": 1.1501581652827204,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004875973977838639,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.20060469955205917,
|
|
"num_tokens": 26640996.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.525980710983276,
|
|
"epoch": 1.150652431791222,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048758584036193587,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.20681791603565217,
|
|
"num_tokens": 26652416.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.604940414428711,
|
|
"epoch": 1.1511466982997232,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004875742777103632,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.1943777620792389,
|
|
"num_tokens": 26663649.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.642388439178466,
|
|
"epoch": 1.1516409648082246,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048756270982943035,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.19223594218492507,
|
|
"num_tokens": 26676138.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.678112506866455,
|
|
"epoch": 1.152135231316726,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004875511367194219,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.19011210799217224,
|
|
"num_tokens": 26687364.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.614232921600342,
|
|
"epoch": 1.1526294978252274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875395583806225,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.19905974715948105,
|
|
"num_tokens": 26698135.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.603475761413574,
|
|
"epoch": 1.1531237643337287,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004875279748133169,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.2048828646540642,
|
|
"num_tokens": 26710495.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.675576496124267,
|
|
"epoch": 1.1536180308422301,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004875163860177902,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.18887696117162706,
|
|
"num_tokens": 26722876.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.629246473312378,
|
|
"epoch": 1.1541122973507316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048750479199432753,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19840702563524246,
|
|
"num_tokens": 26733548.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.558599376678467,
|
|
"epoch": 1.1546065638592329,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004874931927432139,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.20664387792348862,
|
|
"num_tokens": 26744754.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.560123586654663,
|
|
"epoch": 1.1551008303677344,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004874815882647348,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19843924045562744,
|
|
"num_tokens": 26757416.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.56107382774353,
|
|
"epoch": 1.1555950968762356,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004874699785591756,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20160049051046372,
|
|
"num_tokens": 26768572.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.566872215270996,
|
|
"epoch": 1.1560893633847371,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048745836362682203,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.20748162418603897,
|
|
"num_tokens": 26779309.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.628466987609864,
|
|
"epoch": 1.1565836298932384,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004874467434679598,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.20000311434268953,
|
|
"num_tokens": 26791107.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.569167947769165,
|
|
"epoch": 1.1570778964017399,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004874351180828746,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20910670161247252,
|
|
"num_tokens": 26801334.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.599823808670044,
|
|
"epoch": 1.1575721629102411,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004874234874718526,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.19623263776302338,
|
|
"num_tokens": 26812972.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.625125408172607,
|
|
"epoch": 1.1580664294187426,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048741185163517984,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.19551342129707336,
|
|
"num_tokens": 26823683.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.651418924331665,
|
|
"epoch": 1.1585606959272439,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048740021057314267,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.2049514576792717,
|
|
"num_tokens": 26835898.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.589020490646362,
|
|
"epoch": 1.1590549624357454,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048738856428602736,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20191656947135925,
|
|
"num_tokens": 26847363.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.5678403854370115,
|
|
"epoch": 1.1595492289442468,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004873769127741203,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20453623086214065,
|
|
"num_tokens": 26859081.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.594265413284302,
|
|
"epoch": 1.160043495452748,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004873652560377083,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.208095084130764,
|
|
"num_tokens": 26869966.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.583975172042846,
|
|
"epoch": 1.1605377619612496,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000487353594077078,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20198491364717483,
|
|
"num_tokens": 26880673.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.602110576629639,
|
|
"epoch": 1.1610320284697508,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048734192689251643,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.2037808582186699,
|
|
"num_tokens": 26892306.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.659937381744385,
|
|
"epoch": 1.1615262949782523,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004873302544843104,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.19477305114269255,
|
|
"num_tokens": 26904655.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.607494354248047,
|
|
"epoch": 1.1620205614867536,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004873185768527473,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.20037308037281037,
|
|
"num_tokens": 26916580.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.59541597366333,
|
|
"epoch": 1.162514827995255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048730689399811427,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.19932375848293304,
|
|
"num_tokens": 26927033.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.5870747566223145,
|
|
"epoch": 1.1630090945037563,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004872952059206986,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.19576814472675325,
|
|
"num_tokens": 26938594.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.582853078842163,
|
|
"epoch": 1.1635033610122578,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004872835126207881,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20771938413381577,
|
|
"num_tokens": 26949595.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.660822582244873,
|
|
"epoch": 1.163997627520759,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004872718140986701,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19752313047647477,
|
|
"num_tokens": 26961692.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.625831651687622,
|
|
"epoch": 1.1644918940292606,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048726011035463265,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.20097362101078034,
|
|
"num_tokens": 26972062.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.627157592773438,
|
|
"epoch": 1.164986160537762,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004872484013889635,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.2023749440908432,
|
|
"num_tokens": 26983353.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.638576173782349,
|
|
"epoch": 1.1654804270462633,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048723668720195067,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19006135314702988,
|
|
"num_tokens": 26994828.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.5532777309417725,
|
|
"epoch": 1.1659746935547648,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004872249677938825,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.2054157242178917,
|
|
"num_tokens": 27008311.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.545829200744629,
|
|
"epoch": 1.166468960063266,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004872132431650472,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20460338443517684,
|
|
"num_tokens": 27018984.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.6383496761322025,
|
|
"epoch": 1.1669632265717675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048720151331573317,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19370283484458922,
|
|
"num_tokens": 27029183.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.531656646728516,
|
|
"epoch": 1.1674574930802688,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000487189778246229,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.21045765280723572,
|
|
"num_tokens": 27039661.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.641313743591309,
|
|
"epoch": 1.1679517595887703,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048717803795682334,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.19960915595293044,
|
|
"num_tokens": 27051685.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.677731704711914,
|
|
"epoch": 1.1684460260972718,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004871662924478051,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.2004316419363022,
|
|
"num_tokens": 27062096.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.566514873504639,
|
|
"epoch": 1.168940292605773,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004871545417194631,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.202404448390007,
|
|
"num_tokens": 27073059.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.648821687698364,
|
|
"epoch": 1.1694345591142743,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048714278577208643,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19836764186620712,
|
|
"num_tokens": 27085272.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.663919734954834,
|
|
"epoch": 1.1699288256227758,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004871310246059644,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19877843856811522,
|
|
"num_tokens": 27096651.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.591395521163941,
|
|
"epoch": 1.1704230921312773,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048711925822138627,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.20013082921504974,
|
|
"num_tokens": 27108180.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.65935173034668,
|
|
"epoch": 1.1709173586397785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048710748661864135,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.1983470931649208,
|
|
"num_tokens": 27118902.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.627192831039428,
|
|
"epoch": 1.17141162514828,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048709570979801946,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.20421404987573624,
|
|
"num_tokens": 27131279.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.55908317565918,
|
|
"epoch": 1.1719058916567813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048708392775981014,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.20507726520299913,
|
|
"num_tokens": 27142983.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.625089979171753,
|
|
"epoch": 1.1724001581652828,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004870721405043033,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.2035112828016281,
|
|
"num_tokens": 27154516.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.62056975364685,
|
|
"epoch": 1.172894424673784,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004870603480317889,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.20283437967300416,
|
|
"num_tokens": 27164717.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.61588191986084,
|
|
"epoch": 1.1733886911822855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048704855034255713,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.20290824621915818,
|
|
"num_tokens": 27174830.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.58607234954834,
|
|
"epoch": 1.173882957690787,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048703674743689806,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.1991803303360939,
|
|
"num_tokens": 27186724.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.5404561996459964,
|
|
"epoch": 1.1743772241992882,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004870249393151021,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20301436632871628,
|
|
"num_tokens": 27198416.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.570279598236084,
|
|
"epoch": 1.1748714907077897,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048701312597745986,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.2034875750541687,
|
|
"num_tokens": 27209347.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.626441144943238,
|
|
"epoch": 1.175365757216291,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048700130742426165,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.19788456857204437,
|
|
"num_tokens": 27221061.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.538058948516846,
|
|
"epoch": 1.1758600237247925,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004869894836557985,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.2129423052072525,
|
|
"num_tokens": 27233436.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.573163318634033,
|
|
"epoch": 1.1763542902332937,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048697765467236117,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.21005520075559617,
|
|
"num_tokens": 27246308.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.593556213378906,
|
|
"epoch": 1.1768485567417952,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048696582047424053,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.199239319562912,
|
|
"num_tokens": 27258187.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.5561316967010494,
|
|
"epoch": 1.1773428232502965,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048695398106172793,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.20541492998600006,
|
|
"num_tokens": 27269411.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.611875343322754,
|
|
"epoch": 1.177837089758798,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004869421364351145,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.20315765738487243,
|
|
"num_tokens": 27280592.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.683233690261841,
|
|
"epoch": 1.1783313562672992,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048693028659469156,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.1890906199812889,
|
|
"num_tokens": 27292151.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.610967111587525,
|
|
"epoch": 1.1788256227758007,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048691843154075075,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.2052637293934822,
|
|
"num_tokens": 27305371.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.579727268218994,
|
|
"epoch": 1.1793198892843022,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048690657127358367,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.1920991212129593,
|
|
"num_tokens": 27316810.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.588397884368897,
|
|
"epoch": 1.1798141557928035,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048689470579348207,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.20227353870868683,
|
|
"num_tokens": 27328412.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.6597496509552006,
|
|
"epoch": 1.180308422301305,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048688283510073775,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19740669429302216,
|
|
"num_tokens": 27340216.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.609868097305298,
|
|
"epoch": 1.1808026888098062,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004868709591956429,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.203493170440197,
|
|
"num_tokens": 27350290.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.589484691619873,
|
|
"epoch": 1.1812969553183077,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048685907807848955,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.19132159352302552,
|
|
"num_tokens": 27360639.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.528190088272095,
|
|
"epoch": 1.181791221826809,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048684719174957005,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2117920696735382,
|
|
"num_tokens": 27372059.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.626075744628906,
|
|
"epoch": 1.1822854883353104,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004868353002091767,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19016459286212922,
|
|
"num_tokens": 27384308.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.563534784317016,
|
|
"epoch": 1.1827797548438117,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004868234034576021,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.21657481789588928,
|
|
"num_tokens": 27395510.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.565920400619507,
|
|
"epoch": 1.1832740213523132,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000486811501495139,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.19558025002479554,
|
|
"num_tokens": 27406697.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.576605987548828,
|
|
"epoch": 1.1837682878608144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004867995943220801,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.2068494588136673,
|
|
"num_tokens": 27418047.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.6756151676177975,
|
|
"epoch": 1.184262554369316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048678768193871825,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.19117049127817154,
|
|
"num_tokens": 27430044.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.576125001907348,
|
|
"epoch": 1.1847568208778174,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004867757643453466,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.19635282158851625,
|
|
"num_tokens": 27441392.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.6109843254089355,
|
|
"epoch": 1.1852510873863187,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048676384154225827,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.19204170107841492,
|
|
"num_tokens": 27451356.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.580730199813843,
|
|
"epoch": 1.1857453538948202,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004867519135297466,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.21453266739845275,
|
|
"num_tokens": 27462358.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.562673139572143,
|
|
"epoch": 1.1862396204033214,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048673998030810507,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.2045995220541954,
|
|
"num_tokens": 27474144.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1862396204033214,
|
|
"eval_entropy": 5.383485007667307,
|
|
"eval_loss": 5.234320640563965,
|
|
"eval_mean_token_accuracy": 0.20572784973759786,
|
|
"eval_num_tokens": 27474144.0,
|
|
"eval_runtime": 20.2804,
|
|
"eval_samples_per_second": 1603.177,
|
|
"eval_steps_per_second": 200.44,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.653583526611328,
|
|
"epoch": 1.186733886911823,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048672804187762704,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.19092400819063188,
|
|
"num_tokens": 27486337.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.649458265304565,
|
|
"epoch": 1.1872281534203242,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004867160982386065,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.2044711634516716,
|
|
"num_tokens": 27498686.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.6351463317871096,
|
|
"epoch": 1.1877224199288257,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048670414939133694,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.19753533452749253,
|
|
"num_tokens": 27509850.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.695661449432373,
|
|
"epoch": 1.188216686437327,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004866921953361125,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18923946022987365,
|
|
"num_tokens": 27521994.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.621406078338623,
|
|
"epoch": 1.1887109529458284,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004866802360732273,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.19785112142562866,
|
|
"num_tokens": 27534980.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.579017210006714,
|
|
"epoch": 1.1892052194543297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004866682716029754,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20326415002346038,
|
|
"num_tokens": 27546461.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.552903175354004,
|
|
"epoch": 1.1896994859628311,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048665630192565117,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.2066235661506653,
|
|
"num_tokens": 27557076.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.570175457000732,
|
|
"epoch": 1.1901937524713326,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004866443270415491,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20561925768852235,
|
|
"num_tokens": 27569807.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.585324239730835,
|
|
"epoch": 1.190688018979834,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004866323469509637,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.2063242346048355,
|
|
"num_tokens": 27579858.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.592084646224976,
|
|
"epoch": 1.1911822854883354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004866203616541898,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1929704427719116,
|
|
"num_tokens": 27590192.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.568342113494873,
|
|
"epoch": 1.1916765519968366,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048660837115152214,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.1993996888399124,
|
|
"num_tokens": 27601756.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.577364253997803,
|
|
"epoch": 1.1921708185053381,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004865963754432557,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20514120906591415,
|
|
"num_tokens": 27614019.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.58779125213623,
|
|
"epoch": 1.1926650850138394,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004865843745296856,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.20542415529489516,
|
|
"num_tokens": 27626900.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.600142621994019,
|
|
"epoch": 1.1931593515223409,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048657236841110707,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.20728186815977095,
|
|
"num_tokens": 27637897.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.600163364410401,
|
|
"epoch": 1.1936536180308421,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004865603570878155,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19757177233695983,
|
|
"num_tokens": 27649523.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.639275693893433,
|
|
"epoch": 1.1941478845393436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004865483405601063,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.1940677896142006,
|
|
"num_tokens": 27659406.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.556991195678711,
|
|
"epoch": 1.1946421510478449,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004865363188282751,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.2022227704524994,
|
|
"num_tokens": 27670912.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.607714128494263,
|
|
"epoch": 1.1951364175563464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048652429189261767,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.2045132339000702,
|
|
"num_tokens": 27681667.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.630290269851685,
|
|
"epoch": 1.1956306840648478,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004865122597534298,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20539135336875916,
|
|
"num_tokens": 27692170.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.527071571350097,
|
|
"epoch": 1.196124950573349,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004865002224110075,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21391580402851104,
|
|
"num_tokens": 27702533.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.526327133178711,
|
|
"epoch": 1.1966192170818506,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000486488179865647,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.21101298779249192,
|
|
"num_tokens": 27713795.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.616069793701172,
|
|
"epoch": 1.1971134835903519,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004864761321176444,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.20291955918073654,
|
|
"num_tokens": 27725404.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.58313684463501,
|
|
"epoch": 1.1976077500988533,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004864640791672962,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.20194893479347228,
|
|
"num_tokens": 27737537.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.565320444107056,
|
|
"epoch": 1.1981020166073546,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004864520210148988,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20830781161785125,
|
|
"num_tokens": 27749841.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.5944469451904295,
|
|
"epoch": 1.198596283115856,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004864399576607489,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.1986828327178955,
|
|
"num_tokens": 27760302.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.590524101257325,
|
|
"epoch": 1.1990905496243576,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048642788910514324,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19550853967666626,
|
|
"num_tokens": 27770989.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.621889114379883,
|
|
"epoch": 1.1995848161328588,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048641581534837863,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.20311632007360458,
|
|
"num_tokens": 27785196.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.639049291610718,
|
|
"epoch": 1.2000790826413603,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048640373639075225,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19853634685277938,
|
|
"num_tokens": 27795588.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.53092041015625,
|
|
"epoch": 1.2005733491498616,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048639165223256117,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.20777903795242308,
|
|
"num_tokens": 27807204.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.56425895690918,
|
|
"epoch": 1.201067615658363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048637956287410263,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.2083168163895607,
|
|
"num_tokens": 27817959.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.622759914398193,
|
|
"epoch": 1.2015618821668643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048636746831567403,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.1951030135154724,
|
|
"num_tokens": 27830736.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.614208507537842,
|
|
"epoch": 1.2020561486753658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004863553685575729,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.1959793120622635,
|
|
"num_tokens": 27840992.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.634388017654419,
|
|
"epoch": 1.202550415183867,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004863432636000969,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.20044248551130295,
|
|
"num_tokens": 27852747.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.61766095161438,
|
|
"epoch": 1.2030446816923686,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004863311534435439,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.19313942044973373,
|
|
"num_tokens": 27865136.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.647297811508179,
|
|
"epoch": 1.2035389482008698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048631903808821176,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.20663827955722808,
|
|
"num_tokens": 27876489.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.587033033370972,
|
|
"epoch": 1.2040332147093713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048630691753439844,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20373774766921998,
|
|
"num_tokens": 27886478.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.587065601348877,
|
|
"epoch": 1.2045274812178728,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004862947917824022,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.21140831410884858,
|
|
"num_tokens": 27897473.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.559801149368286,
|
|
"epoch": 1.205021747726374,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048628266083252124,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.20312462300062178,
|
|
"num_tokens": 27908390.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.656748962402344,
|
|
"epoch": 1.2055160142348755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004862705246850541,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.19710809737443924,
|
|
"num_tokens": 27919372.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.565665912628174,
|
|
"epoch": 1.2060102807433768,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004862583833402993,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.20071054995059967,
|
|
"num_tokens": 27931294.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.597567462921143,
|
|
"epoch": 1.2065045472518783,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004862462367985554,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.20094138383865356,
|
|
"num_tokens": 27941782.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.587536239624024,
|
|
"epoch": 1.2069988137603795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004862340850601214,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.21630823761224746,
|
|
"num_tokens": 27951703.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.619594955444336,
|
|
"epoch": 1.207493080268881,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004862219281252961,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.20819125026464463,
|
|
"num_tokens": 27962049.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.609088659286499,
|
|
"epoch": 1.2079873467773823,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004862097659943786,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.20220282673835754,
|
|
"num_tokens": 27973502.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.529992008209229,
|
|
"epoch": 1.2084816132858838,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048619759866766807,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21259839087724686,
|
|
"num_tokens": 27984653.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.646906518936158,
|
|
"epoch": 1.208975879794385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048618542614546384,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.1931415766477585,
|
|
"num_tokens": 27995152.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.687624454498291,
|
|
"epoch": 1.2094701463028865,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048617324842806545,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1986030176281929,
|
|
"num_tokens": 28006928.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.634944057464599,
|
|
"epoch": 1.209964412811388,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048616106551577226,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.20146350413560868,
|
|
"num_tokens": 28018004.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.635783529281616,
|
|
"epoch": 1.2104586793198893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048614887740888426,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.19530068784952165,
|
|
"num_tokens": 28030645.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.6136678695678714,
|
|
"epoch": 1.2109529458283907,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000486136684107701,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19772738963365555,
|
|
"num_tokens": 28042591.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.595608568191528,
|
|
"epoch": 1.211447212336892,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004861244856125226,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.2071019947528839,
|
|
"num_tokens": 28053285.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.497919750213623,
|
|
"epoch": 1.2119414788453935,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004861122819236491,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.20923605412244797,
|
|
"num_tokens": 28065747.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.547616672515869,
|
|
"epoch": 1.2124357453538948,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048610007304138067,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.2066199079155922,
|
|
"num_tokens": 28077112.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.576477956771851,
|
|
"epoch": 1.2129300118623962,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004860878589660177,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20805134773254394,
|
|
"num_tokens": 28088835.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.7280186176300045,
|
|
"epoch": 1.2134242783708975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004860756396978607,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.19641973823308945,
|
|
"num_tokens": 28100921.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.621302747726441,
|
|
"epoch": 1.213918544879399,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004860634152372102,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20396069437265396,
|
|
"num_tokens": 28112531.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.600346088409424,
|
|
"epoch": 1.2144128113879002,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004860511855843669,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.19917640835046768,
|
|
"num_tokens": 28123821.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.597126102447509,
|
|
"epoch": 1.2149070778964017,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048603895073963177,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.20004457384347915,
|
|
"num_tokens": 28135046.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.578131484985351,
|
|
"epoch": 1.2154013444049032,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048602671070330564,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20418113619089126,
|
|
"num_tokens": 28145870.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.637307739257812,
|
|
"epoch": 1.2158956109134045,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048601446547568973,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.199427792429924,
|
|
"num_tokens": 28156078.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.6564719676971436,
|
|
"epoch": 1.216389877421906,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004860022150570852,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.20048206448554992,
|
|
"num_tokens": 28166658.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.602855062484741,
|
|
"epoch": 1.2168841439304072,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048598995944779344,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.19947403073310851,
|
|
"num_tokens": 28178890.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.5516801357269285,
|
|
"epoch": 1.2173784104389087,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048597769864811604,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.20558477193117142,
|
|
"num_tokens": 28191101.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.575514507293701,
|
|
"epoch": 1.21787267694741,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004859654326583544,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.19524018615484237,
|
|
"num_tokens": 28202877.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.648002243041992,
|
|
"epoch": 1.2183669434559115,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004859531614788105,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.19933852553367615,
|
|
"num_tokens": 28214762.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.610240650177002,
|
|
"epoch": 1.2188612099644127,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000485940885109786,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.19939442574977875,
|
|
"num_tokens": 28225830.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.549664926528931,
|
|
"epoch": 1.2193554764729142,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048592860355158306,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.20628627836704255,
|
|
"num_tokens": 28237302.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.630464220046997,
|
|
"epoch": 1.2198497429814155,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004859163168045038,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.20821657925844192,
|
|
"num_tokens": 28247658.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.604777765274048,
|
|
"epoch": 1.220344009489917,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004859040248688503,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.20057357251644134,
|
|
"num_tokens": 28258473.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.673536539077759,
|
|
"epoch": 1.2208382759984184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048589172774492515,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.1946871757507324,
|
|
"num_tokens": 28270167.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.574902677536011,
|
|
"epoch": 1.2213325425069197,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048587942543303075,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.20437152683734894,
|
|
"num_tokens": 28282047.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.617326784133911,
|
|
"epoch": 1.2218268090154212,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004858671179334698,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.20207096338272096,
|
|
"num_tokens": 28292868.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.668056678771973,
|
|
"epoch": 1.2223210755239224,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048585480524654504,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.18875020146369934,
|
|
"num_tokens": 28303816.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.703281879425049,
|
|
"epoch": 1.222815342032424,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004858424873725593,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.19464305192232131,
|
|
"num_tokens": 28315191.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.62325382232666,
|
|
"epoch": 1.2233096085409252,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004858301643118157,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.20906853675842285,
|
|
"num_tokens": 28325312.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.597158765792846,
|
|
"epoch": 1.2238038750494267,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004858178360646174,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.19559988826513292,
|
|
"num_tokens": 28336171.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.62886118888855,
|
|
"epoch": 1.2242981415579282,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048580550263126757,
|
|
"loss": 5.1685,
|
|
"mean_token_accuracy": 0.19308807253837584,
|
|
"num_tokens": 28347488.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.630147314071655,
|
|
"epoch": 1.2247924080664294,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004857931640120697,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.208355675637722,
|
|
"num_tokens": 28358653.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.56231837272644,
|
|
"epoch": 1.2252866745749307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048578082020732724,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.21470384895801545,
|
|
"num_tokens": 28369588.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.539016628265381,
|
|
"epoch": 1.2257809410834322,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000485768471217344,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20441180020570754,
|
|
"num_tokens": 28382009.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.6225905418396,
|
|
"epoch": 1.2262752075919336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004857561170424235,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.1935718074440956,
|
|
"num_tokens": 28394376.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.661586666107178,
|
|
"epoch": 1.226769474100435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048574375768286996,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19408906549215316,
|
|
"num_tokens": 28406453.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.649782705307007,
|
|
"epoch": 1.2272637406089364,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048573139313898723,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.2031419813632965,
|
|
"num_tokens": 28417178.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.637105798721313,
|
|
"epoch": 1.2277580071174377,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004857190234110795,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.20015554428100585,
|
|
"num_tokens": 28428396.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.512139701843262,
|
|
"epoch": 1.2282522736259391,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004857066484994512,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.20210360139608383,
|
|
"num_tokens": 28441239.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.667537689208984,
|
|
"epoch": 1.2287465401344404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004856942684044067,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.19752326160669326,
|
|
"num_tokens": 28453671.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.582129287719726,
|
|
"epoch": 1.2292408066429419,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048568188312625037,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.20495306998491286,
|
|
"num_tokens": 28465922.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.602464580535889,
|
|
"epoch": 1.2297350731514434,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004856694926652871,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20125184953212738,
|
|
"num_tokens": 28477559.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.598109722137451,
|
|
"epoch": 1.2302293396599446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048565709702182164,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.20271470993757248,
|
|
"num_tokens": 28489276.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.656957721710205,
|
|
"epoch": 1.2307236061684461,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004856446961961589,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19666676521301268,
|
|
"num_tokens": 28500821.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.626819658279419,
|
|
"epoch": 1.2312178726769474,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048563229018860394,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.1995206817984581,
|
|
"num_tokens": 28513646.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.625207901000977,
|
|
"epoch": 1.2317121391854489,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048561987899946204,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.20061760991811753,
|
|
"num_tokens": 28525508.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.671635484695434,
|
|
"epoch": 1.2322064056939501,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048560746262903836,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.20013634413480758,
|
|
"num_tokens": 28537863.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.594590187072754,
|
|
"epoch": 1.2327006722024516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004855950410776385,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.20013972073793412,
|
|
"num_tokens": 28550163.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.569287204742432,
|
|
"epoch": 1.2331949387109529,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004855826143455678,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.2044650748372078,
|
|
"num_tokens": 28560501.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.642317914962769,
|
|
"epoch": 1.2336892052194544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004855701824331323,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.19111482053995132,
|
|
"num_tokens": 28573057.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.6599585056304935,
|
|
"epoch": 1.2341834717279556,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048555774534063753,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.19412537068128585,
|
|
"num_tokens": 28585147.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.5681092739105225,
|
|
"epoch": 1.234677738236457,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004855453030683896,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.20180812925100328,
|
|
"num_tokens": 28597774.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.5877790451049805,
|
|
"epoch": 1.2351720047449586,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004855328556166945,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.20889432430267335,
|
|
"num_tokens": 28610031.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.678851747512818,
|
|
"epoch": 1.2356662712534598,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004855204029858586,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.19768964350223542,
|
|
"num_tokens": 28621485.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.553160524368286,
|
|
"epoch": 1.2361605377619613,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004855079451761881,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.2095265194773674,
|
|
"num_tokens": 28632213.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.653820276260376,
|
|
"epoch": 1.2366548042704626,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004854954821879894,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.19858562648296357,
|
|
"num_tokens": 28643994.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.689612770080567,
|
|
"epoch": 1.237149070778964,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048548301402156927,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20170676112174987,
|
|
"num_tokens": 28656556.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.559452867507934,
|
|
"epoch": 1.2376433372874653,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004854705406772343,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.21086514443159105,
|
|
"num_tokens": 28668022.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.578398942947388,
|
|
"epoch": 1.2381376037959668,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048545806215529136,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.1932649776339531,
|
|
"num_tokens": 28679074.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.584602975845337,
|
|
"epoch": 1.238631870304468,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048544557845604753,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20529838353395463,
|
|
"num_tokens": 28691872.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.68801794052124,
|
|
"epoch": 1.2391261368129696,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048543308957980973,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20175143778324128,
|
|
"num_tokens": 28703367.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.544709205627441,
|
|
"epoch": 1.2396204033214708,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004854205955268853,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.21557773202657698,
|
|
"num_tokens": 28713841.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.614033794403076,
|
|
"epoch": 1.2401146698299723,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048540809629758167,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.19133178740739823,
|
|
"num_tokens": 28724924.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.646211719512939,
|
|
"epoch": 1.2406089363384738,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004853955918922061,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.20168422311544418,
|
|
"num_tokens": 28736236.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.6162806987762455,
|
|
"epoch": 1.241103202846975,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004853830823110663,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.20196668654680253,
|
|
"num_tokens": 28748841.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.614727544784546,
|
|
"epoch": 1.2415974693554765,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004853705675544702,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.20583087652921678,
|
|
"num_tokens": 28759491.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.5234678268432615,
|
|
"epoch": 1.2420917358639778,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004853580476227254,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.21282768100500107,
|
|
"num_tokens": 28771668.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.591923666000366,
|
|
"epoch": 1.2425860023724793,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048534552251614,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.2023793265223503,
|
|
"num_tokens": 28783102.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.6146016120910645,
|
|
"epoch": 1.2430802688809806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048533299223502217,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.20200454741716384,
|
|
"num_tokens": 28794643.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.647573947906494,
|
|
"epoch": 1.243574535389482,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004853204567796801,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.1998774752020836,
|
|
"num_tokens": 28806597.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.6524921417236325,
|
|
"epoch": 1.2440688018979833,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000485307916150422,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20473649948835373,
|
|
"num_tokens": 28817379.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.5983129978179935,
|
|
"epoch": 1.2445630684064848,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004852953703475567,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.19593906551599502,
|
|
"num_tokens": 28828412.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.552895498275757,
|
|
"epoch": 1.245057334914986,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048528281937139264,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.20716252774000168,
|
|
"num_tokens": 28839888.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.688387203216553,
|
|
"epoch": 1.2455516014234875,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048527026322223854,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.19356297254562377,
|
|
"num_tokens": 28852113.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.703811073303223,
|
|
"epoch": 1.246045867931989,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004852577019004035,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.20062498301267623,
|
|
"num_tokens": 28864715.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.551042604446411,
|
|
"epoch": 1.2465401344404903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004852451354061962,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.2075832813978195,
|
|
"num_tokens": 28875166.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.565544986724854,
|
|
"epoch": 1.2470344009489918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048523256373992604,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.20261204987764359,
|
|
"num_tokens": 28885946.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.61906590461731,
|
|
"epoch": 1.247528667457493,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004852199869019021,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20566643625497819,
|
|
"num_tokens": 28896654.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.638206338882446,
|
|
"epoch": 1.2480229339659945,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048520740489243396,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.2058072954416275,
|
|
"num_tokens": 28908306.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.663869333267212,
|
|
"epoch": 1.2485172004744958,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048519481771183107,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.1978392481803894,
|
|
"num_tokens": 28921044.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.596053504943848,
|
|
"epoch": 1.2490114669829973,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000485182225360403,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20777199566364288,
|
|
"num_tokens": 28932290.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.64762167930603,
|
|
"epoch": 1.2495057334914987,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004851696278384596,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.20753619372844695,
|
|
"num_tokens": 28943482.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.569782781600952,
|
|
"epoch": 1.25,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004851570251463107,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.2050385981798172,
|
|
"num_tokens": 28954749.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.661541509628296,
|
|
"epoch": 1.2504942665085013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048514441728426646,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.1963829755783081,
|
|
"num_tokens": 28965304.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.589245271682739,
|
|
"epoch": 1.2509885330170027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004851318042526369,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20160708725452423,
|
|
"num_tokens": 28976267.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.671817922592163,
|
|
"epoch": 1.2514827995255042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004851191860517324,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.19921755194664,
|
|
"num_tokens": 28986492.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.639932298660279,
|
|
"epoch": 1.2519770660340055,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048510656268186325,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.20819203853607177,
|
|
"num_tokens": 28996693.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.628533124923706,
|
|
"epoch": 1.252471332542507,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004850939341433401,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.2071919322013855,
|
|
"num_tokens": 29008498.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.700745630264282,
|
|
"epoch": 1.2529655990510082,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048508130043647366,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19921180754899978,
|
|
"num_tokens": 29018563.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.6038453578948975,
|
|
"epoch": 1.2534598655595097,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004850686615615745,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20676477998495102,
|
|
"num_tokens": 29029204.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.5950610637664795,
|
|
"epoch": 1.253954132068011,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048505601751895383,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19542920589447021,
|
|
"num_tokens": 29041112.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.755059814453125,
|
|
"epoch": 1.2544483985765125,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004850433683089224,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.2016877919435501,
|
|
"num_tokens": 29052791.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.643318843841553,
|
|
"epoch": 1.254942665085014,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004850307139317916,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19817846715450288,
|
|
"num_tokens": 29064525.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.4800217628479,
|
|
"epoch": 1.2554369315935152,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004850180543878726,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.20993019193410872,
|
|
"num_tokens": 29077265.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.587852191925049,
|
|
"epoch": 1.2559311981020165,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004850053896774769,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20622878819704055,
|
|
"num_tokens": 29088022.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.616099786758423,
|
|
"epoch": 1.256425464610518,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004849927198009161,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.20228475332260132,
|
|
"num_tokens": 29099901.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.629412126541138,
|
|
"epoch": 1.2569197311190194,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048498004475850174,
|
|
"loss": 5.1443,
|
|
"mean_token_accuracy": 0.20299194753170013,
|
|
"num_tokens": 29111249.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.55161943435669,
|
|
"epoch": 1.2574139976275207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048496736455054567,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.20392204374074935,
|
|
"num_tokens": 29121261.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.662248802185059,
|
|
"epoch": 1.2579082641360222,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048495467917736003,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.19820868223905563,
|
|
"num_tokens": 29133987.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.692547988891602,
|
|
"epoch": 1.2584025306445235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004849419886392565,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.20418147891759872,
|
|
"num_tokens": 29146499.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.610771369934082,
|
|
"epoch": 1.258896797153025,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004849292929365476,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.2084289789199829,
|
|
"num_tokens": 29157892.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.598493909835815,
|
|
"epoch": 1.2593910636615262,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004849165920695455,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.19636119306087493,
|
|
"num_tokens": 29169823.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.714604711532592,
|
|
"epoch": 1.2598853301700277,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004849038860385627,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.19635072052478791,
|
|
"num_tokens": 29181065.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.628191614151001,
|
|
"epoch": 1.2603795966785292,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004848911748439117,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.20198585093021393,
|
|
"num_tokens": 29192711.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.50081696510315,
|
|
"epoch": 1.2608738631870304,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004848784584859052,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.20408947467803956,
|
|
"num_tokens": 29204688.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.52916784286499,
|
|
"epoch": 1.2613681296955317,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004848657369648561,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.2054903730750084,
|
|
"num_tokens": 29216326.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.584849262237549,
|
|
"epoch": 1.2618623962040332,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048485301028107736,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.20986506193876267,
|
|
"num_tokens": 29226805.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.510245895385742,
|
|
"epoch": 1.2623566627125347,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000484840278434882,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20578916221857071,
|
|
"num_tokens": 29239334.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.670744895935059,
|
|
"epoch": 1.262850929221036,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004848275414265832,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20084321945905687,
|
|
"num_tokens": 29250443.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.627966594696045,
|
|
"epoch": 1.2633451957295374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048481479925649435,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2029610589146614,
|
|
"num_tokens": 29261209.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.58952145576477,
|
|
"epoch": 1.2638394622380387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048480205192492887,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.1942895010113716,
|
|
"num_tokens": 29273761.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.633354663848877,
|
|
"epoch": 1.2643337287465402,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004847892994322004,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.1991262122988701,
|
|
"num_tokens": 29285157.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.647629833221435,
|
|
"epoch": 1.2648279952550414,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004847765417786226,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.20010811984539031,
|
|
"num_tokens": 29295903.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.6801337718963625,
|
|
"epoch": 1.265322261763543,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004847637789645093,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.1975858509540558,
|
|
"num_tokens": 29307865.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.71594123840332,
|
|
"epoch": 1.2658165282720444,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004847510109901745,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.19260375797748566,
|
|
"num_tokens": 29319614.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.600550794601441,
|
|
"epoch": 1.2663107947805456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004847382378559323,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.20230374187231065,
|
|
"num_tokens": 29330306.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.581346225738526,
|
|
"epoch": 1.2668050612890471,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048472545956209696,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.20297340750694276,
|
|
"num_tokens": 29341611.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.544973516464234,
|
|
"epoch": 1.2672993277975484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004847126761089827,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21368690431118012,
|
|
"num_tokens": 29353481.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.529405307769776,
|
|
"epoch": 1.2677935943060499,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004846998874969041,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.2066498577594757,
|
|
"num_tokens": 29365388.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.652158975601196,
|
|
"epoch": 1.2682878608145511,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004846870937261758,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.19062366634607314,
|
|
"num_tokens": 29377805.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.589198589324951,
|
|
"epoch": 1.2687821273230526,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048467429479711233,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.2064957708120346,
|
|
"num_tokens": 29389736.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.5553840637207035,
|
|
"epoch": 1.269276393831554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048466149071002876,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.2071990981698036,
|
|
"num_tokens": 29401256.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.634617614746094,
|
|
"epoch": 1.2697706603400554,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048464868146524,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.20588081926107407,
|
|
"num_tokens": 29413287.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.627452373504639,
|
|
"epoch": 1.2702649268485566,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048463586706306113,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.2002803385257721,
|
|
"num_tokens": 29424151.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.6100116729736325,
|
|
"epoch": 1.2707591933570581,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004846230475038074,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.19904198199510575,
|
|
"num_tokens": 29435006.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.571206140518188,
|
|
"epoch": 1.2712534598655596,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004846102227877942,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.2050365000963211,
|
|
"num_tokens": 29446453.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.6743629455566404,
|
|
"epoch": 1.2717477263740609,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048459739291533706,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.19746432453393936,
|
|
"num_tokens": 29458468.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.661905574798584,
|
|
"epoch": 1.2722419928825623,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004845845578867514,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.194038487970829,
|
|
"num_tokens": 29471167.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.646562910079956,
|
|
"epoch": 1.2727362593910636,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048457171770235327,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.207851405441761,
|
|
"num_tokens": 29482668.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.658450698852539,
|
|
"epoch": 1.273230525899565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845588723624582,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.19728438407182694,
|
|
"num_tokens": 29495424.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.564928293228149,
|
|
"epoch": 1.2737247924080664,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004845460218673825,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.20520664900541305,
|
|
"num_tokens": 29508388.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.6171262741088865,
|
|
"epoch": 1.2742190589165678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004845331662174421,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.20575871467590331,
|
|
"num_tokens": 29519884.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.689295101165771,
|
|
"epoch": 1.2747133254250693,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004845203054129533,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.1942901998758316,
|
|
"num_tokens": 29532398.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.628507137298584,
|
|
"epoch": 1.2752075919335706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048450743945423246,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.2119820237159729,
|
|
"num_tokens": 29544394.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.673480558395386,
|
|
"epoch": 1.2757018584420718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004844945683415961,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.2002863645553589,
|
|
"num_tokens": 29555027.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.616532039642334,
|
|
"epoch": 1.2761961249505733,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000484481692075361,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.2002000167965889,
|
|
"num_tokens": 29567386.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.717002820968628,
|
|
"epoch": 1.2766903914590748,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048446881065584367,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.19442391246557236,
|
|
"num_tokens": 29577832.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.570171928405761,
|
|
"epoch": 1.277184657967576,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048445592408336106,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.20917456299066545,
|
|
"num_tokens": 29590163.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.632161235809326,
|
|
"epoch": 1.2776789244760776,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048444303235823023,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.20921237170696258,
|
|
"num_tokens": 29601531.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.6455076217651365,
|
|
"epoch": 1.2781731909845788,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004844301354807683,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19835297614336014,
|
|
"num_tokens": 29612417.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.644040107727051,
|
|
"epoch": 1.2786674574930803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048441723345129265,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.19811962693929672,
|
|
"num_tokens": 29622087.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.72923002243042,
|
|
"epoch": 1.2791617240015816,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004844043262701205,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.19344150722026826,
|
|
"num_tokens": 29633564.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.566200399398804,
|
|
"epoch": 1.279655990510083,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004843914139375695,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.2096967577934265,
|
|
"num_tokens": 29644626.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.54102725982666,
|
|
"epoch": 1.2801502570185845,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048437849645395714,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.207371324300766,
|
|
"num_tokens": 29655587.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.65713062286377,
|
|
"epoch": 1.2806445235270858,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004843655738196013,
|
|
"loss": 5.1685,
|
|
"mean_token_accuracy": 0.20464203655719757,
|
|
"num_tokens": 29665067.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.629691028594971,
|
|
"epoch": 1.281138790035587,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004843526460348199,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.20919883251190186,
|
|
"num_tokens": 29676663.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.487932205200195,
|
|
"epoch": 1.2816330565440885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004843397130999309,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.2088191330432892,
|
|
"num_tokens": 29688242.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.666353368759156,
|
|
"epoch": 1.28212732305259,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048432677501525253,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.19449738115072251,
|
|
"num_tokens": 29699184.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.60735969543457,
|
|
"epoch": 1.2826215895610913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000484313831781103,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.20705566704273223,
|
|
"num_tokens": 29709610.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.565745449066162,
|
|
"epoch": 1.2831158560695928,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004843008833978007,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21079954206943513,
|
|
"num_tokens": 29720359.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.67177734375,
|
|
"epoch": 1.283610122578094,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048428792986566425,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19492763429880142,
|
|
"num_tokens": 29732411.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.588061857223511,
|
|
"epoch": 1.2841043890865955,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004842749711850122,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.2178141340613365,
|
|
"num_tokens": 29743394.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.631382751464844,
|
|
"epoch": 1.2845986555950968,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048426200735616343,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.20099123567342758,
|
|
"num_tokens": 29754798.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.60563817024231,
|
|
"epoch": 1.2850929221035983,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004842490383794368,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20183158218860625,
|
|
"num_tokens": 29767891.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.595604038238525,
|
|
"epoch": 1.2855871886120998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048423606425515136,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.2148740202188492,
|
|
"num_tokens": 29780264.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.628677797317505,
|
|
"epoch": 1.286081455120601,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048422308498362635,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.1982138127088547,
|
|
"num_tokens": 29792184.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.605609130859375,
|
|
"epoch": 1.2865757216291023,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004842101005651809,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20221961438655853,
|
|
"num_tokens": 29802651.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.6056290626525875,
|
|
"epoch": 1.2870699881376038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004841971110001346,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.2072314888238907,
|
|
"num_tokens": 29814172.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.634095811843872,
|
|
"epoch": 1.2875642546461052,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048418411628880684,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.1982515960931778,
|
|
"num_tokens": 29826636.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.586856079101563,
|
|
"epoch": 1.2880585211546065,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004841711164315174,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2053912341594696,
|
|
"num_tokens": 29838532.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.588652515411377,
|
|
"epoch": 1.288552787663108,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000484158111428586,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.20414370894432068,
|
|
"num_tokens": 29849889.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.6551511764526365,
|
|
"epoch": 1.2890470541716093,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048414510128033265,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.1907067447900772,
|
|
"num_tokens": 29860856.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.6138053894042965,
|
|
"epoch": 1.2895413206801107,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004841320859870774,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20792338103055955,
|
|
"num_tokens": 29871921.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.595465755462646,
|
|
"epoch": 1.290035587188612,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048411906554914037,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.2023842990398407,
|
|
"num_tokens": 29883410.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.72114315032959,
|
|
"epoch": 1.2905298536971135,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048410603996684184,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.1980239510536194,
|
|
"num_tokens": 29895640.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.601849555969238,
|
|
"epoch": 1.291024120205615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004840930092405023,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.21375047117471696,
|
|
"num_tokens": 29907797.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.4979503631591795,
|
|
"epoch": 1.2915183867141162,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048407997337044235,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.2045082226395607,
|
|
"num_tokens": 29919085.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.613076114654541,
|
|
"epoch": 1.2920126532226177,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004840669323569826,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.19091561138629914,
|
|
"num_tokens": 29930658.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.684546375274659,
|
|
"epoch": 1.292506919731119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048405388620044383,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.20873122215270995,
|
|
"num_tokens": 29942550.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.60660605430603,
|
|
"epoch": 1.2930011862396205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004840408349011471,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.20811329334974288,
|
|
"num_tokens": 29953600.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.585329532623291,
|
|
"epoch": 1.2934954527481217,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004840277784594133,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.2076566442847252,
|
|
"num_tokens": 29965694.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.571979808807373,
|
|
"epoch": 1.2939897192566232,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004840147168755638,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.2022727206349373,
|
|
"num_tokens": 29977216.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.550666093826294,
|
|
"epoch": 1.2944839857651247,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004840016501499198,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.21699091792106628,
|
|
"num_tokens": 29988036.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.683322906494141,
|
|
"epoch": 1.294978252273626,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048398857828280286,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.20493147373199463,
|
|
"num_tokens": 30000711.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.666690254211426,
|
|
"epoch": 1.2954725187821272,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048397550127453445,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.19912731945514678,
|
|
"num_tokens": 30013607.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.585352993011474,
|
|
"epoch": 1.2959667852906287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004839624191254362,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20967813730239868,
|
|
"num_tokens": 30024375.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.635384607315063,
|
|
"epoch": 1.2964610517991302,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048394933183583004,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.2004389211535454,
|
|
"num_tokens": 30035476.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.6564915657043455,
|
|
"epoch": 1.2969553183076314,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000483936239406038,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.19900626540184022,
|
|
"num_tokens": 30047193.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.688546991348266,
|
|
"epoch": 1.297449584816133,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000483923141836382,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.196270215511322,
|
|
"num_tokens": 30059873.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.588563108444214,
|
|
"epoch": 1.2979438513246342,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004839100391271843,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.20142207741737367,
|
|
"num_tokens": 30071318.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.5738953113555905,
|
|
"epoch": 1.2984381178331357,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004838969312787672,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.19889250844717027,
|
|
"num_tokens": 30082750.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.637119436264038,
|
|
"epoch": 1.298932384341637,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004838838182914532,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.1986639603972435,
|
|
"num_tokens": 30093730.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.686075687408447,
|
|
"epoch": 1.2994266508501384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004838707001655649,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.2031036838889122,
|
|
"num_tokens": 30104776.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.5278623580932615,
|
|
"epoch": 1.29992091735864,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004838575769014249,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.20860342234373092,
|
|
"num_tokens": 30115110.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.56875696182251,
|
|
"epoch": 1.3004151838671412,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004838444484993562,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20222692787647248,
|
|
"num_tokens": 30126678.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.629803562164307,
|
|
"epoch": 1.3009094503756424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048383131495968165,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.2047524020075798,
|
|
"num_tokens": 30137703.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.596798086166382,
|
|
"epoch": 1.301403716884144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048381817628272427,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.1999189242720604,
|
|
"num_tokens": 30147624.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.5678177833557125,
|
|
"epoch": 1.3018979833926454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004838050324688074,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.20604999959468842,
|
|
"num_tokens": 30158863.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.567528963088989,
|
|
"epoch": 1.3023922499011467,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004837918835182544,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.20170849114656447,
|
|
"num_tokens": 30170876.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.609790372848511,
|
|
"epoch": 1.3028865164096481,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004837787294313886,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.2102002590894699,
|
|
"num_tokens": 30182267.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.618350028991699,
|
|
"epoch": 1.3033807829181494,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004837655702085337,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.20405103713274003,
|
|
"num_tokens": 30193572.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.525047063827515,
|
|
"epoch": 1.303875049426651,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004837524058500134,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.21768395304679872,
|
|
"num_tokens": 30206341.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.620477771759033,
|
|
"epoch": 1.3043693159351522,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048373923635615146,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.2048261895775795,
|
|
"num_tokens": 30216067.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.582502698898315,
|
|
"epoch": 1.3048635824436536,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048372606172727197,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.20000579506158828,
|
|
"num_tokens": 30227033.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.614817905426025,
|
|
"epoch": 1.3053578489521551,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000483712881963699,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.2024090126156807,
|
|
"num_tokens": 30238766.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.654478406906128,
|
|
"epoch": 1.3058521154606564,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048369969706575666,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19813061952590943,
|
|
"num_tokens": 30250180.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.582340431213379,
|
|
"epoch": 1.3063463819691576,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048368650703376956,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.22176175564527512,
|
|
"num_tokens": 30260704.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.5388672828674315,
|
|
"epoch": 1.3068406484776591,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004836733118680619,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.2105252668261528,
|
|
"num_tokens": 30273547.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.569856834411621,
|
|
"epoch": 1.3073349149861606,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004836601115689584,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.1983140751719475,
|
|
"num_tokens": 30284872.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.591059017181396,
|
|
"epoch": 1.3078291814946619,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004836469061367838,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.2002413511276245,
|
|
"num_tokens": 30296768.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.5634337902069095,
|
|
"epoch": 1.3083234480031634,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048363369557186293,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21105372607707978,
|
|
"num_tokens": 30308307.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.683237791061401,
|
|
"epoch": 1.3088177145116646,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048362047987452085,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19840551912784576,
|
|
"num_tokens": 30318987.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.641138362884521,
|
|
"epoch": 1.309311981020166,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004836072590450825,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.20503804683685303,
|
|
"num_tokens": 30330401.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.614210605621338,
|
|
"epoch": 1.3098062475286674,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048359403308387327,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.20154459178447723,
|
|
"num_tokens": 30341485.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.664960336685181,
|
|
"epoch": 1.3103005140371689,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048358080199121845,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18952129483222963,
|
|
"num_tokens": 30352854.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.614191246032715,
|
|
"epoch": 1.3107947805456703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048356756576744354,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.20869097262620925,
|
|
"num_tokens": 30363944.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.621957874298095,
|
|
"epoch": 1.3112890470541716,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004835543244128742,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.1947029560804367,
|
|
"num_tokens": 30375678.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.662030649185181,
|
|
"epoch": 1.3117833135626729,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004835410779278361,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.21112427860498428,
|
|
"num_tokens": 30387206.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.634161710739136,
|
|
"epoch": 1.3122775800711743,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004835278263126551,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.20303516387939452,
|
|
"num_tokens": 30398769.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.5899265766143795,
|
|
"epoch": 1.3127718465796758,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004835145695676572,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.21250196248292924,
|
|
"num_tokens": 30409626.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.59963846206665,
|
|
"epoch": 1.313266113088177,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004835013076931686,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19669281095266342,
|
|
"num_tokens": 30421142.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.590960836410522,
|
|
"epoch": 1.3137603795966786,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048348804068951547,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.22475171685218812,
|
|
"num_tokens": 30430438.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.683440923690796,
|
|
"epoch": 1.3142546461051798,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048347476855702413,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19917036443948746,
|
|
"num_tokens": 30442351.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.623887205123902,
|
|
"epoch": 1.3147489126136813,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048346149129602125,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.19664940387010574,
|
|
"num_tokens": 30454987.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.547984552383423,
|
|
"epoch": 1.3152431791221826,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048344820890683333,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.21098305881023408,
|
|
"num_tokens": 30466186.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.644335556030273,
|
|
"epoch": 1.315737445630684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048343492138978704,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.20406100153923035,
|
|
"num_tokens": 30477944.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.667482900619507,
|
|
"epoch": 1.3162317121391856,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004834216287452094,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.20811109691858293,
|
|
"num_tokens": 30489922.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.610061597824097,
|
|
"epoch": 1.3167259786476868,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004834083309734274,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.20888471752405166,
|
|
"num_tokens": 30501739.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.621616077423096,
|
|
"epoch": 1.3172202451561883,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004833950280747681,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.1952672392129898,
|
|
"num_tokens": 30512213.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.641869020462036,
|
|
"epoch": 1.3177145116646896,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004833817200495588,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.1966168165206909,
|
|
"num_tokens": 30524300.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.611938095092773,
|
|
"epoch": 1.318208778173191,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048336840689812676,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.19766110628843309,
|
|
"num_tokens": 30536137.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.569254541397095,
|
|
"epoch": 1.3187030446816923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048335508862079975,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19724526554346083,
|
|
"num_tokens": 30548657.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.673091411590576,
|
|
"epoch": 1.3191973111901938,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048334176521790513,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.1978044956922531,
|
|
"num_tokens": 30560274.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.592550039291382,
|
|
"epoch": 1.3196915776986953,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004833284366897707,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.21394705772399902,
|
|
"num_tokens": 30571026.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.5358367443084715,
|
|
"epoch": 1.3201858442071965,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048331510303672456,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.21821095198392867,
|
|
"num_tokens": 30582210.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.621235418319702,
|
|
"epoch": 1.3206801107156978,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004833017642590945,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19779142141342163,
|
|
"num_tokens": 30594049.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.6345305919647215,
|
|
"epoch": 1.3211743772241993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048328842035720863,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19423036128282548,
|
|
"num_tokens": 30604713.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.607487535476684,
|
|
"epoch": 1.3216686437327008,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004832750713313954,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.2047680288553238,
|
|
"num_tokens": 30615906.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.610043621063232,
|
|
"epoch": 1.322162910241202,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048326171718198315,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.2021957367658615,
|
|
"num_tokens": 30628191.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.700873231887817,
|
|
"epoch": 1.3226571767497035,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048324835790930027,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19946785718202592,
|
|
"num_tokens": 30640667.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.648640155792236,
|
|
"epoch": 1.3231514432582048,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004832349935136755,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.19571209996938704,
|
|
"num_tokens": 30651779.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.520129203796387,
|
|
"epoch": 1.3236457097667063,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004832216239954376,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.21599539816379548,
|
|
"num_tokens": 30662396.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.626581287384033,
|
|
"epoch": 1.3241399762752075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004832082493549154,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.20883004516363143,
|
|
"num_tokens": 30674476.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.549543237686157,
|
|
"epoch": 1.324634242783709,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004831948695924381,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.20335110425949096,
|
|
"num_tokens": 30687417.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.599669122695923,
|
|
"epoch": 1.3251285092922105,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004831814847083346,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.2008520781993866,
|
|
"num_tokens": 30698925.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.696349048614502,
|
|
"epoch": 1.3256227758007118,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048316809470293426,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.2049960970878601,
|
|
"num_tokens": 30711237.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.700071334838867,
|
|
"epoch": 1.326117042309213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048315469957656656,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.19999991357326508,
|
|
"num_tokens": 30721900.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.602146339416504,
|
|
"epoch": 1.3266113088177145,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004831412993295609,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.19940171986818314,
|
|
"num_tokens": 30734738.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.656092977523803,
|
|
"epoch": 1.327105575326216,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048312789396224697,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.20247715711593628,
|
|
"num_tokens": 30745849.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.6598176002502445,
|
|
"epoch": 1.3275998418347172,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048311448347495466,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20361586511135102,
|
|
"num_tokens": 30757118.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.663207578659057,
|
|
"epoch": 1.3280941083432187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004831010678680137,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19691812992095947,
|
|
"num_tokens": 30768692.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.659649085998535,
|
|
"epoch": 1.32858837485172,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004830876471417542,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.20277627259492875,
|
|
"num_tokens": 30780241.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.592961549758911,
|
|
"epoch": 1.3290826413602215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004830742212965063,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.1969238445162773,
|
|
"num_tokens": 30792733.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.607402324676514,
|
|
"epoch": 1.3295769078687227,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004830607903326003,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20491096675395964,
|
|
"num_tokens": 30803997.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.612654352188111,
|
|
"epoch": 1.3300711743772242,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004830473542503665,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.21016157269477845,
|
|
"num_tokens": 30815322.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.581298589706421,
|
|
"epoch": 1.3305654408857257,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048303391305013556,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.20046816319227218,
|
|
"num_tokens": 30825572.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.544621133804322,
|
|
"epoch": 1.331059707394227,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048302046673223816,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.21242139637470245,
|
|
"num_tokens": 30837451.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.581330442428589,
|
|
"epoch": 1.3315539739027282,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004830070152970049,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.20713725835084915,
|
|
"num_tokens": 30849418.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.742777681350708,
|
|
"epoch": 1.3320482404112297,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048299355874476685,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19241924285888673,
|
|
"num_tokens": 30860387.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.56495213508606,
|
|
"epoch": 1.3325425069197312,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000482980097075855,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.2067767783999443,
|
|
"num_tokens": 30871599.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.5496296882629395,
|
|
"epoch": 1.3330367734282325,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048296663029060046,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.2087247282266617,
|
|
"num_tokens": 30882298.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.575323390960693,
|
|
"epoch": 1.333531039936734,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004829531583893345,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.2056186556816101,
|
|
"num_tokens": 30893589.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.61162691116333,
|
|
"epoch": 1.3340253064452352,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004829396813723886,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.2037839874625206,
|
|
"num_tokens": 30905041.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.634920120239258,
|
|
"epoch": 1.3345195729537367,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004829261992400944,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.19951413273811341,
|
|
"num_tokens": 30916244.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.660445880889893,
|
|
"epoch": 1.335013839462238,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004829127119927833,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.20477635711431502,
|
|
"num_tokens": 30927444.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.614697122573853,
|
|
"epoch": 1.3355081059707394,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004828992196307873,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.20805686861276626,
|
|
"num_tokens": 30939402.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.639791488647461,
|
|
"epoch": 1.336002372479241,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048288572215443825,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.19690326154232024,
|
|
"num_tokens": 30951598.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.657807493209839,
|
|
"epoch": 1.3364966389877422,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004828722195640681,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.2008562669157982,
|
|
"num_tokens": 30963897.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.582900857925415,
|
|
"epoch": 1.3369909054962434,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048285871186000916,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20277899950742723,
|
|
"num_tokens": 30975143.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.653321981430054,
|
|
"epoch": 1.337485172004745,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048284519904259374,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.19762582331895828,
|
|
"num_tokens": 30986656.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.690500259399414,
|
|
"epoch": 1.3379794385132464,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004828316811121541,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.2017880216240883,
|
|
"num_tokens": 30999904.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.578328418731689,
|
|
"epoch": 1.3384737050217477,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048281815806902286,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.21452177315950394,
|
|
"num_tokens": 31012287.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.629869079589843,
|
|
"epoch": 1.3389679715302492,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048280462991353267,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.2072999134659767,
|
|
"num_tokens": 31023954.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.6018494129180905,
|
|
"epoch": 1.3394622380387504,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004827910966460164,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.21031637489795685,
|
|
"num_tokens": 31035365.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.61262526512146,
|
|
"epoch": 1.339956504547252,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004827775582668069,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.20690284073352813,
|
|
"num_tokens": 31046814.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.584403705596924,
|
|
"epoch": 1.3404507710557532,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004827640147762372,
|
|
"loss": 5.0826,
|
|
"mean_token_accuracy": 0.2025834158062935,
|
|
"num_tokens": 31058112.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.533053159713745,
|
|
"epoch": 1.3409450375642546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048275046617464055,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.20717596411705017,
|
|
"num_tokens": 31068703.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.567405700683594,
|
|
"epoch": 1.3414393040727561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004827369124623502,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.20895096361637117,
|
|
"num_tokens": 31080018.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.675594758987427,
|
|
"epoch": 1.3419335705812574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048272335363969956,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.2001889869570732,
|
|
"num_tokens": 31091103.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.714786338806152,
|
|
"epoch": 1.3424278370897589,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004827097897070222,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.19535735845565796,
|
|
"num_tokens": 31102731.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.539995288848877,
|
|
"epoch": 1.3429221035982601,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004826962206646518,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.22156852632761,
|
|
"num_tokens": 31114080.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.5876288414001465,
|
|
"epoch": 1.3434163701067616,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048268264651292215,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20011308193206787,
|
|
"num_tokens": 31125875.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.623209714889526,
|
|
"epoch": 1.3439106366152629,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048266906725216713,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.20724166333675384,
|
|
"num_tokens": 31139246.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.572435140609741,
|
|
"epoch": 1.3444049031237644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048265548288272086,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21015098094940185,
|
|
"num_tokens": 31150606.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.5956724166870115,
|
|
"epoch": 1.3448991696322659,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048264189340491755,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.20123213827610015,
|
|
"num_tokens": 31162413.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.64529504776001,
|
|
"epoch": 1.3453934361407671,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048262829881909135,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1971070185303688,
|
|
"num_tokens": 31172832.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.591051959991455,
|
|
"epoch": 1.3458877026492684,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048261469912557685,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.20555301904678344,
|
|
"num_tokens": 31186172.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.621967029571533,
|
|
"epoch": 1.3463819691577699,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048260109432470856,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.21196128726005553,
|
|
"num_tokens": 31197580.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.645824384689331,
|
|
"epoch": 1.3468762356662713,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048258748441682114,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.20411398410797119,
|
|
"num_tokens": 31209262.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.616498374938965,
|
|
"epoch": 1.3473705021747726,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004825738694022494,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.2024114340543747,
|
|
"num_tokens": 31221722.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.538830709457398,
|
|
"epoch": 1.347864768683274,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048256024928132826,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21879221647977828,
|
|
"num_tokens": 31232871.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.566106557846069,
|
|
"epoch": 1.3483590351917754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004825466240543928,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.20788703560829164,
|
|
"num_tokens": 31244010.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.604892587661743,
|
|
"epoch": 1.3488533017002768,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004825329937217782,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.20612962394952775,
|
|
"num_tokens": 31255643.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.718273782730103,
|
|
"epoch": 1.349347568208778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004825193582838196,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.19661683738231658,
|
|
"num_tokens": 31266764.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.632385635375977,
|
|
"epoch": 1.3498418347172796,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004825057177408528,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.21144485771656035,
|
|
"num_tokens": 31277533.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.598846197128296,
|
|
"epoch": 1.350336101225781,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000482492072093213,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.2066216617822647,
|
|
"num_tokens": 31289509.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.63708004951477,
|
|
"epoch": 1.3508303677342823,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048247842134123615,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.2084190994501114,
|
|
"num_tokens": 31300909.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.631771087646484,
|
|
"epoch": 1.3513246342427836,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004824647654852579,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20003409087657928,
|
|
"num_tokens": 31312148.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.571789169311524,
|
|
"epoch": 1.351818900751285,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004824511045256142,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.21809465140104295,
|
|
"num_tokens": 31323388.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.598620128631592,
|
|
"epoch": 1.3523131672597866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048243743846264125,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.21112680286169053,
|
|
"num_tokens": 31334103.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.6024384021759035,
|
|
"epoch": 1.3528074337682878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004824237672966751,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20438385456800462,
|
|
"num_tokens": 31345456.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.513204526901245,
|
|
"epoch": 1.3533017002767893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000482410091028052,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2206907868385315,
|
|
"num_tokens": 31356482.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.664078044891357,
|
|
"epoch": 1.3537959667852906,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048239640965710854,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.19624772816896438,
|
|
"num_tokens": 31367103.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.672888565063476,
|
|
"epoch": 1.354290233293792,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048238272318418127,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.20148972868919374,
|
|
"num_tokens": 31378564.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.624864864349365,
|
|
"epoch": 1.3547844998022933,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048236903160960677,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.20606144666671752,
|
|
"num_tokens": 31391435.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.5920000076293945,
|
|
"epoch": 1.3552787663107948,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000482355334933722,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.2011793866753578,
|
|
"num_tokens": 31403422.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.546343374252319,
|
|
"epoch": 1.3557730328192963,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048234163315686375,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.21738474667072297,
|
|
"num_tokens": 31414940.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.619782876968384,
|
|
"epoch": 1.3562672993277975,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004823279262793692,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20324739515781404,
|
|
"num_tokens": 31426369.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.587670421600341,
|
|
"epoch": 1.3567615658362988,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048231421430157547,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20976515114307404,
|
|
"num_tokens": 31438426.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.554611778259277,
|
|
"epoch": 1.3572558323448003,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004823004972238199,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.20715293288230896,
|
|
"num_tokens": 31450230.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.6364199161529545,
|
|
"epoch": 1.3577500988533018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048228677504643996,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19538681358098983,
|
|
"num_tokens": 31462564.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.596657609939575,
|
|
"epoch": 1.358244365361803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004822730477697732,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.21227219551801682,
|
|
"num_tokens": 31475053.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.586292743682861,
|
|
"epoch": 1.3587386318703045,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004822593153941573,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20795868039131166,
|
|
"num_tokens": 31487187.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.629172372817993,
|
|
"epoch": 1.3592328983788058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048224557791993013,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.20753535479307175,
|
|
"num_tokens": 31499288.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.62320294380188,
|
|
"epoch": 1.3597271648873073,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048223183534742953,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.20413176566362382,
|
|
"num_tokens": 31510113.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.606292724609375,
|
|
"epoch": 1.3602214313958085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048221808767699373,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.206664477288723,
|
|
"num_tokens": 31520900.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.632293939590454,
|
|
"epoch": 1.36071569790431,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004822043349089607,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.20937667936086654,
|
|
"num_tokens": 31533085.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.626890230178833,
|
|
"epoch": 1.3612099644128115,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004821905770436689,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.2010658249258995,
|
|
"num_tokens": 31544287.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.53405613899231,
|
|
"epoch": 1.3617042309213128,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004821768140814568,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.21245523542165756,
|
|
"num_tokens": 31555233.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.591294813156128,
|
|
"epoch": 1.362198497429814,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004821630460226629,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.21653452664613723,
|
|
"num_tokens": 31565421.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.6408836364746096,
|
|
"epoch": 1.3626927639383155,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000482149272867626,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.20694349110126495,
|
|
"num_tokens": 31576787.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.642703819274902,
|
|
"epoch": 1.363187030446817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048213549461668476,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.19599164575338363,
|
|
"num_tokens": 31587563.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.653098917007446,
|
|
"epoch": 1.3636812969553183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048212171127017835,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.2060033768415451,
|
|
"num_tokens": 31598186.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.611880731582642,
|
|
"epoch": 1.3641755634638197,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004821079228284456,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.20267678946256637,
|
|
"num_tokens": 31609458.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.5643839836120605,
|
|
"epoch": 1.364669829972321,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048209412929182586,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.21396753042936326,
|
|
"num_tokens": 31619497.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.6343504905700685,
|
|
"epoch": 1.3651640964808225,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004820803306606584,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.19878305345773697,
|
|
"num_tokens": 31630838.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.666799163818359,
|
|
"epoch": 1.3656583629893237,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004820665269352827,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.19824098497629167,
|
|
"num_tokens": 31642234.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.651125049591064,
|
|
"epoch": 1.3661526294978252,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048205271811603827,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.19781574755907058,
|
|
"num_tokens": 31653283.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.634519910812378,
|
|
"epoch": 1.3666468960063267,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004820389042032649,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.20878508687019348,
|
|
"num_tokens": 31663284.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.559124946594238,
|
|
"epoch": 1.367141162514828,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004820250851973023,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.2092303901910782,
|
|
"num_tokens": 31674379.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.633234453201294,
|
|
"epoch": 1.3676354290233292,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004820112610984906,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.1970619112253189,
|
|
"num_tokens": 31686420.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.561041831970215,
|
|
"epoch": 1.3681296955318307,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048199743190716966,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21974865198135377,
|
|
"num_tokens": 31696919.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.5726855278015135,
|
|
"epoch": 1.3686239620403322,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048198359762367983,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.1981720134615898,
|
|
"num_tokens": 31708878.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.629126644134521,
|
|
"epoch": 1.3691182285488335,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048196975824836135,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20372524708509446,
|
|
"num_tokens": 31719348.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.599943351745606,
|
|
"epoch": 1.369612495057335,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004819559137815547,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.20893210172653198,
|
|
"num_tokens": 31729349.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.650749826431275,
|
|
"epoch": 1.3701067615658362,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004819420642236005,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.20287689715623855,
|
|
"num_tokens": 31740345.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.6893562316894535,
|
|
"epoch": 1.3706010280743377,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004819282095748395,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.20337540209293364,
|
|
"num_tokens": 31752231.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.637573146820069,
|
|
"epoch": 1.371095294582839,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004819143498356123,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.202819587290287,
|
|
"num_tokens": 31764248.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.542523050308228,
|
|
"epoch": 1.3715895610913404,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004819004850062601,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.21397878229618073,
|
|
"num_tokens": 31774173.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.621614170074463,
|
|
"epoch": 1.372083827599842,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048188661508712376,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.20047813206911086,
|
|
"num_tokens": 31784860.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.6016740798950195,
|
|
"epoch": 1.3725780941083432,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004818727400785447,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.2028560906648636,
|
|
"num_tokens": 31797012.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.5652588367462155,
|
|
"epoch": 1.3730723606168447,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004818588599808641,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.20608923882246016,
|
|
"num_tokens": 31808216.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.621253824234008,
|
|
"epoch": 1.373566627125346,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048184497479442345,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.19993028193712234,
|
|
"num_tokens": 31820097.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.678194332122803,
|
|
"epoch": 1.3740608936338474,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004818310845195643,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.1923782557249069,
|
|
"num_tokens": 31832252.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.6655004024505615,
|
|
"epoch": 1.3745551601423487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004818171891566284,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19656164348125457,
|
|
"num_tokens": 31842928.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.596347904205322,
|
|
"epoch": 1.3750494266508502,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004818032887059576,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.21287390291690828,
|
|
"num_tokens": 31854072.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.6763495922088625,
|
|
"epoch": 1.3755436931593517,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004817893831678938,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.207238632440567,
|
|
"num_tokens": 31865163.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.572414445877075,
|
|
"epoch": 1.376037959667853,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048177547254277904,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.21978972256183624,
|
|
"num_tokens": 31876583.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.576935434341431,
|
|
"epoch": 1.3765322261763542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004817615568309557,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.20927923768758774,
|
|
"num_tokens": 31886794.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.675946855545044,
|
|
"epoch": 1.3770264926848557,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004817476360327658,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.19947443753480912,
|
|
"num_tokens": 31899980.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.558408212661743,
|
|
"epoch": 1.3775207591933571,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004817337101485521,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.2181350141763687,
|
|
"num_tokens": 31909906.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.544005250930786,
|
|
"epoch": 1.3780150257018584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048171977917865706,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.21658429205417634,
|
|
"num_tokens": 31920499.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.559505844116211,
|
|
"epoch": 1.37850929221036,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048170584312342337,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.21114960610866546,
|
|
"num_tokens": 31931031.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.618653106689453,
|
|
"epoch": 1.3790035587188612,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004816919019831939,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.20493866205215455,
|
|
"num_tokens": 31941887.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.645064449310302,
|
|
"epoch": 1.3794978252273626,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048167795575831154,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.1991904303431511,
|
|
"num_tokens": 31953727.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.627020072937012,
|
|
"epoch": 1.379992091735864,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004816640044491193,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.2031105563044548,
|
|
"num_tokens": 31965418.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.60790605545044,
|
|
"epoch": 1.3804863582443654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004816500480559607,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.20049550235271454,
|
|
"num_tokens": 31976528.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.640352201461792,
|
|
"epoch": 1.3809806247528669,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048163608657917874,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.19914113432168962,
|
|
"num_tokens": 31987921.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.602838945388794,
|
|
"epoch": 1.3814748912613681,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000481622120019117,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.21126280277967452,
|
|
"num_tokens": 31998824.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.612262773513794,
|
|
"epoch": 1.3819691577698694,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004816081483761191,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19616341590881348,
|
|
"num_tokens": 32011690.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.644180631637573,
|
|
"epoch": 1.3824634242783709,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004815941716505286,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20745431929826735,
|
|
"num_tokens": 32022946.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.657692813873291,
|
|
"epoch": 1.3829576907868724,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048158018984268954,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.2021471604704857,
|
|
"num_tokens": 32033683.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.675225019454956,
|
|
"epoch": 1.3834519572953736,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004815662029529457,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19482744634151458,
|
|
"num_tokens": 32045334.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.607575464248657,
|
|
"epoch": 1.383946223803875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048155221098164123,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.20586711466312407,
|
|
"num_tokens": 32056425.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.640638589859009,
|
|
"epoch": 1.3844404903123764,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048153821392912035,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.20203779488801957,
|
|
"num_tokens": 32068053.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.6490569591522215,
|
|
"epoch": 1.3849347568208779,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004815242117957273,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.20607091784477233,
|
|
"num_tokens": 32079462.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.5456360340118405,
|
|
"epoch": 1.3854290233293791,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048151020458180667,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.20912338346242904,
|
|
"num_tokens": 32090566.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.670550537109375,
|
|
"epoch": 1.3859232898378806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000481496192287703,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.20272917300462723,
|
|
"num_tokens": 32101535.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.6001630306243895,
|
|
"epoch": 1.386417556346382,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004814821749137609,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.20918342024087905,
|
|
"num_tokens": 32112450.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.606808233261108,
|
|
"epoch": 1.3869118228548833,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004814681524603252,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.19809990376234055,
|
|
"num_tokens": 32123675.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.641811418533325,
|
|
"epoch": 1.3874060893633846,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000481454124927741,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.20118145495653153,
|
|
"num_tokens": 32135283.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.589032125473023,
|
|
"epoch": 1.387900355871886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048144009231635326,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.2131883680820465,
|
|
"num_tokens": 32146715.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.577646970748901,
|
|
"epoch": 1.3883946223803876,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004814260546265073,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.20800792425870895,
|
|
"num_tokens": 32158323.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.615857028961182,
|
|
"epoch": 1.3888888888888888,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004814120118585483,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19818728417158127,
|
|
"num_tokens": 32170453.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.715055656433106,
|
|
"epoch": 1.3893831553973903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004813979640128218,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.1981535479426384,
|
|
"num_tokens": 32181596.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.670522260665893,
|
|
"epoch": 1.3898774219058916,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004813839110896734,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.20382706224918365,
|
|
"num_tokens": 32194603.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.542845249176025,
|
|
"epoch": 1.390371688414393,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048136985308944874,
|
|
"loss": 5.0805,
|
|
"mean_token_accuracy": 0.2068536937236786,
|
|
"num_tokens": 32206064.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.645622062683105,
|
|
"epoch": 1.3908659549228943,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048135579001249367,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.19699158221483232,
|
|
"num_tokens": 32217254.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.692801427841187,
|
|
"epoch": 1.3913602214313958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004813417218591542,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.18540519326925278,
|
|
"num_tokens": 32228821.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.6582622051239015,
|
|
"epoch": 1.3918544879398973,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004813276486297763,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.20234095454216003,
|
|
"num_tokens": 32239476.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.634127426147461,
|
|
"epoch": 1.3923487544483986,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004813135703247062,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.2068355619907379,
|
|
"num_tokens": 32250975.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.625942325592041,
|
|
"epoch": 1.3928430209568998,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048129948694429036,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.2142017066478729,
|
|
"num_tokens": 32261675.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.537230539321899,
|
|
"epoch": 1.3933372874654013,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048128539848887517,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.2196858063340187,
|
|
"num_tokens": 32272523.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.584447240829467,
|
|
"epoch": 1.3938315539739028,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048127130495880703,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.1990736648440361,
|
|
"num_tokens": 32284140.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.578996849060059,
|
|
"epoch": 1.394325820482404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004812572063544329,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.20740812718868257,
|
|
"num_tokens": 32296286.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.625456285476685,
|
|
"epoch": 1.3948200869909055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048124310267609946,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.20719753801822663,
|
|
"num_tokens": 32307394.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.679070520401001,
|
|
"epoch": 1.3953143534994068,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004812289939241537,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.1978344663977623,
|
|
"num_tokens": 32318788.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.660312223434448,
|
|
"epoch": 1.3958086200079083,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004812148800989427,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.20292219519615173,
|
|
"num_tokens": 32332395.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.693870639801025,
|
|
"epoch": 1.3963028865164095,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048120076120081363,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.20147991925477982,
|
|
"num_tokens": 32344226.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.687062501907349,
|
|
"epoch": 1.396797153024911,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048118663723011393,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19693832695484162,
|
|
"num_tokens": 32354677.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.5823344707489015,
|
|
"epoch": 1.3972914195334125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004811725081871909,
|
|
"loss": 5.0638,
|
|
"mean_token_accuracy": 0.20502374321222305,
|
|
"num_tokens": 32365054.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.555253314971924,
|
|
"epoch": 1.3977856860419138,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004811583740723922,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.22205565571784974,
|
|
"num_tokens": 32376215.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.643561697006225,
|
|
"epoch": 1.3982799525504153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048114423488606543,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.20101319253444672,
|
|
"num_tokens": 32386880.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.614909648895264,
|
|
"epoch": 1.3987742190589165,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048113009062855866,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.20705096423625946,
|
|
"num_tokens": 32398227.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.72637414932251,
|
|
"epoch": 1.399268485567418,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004811159413002196,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.20389332622289658,
|
|
"num_tokens": 32410091.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.6355955600738525,
|
|
"epoch": 1.3997627520759193,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004811017869013963,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.2034035474061966,
|
|
"num_tokens": 32422710.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.601515054702759,
|
|
"epoch": 1.4002570185844208,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004810876274324372,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.20512807071208955,
|
|
"num_tokens": 32433691.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.578893184661865,
|
|
"epoch": 1.4007512850929222,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004810734628936905,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.20984972268342972,
|
|
"num_tokens": 32445370.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.566232204437256,
|
|
"epoch": 1.4012455516014235,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048105929328550465,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.2154087245464325,
|
|
"num_tokens": 32456737.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.602679824829101,
|
|
"epoch": 1.4017398181099248,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004810451186082282,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.2001642182469368,
|
|
"num_tokens": 32467957.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.6458765983581545,
|
|
"epoch": 1.4022340846184262,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048103093886220984,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.1992192327976227,
|
|
"num_tokens": 32481697.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.605352830886841,
|
|
"epoch": 1.4027283511269277,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048101675404779834,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.21666280776262284,
|
|
"num_tokens": 32492828.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.728411340713501,
|
|
"epoch": 1.403222617635429,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004810025641653428,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.19957058876752853,
|
|
"num_tokens": 32505120.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.561610221862793,
|
|
"epoch": 1.4037168841439305,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004809883692151923,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21009375154972076,
|
|
"num_tokens": 32516837.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.578215742111206,
|
|
"epoch": 1.4042111506524317,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048097416919769595,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.20837534517049788,
|
|
"num_tokens": 32526906.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.650358200073242,
|
|
"epoch": 1.4047054171609332,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048095996411320294,
|
|
"loss": 5.1985,
|
|
"mean_token_accuracy": 0.19775691479444504,
|
|
"num_tokens": 32537929.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.6217866897583,
|
|
"epoch": 1.4051996836694345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048094575396206296,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.2025961697101593,
|
|
"num_tokens": 32549458.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.59423713684082,
|
|
"epoch": 1.405693950177936,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004809315387446255,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2067585274577141,
|
|
"num_tokens": 32560244.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.629499864578247,
|
|
"epoch": 1.4061882166864375,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004809173184612402,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.20051494538784026,
|
|
"num_tokens": 32571337.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.612876892089844,
|
|
"epoch": 1.4066824831949387,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004809030931122569,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.20899404883384703,
|
|
"num_tokens": 32582325.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.671245050430298,
|
|
"epoch": 1.40717674970344,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048088886269802565,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20856704711914062,
|
|
"num_tokens": 32592953.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.589275074005127,
|
|
"epoch": 1.4076710162119415,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004808746272188964,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.20493419021368026,
|
|
"num_tokens": 32604190.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.701703071594238,
|
|
"epoch": 1.408165282720443,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048086038667521935,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.20849090814590454,
|
|
"num_tokens": 32614467.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.6126221179962155,
|
|
"epoch": 1.4086595492289442,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004808461410673449,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.20515074133872985,
|
|
"num_tokens": 32624022.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.5914084911346436,
|
|
"epoch": 1.4091538157374457,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004808318903956234,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.20728608220815659,
|
|
"num_tokens": 32634363.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.578840208053589,
|
|
"epoch": 1.409648082245947,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004808176346604055,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.2159786120057106,
|
|
"num_tokens": 32646143.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.642100524902344,
|
|
"epoch": 1.4101423487544484,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004808033738620419,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.20500846356153488,
|
|
"num_tokens": 32658735.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.681474256515503,
|
|
"epoch": 1.4106366152629497,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048078910800088327,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.19852082878351213,
|
|
"num_tokens": 32669337.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.588520622253418,
|
|
"epoch": 1.4111308817714512,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807748370772807,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.2153138980269432,
|
|
"num_tokens": 32680072.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.594472074508667,
|
|
"epoch": 1.4116251482799527,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048076056109158525,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.2063888981938362,
|
|
"num_tokens": 32691142.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.635201120376587,
|
|
"epoch": 1.412119414788454,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004807462800441481,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.19340236485004425,
|
|
"num_tokens": 32702482.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.642690992355346,
|
|
"epoch": 1.4126136812969552,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807319939353204,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.19748948514461517,
|
|
"num_tokens": 32714456.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.675623035430908,
|
|
"epoch": 1.4131079478054567,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048071770276545377,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.2045276328921318,
|
|
"num_tokens": 32726305.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.536628532409668,
|
|
"epoch": 1.4136022143139582,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048070340653489984,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.21360989212989806,
|
|
"num_tokens": 32736446.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.611797237396241,
|
|
"epoch": 1.4140964808224594,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048068910524401014,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.2005527436733246,
|
|
"num_tokens": 32746798.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.567839193344116,
|
|
"epoch": 1.414590747330961,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048067479889313654,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.21380539536476134,
|
|
"num_tokens": 32758647.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.58606538772583,
|
|
"epoch": 1.4150850138394622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048066048748263097,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.19744468480348587,
|
|
"num_tokens": 32770759.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.61635913848877,
|
|
"epoch": 1.4155792803479637,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048064617101284553,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20908693224191666,
|
|
"num_tokens": 32783398.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.6637269973754885,
|
|
"epoch": 1.416073546856465,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048063184948413237,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.19419751763343812,
|
|
"num_tokens": 32795995.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.654235410690307,
|
|
"epoch": 1.4165678133649664,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048061752289684385,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.1990462586283684,
|
|
"num_tokens": 32808700.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.658757972717285,
|
|
"epoch": 1.4170620798734679,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004806031912513323,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.18795543760061265,
|
|
"num_tokens": 32820815.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.679477071762085,
|
|
"epoch": 1.4175563463819691,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048058885454795036,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.20802749544382096,
|
|
"num_tokens": 32832216.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.714205265045166,
|
|
"epoch": 1.4180506128904704,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004805745127870508,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.20011613965034486,
|
|
"num_tokens": 32845118.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.631936931610108,
|
|
"epoch": 1.418544879398972,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004805601659689862,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.20834077447652816,
|
|
"num_tokens": 32855662.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.649257755279541,
|
|
"epoch": 1.4190391459074734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004805458140941097,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.20215853601694106,
|
|
"num_tokens": 32865530.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.6408421993255615,
|
|
"epoch": 1.4195334124159746,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048053145716277424,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.1963965117931366,
|
|
"num_tokens": 32877542.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.578440761566162,
|
|
"epoch": 1.4200276789244761,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004805170951753331,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.20376827269792558,
|
|
"num_tokens": 32888197.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.634745979309082,
|
|
"epoch": 1.4205219454329774,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004805027281321395,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.20607379525899888,
|
|
"num_tokens": 32899633.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.611330890655518,
|
|
"epoch": 1.4210162119414789,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004804883560335469,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.21060470640659332,
|
|
"num_tokens": 32910334.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.682684755325317,
|
|
"epoch": 1.4215104784499801,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004804739788799089,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.20522015690803527,
|
|
"num_tokens": 32920071.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.6063316822052,
|
|
"epoch": 1.4220047449584816,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048045959667157914,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20691885948181152,
|
|
"num_tokens": 32931391.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.645744800567627,
|
|
"epoch": 1.422499011466983,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004804452094089114,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.20469192564487457,
|
|
"num_tokens": 32941831.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.623583889007568,
|
|
"epoch": 1.4229932779754844,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004804308170922597,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.2055029809474945,
|
|
"num_tokens": 32952949.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.653655004501343,
|
|
"epoch": 1.4234875444839858,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004804164197219779,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20250540524721145,
|
|
"num_tokens": 32964411.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.71836633682251,
|
|
"epoch": 1.423981810992487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004804020172984204,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.2043540969491005,
|
|
"num_tokens": 32975484.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.5883924007415775,
|
|
"epoch": 1.4244760775009886,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048038760982194135,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.20762426853179933,
|
|
"num_tokens": 32986691.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.5945367336273195,
|
|
"epoch": 1.4249703440094899,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004803731972928954,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20765080600976943,
|
|
"num_tokens": 32998357.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.6281044483184814,
|
|
"epoch": 1.4254646105179913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048035877971163674,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.20438505113124847,
|
|
"num_tokens": 33009451.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.56379132270813,
|
|
"epoch": 1.4259588770264928,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004803443570785203,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.2147312954068184,
|
|
"num_tokens": 33020143.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.564149284362793,
|
|
"epoch": 1.426453143534994,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048032992939390086,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.21063413470983505,
|
|
"num_tokens": 33031448.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.6598961353302,
|
|
"epoch": 1.4269474100434953,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004803154966581333,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.20257274210453033,
|
|
"num_tokens": 33041545.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.628686428070068,
|
|
"epoch": 1.4274416765519968,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048030105887157253,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20715977996587753,
|
|
"num_tokens": 33051681.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.690445852279663,
|
|
"epoch": 1.4279359430604983,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048028661603457406,
|
|
"loss": 5.1553,
|
|
"mean_token_accuracy": 0.2038111299276352,
|
|
"num_tokens": 33062735.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.584023141860962,
|
|
"epoch": 1.4284302095689996,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004802721681474929,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.21745353639125825,
|
|
"num_tokens": 33073975.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.5817770004272464,
|
|
"epoch": 1.428924476077501,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048025771521068456,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2072425127029419,
|
|
"num_tokens": 33086928.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.69152421951294,
|
|
"epoch": 1.4294187425860023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048024325722450454,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.20226527452468873,
|
|
"num_tokens": 33099073.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.720927715301514,
|
|
"epoch": 1.4299130090945038,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004802287941893087,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.20148490667343139,
|
|
"num_tokens": 33110245.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.606685590744019,
|
|
"epoch": 1.430407275603005,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004802143261054525,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.20594661235809325,
|
|
"num_tokens": 33121659.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.568376779556274,
|
|
"epoch": 1.4309015421115066,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048019985297329215,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.20366569459438325,
|
|
"num_tokens": 33133296.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.61742787361145,
|
|
"epoch": 1.431395808620008,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004801853747931836,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.20043433755636214,
|
|
"num_tokens": 33145069.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.680567502975464,
|
|
"epoch": 1.4318900751285093,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048017089156548293,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.20222632288932801,
|
|
"num_tokens": 33156089.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.719624805450439,
|
|
"epoch": 1.4323843416370106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048015640329054655,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.20392367243766785,
|
|
"num_tokens": 33168300.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.579700994491577,
|
|
"epoch": 1.432878608145512,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048014190996873075,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.2175782322883606,
|
|
"num_tokens": 33179072.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.606197023391724,
|
|
"epoch": 1.4333728746540135,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048012741160039223,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.20735974460840226,
|
|
"num_tokens": 33190888.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.613743019104004,
|
|
"epoch": 1.4338671411625148,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004801129081858875,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.20135421454906463,
|
|
"num_tokens": 33202747.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.697780752182007,
|
|
"epoch": 1.4343614076710163,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004800983997255735,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.2026538759469986,
|
|
"num_tokens": 33213917.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.626916980743408,
|
|
"epoch": 1.4348556741795175,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004800838862198069,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.19901390373706818,
|
|
"num_tokens": 33223924.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.591383838653565,
|
|
"epoch": 1.435349940688019,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000480069367668945,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.21088364869356155,
|
|
"num_tokens": 33234487.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.616255378723144,
|
|
"epoch": 1.4358442071965203,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048005484407334474,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.20353857427835464,
|
|
"num_tokens": 33245585.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.607338571548462,
|
|
"epoch": 1.4363384737050218,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004800403154333636,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.21327709257602692,
|
|
"num_tokens": 33256545.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.602349710464478,
|
|
"epoch": 1.4368327402135233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004800257817493589,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.2102528229355812,
|
|
"num_tokens": 33267946.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.612630844116211,
|
|
"epoch": 1.4373270067220245,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048001124302168814,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.2090987578034401,
|
|
"num_tokens": 33279099.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.637448072433472,
|
|
"epoch": 1.4378212732305258,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004799966992507089,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19989199936389923,
|
|
"num_tokens": 33290544.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.605366659164429,
|
|
"epoch": 1.4383155397390273,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047998215043677914,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21172415018081664,
|
|
"num_tokens": 33302317.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.582393550872803,
|
|
"epoch": 1.4388098062475287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004799675965802567,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20671846866607665,
|
|
"num_tokens": 33313553.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.64116473197937,
|
|
"epoch": 1.43930407275603,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047995303768149955,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20244540721178056,
|
|
"num_tokens": 33324610.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.630063199996949,
|
|
"epoch": 1.4397983392645315,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004799384737408659,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.20536391139030458,
|
|
"num_tokens": 33335562.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.686969518661499,
|
|
"epoch": 1.4402926057730328,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047992390475871396,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.1937730848789215,
|
|
"num_tokens": 33346778.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.646197748184204,
|
|
"epoch": 1.4407868722815342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004799093307354022,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.19454217851161956,
|
|
"num_tokens": 33358712.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.628198766708374,
|
|
"epoch": 1.4412811387900355,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004798947516712891,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20375979095697402,
|
|
"num_tokens": 33369293.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.665508222579956,
|
|
"epoch": 1.441775405298537,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047988016756673335,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.20164646953344345,
|
|
"num_tokens": 33383119.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.647028398513794,
|
|
"epoch": 1.4422696718070385,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004798655784220937,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20482838451862334,
|
|
"num_tokens": 33395334.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.526140785217285,
|
|
"epoch": 1.4427639383155397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479850984237729,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.2158469781279564,
|
|
"num_tokens": 33406676.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.702689981460571,
|
|
"epoch": 1.443258204824041,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004798363850139983,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.19714969545602798,
|
|
"num_tokens": 33419153.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.6442890644073485,
|
|
"epoch": 1.4437524713325425,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004798217807512608,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.21304947435855864,
|
|
"num_tokens": 33430146.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.609884548187256,
|
|
"epoch": 1.444246737841044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047980717144987574,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1928389251232147,
|
|
"num_tokens": 33441484.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.635182332992554,
|
|
"epoch": 1.4447410043495452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047979255711020236,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.21075436025857924,
|
|
"num_tokens": 33451817.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.647863864898682,
|
|
"epoch": 1.4452352708580467,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004797779377326004,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.20417464524507523,
|
|
"num_tokens": 33463805.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.658398723602295,
|
|
"epoch": 1.445729537366548,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004797633133174295,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19467395097017287,
|
|
"num_tokens": 33475931.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.648201608657837,
|
|
"epoch": 1.4462238038750495,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004797486838650491,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.2030662477016449,
|
|
"num_tokens": 33487306.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.592539834976196,
|
|
"epoch": 1.4467180703835507,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004797340493758195,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.2049478530883789,
|
|
"num_tokens": 33499049.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.604086875915527,
|
|
"epoch": 1.4472123368920522,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004797194098501004,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20765445083379747,
|
|
"num_tokens": 33509626.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.670121097564698,
|
|
"epoch": 1.4477066034005537,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004797047652882521,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.20340337008237838,
|
|
"num_tokens": 33521510.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.640949535369873,
|
|
"epoch": 1.448200869909055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047969011569063487,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.20753959566354752,
|
|
"num_tokens": 33532622.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.578786087036133,
|
|
"epoch": 1.4486951364175564,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004796754610576091,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.21564222425222396,
|
|
"num_tokens": 33544196.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.709120512008667,
|
|
"epoch": 1.4491894029260577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047966080138953505,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.200199456512928,
|
|
"num_tokens": 33554927.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.681809711456299,
|
|
"epoch": 1.4496836694345592,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004796461366867736,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.1929416239261627,
|
|
"num_tokens": 33566412.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.537728023529053,
|
|
"epoch": 1.4501779359430604,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047963146694968546,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.2090535581111908,
|
|
"num_tokens": 33578010.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.656638145446777,
|
|
"epoch": 1.450672202451562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004796167921786315,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.20002202689647675,
|
|
"num_tokens": 33589647.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.756833839416504,
|
|
"epoch": 1.4511664689600634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047960211237397274,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.19240587800741196,
|
|
"num_tokens": 33601292.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.6825926303863525,
|
|
"epoch": 1.4516607354685647,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047958742753607015,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.2025387018918991,
|
|
"num_tokens": 33612878.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.604502248764038,
|
|
"epoch": 1.452155001977066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047957273766528524,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.20836717635393143,
|
|
"num_tokens": 33625680.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.601333141326904,
|
|
"epoch": 1.4526492684855674,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004795580427619791,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.20571608394384383,
|
|
"num_tokens": 33637066.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.685100507736206,
|
|
"epoch": 1.453143534994069,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047954334282651357,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.19693191051483155,
|
|
"num_tokens": 33648213.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.696942901611328,
|
|
"epoch": 1.4536378015025702,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795286378592499,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.2084663912653923,
|
|
"num_tokens": 33661582.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.572276067733765,
|
|
"epoch": 1.4541320680110716,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004795139278605501,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.20800964534282684,
|
|
"num_tokens": 33673122.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.618852853775024,
|
|
"epoch": 1.454626334519573,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047949921283077594,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.20954607725143432,
|
|
"num_tokens": 33683926.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.65477147102356,
|
|
"epoch": 1.4551206010280744,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004794844927702894,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.20922775864601134,
|
|
"num_tokens": 33694529.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.685581827163697,
|
|
"epoch": 1.4556148675365757,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004794697676794526,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20757144391536714,
|
|
"num_tokens": 33704618.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.590685844421387,
|
|
"epoch": 1.4561091340450771,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004794550375586278,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.2037761926651001,
|
|
"num_tokens": 33716354.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.57126784324646,
|
|
"epoch": 1.4566034005535786,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004794403024081774,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.2178380474448204,
|
|
"num_tokens": 33728065.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.652676916122436,
|
|
"epoch": 1.4570976670620799,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004794255622284638,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.2052391514182091,
|
|
"num_tokens": 33740207.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.688069915771484,
|
|
"epoch": 1.4575919335705811,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047941081701984966,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20300686955451966,
|
|
"num_tokens": 33750768.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.6199970722198485,
|
|
"epoch": 1.4580862000790826,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047939606678269774,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.20239212214946747,
|
|
"num_tokens": 33762029.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.587669897079468,
|
|
"epoch": 1.4585804665875841,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004793813115173708,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.20789657831192015,
|
|
"num_tokens": 33773483.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.631736135482788,
|
|
"epoch": 1.4590747330960854,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000479366551224232,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20650596022605897,
|
|
"num_tokens": 33784404.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.605930471420288,
|
|
"epoch": 1.4595689996045869,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004793517859036443,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.2082611232995987,
|
|
"num_tokens": 33794625.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.679031705856323,
|
|
"epoch": 1.4600632661130881,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004793370155559709,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.2027290165424347,
|
|
"num_tokens": 33805872.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.572883558273316,
|
|
"epoch": 1.4605575326215896,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004793222401815753,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.218462236225605,
|
|
"num_tokens": 33815979.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.64464111328125,
|
|
"epoch": 1.4610517991300909,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004793074597808208,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.20061933845281602,
|
|
"num_tokens": 33827571.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.619323015213013,
|
|
"epoch": 1.4615460656385924,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047929267435407115,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20190549194812774,
|
|
"num_tokens": 33838749.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.618338394165039,
|
|
"epoch": 1.4620403321470938,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047927788390168997,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.20530849546194077,
|
|
"num_tokens": 33849494.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.722569751739502,
|
|
"epoch": 1.462534598655595,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047926308842404126,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20348389446735382,
|
|
"num_tokens": 33860586.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.548217535018921,
|
|
"epoch": 1.4630288651640964,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004792482879214888,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.21707000583410263,
|
|
"num_tokens": 33871261.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.5918268203735355,
|
|
"epoch": 1.4635231316725978,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004792334823943968,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.21082292199134828,
|
|
"num_tokens": 33883160.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.65144944190979,
|
|
"epoch": 1.4640173981810993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004792186718431294,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.20619553625583648,
|
|
"num_tokens": 33894250.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.611075782775879,
|
|
"epoch": 1.4645116646896006,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479203856268051,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.2053865522146225,
|
|
"num_tokens": 33905076.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.559146404266357,
|
|
"epoch": 1.465005931198102,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004791890356695261,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.20374254286289215,
|
|
"num_tokens": 33916982.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.664211797714233,
|
|
"epoch": 1.4655001977066033,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004791742100479193,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.1992834687232971,
|
|
"num_tokens": 33928306.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.722946357727051,
|
|
"epoch": 1.4659944642151048,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004791593794035952,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.20044542998075485,
|
|
"num_tokens": 33940371.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.6580885887146,
|
|
"epoch": 1.466488730723606,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004791445437369187,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.1978037029504776,
|
|
"num_tokens": 33952250.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.678111124038696,
|
|
"epoch": 1.4669829972321076,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004791297030482547,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20736127346754074,
|
|
"num_tokens": 33963426.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.625491285324097,
|
|
"epoch": 1.467477263740609,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004791148573379684,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.20211670696735382,
|
|
"num_tokens": 33974982.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.558540725708008,
|
|
"epoch": 1.4679715302491103,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047910000660642487,
|
|
"loss": 5.1189,
|
|
"mean_token_accuracy": 0.20599121302366258,
|
|
"num_tokens": 33986413.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.640130996704102,
|
|
"epoch": 1.4684657967576116,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004790851508539896,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21334557384252548,
|
|
"num_tokens": 33996821.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.653210592269898,
|
|
"epoch": 1.468960063266113,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004790702900810279,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.2033732458949089,
|
|
"num_tokens": 34008817.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.5997405529022215,
|
|
"epoch": 1.4694543297746145,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047905542428790536,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.2094780370593071,
|
|
"num_tokens": 34020051.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.58722767829895,
|
|
"epoch": 1.4699485962831158,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004790405534749878,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.21693538129329681,
|
|
"num_tokens": 34032764.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.647005414962768,
|
|
"epoch": 1.4704428627916173,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000479025677642641,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.19891394525766373,
|
|
"num_tokens": 34042868.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.650889205932617,
|
|
"epoch": 1.4709371293001186,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004790107967912309,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.2071160927414894,
|
|
"num_tokens": 34054807.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.689156341552734,
|
|
"epoch": 1.47143139580862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047899591092112343,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.20053746402263642,
|
|
"num_tokens": 34066378.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.66139783859253,
|
|
"epoch": 1.4719256623171213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000478981020032685,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.1981125846505165,
|
|
"num_tokens": 34078267.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.615288400650025,
|
|
"epoch": 1.4724199288256228,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047896612412628184,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19527619928121567,
|
|
"num_tokens": 34090356.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.6585863590240475,
|
|
"epoch": 1.4729141953341243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047895122320228026,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.20997068285942078,
|
|
"num_tokens": 34101143.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.651142120361328,
|
|
"epoch": 1.4734084618426255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047893631726104703,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20709949731826782,
|
|
"num_tokens": 34112655.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.598107957839966,
|
|
"epoch": 1.4739027283511268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004789214063029488,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.20316775739192963,
|
|
"num_tokens": 34123825.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.6166972637176515,
|
|
"epoch": 1.4743969948596283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047890649032835233,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.20826441347599028,
|
|
"num_tokens": 34135416.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.683547115325927,
|
|
"epoch": 1.4748912613681298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004788915693376245,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.2013564482331276,
|
|
"num_tokens": 34146797.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.678540992736816,
|
|
"epoch": 1.475385527876631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047887664333113244,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.20005709081888198,
|
|
"num_tokens": 34158749.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.607329607009888,
|
|
"epoch": 1.4758797943851325,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004788617123092434,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.20887787789106368,
|
|
"num_tokens": 34169694.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.665381336212159,
|
|
"epoch": 1.4763740608936338,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004788467762723245,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.2008237898349762,
|
|
"num_tokens": 34182166.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.659751224517822,
|
|
"epoch": 1.4768683274021353,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047883183522074335,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20823128670454025,
|
|
"num_tokens": 34193651.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.6963231563568115,
|
|
"epoch": 1.4773625939106365,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047881688915486743,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.19865045100450515,
|
|
"num_tokens": 34204173.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.6055628776550295,
|
|
"epoch": 1.477856860419138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047880193807506446,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.20975897014141082,
|
|
"num_tokens": 34214872.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.630388641357422,
|
|
"epoch": 1.4783511269276395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004787869819817021,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.20641892850399018,
|
|
"num_tokens": 34226433.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.607855653762817,
|
|
"epoch": 1.4788453934361407,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047877202087514843,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.20702054053545,
|
|
"num_tokens": 34238047.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.648554801940918,
|
|
"epoch": 1.4793396599446422,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004787570547557715,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.20462193489074706,
|
|
"num_tokens": 34250445.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.614186382293701,
|
|
"epoch": 1.4798339264531435,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047874208362393925,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.2114282011985779,
|
|
"num_tokens": 34261324.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.626661491394043,
|
|
"epoch": 1.480328192961645,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047872710748002024,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.20616672188043594,
|
|
"num_tokens": 34272074.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.6074522018432615,
|
|
"epoch": 1.4808224594701462,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004787121263243827,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.2012472465634346,
|
|
"num_tokens": 34282958.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.615146923065185,
|
|
"epoch": 1.4813167259786477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047869714015739533,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.20998490750789642,
|
|
"num_tokens": 34294999.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.66670331954956,
|
|
"epoch": 1.4818109924871492,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047868214897942675,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.20533516108989716,
|
|
"num_tokens": 34305363.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.639868354797363,
|
|
"epoch": 1.4823052589956505,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004786671527908456,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.20296799689531325,
|
|
"num_tokens": 34317467.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.683561849594116,
|
|
"epoch": 1.4827995255041517,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000478652151592021,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.19945032745599747,
|
|
"num_tokens": 34331058.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.4827995255041517,
|
|
"eval_entropy": 5.403352318654641,
|
|
"eval_loss": 5.1667375564575195,
|
|
"eval_mean_token_accuracy": 0.21148919851357648,
|
|
"eval_num_tokens": 34331058.0,
|
|
"eval_runtime": 20.5668,
|
|
"eval_samples_per_second": 1580.847,
|
|
"eval_steps_per_second": 197.648,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.628737926483154,
|
|
"epoch": 1.4832937920126532,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004786371453833217,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.2031007379293442,
|
|
"num_tokens": 34342593.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.640901708602906,
|
|
"epoch": 1.4837880585211547,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047862213416511717,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.2082556739449501,
|
|
"num_tokens": 34353507.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.545519924163818,
|
|
"epoch": 1.484282325029656,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004786071179377766,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.22022201716899872,
|
|
"num_tokens": 34365606.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.651801586151123,
|
|
"epoch": 1.4847765915381574,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004785920967016692,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.2073872372508049,
|
|
"num_tokens": 34375925.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.707785129547119,
|
|
"epoch": 1.4852708580466587,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047857707045716473,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.2005259081721306,
|
|
"num_tokens": 34387806.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.572797393798828,
|
|
"epoch": 1.4857651245551602,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047856203920463273,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.220612271130085,
|
|
"num_tokens": 34400367.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.6169829845428465,
|
|
"epoch": 1.4862593910636615,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000478547002944443,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.20651420205831528,
|
|
"num_tokens": 34412082.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.614314889907837,
|
|
"epoch": 1.486753657572163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004785319616769654,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.21144096404314042,
|
|
"num_tokens": 34423315.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.619121789932251,
|
|
"epoch": 1.4872479240806644,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047851691540256995,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.20070331990718843,
|
|
"num_tokens": 34433748.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.59445161819458,
|
|
"epoch": 1.4877421905891657,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047850186412162684,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.20647461116313934,
|
|
"num_tokens": 34444425.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.662446737289429,
|
|
"epoch": 1.488236457097667,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004784868078345063,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.20576656758785247,
|
|
"num_tokens": 34456350.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.682982921600342,
|
|
"epoch": 1.4887307236061684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004784717465415787,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.1999848112463951,
|
|
"num_tokens": 34466606.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.664536476135254,
|
|
"epoch": 1.48922499011467,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047845668024321455,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.20095517635345458,
|
|
"num_tokens": 34478085.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.645543098449707,
|
|
"epoch": 1.4897192566231712,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004784416089397846,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.19967044442892073,
|
|
"num_tokens": 34488437.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.663934946060181,
|
|
"epoch": 1.4902135231316727,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004784265326316594,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.20241033732891084,
|
|
"num_tokens": 34499999.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.700486564636231,
|
|
"epoch": 1.490707789640174,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047841145131921,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.20515956431627275,
|
|
"num_tokens": 34510509.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.655774354934692,
|
|
"epoch": 1.4912020561486754,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047839636500280724,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.1992002934217453,
|
|
"num_tokens": 34521192.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.634477949142456,
|
|
"epoch": 1.4916963226571767,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004783812736828225,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.20752955228090286,
|
|
"num_tokens": 34532401.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.645729064941406,
|
|
"epoch": 1.4921905891656781,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047836617735962675,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.20297013521194457,
|
|
"num_tokens": 34544306.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.6152520179748535,
|
|
"epoch": 1.4926848556741796,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004783510760335915,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20567697286605835,
|
|
"num_tokens": 34557122.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.626222801208496,
|
|
"epoch": 1.493179122182681,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004783359697050883,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.2116522952914238,
|
|
"num_tokens": 34568302.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.629308032989502,
|
|
"epoch": 1.4936733886911822,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047832085837448864,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.21368865966796874,
|
|
"num_tokens": 34578536.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.644666433334351,
|
|
"epoch": 1.4941676551996836,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047830574204216436,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.2058485046029091,
|
|
"num_tokens": 34590333.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.694665765762329,
|
|
"epoch": 1.4946619217081851,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004782906207084873,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19914036244153976,
|
|
"num_tokens": 34601447.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.598982572555542,
|
|
"epoch": 1.4951561882166864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004782754943738294,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.19607243835926055,
|
|
"num_tokens": 34613559.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.622142648696899,
|
|
"epoch": 1.4956504547251879,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004782603630385628,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20406719595193862,
|
|
"num_tokens": 34624354.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.660828685760498,
|
|
"epoch": 1.4961447212336891,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004782452267030598,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.20239893198013306,
|
|
"num_tokens": 34636093.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.674472999572754,
|
|
"epoch": 1.4966389877421906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004782300853676926,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.2111292764544487,
|
|
"num_tokens": 34647503.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.643357419967652,
|
|
"epoch": 1.4971332542506919,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047821493903283383,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.20439985990524293,
|
|
"num_tokens": 34660258.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.626752138137817,
|
|
"epoch": 1.4976275207591934,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000478199787698856,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20463467091321946,
|
|
"num_tokens": 34672199.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.619792079925537,
|
|
"epoch": 1.4981217872676948,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047818463136613184,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.20960963368415833,
|
|
"num_tokens": 34684419.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.520537948608398,
|
|
"epoch": 1.498616053776196,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047816947003503425,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.22313119024038314,
|
|
"num_tokens": 34695649.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.666916131973267,
|
|
"epoch": 1.4991103202846974,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047815430370593627,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.1994324192404747,
|
|
"num_tokens": 34707019.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.615766763687134,
|
|
"epoch": 1.4996045867931989,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047813913237921077,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.21499777138233184,
|
|
"num_tokens": 34717609.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.630023431777954,
|
|
"epoch": 1.5000988533017003,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004781239560552312,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.20035023540258406,
|
|
"num_tokens": 34728607.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.532263517379761,
|
|
"epoch": 1.5005931198102016,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047810877473437077,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.20856608003377913,
|
|
"num_tokens": 34739537.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.617901706695557,
|
|
"epoch": 1.501087386318703,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047809358841700297,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2063499167561531,
|
|
"num_tokens": 34751814.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.674693918228149,
|
|
"epoch": 1.5015816528272046,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004780783971035014,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20883031487464904,
|
|
"num_tokens": 34762647.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.639305591583252,
|
|
"epoch": 1.5020759193357058,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004780632007942397,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.20092812925577164,
|
|
"num_tokens": 34774157.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.6152464866638185,
|
|
"epoch": 1.502570185844207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004780479994895918,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.21540403515100479,
|
|
"num_tokens": 34785244.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.62833685874939,
|
|
"epoch": 1.5030644523527086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004780327931899316,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.20929554402828215,
|
|
"num_tokens": 34797090.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.6154571056365965,
|
|
"epoch": 1.50355871886121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047801758189563315,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.20904543101787568,
|
|
"num_tokens": 34808598.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.650859594345093,
|
|
"epoch": 1.5040529853697113,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047800236560707076,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.20651521235704423,
|
|
"num_tokens": 34820619.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.6188746929168705,
|
|
"epoch": 1.5045472518782126,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047798714432461864,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.20545910447835922,
|
|
"num_tokens": 34832463.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.656143760681152,
|
|
"epoch": 1.505041518386714,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004779719180486513,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.20329544246196746,
|
|
"num_tokens": 34844255.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.587829446792602,
|
|
"epoch": 1.5055357848952156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004779566867795433,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.20231008976697923,
|
|
"num_tokens": 34857215.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.6186174869537355,
|
|
"epoch": 1.5060300514037168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047794145051766935,
|
|
"loss": 5.0572,
|
|
"mean_token_accuracy": 0.2131394326686859,
|
|
"num_tokens": 34868831.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.633277130126953,
|
|
"epoch": 1.5065243179122183,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004779262092634042,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.22196642607450484,
|
|
"num_tokens": 34879258.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.653389596939087,
|
|
"epoch": 1.5070185844207198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047791096301712276,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.20166624039411546,
|
|
"num_tokens": 34891492.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.590588140487671,
|
|
"epoch": 1.507512850929221,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047789571177920024,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20609273463487626,
|
|
"num_tokens": 34901836.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.61017599105835,
|
|
"epoch": 1.5080071174377223,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004778804555500117,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20863416343927382,
|
|
"num_tokens": 34913892.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.678241395950318,
|
|
"epoch": 1.5085013839462238,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004778651943299324,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.1990362212061882,
|
|
"num_tokens": 34925657.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.673215675354004,
|
|
"epoch": 1.5089956504547253,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000477849928119338,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.20228348821401596,
|
|
"num_tokens": 34937921.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.6267897605896,
|
|
"epoch": 1.5094899169632265,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004778346569186038,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.20743319094181062,
|
|
"num_tokens": 34948742.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.610459804534912,
|
|
"epoch": 1.5099841834717278,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047781938072810555,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.20719307512044907,
|
|
"num_tokens": 34960912.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.6812296390533445,
|
|
"epoch": 1.5104784499802293,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047780409954821914,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20121535509824753,
|
|
"num_tokens": 34971188.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.635833978652954,
|
|
"epoch": 1.5109727164887308,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047778881337932037,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20392437130212784,
|
|
"num_tokens": 34983316.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.729225730895996,
|
|
"epoch": 1.511466982997232,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047777352222178537,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19305842220783234,
|
|
"num_tokens": 34995698.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.614221525192261,
|
|
"epoch": 1.5119612495057335,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047775822607599023,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.21283836662769318,
|
|
"num_tokens": 35007296.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.703234434127808,
|
|
"epoch": 1.512455516014235,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004777429249423113,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.19829242676496506,
|
|
"num_tokens": 35019126.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.6182215213775635,
|
|
"epoch": 1.5129497825227363,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047772761882112493,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.20833459943532945,
|
|
"num_tokens": 35030213.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.570404195785523,
|
|
"epoch": 1.5134440490312375,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004777123077128077,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.2057537019252777,
|
|
"num_tokens": 35043134.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.672547721862793,
|
|
"epoch": 1.513938315539739,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004776969916177363,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.20529075115919113,
|
|
"num_tokens": 35055484.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.650968360900879,
|
|
"epoch": 1.5144325820482405,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004776816705362874,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.2030738115310669,
|
|
"num_tokens": 35067037.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.608605813980103,
|
|
"epoch": 1.5149268485567418,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004776663444688381,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.2053129181265831,
|
|
"num_tokens": 35078340.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.65444016456604,
|
|
"epoch": 1.515421115065243,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004776510134157651,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.2057296946644783,
|
|
"num_tokens": 35090526.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.644522666931152,
|
|
"epoch": 1.5159153815737447,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047763567737744576,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.19836077839136124,
|
|
"num_tokens": 35103757.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.631564807891846,
|
|
"epoch": 1.516409648082246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004776203363542574,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.2103525608778,
|
|
"num_tokens": 35115694.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.608538341522217,
|
|
"epoch": 1.5169039145907472,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004776049903465773,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.21343359500169753,
|
|
"num_tokens": 35126691.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.59264760017395,
|
|
"epoch": 1.5173981810992487,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000477589639354783,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.20746424198150634,
|
|
"num_tokens": 35137851.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.63398323059082,
|
|
"epoch": 1.5178924476077502,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004775742833792521,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20059269070625305,
|
|
"num_tokens": 35148583.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.645005798339843,
|
|
"epoch": 1.5183867141162515,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004775589224203625,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20101388841867446,
|
|
"num_tokens": 35161469.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.617642164230347,
|
|
"epoch": 1.5188809806247527,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047754355647849185,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.21345510333776474,
|
|
"num_tokens": 35172349.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.565447902679443,
|
|
"epoch": 1.5193752471332542,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047752818555401845,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20583029538393022,
|
|
"num_tokens": 35183118.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.68081636428833,
|
|
"epoch": 1.5198695136417557,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047751280964732014,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.20419151782989503,
|
|
"num_tokens": 35195702.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.757663583755493,
|
|
"epoch": 1.520363780150257,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047749742875877535,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.1927846759557724,
|
|
"num_tokens": 35207356.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.642683982849121,
|
|
"epoch": 1.5208580466587585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004774820428887624,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.2070205867290497,
|
|
"num_tokens": 35219207.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.598497676849365,
|
|
"epoch": 1.52135231316726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004774666520376597,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.20306819975376128,
|
|
"num_tokens": 35230396.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.647071599960327,
|
|
"epoch": 1.5218465796757612,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004774512562058461,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.20009008496999742,
|
|
"num_tokens": 35242320.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.696912097930908,
|
|
"epoch": 1.5223408461842625,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004774358553937001,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.20332014113664626,
|
|
"num_tokens": 35252926.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.728696537017822,
|
|
"epoch": 1.522835112692764,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004774204496016006,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19837433844804764,
|
|
"num_tokens": 35263833.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.658403730392456,
|
|
"epoch": 1.5233293792012654,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047740503882992677,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.1956457495689392,
|
|
"num_tokens": 35274951.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.709320449829102,
|
|
"epoch": 1.5238236457097667,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004773896230790575,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.20209180265665055,
|
|
"num_tokens": 35287940.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.614229917526245,
|
|
"epoch": 1.524317912218268,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047737420234937215,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.2148742586374283,
|
|
"num_tokens": 35299321.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.59562726020813,
|
|
"epoch": 1.5248121787267694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047735877664125,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.2044736251235008,
|
|
"num_tokens": 35310181.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.641772222518921,
|
|
"epoch": 1.525306445235271,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047734334595507045,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.2008500263094902,
|
|
"num_tokens": 35320435.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.645095252990723,
|
|
"epoch": 1.5258007117437722,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004773279102912134,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1974768042564392,
|
|
"num_tokens": 35332533.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.597971057891845,
|
|
"epoch": 1.5262949782522737,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004773124696500582,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.2169189929962158,
|
|
"num_tokens": 35344289.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.645440101623535,
|
|
"epoch": 1.5267892447607752,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004772970240319849,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.21002120673656463,
|
|
"num_tokens": 35355679.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.659654998779297,
|
|
"epoch": 1.5272835112692764,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047728157343737346,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.2069590613245964,
|
|
"num_tokens": 35367489.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.571872806549072,
|
|
"epoch": 1.5277777777777777,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047726611786660396,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.2080030545592308,
|
|
"num_tokens": 35378349.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.622277736663818,
|
|
"epoch": 1.5282720442862792,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047725065732005654,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.2074512720108032,
|
|
"num_tokens": 35388927.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.603553199768067,
|
|
"epoch": 1.5287663107947806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004772351917981115,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.20765552967786788,
|
|
"num_tokens": 35401859.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.722529649734497,
|
|
"epoch": 1.529260577303282,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004772197213011494,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.20230091214179993,
|
|
"num_tokens": 35412735.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.576672077178955,
|
|
"epoch": 1.5297548438117832,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004772042458295509,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20596996694803238,
|
|
"num_tokens": 35422960.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.662555360794068,
|
|
"epoch": 1.5302491103202847,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047718876538369655,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.19537301659584044,
|
|
"num_tokens": 35435054.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.657025384902954,
|
|
"epoch": 1.5307433768287861,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047717327996396716,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.20128289312124253,
|
|
"num_tokens": 35447388.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.674860191345215,
|
|
"epoch": 1.5312376433372874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004771577895707437,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.2024154022336006,
|
|
"num_tokens": 35459181.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.582071971893311,
|
|
"epoch": 1.5317319098457889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004771422942044073,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.2058621808886528,
|
|
"num_tokens": 35469978.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.554481410980225,
|
|
"epoch": 1.5322261763542904,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004771267938653391,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.21437713056802749,
|
|
"num_tokens": 35482196.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.578401708602906,
|
|
"epoch": 1.5327204428627916,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004771112885539204,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.22001434564590455,
|
|
"num_tokens": 35493025.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.610587406158447,
|
|
"epoch": 1.533214709371293,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047709577827053257,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20879072844982147,
|
|
"num_tokens": 35504379.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.593979072570801,
|
|
"epoch": 1.5337089758797944,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047708026301555736,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.212285615503788,
|
|
"num_tokens": 35515401.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.685194253921509,
|
|
"epoch": 1.5342032423882959,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047706474278937626,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.207123002409935,
|
|
"num_tokens": 35527625.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.653115701675415,
|
|
"epoch": 1.5346975088967971,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047704921759237116,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20533392280340196,
|
|
"num_tokens": 35539484.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.683358430862427,
|
|
"epoch": 1.5351917754052984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047703368742492403,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.20389192551374435,
|
|
"num_tokens": 35550362.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.641043329238892,
|
|
"epoch": 1.5356860419137999,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004770181522874167,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20523983091115952,
|
|
"num_tokens": 35561564.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.602515125274659,
|
|
"epoch": 1.5361803084223014,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004770026121802316,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.2063030034303665,
|
|
"num_tokens": 35572216.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.565678977966309,
|
|
"epoch": 1.5366745749308026,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004769870671037509,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.22281621247529984,
|
|
"num_tokens": 35584471.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.611315584182739,
|
|
"epoch": 1.537168841439304,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047697151705835693,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.21293119788169862,
|
|
"num_tokens": 35596551.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.656266403198242,
|
|
"epoch": 1.5376631079478056,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004769559620444324,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20882682353258133,
|
|
"num_tokens": 35607425.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.547824668884277,
|
|
"epoch": 1.5381573744563068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047694040206235983,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.20869130641222,
|
|
"num_tokens": 35618900.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.640917062759399,
|
|
"epoch": 1.538651640964808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000476924837112522,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.2151516929268837,
|
|
"num_tokens": 35630126.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.643178939819336,
|
|
"epoch": 1.5391459074733096,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047690926719530193,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.21213618218898772,
|
|
"num_tokens": 35642406.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.563924980163574,
|
|
"epoch": 1.539640173981811,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047689369231108253,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.19852605909109117,
|
|
"num_tokens": 35654701.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.714000606536866,
|
|
"epoch": 1.5401344404903123,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000476878112460247,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.20168547183275223,
|
|
"num_tokens": 35665668.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.603884744644165,
|
|
"epoch": 1.5406287069988136,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047686252764317854,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20463287830352783,
|
|
"num_tokens": 35676940.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.65649447441101,
|
|
"epoch": 1.5411229735073153,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047684693786026054,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.19783479869365692,
|
|
"num_tokens": 35687860.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.6252046585083,
|
|
"epoch": 1.5416172400158166,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047683134311187663,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.21191117763519288,
|
|
"num_tokens": 35698349.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.612479829788208,
|
|
"epoch": 1.5421115065243178,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047681574339841044,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.21050350815057756,
|
|
"num_tokens": 35709649.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.592451381683349,
|
|
"epoch": 1.5426057730328193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047680013872024546,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21622900664806366,
|
|
"num_tokens": 35720806.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.671254014968872,
|
|
"epoch": 1.5431000395413208,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004767845290777659,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.20674313306808473,
|
|
"num_tokens": 35732044.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.63401312828064,
|
|
"epoch": 1.543594306049822,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004767689144713556,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.20659202635288237,
|
|
"num_tokens": 35743758.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.64555172920227,
|
|
"epoch": 1.5440885725583233,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047675329490139866,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20476967096328735,
|
|
"num_tokens": 35756184.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.59131932258606,
|
|
"epoch": 1.5445828390668248,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047673767036827947,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20350214689970017,
|
|
"num_tokens": 35768255.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.618579530715943,
|
|
"epoch": 1.5450771055753263,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004767220408723822,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19749178290367125,
|
|
"num_tokens": 35779111.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.678879594802856,
|
|
"epoch": 1.5455713720838276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004767064064140915,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.20307909548282624,
|
|
"num_tokens": 35791676.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.618720197677613,
|
|
"epoch": 1.546065638592329,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004766907669937919,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.21910729259252548,
|
|
"num_tokens": 35801868.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.706525373458862,
|
|
"epoch": 1.5465599051008305,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000476675122611868,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.1961040034890175,
|
|
"num_tokens": 35812428.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.63280029296875,
|
|
"epoch": 1.5470541716093318,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000476659473268705,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21166671216487884,
|
|
"num_tokens": 35823600.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.660809850692749,
|
|
"epoch": 1.547548438117833,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004766438189646876,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.20329172015190125,
|
|
"num_tokens": 35834988.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.642134809494019,
|
|
"epoch": 1.5480427046263345,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047662815970020086,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20555311888456346,
|
|
"num_tokens": 35846110.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.559690141677857,
|
|
"epoch": 1.548536971134836,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004766124954756302,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.21148962825536727,
|
|
"num_tokens": 35858276.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.697453737258911,
|
|
"epoch": 1.5490312376433373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047659682629136094,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20239807069301605,
|
|
"num_tokens": 35870705.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.645835876464844,
|
|
"epoch": 1.5495255041518385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004765811521477784,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.20744663327932358,
|
|
"num_tokens": 35882298.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.533794021606445,
|
|
"epoch": 1.55001977066034,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004765654730452682,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.21112847328186035,
|
|
"num_tokens": 35894665.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.616817903518677,
|
|
"epoch": 1.5505140371688415,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004765497889842161,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.21268761456012725,
|
|
"num_tokens": 35905893.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.652978324890137,
|
|
"epoch": 1.5510083036773428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047653409996500803,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.21505192369222642,
|
|
"num_tokens": 35917883.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.6402928829193115,
|
|
"epoch": 1.5515025701858443,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047651840598802976,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.21264520287513733,
|
|
"num_tokens": 35929863.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.6845055103302,
|
|
"epoch": 1.5519968366943457,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004765027070536674,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.20657283514738084,
|
|
"num_tokens": 35940843.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.57261848449707,
|
|
"epoch": 1.552491103202847,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004764870031623073,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.20988332033157348,
|
|
"num_tokens": 35953516.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.601561641693115,
|
|
"epoch": 1.5529853697113483,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047647129431433566,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20155519098043442,
|
|
"num_tokens": 35965481.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.644263744354248,
|
|
"epoch": 1.5534796362198497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004764555805101388,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.2083817720413208,
|
|
"num_tokens": 35976434.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.611486148834229,
|
|
"epoch": 1.5539739027283512,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004764398617501035,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.21062158942222595,
|
|
"num_tokens": 35987644.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.6900170803070065,
|
|
"epoch": 1.5544681692368525,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004764241380346163,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20572462379932405,
|
|
"num_tokens": 35999630.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.690995216369629,
|
|
"epoch": 1.5549624357453538,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004764084093640641,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.20480404794216156,
|
|
"num_tokens": 36011889.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.70372748374939,
|
|
"epoch": 1.5554567022538552,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004763926757388338,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.19814835786819457,
|
|
"num_tokens": 36024131.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.631671524047851,
|
|
"epoch": 1.5559509687623567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004763769371593124,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.21356480866670607,
|
|
"num_tokens": 36035759.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.646696376800537,
|
|
"epoch": 1.556445235270858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004763611936258871,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.2036789044737816,
|
|
"num_tokens": 36047882.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.649219274520874,
|
|
"epoch": 1.5569395017793595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004763454451389452,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.20744592994451522,
|
|
"num_tokens": 36058268.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.673025131225586,
|
|
"epoch": 1.557433768287861,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047632969169887407,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.20662508755922318,
|
|
"num_tokens": 36070797.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.63532977104187,
|
|
"epoch": 1.5579280347963622,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004763139333060613,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.20557064563035965,
|
|
"num_tokens": 36082858.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.667416286468506,
|
|
"epoch": 1.5584223013048635,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047629816996089464,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.20567771196365356,
|
|
"num_tokens": 36094825.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.66994047164917,
|
|
"epoch": 1.558916567813365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047628240166376173,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.1975449427962303,
|
|
"num_tokens": 36106379.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.607513952255249,
|
|
"epoch": 1.5594108343218664,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047626662841505045,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.21180902421474457,
|
|
"num_tokens": 36117137.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.670084857940674,
|
|
"epoch": 1.5599051008303677,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000476250850215149,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.2009461760520935,
|
|
"num_tokens": 36128420.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.658207130432129,
|
|
"epoch": 1.560399367338869,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004762350670644453,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.21478918343782424,
|
|
"num_tokens": 36139017.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.6426561832427975,
|
|
"epoch": 1.5608936338473705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004762192789633278,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.2069251611828804,
|
|
"num_tokens": 36151748.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.680469942092896,
|
|
"epoch": 1.561387900355872,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047620348591218475,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20413585752248764,
|
|
"num_tokens": 36163114.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.643116617202759,
|
|
"epoch": 1.5618821668643732,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004761876879114048,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.20553410053253174,
|
|
"num_tokens": 36174601.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.652243661880493,
|
|
"epoch": 1.5623764333728747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004761718849613765,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.2113827034831047,
|
|
"num_tokens": 36185081.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.67322473526001,
|
|
"epoch": 1.5628706998813762,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004761560770624886,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.2059912234544754,
|
|
"num_tokens": 36196547.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.630122184753418,
|
|
"epoch": 1.5633649663898774,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004761402642151301,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.21676377952098846,
|
|
"num_tokens": 36208115.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.636424398422241,
|
|
"epoch": 1.5638592328983787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004761244464196897,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.20528201758861542,
|
|
"num_tokens": 36219571.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.642731761932373,
|
|
"epoch": 1.5643534994068802,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004761086236765569,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.2052553340792656,
|
|
"num_tokens": 36232219.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.656517410278321,
|
|
"epoch": 1.5648477659153817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004760927959861206,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.20690458714962007,
|
|
"num_tokens": 36243761.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.591429090499878,
|
|
"epoch": 1.565342032423883,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004760769633487704,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.2079397678375244,
|
|
"num_tokens": 36255466.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.583880090713501,
|
|
"epoch": 1.5658362989323842,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047606112576489574,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.20147510021924972,
|
|
"num_tokens": 36267252.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.654772233963013,
|
|
"epoch": 1.566330565440886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004760452832348862,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.2081206411123276,
|
|
"num_tokens": 36278149.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.759261274337769,
|
|
"epoch": 1.5668248319493872,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047602943575913146,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.2096457675099373,
|
|
"num_tokens": 36290583.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.666076421737671,
|
|
"epoch": 1.5673190984578884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004760135833380214,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20568101704120637,
|
|
"num_tokens": 36301508.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.579487895965576,
|
|
"epoch": 1.56781336496639,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000475997725971946,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.2172827959060669,
|
|
"num_tokens": 36312488.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.606219291687012,
|
|
"epoch": 1.5683076314748914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004759818636612954,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.21143974512815475,
|
|
"num_tokens": 36323263.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.642297697067261,
|
|
"epoch": 1.5688018979833926,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047596599640645974,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.20268432497978212,
|
|
"num_tokens": 36336095.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.640225505828857,
|
|
"epoch": 1.569296164491894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047595012420782946,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.21111956089735032,
|
|
"num_tokens": 36346653.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.635346412658691,
|
|
"epoch": 1.5697904310003954,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004759342470657949,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.2095737338066101,
|
|
"num_tokens": 36358190.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.6698637962341305,
|
|
"epoch": 1.5702846975088969,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004759183649807467,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.20426882058382034,
|
|
"num_tokens": 36369037.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.684367418289185,
|
|
"epoch": 1.5707789640173981,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004759024779530755,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.20914275497198104,
|
|
"num_tokens": 36379881.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.640315198898316,
|
|
"epoch": 1.5712732305258994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047588658598317227,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.21390317082405091,
|
|
"num_tokens": 36390927.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.673428153991699,
|
|
"epoch": 1.571767497034401,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047587068907142783,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.2052227348089218,
|
|
"num_tokens": 36402398.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.601392078399658,
|
|
"epoch": 1.5722617635429024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004758547872182332,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.20985287427902222,
|
|
"num_tokens": 36413991.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.592830991744995,
|
|
"epoch": 1.5727560300514036,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004758388804239797,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.20902470648288726,
|
|
"num_tokens": 36425807.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.646934223175049,
|
|
"epoch": 1.5732502965599051,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004758229686890586,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.2092263087630272,
|
|
"num_tokens": 36437968.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.689522409439087,
|
|
"epoch": 1.5737445630684066,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047580705201386134,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.20176875591278076,
|
|
"num_tokens": 36449803.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.676580238342285,
|
|
"epoch": 1.5742388295769079,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004757911303987794,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.19782371670007706,
|
|
"num_tokens": 36461849.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.601644134521484,
|
|
"epoch": 1.5747330960854091,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004757752038442045,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.21730395704507827,
|
|
"num_tokens": 36473324.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.699030876159668,
|
|
"epoch": 1.5752273625939106,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004757592723505284,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.20389930307865142,
|
|
"num_tokens": 36483949.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.559926176071167,
|
|
"epoch": 1.575721629102412,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004757433359181431,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.216501484811306,
|
|
"num_tokens": 36495308.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.55944037437439,
|
|
"epoch": 1.5762158956109134,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047572739454744057,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.2072858676314354,
|
|
"num_tokens": 36506052.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.5546012878417965,
|
|
"epoch": 1.5767101621194148,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000475711448238813,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.22035402357578276,
|
|
"num_tokens": 36519175.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.702780818939209,
|
|
"epoch": 1.5772044286279163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047569549699265275,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.2117873966693878,
|
|
"num_tokens": 36529736.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.584452390670776,
|
|
"epoch": 1.5776986951364176,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047567954080935206,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.20884144455194473,
|
|
"num_tokens": 36541715.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.640492868423462,
|
|
"epoch": 1.5781929616449188,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004756635796893036,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.20592144429683684,
|
|
"num_tokens": 36553807.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.685679531097412,
|
|
"epoch": 1.5786872281534203,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004756476136328998,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.20124875754117966,
|
|
"num_tokens": 36566053.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.649059200286866,
|
|
"epoch": 1.5791814946619218,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047563164264053374,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.21152640581130983,
|
|
"num_tokens": 36577637.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.683610486984253,
|
|
"epoch": 1.579675761170423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047561566671259803,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.2067289635539055,
|
|
"num_tokens": 36587767.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.590875148773193,
|
|
"epoch": 1.5801700276789243,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047559968584948587,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.21321150064468383,
|
|
"num_tokens": 36599163.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.621867656707764,
|
|
"epoch": 1.5806642941874258,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004755837000515903,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.19817873388528823,
|
|
"num_tokens": 36611170.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.706474113464355,
|
|
"epoch": 1.5811585606959273,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004755677093193046,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.20007775574922562,
|
|
"num_tokens": 36622907.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.67011513710022,
|
|
"epoch": 1.5816528272044286,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004755517136530221,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.20455151796340942,
|
|
"num_tokens": 36635197.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.619413089752197,
|
|
"epoch": 1.58214709371293,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047553571305313636,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.21277602910995483,
|
|
"num_tokens": 36646965.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.582041168212891,
|
|
"epoch": 1.5826413602214315,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047551970752004097,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.219027516245842,
|
|
"num_tokens": 36657344.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.562989664077759,
|
|
"epoch": 1.5831356267299328,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047550369705412964,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.21531175971031188,
|
|
"num_tokens": 36668833.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.601619815826416,
|
|
"epoch": 1.583629893238434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004754876816557963,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21647660732269286,
|
|
"num_tokens": 36680902.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.594106817245484,
|
|
"epoch": 1.5841241597469355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047547166132543483,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.21841098815202714,
|
|
"num_tokens": 36691312.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.599699592590332,
|
|
"epoch": 1.584618426255437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047545563606343945,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.21125156581401824,
|
|
"num_tokens": 36701091.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.673898792266845,
|
|
"epoch": 1.5851126927639383,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004754396058702043,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.20579106211662293,
|
|
"num_tokens": 36712524.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.71528058052063,
|
|
"epoch": 1.5856069592724396,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047542357074612375,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.20401956737041474,
|
|
"num_tokens": 36724181.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.602558755874634,
|
|
"epoch": 1.586101225780941,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047540753069159224,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.21309050768613816,
|
|
"num_tokens": 36734777.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.614723587036133,
|
|
"epoch": 1.5865954922894425,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047539148570700443,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20834114998579026,
|
|
"num_tokens": 36746437.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.726670169830323,
|
|
"epoch": 1.5870897587979438,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047537543579275496,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.19890925288200378,
|
|
"num_tokens": 36759615.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.673828220367431,
|
|
"epoch": 1.5875840253064453,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004753593809492387,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.20403649359941484,
|
|
"num_tokens": 36770762.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.67295470237732,
|
|
"epoch": 1.5880782918149468,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004753433211768506,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19960034340620042,
|
|
"num_tokens": 36781410.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.689975643157959,
|
|
"epoch": 1.588572558323448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047532725647598563,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.207893668115139,
|
|
"num_tokens": 36792737.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.565967416763305,
|
|
"epoch": 1.5890668248319493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047531118684703916,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21792840212583542,
|
|
"num_tokens": 36804626.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.615782070159912,
|
|
"epoch": 1.5895610913404508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004752951122904064,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20347400456666948,
|
|
"num_tokens": 36815964.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.612174034118652,
|
|
"epoch": 1.5900553578489522,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004752790328064828,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.21989541947841645,
|
|
"num_tokens": 36828180.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.633416843414307,
|
|
"epoch": 1.5905496243574535,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047526294839566393,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.2109816461801529,
|
|
"num_tokens": 36839589.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.664599370956421,
|
|
"epoch": 1.5910438908659548,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004752468590583454,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.2100950852036476,
|
|
"num_tokens": 36850392.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.59595422744751,
|
|
"epoch": 1.5915381573744563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004752307647949232,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.21651246398687363,
|
|
"num_tokens": 36862334.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.576037073135376,
|
|
"epoch": 1.5920324238829577,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000475214665605793,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.21234441548585892,
|
|
"num_tokens": 36874837.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.605429315567017,
|
|
"epoch": 1.592526690391459,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000475198561491351,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.2099752739071846,
|
|
"num_tokens": 36886375.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.631845331192016,
|
|
"epoch": 1.5930209568999605,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004751824524519934,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.20649502128362657,
|
|
"num_tokens": 36897731.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.645301342010498,
|
|
"epoch": 1.593515223408462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004751663384881163,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.19925479590892792,
|
|
"num_tokens": 36909647.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.6408302783966064,
|
|
"epoch": 1.5940094899169632,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004751502196001163,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.20646788477897643,
|
|
"num_tokens": 36919960.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.6519537448883055,
|
|
"epoch": 1.5945037564254645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004751340957883898,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.19833845943212508,
|
|
"num_tokens": 36930520.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.692642164230347,
|
|
"epoch": 1.594998022933966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004751179670533335,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.20835266560316085,
|
|
"num_tokens": 36942627.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.666954374313354,
|
|
"epoch": 1.5954922894424675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004751018333953442,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.20928271859884262,
|
|
"num_tokens": 36954276.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.590887928009034,
|
|
"epoch": 1.5959865559509687,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004750856948148187,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.2127310037612915,
|
|
"num_tokens": 36965840.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.607626914978027,
|
|
"epoch": 1.59648082245947,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004750695513121541,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.21207628399133682,
|
|
"num_tokens": 36977133.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.689652442932129,
|
|
"epoch": 1.5969750889679717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004750534028877475,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.20610555112361909,
|
|
"num_tokens": 36989013.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.594076681137085,
|
|
"epoch": 1.597469355476473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004750372495419962,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.2043193593621254,
|
|
"num_tokens": 37000324.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.647673177719116,
|
|
"epoch": 1.5979636219849742,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004750210912752975,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.20846983790397644,
|
|
"num_tokens": 37010551.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.725697326660156,
|
|
"epoch": 1.5984578884934757,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004750049280880489,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.1990692988038063,
|
|
"num_tokens": 37022732.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.6719398021698,
|
|
"epoch": 1.5989521550019772,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047498875998064805,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.20491549223661423,
|
|
"num_tokens": 37033230.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.620753908157349,
|
|
"epoch": 1.5994464215104784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004749725869534926,
|
|
"loss": 5.0229,
|
|
"mean_token_accuracy": 0.21607371270656586,
|
|
"num_tokens": 37043854.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.636800861358642,
|
|
"epoch": 1.5999406880189797,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047495640900698064,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20790434628725052,
|
|
"num_tokens": 37055208.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.681601810455322,
|
|
"epoch": 1.6004349545274812,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047494022614150995,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.19896961003541946,
|
|
"num_tokens": 37065938.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.675406885147095,
|
|
"epoch": 1.6009292210359827,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004749240383574786,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.20739221572875977,
|
|
"num_tokens": 37077252.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.6091173648834225,
|
|
"epoch": 1.601423487544484,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000474907845655285,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.211248916387558,
|
|
"num_tokens": 37087443.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.533440351486206,
|
|
"epoch": 1.6019177540529854,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004748916480353273,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.2262212321162224,
|
|
"num_tokens": 37097621.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.608812522888184,
|
|
"epoch": 1.602412020561487,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047487544549800403,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.20517307817935942,
|
|
"num_tokens": 37110026.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.591574048995971,
|
|
"epoch": 1.6029062870699882,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004748592380437138,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.2056450992822647,
|
|
"num_tokens": 37121447.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.658017492294311,
|
|
"epoch": 1.6034005535784894,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004748430256728554,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20587513595819473,
|
|
"num_tokens": 37132245.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.717420387268066,
|
|
"epoch": 1.603894820086991,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047482680838582754,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20500980764627458,
|
|
"num_tokens": 37144135.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.677254343032837,
|
|
"epoch": 1.6043890865954924,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004748105861830292,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.2013164386153221,
|
|
"num_tokens": 37155716.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.69262318611145,
|
|
"epoch": 1.6048833531039937,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004747943590648594,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.19513586312532424,
|
|
"num_tokens": 37166701.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.691154670715332,
|
|
"epoch": 1.605377619612495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047477812703171737,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.1992193952202797,
|
|
"num_tokens": 37177655.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.650859689712524,
|
|
"epoch": 1.6058718861209964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047476189008400246,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.1991295337677002,
|
|
"num_tokens": 37189925.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.601884412765503,
|
|
"epoch": 1.606366152629498,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000474745648222114,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.2036278709769249,
|
|
"num_tokens": 37200756.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.664300584793091,
|
|
"epoch": 1.6068604191379992,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004747294014464516,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.205324125289917,
|
|
"num_tokens": 37213252.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.68650803565979,
|
|
"epoch": 1.6073546856465006,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000474713149757415,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.20417952090501784,
|
|
"num_tokens": 37223754.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.6628519058227536,
|
|
"epoch": 1.6078489521550021,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047469689315540395,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.19772956520318985,
|
|
"num_tokens": 37235930.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.620091915130615,
|
|
"epoch": 1.6083432186635034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047468063164081826,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.2219562441110611,
|
|
"num_tokens": 37246794.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.614759254455566,
|
|
"epoch": 1.6088374851720046,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004746643652140581,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.2047746002674103,
|
|
"num_tokens": 37257523.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.636906623840332,
|
|
"epoch": 1.6093317516805061,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047464809387552366,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.20553416907787322,
|
|
"num_tokens": 37269505.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.679425668716431,
|
|
"epoch": 1.6098260181890076,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000474631817625615,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20973817706108094,
|
|
"num_tokens": 37281139.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.587860488891602,
|
|
"epoch": 1.6103202846975089,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004746155364647327,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.21218821108341218,
|
|
"num_tokens": 37291784.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.5892064571380615,
|
|
"epoch": 1.6108145512060101,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047459925039327727,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.20604258030653,
|
|
"num_tokens": 37302754.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.600971269607544,
|
|
"epoch": 1.6113088177145116,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047458295941164933,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.2116978421807289,
|
|
"num_tokens": 37313478.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.64858660697937,
|
|
"epoch": 1.611803084223013,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004745666635202496,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.21234301030635833,
|
|
"num_tokens": 37325223.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.649829435348511,
|
|
"epoch": 1.6122973507315144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000474550362719479,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.20678011924028397,
|
|
"num_tokens": 37336794.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.777989149093628,
|
|
"epoch": 1.6127916172400159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047453405700973844,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19229091554880143,
|
|
"num_tokens": 37349171.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.657331943511963,
|
|
"epoch": 1.6132858837485173,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745177463914292,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.19881784170866013,
|
|
"num_tokens": 37362201.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.68917031288147,
|
|
"epoch": 1.6137801502570186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047450143086495244,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.1960347518324852,
|
|
"num_tokens": 37373858.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.698743391036987,
|
|
"epoch": 1.6142744167655199,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004744851104307095,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.20137936025857925,
|
|
"num_tokens": 37385973.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.7050152778625485,
|
|
"epoch": 1.6147686832740213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047446878508910194,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.20231731086969376,
|
|
"num_tokens": 37398054.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.67799825668335,
|
|
"epoch": 1.6152629497825228,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047445245484053133,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.20149558037519455,
|
|
"num_tokens": 37408656.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.586386871337891,
|
|
"epoch": 1.615757216291024,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004744361196853994,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.21588570177555083,
|
|
"num_tokens": 37420454.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.6465349197387695,
|
|
"epoch": 1.6162514827995254,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004744197796241079,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.211423759162426,
|
|
"num_tokens": 37431879.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.689335012435913,
|
|
"epoch": 1.6167457493080268,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004744034346570589,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20028213262557984,
|
|
"num_tokens": 37443487.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.585658693313599,
|
|
"epoch": 1.6172400158165283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004743870847846546,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2151515081524849,
|
|
"num_tokens": 37455726.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.668115854263306,
|
|
"epoch": 1.6177342823250296,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004743707300072969,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.20477477908134462,
|
|
"num_tokens": 37466735.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.697688007354737,
|
|
"epoch": 1.618228548833531,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047435437032538843,
|
|
"loss": 5.1958,
|
|
"mean_token_accuracy": 0.20168110728263855,
|
|
"num_tokens": 37479599.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.612147331237793,
|
|
"epoch": 1.6187228153420326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047433800573933147,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.20691879391670226,
|
|
"num_tokens": 37490896.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.609230327606201,
|
|
"epoch": 1.6192170818505338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047432163624952874,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.2020452782511711,
|
|
"num_tokens": 37501474.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.603456449508667,
|
|
"epoch": 1.619711348359035,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004743052618563827,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.21082838624715805,
|
|
"num_tokens": 37513410.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.628796005249024,
|
|
"epoch": 1.6202056148675366,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004742888825602964,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.21600966900587082,
|
|
"num_tokens": 37522612.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.7124124526977536,
|
|
"epoch": 1.620699881376038,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004742724983616726,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.19519510567188264,
|
|
"num_tokens": 37534320.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.653437376022339,
|
|
"epoch": 1.6211941478845393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047425610926091444,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.20276180207729338,
|
|
"num_tokens": 37545599.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.677180910110474,
|
|
"epoch": 1.6216884143930406,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004742397152584251,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.20989055931568146,
|
|
"num_tokens": 37558002.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.635497283935547,
|
|
"epoch": 1.6221826809015423,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047422331635460784,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.2090867504477501,
|
|
"num_tokens": 37570808.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.64206223487854,
|
|
"epoch": 1.6226769474100435,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047420691254986615,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.21124210208654404,
|
|
"num_tokens": 37581065.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.6563005447387695,
|
|
"epoch": 1.6231712139185448,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047419050384460345,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.20886942446231843,
|
|
"num_tokens": 37592472.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.634222459793091,
|
|
"epoch": 1.6236654804270463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004741740902392235,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.2028845027089119,
|
|
"num_tokens": 37604601.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.656680536270142,
|
|
"epoch": 1.6241597469355478,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004741576717341299,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.21140608042478562,
|
|
"num_tokens": 37615978.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.60361499786377,
|
|
"epoch": 1.624654013444049,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004741412483297268,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.21130236238241196,
|
|
"num_tokens": 37627532.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.688641786575317,
|
|
"epoch": 1.6251482799525503,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004741248200264181,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.20178515315055848,
|
|
"num_tokens": 37640508.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.60727071762085,
|
|
"epoch": 1.6256425464610518,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004741083868246079,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.2072846323251724,
|
|
"num_tokens": 37652095.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.561648654937744,
|
|
"epoch": 1.6261368129695533,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004740919487247005,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21318426728248596,
|
|
"num_tokens": 37663481.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.666745185852051,
|
|
"epoch": 1.6266310794780545,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004740755057271003,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.20912799537181853,
|
|
"num_tokens": 37675259.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.611609840393067,
|
|
"epoch": 1.627125345986556,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047405905783221177,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.2056804671883583,
|
|
"num_tokens": 37686006.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.607225847244263,
|
|
"epoch": 1.6276196124950575,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047404260504043945,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.21081357449293137,
|
|
"num_tokens": 37697642.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.678597640991211,
|
|
"epoch": 1.6281138790035588,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047402614735218824,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.2028450071811676,
|
|
"num_tokens": 37707714.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.638219833374023,
|
|
"epoch": 1.62860814551206,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004740096847678629,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.2126691535115242,
|
|
"num_tokens": 37719562.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.621192264556885,
|
|
"epoch": 1.6291024120205615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004739932172878685,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.21625596582889556,
|
|
"num_tokens": 37731521.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.685755491256714,
|
|
"epoch": 1.629596678529063,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047397674491261003,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.2032778725028038,
|
|
"num_tokens": 37743015.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.649811458587647,
|
|
"epoch": 1.6300909450375642,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047396026764249285,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.20121197700500487,
|
|
"num_tokens": 37754219.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.625334072113037,
|
|
"epoch": 1.6305852115460655,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004739437854779222,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.20063350349664688,
|
|
"num_tokens": 37765738.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.486595916748047,
|
|
"epoch": 1.631079478054567,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047392729841930345,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.2310355231165886,
|
|
"num_tokens": 37778647.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.631074047088623,
|
|
"epoch": 1.6315737445630685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047391080646704237,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.21045584082603455,
|
|
"num_tokens": 37790380.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.634944820404053,
|
|
"epoch": 1.6320680110715697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047389430962154464,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.2081418216228485,
|
|
"num_tokens": 37802474.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.617556238174439,
|
|
"epoch": 1.6325622775800712,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047387780788321594,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.203238645195961,
|
|
"num_tokens": 37814154.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.736549997329712,
|
|
"epoch": 1.6330565440885727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004738613012524624,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.2079269766807556,
|
|
"num_tokens": 37825371.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.70437273979187,
|
|
"epoch": 1.633550810597074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047384478972968997,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20257657617330552,
|
|
"num_tokens": 37836475.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.6924450397491455,
|
|
"epoch": 1.6340450771055752,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047382827331530483,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.20631492137908936,
|
|
"num_tokens": 37848413.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.5530375957489015,
|
|
"epoch": 1.6345393436140767,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004738117520097133,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.2134894922375679,
|
|
"num_tokens": 37858174.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.664174318313599,
|
|
"epoch": 1.6350336101225782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000473795225813322,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.2037930279970169,
|
|
"num_tokens": 37869987.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.643085908889771,
|
|
"epoch": 1.6355278766310795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047377869472653704,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21787209808826447,
|
|
"num_tokens": 37882050.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.628175401687622,
|
|
"epoch": 1.6360221431395807,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004737621587497655,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.2079532951116562,
|
|
"num_tokens": 37894537.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.636962842941284,
|
|
"epoch": 1.6365164096480822,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000473745617883414,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.21517642289400102,
|
|
"num_tokens": 37905795.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.63035135269165,
|
|
"epoch": 1.6370106761565837,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047372907212788953,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.21291921585798262,
|
|
"num_tokens": 37918778.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.655758666992187,
|
|
"epoch": 1.637504942665085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047371252148359897,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.19588107615709305,
|
|
"num_tokens": 37930963.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.6494310855865475,
|
|
"epoch": 1.6379992091735864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004736959659509496,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.2051742658019066,
|
|
"num_tokens": 37943067.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.696420049667358,
|
|
"epoch": 1.638493475682088,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004736794055303487,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20583923012018204,
|
|
"num_tokens": 37953425.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.583119916915893,
|
|
"epoch": 1.6389877421905892,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047366284022220346,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.21318329721689225,
|
|
"num_tokens": 37965801.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.639124536514283,
|
|
"epoch": 1.6394820086990904,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004736462700269216,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.2041945978999138,
|
|
"num_tokens": 37978169.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.640938234329224,
|
|
"epoch": 1.639976275207592,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047362969494491063,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.20794485211372377,
|
|
"num_tokens": 37990154.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.675646114349365,
|
|
"epoch": 1.6404705417160934,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047361311497657845,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.213459549844265,
|
|
"num_tokens": 38001249.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.607346868515014,
|
|
"epoch": 1.6409648082245947,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004735965301223328,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.21928873062133789,
|
|
"num_tokens": 38013453.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.685328388214112,
|
|
"epoch": 1.641459074733096,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047357994038258166,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.1949417695403099,
|
|
"num_tokens": 38024463.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.662952136993408,
|
|
"epoch": 1.6419533412415974,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047356334575773324,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20689620822668076,
|
|
"num_tokens": 38036131.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.631861305236816,
|
|
"epoch": 1.642447607750099,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004735467462481956,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.21428054720163345,
|
|
"num_tokens": 38047428.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.631965827941895,
|
|
"epoch": 1.6429418742586002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004735301418543773,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.2130819246172905,
|
|
"num_tokens": 38059864.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.679200887680054,
|
|
"epoch": 1.6434361407671016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047351353257668675,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.20570430159568787,
|
|
"num_tokens": 38071356.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.704501056671143,
|
|
"epoch": 1.6439304072756031,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004734969184155324,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.1975148931145668,
|
|
"num_tokens": 38082124.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.663963365554809,
|
|
"epoch": 1.6444246737841044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047348029937132306,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.2030536338686943,
|
|
"num_tokens": 38093451.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.6562981605529785,
|
|
"epoch": 1.6449189402926057,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047346367544446753,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19989574253559111,
|
|
"num_tokens": 38105078.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.604946088790894,
|
|
"epoch": 1.6454132068011071,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004734470466353749,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.22136687338352204,
|
|
"num_tokens": 38114953.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.627451753616333,
|
|
"epoch": 1.6459074733096086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004734304129444542,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.20915758311748506,
|
|
"num_tokens": 38126465.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.7089221477508545,
|
|
"epoch": 1.6464017398181099,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004734137743721144,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.19919417202472686,
|
|
"num_tokens": 38139223.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.603037405014038,
|
|
"epoch": 1.6468960063266112,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000473397130918765,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21037935614585876,
|
|
"num_tokens": 38151676.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.630107164382935,
|
|
"epoch": 1.6473902728351129,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047338048258481545,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.20580921024084092,
|
|
"num_tokens": 38162759.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.589247751235962,
|
|
"epoch": 1.6478845393436141,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004733638293706752,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.20965877324342727,
|
|
"num_tokens": 38174820.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.595712900161743,
|
|
"epoch": 1.6483788058521154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000473347171276754,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.2190757691860199,
|
|
"num_tokens": 38185558.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.6552613258361815,
|
|
"epoch": 1.6488730723606169,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004733305083034617,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.2049844369292259,
|
|
"num_tokens": 38198231.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.670666837692261,
|
|
"epoch": 1.6493673388691183,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047331384045120803,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.2078383296728134,
|
|
"num_tokens": 38209539.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.664439105987549,
|
|
"epoch": 1.6498616053776196,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004732971677204031,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.2004823014140129,
|
|
"num_tokens": 38220873.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.661258602142334,
|
|
"epoch": 1.6503558718861209,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047328049011145714,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.21104003936052323,
|
|
"num_tokens": 38231186.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.706480360031128,
|
|
"epoch": 1.6508501383946224,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004732638076247804,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.1969300091266632,
|
|
"num_tokens": 38242152.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.671340274810791,
|
|
"epoch": 1.6513444049031238,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047324712026078315,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.20255715698003768,
|
|
"num_tokens": 38254281.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.595852279663086,
|
|
"epoch": 1.651838671411625,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000473230428019876,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2092139407992363,
|
|
"num_tokens": 38265120.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.631833791732788,
|
|
"epoch": 1.6523329379201266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047321373090246957,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.2133242204785347,
|
|
"num_tokens": 38275509.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.5987711429595945,
|
|
"epoch": 1.652827204428628,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047319702890897457,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.2126941278576851,
|
|
"num_tokens": 38285586.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.676436138153076,
|
|
"epoch": 1.6533214709371293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000473180322039802,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.21022467613220214,
|
|
"num_tokens": 38296091.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.622262573242187,
|
|
"epoch": 1.6538157374456306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004731636102953627,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.20357994586229325,
|
|
"num_tokens": 38308520.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.652386331558228,
|
|
"epoch": 1.654310003954132,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004731468936760679,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20697529911994933,
|
|
"num_tokens": 38320584.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.6373037815094,
|
|
"epoch": 1.6548042704626336,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004731301721823287,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20894745886325836,
|
|
"num_tokens": 38332646.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.689837408065796,
|
|
"epoch": 1.6552985369711348,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004731134458145566,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20304924249649048,
|
|
"num_tokens": 38343382.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.739306354522705,
|
|
"epoch": 1.655792803479636,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047309671457316295,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.1941071033477783,
|
|
"num_tokens": 38354809.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.653772163391113,
|
|
"epoch": 1.6562870699881376,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047307997845855946,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20906679332256317,
|
|
"num_tokens": 38366524.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.578066968917847,
|
|
"epoch": 1.656781336496639,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004730632374711578,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.2139671951532364,
|
|
"num_tokens": 38377645.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.6949716091156,
|
|
"epoch": 1.6572756030051403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004730464916113696,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.21014545857906342,
|
|
"num_tokens": 38389633.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.688600301742554,
|
|
"epoch": 1.6577698695136418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047302974087960704,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.19996795803308487,
|
|
"num_tokens": 38401255.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.677191638946534,
|
|
"epoch": 1.6582641360221433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004730129852762822,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.2016428753733635,
|
|
"num_tokens": 38413160.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.654299592971801,
|
|
"epoch": 1.6587584025306445,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047299622480180716,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19921221286058427,
|
|
"num_tokens": 38423789.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.626548194885254,
|
|
"epoch": 1.6592526690391458,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047297945945659424,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.20322513580322266,
|
|
"num_tokens": 38435031.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.665118551254272,
|
|
"epoch": 1.6597469355476473,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047296268924105594,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.2101385474205017,
|
|
"num_tokens": 38445146.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.727446508407593,
|
|
"epoch": 1.6602412020561488,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047294591415560484,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.20375304222106932,
|
|
"num_tokens": 38457429.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.677542018890381,
|
|
"epoch": 1.66073546856465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004729291342006535,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.21290635019540788,
|
|
"num_tokens": 38468218.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.691672277450562,
|
|
"epoch": 1.6612297350731513,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004729123493766147,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.2060929611325264,
|
|
"num_tokens": 38480841.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.628201484680176,
|
|
"epoch": 1.6617240015816528,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004728955596839014,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.2079651191830635,
|
|
"num_tokens": 38493115.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.675645399093628,
|
|
"epoch": 1.6622182680901543,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004728787651229267,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.20970465391874313,
|
|
"num_tokens": 38505187.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.66919527053833,
|
|
"epoch": 1.6627125345986555,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047286196569410366,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.19765817523002624,
|
|
"num_tokens": 38518736.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.629208326339722,
|
|
"epoch": 1.663206801107157,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047284516139784556,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.21328803151845932,
|
|
"num_tokens": 38529703.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.618866777420044,
|
|
"epoch": 1.6637010676156585,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004728283522345658,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.20180267989635467,
|
|
"num_tokens": 38542200.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.640167236328125,
|
|
"epoch": 1.6641953341241598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004728115382046779,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19957370907068253,
|
|
"num_tokens": 38552921.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.692377710342408,
|
|
"epoch": 1.664689600632661,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727947193085954,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.2067711740732193,
|
|
"num_tokens": 38564837.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.6976597785949705,
|
|
"epoch": 1.6651838671411625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047277789554673217,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.20442409962415695,
|
|
"num_tokens": 38575786.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.6965837478637695,
|
|
"epoch": 1.665678133649664,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047276106691950204,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19812016040086747,
|
|
"num_tokens": 38588232.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.673884105682373,
|
|
"epoch": 1.6661724001581653,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047274423342731896,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.20105236619710923,
|
|
"num_tokens": 38600276.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.664705419540406,
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004727273950705971,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.21164128929376602,
|
|
"num_tokens": 38611879.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.685596036911011,
|
|
"epoch": 1.667160933175168,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047271055184975057,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.19727614820003508,
|
|
"num_tokens": 38623032.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.69431619644165,
|
|
"epoch": 1.6676551996836695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004726937037651939,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.20601418912410735,
|
|
"num_tokens": 38633864.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.649168634414673,
|
|
"epoch": 1.6681494661921707,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047267685081734133,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.20862379372119905,
|
|
"num_tokens": 38645208.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.601532363891602,
|
|
"epoch": 1.6686437327006722,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004726599930066076,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.21074121147394181,
|
|
"num_tokens": 38655181.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.68532509803772,
|
|
"epoch": 1.6691379992091737,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004726431303334074,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.2015222951769829,
|
|
"num_tokens": 38667381.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.7018718242645265,
|
|
"epoch": 1.669632265717675,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047262626279815555,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.2033023163676262,
|
|
"num_tokens": 38680479.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.652838897705078,
|
|
"epoch": 1.6701265322261762,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472609390401267,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.20676343739032746,
|
|
"num_tokens": 38691737.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.611469078063965,
|
|
"epoch": 1.6706207987346777,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004725925131431567,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.21196651756763457,
|
|
"num_tokens": 38703306.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.6899176120758055,
|
|
"epoch": 1.6711150652431792,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047257563102424,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.2122243881225586,
|
|
"num_tokens": 38714683.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.676860189437866,
|
|
"epoch": 1.6716093317516805,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004725587440449321,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.19921209812164306,
|
|
"num_tokens": 38727705.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.682914543151855,
|
|
"epoch": 1.6721035982601817,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047254185220564843,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20573200434446334,
|
|
"num_tokens": 38738687.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.635799503326416,
|
|
"epoch": 1.6725978647686834,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047252495550680453,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.20837995857000352,
|
|
"num_tokens": 38749437.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.563814258575439,
|
|
"epoch": 1.6730921312771847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004725080539488162,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.23225947618484497,
|
|
"num_tokens": 38761342.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.694734764099121,
|
|
"epoch": 1.673586397785686,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047249114753209896,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.2025812476873398,
|
|
"num_tokens": 38773019.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.747272682189942,
|
|
"epoch": 1.6740806642941874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047247423625706894,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.2060581460595131,
|
|
"num_tokens": 38785291.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.620439100265503,
|
|
"epoch": 1.674574930802689,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000472457320124142,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.2050535798072815,
|
|
"num_tokens": 38796926.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.6851921558380125,
|
|
"epoch": 1.6750691973111902,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047244039913373444,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.20759534686803818,
|
|
"num_tokens": 38809839.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.704209423065185,
|
|
"epoch": 1.6755634638196915,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004724234732862624,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.19484361112117768,
|
|
"num_tokens": 38823059.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.598594760894775,
|
|
"epoch": 1.676057730328193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004724065425821422,
|
|
"loss": 5.0249,
|
|
"mean_token_accuracy": 0.21442403346300126,
|
|
"num_tokens": 38834275.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.646009540557861,
|
|
"epoch": 1.6765519968366944,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004723896070217905,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.20345908254384995,
|
|
"num_tokens": 38845992.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.661275053024292,
|
|
"epoch": 1.6770462633451957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004723726666056239,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.20883268713951111,
|
|
"num_tokens": 38857269.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.6363331317901615,
|
|
"epoch": 1.677540529853697,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047235572133405904,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20417166948318483,
|
|
"num_tokens": 38869393.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.7397088527679445,
|
|
"epoch": 1.6780347963621987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047233877120751277,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.20554377883672714,
|
|
"num_tokens": 38881625.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.704796886444091,
|
|
"epoch": 1.6785290628707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047232181622640216,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.2012960597872734,
|
|
"num_tokens": 38892452.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.615222930908203,
|
|
"epoch": 1.6790233293792012,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004723048563911443,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.21862960904836654,
|
|
"num_tokens": 38902415.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.638250494003296,
|
|
"epoch": 1.6795175958877027,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047228789170215623,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21899288445711135,
|
|
"num_tokens": 38912655.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.665514183044434,
|
|
"epoch": 1.6800118623962041,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047227092215985553,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20337653458118438,
|
|
"num_tokens": 38923295.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.703656578063965,
|
|
"epoch": 1.6805061289047054,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004722539477646595,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.20113148242235185,
|
|
"num_tokens": 38934879.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.723704099655151,
|
|
"epoch": 1.6810003954132067,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047223696851698575,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.19713475555181503,
|
|
"num_tokens": 38946574.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.660503911972046,
|
|
"epoch": 1.6814946619217082,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472219984417252,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.20540697276592254,
|
|
"num_tokens": 38958136.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.682362747192383,
|
|
"epoch": 1.6819889284302096,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004722029954658761,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.21208843290805818,
|
|
"num_tokens": 38969353.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.626149845123291,
|
|
"epoch": 1.682483194938711,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004721860016632758,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21103858649730683,
|
|
"num_tokens": 38979878.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.6717346668243405,
|
|
"epoch": 1.6829774614472124,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004721690030098693,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.21080494225025176,
|
|
"num_tokens": 38992847.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.626720428466797,
|
|
"epoch": 1.6834717279557139,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004721519995060748,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20758083760738372,
|
|
"num_tokens": 39003874.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.651947641372681,
|
|
"epoch": 1.6839659944642151,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047213499115231043,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.204144287109375,
|
|
"num_tokens": 39014327.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.6625261306762695,
|
|
"epoch": 1.6844602609727164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004721179779489948,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.20793200880289078,
|
|
"num_tokens": 39024507.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.66888918876648,
|
|
"epoch": 1.6849545274812179,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047210095989654624,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.20381729006767274,
|
|
"num_tokens": 39036184.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.603585195541382,
|
|
"epoch": 1.6854487939897194,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047208393699538356,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21668725609779357,
|
|
"num_tokens": 39047649.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.626670074462891,
|
|
"epoch": 1.6859430604982206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047206690924592545,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.20799586921930313,
|
|
"num_tokens": 39058167.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.670682621002197,
|
|
"epoch": 1.6864373270067219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004720498766485907,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.20811321586370468,
|
|
"num_tokens": 39070099.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.638342046737671,
|
|
"epoch": 1.6869315935152234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047203283920379846,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.21226926892995834,
|
|
"num_tokens": 39080337.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.727903175354004,
|
|
"epoch": 1.6874258600237249,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047201579691196784,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.194310499727726,
|
|
"num_tokens": 39093455.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.71069483757019,
|
|
"epoch": 1.6879201265322261,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047199874977351807,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.20192922949790953,
|
|
"num_tokens": 39105424.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.610547351837158,
|
|
"epoch": 1.6884143930407276,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004719816977888685,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.21599644422531128,
|
|
"num_tokens": 39117441.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.639893341064453,
|
|
"epoch": 1.688908659549229,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047196464095843857,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.1990235611796379,
|
|
"num_tokens": 39129853.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.694280195236206,
|
|
"epoch": 1.6894029260577303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004719475792826479,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.21093638986349106,
|
|
"num_tokens": 39141132.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.575330448150635,
|
|
"epoch": 1.6898971925662316,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004719305127619162,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21812281757593155,
|
|
"num_tokens": 39153892.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.655168104171753,
|
|
"epoch": 1.690391459074733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004719134413966635,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.21801987290382385,
|
|
"num_tokens": 39164410.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.644136524200439,
|
|
"epoch": 1.6908857255832346,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047189636518730945,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.21874399185180665,
|
|
"num_tokens": 39174612.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.690845918655396,
|
|
"epoch": 1.6913799920917358,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047187928413427424,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.20817263424396515,
|
|
"num_tokens": 39187355.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.642514944076538,
|
|
"epoch": 1.691874258600237,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047186219823797815,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20654187798500062,
|
|
"num_tokens": 39199145.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.701640796661377,
|
|
"epoch": 1.6923685251087386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047184510749884146,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.20583640933036804,
|
|
"num_tokens": 39210589.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.601072788238525,
|
|
"epoch": 1.69286279161724,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004718280119172846,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.2131732776761055,
|
|
"num_tokens": 39222657.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.603971910476685,
|
|
"epoch": 1.6933570581257413,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047181091149372807,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.22116025686264038,
|
|
"num_tokens": 39233439.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.584670829772949,
|
|
"epoch": 1.6938513246342428,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004717938062285926,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.2202959418296814,
|
|
"num_tokens": 39243787.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.671615409851074,
|
|
"epoch": 1.6943455911427443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047177669612229894,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.20123551785945892,
|
|
"num_tokens": 39255658.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.676954317092895,
|
|
"epoch": 1.6948398576512456,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047175958117526805,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20025734901428222,
|
|
"num_tokens": 39269480.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.669292163848877,
|
|
"epoch": 1.6953341241597468,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047174246138792096,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.20348350405693055,
|
|
"num_tokens": 39281063.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.712950134277344,
|
|
"epoch": 1.6958283906682483,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047172533676067874,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.20576309859752656,
|
|
"num_tokens": 39292188.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.658694553375244,
|
|
"epoch": 1.6963226571767498,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004717082072939628,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.20085755586624146,
|
|
"num_tokens": 39303661.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.612903022766114,
|
|
"epoch": 1.696816923685251,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004716910729881944,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.2021130681037903,
|
|
"num_tokens": 39315028.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.623503684997559,
|
|
"epoch": 1.6973111901937523,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047167393384379513,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.21769197285175323,
|
|
"num_tokens": 39326629.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.593877792358398,
|
|
"epoch": 1.6978054567022538,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047165678986118653,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.2202385574579239,
|
|
"num_tokens": 39338821.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.587291097640991,
|
|
"epoch": 1.6982997232107553,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004716396410407904,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20685794651508332,
|
|
"num_tokens": 39350093.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.604253339767456,
|
|
"epoch": 1.6987939897192565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004716224873830286,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.2190247282385826,
|
|
"num_tokens": 39361120.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.6720184803009035,
|
|
"epoch": 1.699288256227758,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047160532888832315,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.20447756201028824,
|
|
"num_tokens": 39373040.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.650310754776001,
|
|
"epoch": 1.6997825227362595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047158816555709597,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21040756851434708,
|
|
"num_tokens": 39384576.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.621695804595947,
|
|
"epoch": 1.7002767892447608,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004715709973897696,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21406036019325256,
|
|
"num_tokens": 39397550.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.658383846282959,
|
|
"epoch": 1.700771055753262,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047155382438676604,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.20830836445093154,
|
|
"num_tokens": 39407474.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.630543279647827,
|
|
"epoch": 1.7012653222617635,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047153664654850803,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20922174602746962,
|
|
"num_tokens": 39420104.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.727230072021484,
|
|
"epoch": 1.701759588770265,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047151946387541795,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.1977905288338661,
|
|
"num_tokens": 39431887.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.646735763549804,
|
|
"epoch": 1.7022538552787663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004715022763679185,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.21201357543468474,
|
|
"num_tokens": 39442772.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.714088201522827,
|
|
"epoch": 1.7027481217872675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047148508402643273,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20778655260801315,
|
|
"num_tokens": 39455067.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.638282012939453,
|
|
"epoch": 1.7032423882957692,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004714678868513834,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.20488928407430648,
|
|
"num_tokens": 39466700.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.67880482673645,
|
|
"epoch": 1.7037366548042705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004714506848431935,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.21227422952651978,
|
|
"num_tokens": 39477591.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.663312101364136,
|
|
"epoch": 1.7042309213127718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047143347800228624,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.2004741132259369,
|
|
"num_tokens": 39488615.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.6947290897369385,
|
|
"epoch": 1.7047251878212732,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000471416266329085,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.1991410568356514,
|
|
"num_tokens": 39499610.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.669721364974976,
|
|
"epoch": 1.7052194543297747,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004713990498240131,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.21100864708423614,
|
|
"num_tokens": 39511180.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.610219526290893,
|
|
"epoch": 1.705713720838276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047138182848749415,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.2152702584862709,
|
|
"num_tokens": 39523271.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.680809545516968,
|
|
"epoch": 1.7062079873467773,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004713646023199518,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.2092961773276329,
|
|
"num_tokens": 39534334.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.638230848312378,
|
|
"epoch": 1.7067022538552787,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004713473713218097,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.21606237739324569,
|
|
"num_tokens": 39545937.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.725191307067871,
|
|
"epoch": 1.7071965203637802,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004713301354934918,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.20603581815958022,
|
|
"num_tokens": 39558129.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.68611216545105,
|
|
"epoch": 1.7076907868722815,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004713128948354221,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.20499510914087296,
|
|
"num_tokens": 39569649.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.705066394805908,
|
|
"epoch": 1.708185053380783,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004712956493480248,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.2026871144771576,
|
|
"num_tokens": 39581051.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.713614511489868,
|
|
"epoch": 1.7086793198892845,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000471278399031724,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.20385100096464157,
|
|
"num_tokens": 39591225.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.614252710342408,
|
|
"epoch": 1.7091735863977857,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004712611438869442,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.21776041090488435,
|
|
"num_tokens": 39601270.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.60040316581726,
|
|
"epoch": 1.709667852906287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047124388391410975,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.21226860582828522,
|
|
"num_tokens": 39611574.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.581809091567993,
|
|
"epoch": 1.7101621194147885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004712266191136453,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.21703248620033264,
|
|
"num_tokens": 39622889.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.624007511138916,
|
|
"epoch": 1.71065638592329,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004712093494859757,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.2071884900331497,
|
|
"num_tokens": 39634286.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.693114805221557,
|
|
"epoch": 1.7111506524317912,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004711920750315255,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.2043486088514328,
|
|
"num_tokens": 39646653.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.6332635402679445,
|
|
"epoch": 1.7116449189402925,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004711747957507199,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20582227259874344,
|
|
"num_tokens": 39658027.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.695397806167603,
|
|
"epoch": 1.712139185448794,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047115751164398395,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.20508720576763154,
|
|
"num_tokens": 39669912.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.616797590255738,
|
|
"epoch": 1.7126334519572954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004711402227117427,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20992399752140045,
|
|
"num_tokens": 39680857.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.6405223369598385,
|
|
"epoch": 1.7131277184657967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047112292895442156,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.21526055186986923,
|
|
"num_tokens": 39692301.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.675924825668335,
|
|
"epoch": 1.7136219849742982,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000471105630372446,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20561446994543076,
|
|
"num_tokens": 39703641.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.64864673614502,
|
|
"epoch": 1.7141162514827997,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047108832696624145,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.21797345876693724,
|
|
"num_tokens": 39714919.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.606600713729859,
|
|
"epoch": 1.714610517991301,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004710710187362336,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.21241843402385713,
|
|
"num_tokens": 39725658.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.632026815414429,
|
|
"epoch": 1.7151047844998022,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047105370568284834,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.21595085710287093,
|
|
"num_tokens": 39736899.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.7166625499725345,
|
|
"epoch": 1.7155990510083037,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004710363878065115,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.1982549771666527,
|
|
"num_tokens": 39747875.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.730075120925903,
|
|
"epoch": 1.7160933175168052,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004710190651076491,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.2085179641842842,
|
|
"num_tokens": 39760253.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.716611576080322,
|
|
"epoch": 1.7165875840253064,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004710017375866872,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.2037930890917778,
|
|
"num_tokens": 39771031.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.6081701755523685,
|
|
"epoch": 1.7170818505338077,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047098440524405227,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.21361450850963593,
|
|
"num_tokens": 39780850.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.640288972854615,
|
|
"epoch": 1.7175761170423092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004709670680801705,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.21504009515047073,
|
|
"num_tokens": 39792975.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.713556098937988,
|
|
"epoch": 1.7180703835508107,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004709497260954685,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.2164592206478119,
|
|
"num_tokens": 39803574.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.621983289718628,
|
|
"epoch": 1.718564650059312,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047093237929037284,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.21100576519966124,
|
|
"num_tokens": 39814907.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.645440864562988,
|
|
"epoch": 1.7190589165678134,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004709150276653101,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.2026602730154991,
|
|
"num_tokens": 39826344.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.6538001537323,
|
|
"epoch": 1.7195531830763149,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047089767122070756,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.2056430235505104,
|
|
"num_tokens": 39838516.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.82900595664978,
|
|
"epoch": 1.7200474495848161,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047088030995699173,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.19382530003786086,
|
|
"num_tokens": 39850757.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.763367557525635,
|
|
"epoch": 1.7205417160933174,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004708629438745899,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.19756341427564622,
|
|
"num_tokens": 39861105.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.7216246128082275,
|
|
"epoch": 1.721035982601819,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004708455729739293,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.2003402128815651,
|
|
"num_tokens": 39873999.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.601600217819214,
|
|
"epoch": 1.7215302491103204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047082819725543726,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20578068494796753,
|
|
"num_tokens": 39885768.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.750118350982666,
|
|
"epoch": 1.7220245156188216,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004708108167195411,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.2049395889043808,
|
|
"num_tokens": 39897548.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.6922728538513185,
|
|
"epoch": 1.722518782127323,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004707934313666685,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.21417734473943711,
|
|
"num_tokens": 39909192.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.654570531845093,
|
|
"epoch": 1.7230130486358244,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004707760411972471,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.2068054348230362,
|
|
"num_tokens": 39921279.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.712366151809692,
|
|
"epoch": 1.7235073151443259,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004707586462117048,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.20462981462478638,
|
|
"num_tokens": 39931638.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.62876935005188,
|
|
"epoch": 1.7240015816528271,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047074124641046934,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.20841259509325027,
|
|
"num_tokens": 39944239.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.723555946350098,
|
|
"epoch": 1.7244958481613286,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004707238417939689,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.2007894992828369,
|
|
"num_tokens": 39956486.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.616652917861939,
|
|
"epoch": 1.72499011466983,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004707064323626316,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.22301835119724273,
|
|
"num_tokens": 39966271.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.643381881713867,
|
|
"epoch": 1.7254843811783314,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047068901811688564,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.20632551312446595,
|
|
"num_tokens": 39978810.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.6365423679351805,
|
|
"epoch": 1.7259786476868326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004706715990571595,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.21213385611772537,
|
|
"num_tokens": 39989331.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.636999082565308,
|
|
"epoch": 1.726472914195334,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004706541751838817,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2099806100130081,
|
|
"num_tokens": 39999931.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.651962471008301,
|
|
"epoch": 1.7269671807038356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004706367464974808,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.21059638410806655,
|
|
"num_tokens": 40010702.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.668841552734375,
|
|
"epoch": 1.7274614472123369,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047061931299838554,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20745955258607865,
|
|
"num_tokens": 40022897.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.647196674346924,
|
|
"epoch": 1.7279557137208381,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000470601874687025,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.20559781193733215,
|
|
"num_tokens": 40034057.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.6478251934051515,
|
|
"epoch": 1.7284499802293398,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004705844315638279,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20608331263065338,
|
|
"num_tokens": 40044595.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.707750654220581,
|
|
"epoch": 1.728944246737841,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004705669836292234,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20816718637943268,
|
|
"num_tokens": 40055175.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.649977445602417,
|
|
"epoch": 1.7294385132463423,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004705495308836408,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.21891654431819915,
|
|
"num_tokens": 40065276.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.629803657531738,
|
|
"epoch": 1.7299327797548438,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004705320733275094,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.20698062926530839,
|
|
"num_tokens": 40077230.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.604129838943481,
|
|
"epoch": 1.7304270462633453,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004705146109612587,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.21568826735019683,
|
|
"num_tokens": 40088058.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.614049863815308,
|
|
"epoch": 1.7309213127718466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004704971437853182,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.20856080204248428,
|
|
"num_tokens": 40099618.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.674321031570434,
|
|
"epoch": 1.7314155792803478,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004704796718001176,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.21308114677667617,
|
|
"num_tokens": 40111088.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.7032781600952145,
|
|
"epoch": 1.7319098457888493,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047046219500608685,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.20677350461483002,
|
|
"num_tokens": 40122191.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.658462190628052,
|
|
"epoch": 1.7324041122973508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004704447134036557,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.2004654586315155,
|
|
"num_tokens": 40133764.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.655054330825806,
|
|
"epoch": 1.732898378805852,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047042722699325426,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.2149028867483139,
|
|
"num_tokens": 40144502.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.672312068939209,
|
|
"epoch": 1.7333926453143536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004704097357753128,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.20919844955205918,
|
|
"num_tokens": 40155606.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.629111242294312,
|
|
"epoch": 1.733886911822855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004703922397502614,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.21528585106134415,
|
|
"num_tokens": 40166551.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.741749715805054,
|
|
"epoch": 1.7343811783313563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047037473891853066,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.2045356512069702,
|
|
"num_tokens": 40178804.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.734359979629517,
|
|
"epoch": 1.7348754448398576,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047035723328055104,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.2047872692346573,
|
|
"num_tokens": 40189861.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.598839855194091,
|
|
"epoch": 1.735369711348359,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004703397228367532,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.21437882333993913,
|
|
"num_tokens": 40202619.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.612798976898193,
|
|
"epoch": 1.7358639778568605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047032220758756786,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.20802510976791383,
|
|
"num_tokens": 40213509.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.749571704864502,
|
|
"epoch": 1.7363582443653618,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004703046875334259,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20393633991479873,
|
|
"num_tokens": 40224960.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.667768907546997,
|
|
"epoch": 1.736852510873863,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047028716267475827,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2124089166522026,
|
|
"num_tokens": 40238516.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.666321659088135,
|
|
"epoch": 1.7373467773823645,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004702696330119963,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.19746150821447372,
|
|
"num_tokens": 40249123.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.697678470611573,
|
|
"epoch": 1.737841043890866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004702520985455709,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.20866109877824784,
|
|
"num_tokens": 40260168.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.735371017456055,
|
|
"epoch": 1.7383353103993673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047023455927591365,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.1985086530447006,
|
|
"num_tokens": 40273183.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.732580518722534,
|
|
"epoch": 1.7388295769078688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047021701520345594,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.19703421741724014,
|
|
"num_tokens": 40284452.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.622721147537232,
|
|
"epoch": 1.7393238434163703,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047019946632862944,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.21686884760856628,
|
|
"num_tokens": 40295267.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.625744438171386,
|
|
"epoch": 1.7398181099248715,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047018191265186566,
|
|
"loss": 5.0246,
|
|
"mean_token_accuracy": 0.21649386882781982,
|
|
"num_tokens": 40306766.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.615519618988037,
|
|
"epoch": 1.7403123764333728,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047016435417359667,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.2139162912964821,
|
|
"num_tokens": 40317382.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.672899341583252,
|
|
"epoch": 1.7408066429418743,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047014679089425423,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.20881812572479247,
|
|
"num_tokens": 40328273.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.67209300994873,
|
|
"epoch": 1.7413009094503757,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047012922281427046,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.21254054754972457,
|
|
"num_tokens": 40340550.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.760096740722656,
|
|
"epoch": 1.741795175958877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047011164993407753,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.20809393525123596,
|
|
"num_tokens": 40351752.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.693745183944702,
|
|
"epoch": 1.7422894424673783,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047009407225410776,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.2133792981505394,
|
|
"num_tokens": 40363330.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.592019033432007,
|
|
"epoch": 1.7427837089758798,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004700764897747936,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.22014781534671785,
|
|
"num_tokens": 40375674.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.587862825393676,
|
|
"epoch": 1.7432779754843812,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004700589024965674,
|
|
"loss": 5.0817,
|
|
"mean_token_accuracy": 0.21200349926948547,
|
|
"num_tokens": 40387120.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.623182010650635,
|
|
"epoch": 1.7437722419928825,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000470041310419862,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.21184096187353135,
|
|
"num_tokens": 40399196.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.649652767181396,
|
|
"epoch": 1.744266508501384,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004700237135451101,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.20923746526241302,
|
|
"num_tokens": 40411693.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.5795012474060055,
|
|
"epoch": 1.7447607750098855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004700061118727446,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.22386847883462907,
|
|
"num_tokens": 40422866.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.638913345336914,
|
|
"epoch": 1.7452550415183867,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004699885054031985,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.2158359855413437,
|
|
"num_tokens": 40435028.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.765350103378296,
|
|
"epoch": 1.745749308026888,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000469970894136905,
|
|
"loss": 5.213,
|
|
"mean_token_accuracy": 0.2012006640434265,
|
|
"num_tokens": 40446802.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.738206434249878,
|
|
"epoch": 1.7462435745353895,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046995327807429715,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20412439852952957,
|
|
"num_tokens": 40459025.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.722213268280029,
|
|
"epoch": 1.746737841043891,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046993565721580846,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.2030934140086174,
|
|
"num_tokens": 40471486.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.648847579956055,
|
|
"epoch": 1.7472321075523922,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004699180315618723,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.21511089205741882,
|
|
"num_tokens": 40483163.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.663847589492798,
|
|
"epoch": 1.7477263740608935,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004699004011129224,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.20481970459222792,
|
|
"num_tokens": 40494475.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.585296869277954,
|
|
"epoch": 1.748220640569395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046988276586939234,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.20724357664585114,
|
|
"num_tokens": 40504557.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.604759979248047,
|
|
"epoch": 1.7487149070778965,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004698651258317161,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.21568395793437958,
|
|
"num_tokens": 40516147.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.648777341842651,
|
|
"epoch": 1.7492091735863977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004698474810003274,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.21715073734521867,
|
|
"num_tokens": 40527238.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.626388263702393,
|
|
"epoch": 1.7497034400948992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004698298313756605,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.21671604067087175,
|
|
"num_tokens": 40537470.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.587919998168945,
|
|
"epoch": 1.7501977066034007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046981217695814953,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.2120700001716614,
|
|
"num_tokens": 40549865.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.753800630569458,
|
|
"epoch": 1.750691973111902,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004697945177482287,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.20200977772474288,
|
|
"num_tokens": 40561796.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.62843918800354,
|
|
"epoch": 1.7511862396204032,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046977685374633267,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21289912313222886,
|
|
"num_tokens": 40574597.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.607509613037109,
|
|
"epoch": 1.7516805061289047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046975918495289576,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.208287712931633,
|
|
"num_tokens": 40586549.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.65007004737854,
|
|
"epoch": 1.7521747726374062,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004697415113683527,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.2141368493437767,
|
|
"num_tokens": 40597808.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.753819751739502,
|
|
"epoch": 1.7526690391459074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046972383299313813,
|
|
"loss": 5.2293,
|
|
"mean_token_accuracy": 0.20317718535661697,
|
|
"num_tokens": 40608636.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.698234367370605,
|
|
"epoch": 1.7531633056544087,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004697061498276872,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.21300453096628189,
|
|
"num_tokens": 40619099.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.613339519500732,
|
|
"epoch": 1.7536575721629104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046968846187243473,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.21581114530563356,
|
|
"num_tokens": 40630436.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.623360252380371,
|
|
"epoch": 1.7541518386714117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046967076912781585,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.214000104367733,
|
|
"num_tokens": 40643078.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.648283386230469,
|
|
"epoch": 1.754646105179913,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046965307159426594,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.21490106731653214,
|
|
"num_tokens": 40653368.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.696805191040039,
|
|
"epoch": 1.7551403716884144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004696353692722202,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.20477111786603927,
|
|
"num_tokens": 40665377.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.68713264465332,
|
|
"epoch": 1.755634638196916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004696176621621143,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.2039664715528488,
|
|
"num_tokens": 40676599.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.678651189804077,
|
|
"epoch": 1.7561289047054172,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004695999502643836,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2178881585597992,
|
|
"num_tokens": 40687619.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.601548099517823,
|
|
"epoch": 1.7566231712139184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046958223357946395,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.212350694835186,
|
|
"num_tokens": 40699410.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.675449085235596,
|
|
"epoch": 1.75711743772242,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046956451210779113,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.20249725729227067,
|
|
"num_tokens": 40711149.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.629410457611084,
|
|
"epoch": 1.7576117042309214,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046954678584980113,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.21644230037927628,
|
|
"num_tokens": 40722997.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.706714773178101,
|
|
"epoch": 1.7581059707394227,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046952905480593014,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.21086318641901017,
|
|
"num_tokens": 40733786.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.695956468582153,
|
|
"epoch": 1.758600237247924,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046951131897661415,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.2033226326107979,
|
|
"num_tokens": 40745925.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.708040761947632,
|
|
"epoch": 1.7590945037564256,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046949357836228946,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.20594883859157562,
|
|
"num_tokens": 40760031.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.700195169448852,
|
|
"epoch": 1.7595887702649269,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046947583296339266,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.20350323766469955,
|
|
"num_tokens": 40771557.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.671523094177246,
|
|
"epoch": 1.7600830367734281,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046945808278036017,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.19947529584169388,
|
|
"num_tokens": 40783557.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.63581657409668,
|
|
"epoch": 1.7605773032819296,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004694403278136287,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.2222442090511322,
|
|
"num_tokens": 40794213.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.576509952545166,
|
|
"epoch": 1.7610715697904311,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046942256806363497,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.21392759829759597,
|
|
"num_tokens": 40805753.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.6726405143737795,
|
|
"epoch": 1.7615658362989324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046940480353081587,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.2054623246192932,
|
|
"num_tokens": 40818315.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.622264337539673,
|
|
"epoch": 1.7620601028074336,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004693870342156085,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.22082468420267104,
|
|
"num_tokens": 40828740.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.655421781539917,
|
|
"epoch": 1.7625543693159351,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004693692601184499,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.20675967931747435,
|
|
"num_tokens": 40841035.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.63735990524292,
|
|
"epoch": 1.7630486358244366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004693514812397774,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.21401047557592393,
|
|
"num_tokens": 40851857.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.69184455871582,
|
|
"epoch": 1.7635429023329379,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004693336975800283,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.20845876932144164,
|
|
"num_tokens": 40863964.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.65182785987854,
|
|
"epoch": 1.7640371688414394,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046931590913964013,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.20619491040706633,
|
|
"num_tokens": 40876076.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.739889478683471,
|
|
"epoch": 1.7645314353499408,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046929811591905034,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.1992101103067398,
|
|
"num_tokens": 40887839.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.713456344604492,
|
|
"epoch": 1.765025701858442,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004692803179186968,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20356766134500504,
|
|
"num_tokens": 40898978.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.69292254447937,
|
|
"epoch": 1.7655199683669434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004692625151390173,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.20189989358186722,
|
|
"num_tokens": 40910990.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.591503429412842,
|
|
"epoch": 1.7660142348754448,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004692447075804498,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.2161649078130722,
|
|
"num_tokens": 40922299.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.696264266967773,
|
|
"epoch": 1.7665085013839463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004692268952434324,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20588785111904145,
|
|
"num_tokens": 40933181.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.611589956283569,
|
|
"epoch": 1.7670027678924476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004692090781284032,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.20883216410875322,
|
|
"num_tokens": 40944101.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.697702264785766,
|
|
"epoch": 1.7674970344009489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004691912562358006,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.21014407128095627,
|
|
"num_tokens": 40956492.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.731363964080811,
|
|
"epoch": 1.7679913009094503,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046917342956606287,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.1956345558166504,
|
|
"num_tokens": 40967477.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.712242889404297,
|
|
"epoch": 1.7684855674179518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004691555981196287,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.20822285264730453,
|
|
"num_tokens": 40978756.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.66987795829773,
|
|
"epoch": 1.768979833926453,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004691377618969367,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.2123330593109131,
|
|
"num_tokens": 40990583.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.638323640823364,
|
|
"epoch": 1.7694741004349546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046911992089842565,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.21144937425851823,
|
|
"num_tokens": 41002197.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.665036010742187,
|
|
"epoch": 1.769968366943456,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004691020751245344,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.21263960599899293,
|
|
"num_tokens": 41014038.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.62820782661438,
|
|
"epoch": 1.7704626334519573,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000469084224575702,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.20935010612010957,
|
|
"num_tokens": 41025752.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.636728000640869,
|
|
"epoch": 1.7709568999604586,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004690663692523676,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.21387508362531663,
|
|
"num_tokens": 41035974.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.610264301300049,
|
|
"epoch": 1.77145116646896,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046904850915497037,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.20988924205303192,
|
|
"num_tokens": 41047669.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.730341482162475,
|
|
"epoch": 1.7719454329774615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004690306442839497,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.2085108995437622,
|
|
"num_tokens": 41059123.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.623871517181397,
|
|
"epoch": 1.7724396994859628,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004690127746397451,
|
|
"loss": 5.021,
|
|
"mean_token_accuracy": 0.21862275153398514,
|
|
"num_tokens": 41070382.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.695683193206787,
|
|
"epoch": 1.772933965994464,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046899490022279613,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.21285253763198853,
|
|
"num_tokens": 41081672.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.72802209854126,
|
|
"epoch": 1.7734282325029656,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046897702103354256,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.2096857100725174,
|
|
"num_tokens": 41092448.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.636916017532348,
|
|
"epoch": 1.773922499011467,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046895913707242423,
|
|
"loss": 5.0515,
|
|
"mean_token_accuracy": 0.21069349050521852,
|
|
"num_tokens": 41103316.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.640654754638672,
|
|
"epoch": 1.7744167655199683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004689412483398809,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20944785177707673,
|
|
"num_tokens": 41114991.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.670011043548584,
|
|
"epoch": 1.7749110320284698,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046892335483635284,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.21132030189037324,
|
|
"num_tokens": 41126693.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.6659595489501955,
|
|
"epoch": 1.7754052985369713,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004689054565622801,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.2147381365299225,
|
|
"num_tokens": 41138344.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.6837821960449215,
|
|
"epoch": 1.7758995650454725,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004688875535181032,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.21175499856472016,
|
|
"num_tokens": 41148962.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.647116231918335,
|
|
"epoch": 1.7763938315539738,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046886964570426226,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.2142305552959442,
|
|
"num_tokens": 41159317.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.670513868331909,
|
|
"epoch": 1.7768880980624753,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004688517331211981,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.20428019016981125,
|
|
"num_tokens": 41170646.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.647905731201172,
|
|
"epoch": 1.7773823645709768,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004688338157693511,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.20303417593240738,
|
|
"num_tokens": 41182868.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.617476844787598,
|
|
"epoch": 1.777876631079478,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046881589364916224,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.21714070439338684,
|
|
"num_tokens": 41194556.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.679336261749268,
|
|
"epoch": 1.7783708975879793,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004687979667610722,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.21419524848461152,
|
|
"num_tokens": 41207082.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.632538890838623,
|
|
"epoch": 1.778865164096481,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046878003510552224,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.20656305253505708,
|
|
"num_tokens": 41217436.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.644659852981567,
|
|
"epoch": 1.7793594306049823,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004687620986829533,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.20409198999404907,
|
|
"num_tokens": 41228750.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.7793594306049823,
|
|
"eval_entropy": 5.398528424341594,
|
|
"eval_loss": 5.1234822273254395,
|
|
"eval_mean_token_accuracy": 0.21541109032479894,
|
|
"eval_num_tokens": 41228750.0,
|
|
"eval_runtime": 20.3532,
|
|
"eval_samples_per_second": 1597.438,
|
|
"eval_steps_per_second": 199.723,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.619972038269043,
|
|
"epoch": 1.7798536971134835,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046874415749380673,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20641662031412125,
|
|
"num_tokens": 41239110.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.656921625137329,
|
|
"epoch": 1.780347963621985,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004687262115385237,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.20713522434234619,
|
|
"num_tokens": 41251239.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.708002805709839,
|
|
"epoch": 1.7808422301304865,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000468708260817546,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20615365952253342,
|
|
"num_tokens": 41263996.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.755900859832764,
|
|
"epoch": 1.7813364966389877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046869030533131493,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.20020416826009751,
|
|
"num_tokens": 41277210.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.660686492919922,
|
|
"epoch": 1.781830763147489,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004686723450802723,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.20959217846393585,
|
|
"num_tokens": 41288383.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.680165863037109,
|
|
"epoch": 1.7823250296559905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046865438006486,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.21021731495857238,
|
|
"num_tokens": 41300970.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.714421796798706,
|
|
"epoch": 1.782819296164492,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046863641028551984,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.2023463323712349,
|
|
"num_tokens": 41312289.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.646983814239502,
|
|
"epoch": 1.7833135626729932,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046861843574269395,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.20712854713201523,
|
|
"num_tokens": 41323562.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.639797735214233,
|
|
"epoch": 1.7838078291814945,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004686004564368245,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.21321985125541687,
|
|
"num_tokens": 41335175.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.686874198913574,
|
|
"epoch": 1.7843020956899962,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004685824723683538,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.22085983157157899,
|
|
"num_tokens": 41346160.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.6651218891143795,
|
|
"epoch": 1.7847963621984975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004685644835377242,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.20220571607351304,
|
|
"num_tokens": 41358619.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.7042242050170895,
|
|
"epoch": 1.7852906287069987,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046854648994537835,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.21638378798961638,
|
|
"num_tokens": 41369034.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.724549245834351,
|
|
"epoch": 1.7857848952155002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004685284915917588,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20414988696575165,
|
|
"num_tokens": 41380700.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.7238470077514645,
|
|
"epoch": 1.7862791617240017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046851048847730835,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20223015993833543,
|
|
"num_tokens": 41391297.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.691427850723267,
|
|
"epoch": 1.786773428232503,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046849248060246986,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.1980604574084282,
|
|
"num_tokens": 41403418.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.732088994979859,
|
|
"epoch": 1.7872676947410042,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046847446796768633,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20373714864253997,
|
|
"num_tokens": 41414220.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.70937328338623,
|
|
"epoch": 1.7877619612495057,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004684564505734008,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.20973147749900817,
|
|
"num_tokens": 41425933.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.609308290481567,
|
|
"epoch": 1.7882562277580072,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046843842842005665,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.20762808471918107,
|
|
"num_tokens": 41438413.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.569616842269897,
|
|
"epoch": 1.7887504942665085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004684204015080971,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.21697589308023452,
|
|
"num_tokens": 41449104.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.7198670387268065,
|
|
"epoch": 1.78924476077501,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004684023698379657,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1962776228785515,
|
|
"num_tokens": 41460766.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.691362142562866,
|
|
"epoch": 1.7897390272835114,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004683843334101061,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1970644399523735,
|
|
"num_tokens": 41471872.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.7809295654296875,
|
|
"epoch": 1.7902332937920127,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046836629222496174,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20232977122068405,
|
|
"num_tokens": 41483313.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.6637216091156,
|
|
"epoch": 1.790727560300514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004683482462829766,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.22069765925407409,
|
|
"num_tokens": 41492935.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.6538292407989506,
|
|
"epoch": 1.7912218268090154,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004683301955845947,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.20581921935081482,
|
|
"num_tokens": 41504159.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.597244119644165,
|
|
"epoch": 1.791716093317517,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046831214013025996,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.21471045762300492,
|
|
"num_tokens": 41515812.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.614095306396484,
|
|
"epoch": 1.7922103598260182,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004682940799204165,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.2193346858024597,
|
|
"num_tokens": 41527109.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.645464658737183,
|
|
"epoch": 1.7927046263345194,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046827601495550884,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.20737663209438323,
|
|
"num_tokens": 41537183.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.59876594543457,
|
|
"epoch": 1.793198892843021,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004682579452359811,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.2135278046131134,
|
|
"num_tokens": 41548170.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.6358795166015625,
|
|
"epoch": 1.7936931593515224,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000468239870762278,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.2106996312737465,
|
|
"num_tokens": 41558737.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.627870178222656,
|
|
"epoch": 1.7941874258600237,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000468221791534844,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.22028255313634873,
|
|
"num_tokens": 41570096.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.58398814201355,
|
|
"epoch": 1.7946816923685251,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000468203707554124,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.21837358623743058,
|
|
"num_tokens": 41582670.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.623437404632568,
|
|
"epoch": 1.7951759588770266,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004681856188205629,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21855092346668242,
|
|
"num_tokens": 41594300.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.654846048355102,
|
|
"epoch": 1.795670225385528,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004681675253346055,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.2058259963989258,
|
|
"num_tokens": 41606021.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.640331983566284,
|
|
"epoch": 1.7961644918940292,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004681494270966971,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.2108217105269432,
|
|
"num_tokens": 41617338.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.667259693145752,
|
|
"epoch": 1.7966587584025306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004681313241072828,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.20493849664926528,
|
|
"num_tokens": 41628407.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.633599424362183,
|
|
"epoch": 1.7971530249110321,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046811321636680797,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20677267462015153,
|
|
"num_tokens": 41639715.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.669972658157349,
|
|
"epoch": 1.7976472914195334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046809510387571806,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.2038648396730423,
|
|
"num_tokens": 41651078.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.651202726364136,
|
|
"epoch": 1.7981415579280347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004680769866344586,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.20404215008020402,
|
|
"num_tokens": 41661848.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.69904932975769,
|
|
"epoch": 1.7986358244365361,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004680588646434753,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.20718342810869217,
|
|
"num_tokens": 41673452.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.768096446990967,
|
|
"epoch": 1.7991300909450376,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046804073790321403,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.19674696177244186,
|
|
"num_tokens": 41685312.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.702679252624511,
|
|
"epoch": 1.7996243574535389,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046802260641412065,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.21672191768884658,
|
|
"num_tokens": 41696849.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.666657114028931,
|
|
"epoch": 1.8001186239620404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004680044701766413,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.2149655893445015,
|
|
"num_tokens": 41707506.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.6841637134552006,
|
|
"epoch": 1.8006128904705418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004679863291912219,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.20634046345949172,
|
|
"num_tokens": 41718981.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.649560928344727,
|
|
"epoch": 1.8011071569790431,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004679681834583089,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.21213748008012773,
|
|
"num_tokens": 41731638.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.627702426910401,
|
|
"epoch": 1.8016014234875444,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046795003297834864,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.2168886497616768,
|
|
"num_tokens": 41742820.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.600376176834106,
|
|
"epoch": 1.8020956899960459,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046793187775178764,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.21241815388202667,
|
|
"num_tokens": 41754933.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.634930181503296,
|
|
"epoch": 1.8025899565045473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004679137177790725,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.2111673578619957,
|
|
"num_tokens": 41767078.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.717179965972901,
|
|
"epoch": 1.8030842230130486,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004678955530606501,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.2063719481229782,
|
|
"num_tokens": 41778456.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.6972301483154295,
|
|
"epoch": 1.8035784895215499,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046787738359696697,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.20796900391578674,
|
|
"num_tokens": 41791226.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.602676963806152,
|
|
"epoch": 1.8040727560300513,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004678592093884704,
|
|
"loss": 5.0815,
|
|
"mean_token_accuracy": 0.21542239636182786,
|
|
"num_tokens": 41803765.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.633065509796142,
|
|
"epoch": 1.8045670225385528,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046784103043560736,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.20697637796401977,
|
|
"num_tokens": 41815983.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.631524467468262,
|
|
"epoch": 1.805061289047054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046782284673882506,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.21816725879907609,
|
|
"num_tokens": 41826517.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.7214280128479,
|
|
"epoch": 1.8055555555555556,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004678046582985708,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.20802907943725585,
|
|
"num_tokens": 41837064.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.647922801971435,
|
|
"epoch": 1.806049822064057,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000467786465115292,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.21957465559244155,
|
|
"num_tokens": 41849109.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.6076662063598635,
|
|
"epoch": 1.8065440885725583,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004677682671894364,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.214617557823658,
|
|
"num_tokens": 41859349.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.604382133483886,
|
|
"epoch": 1.8070383550810596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046775006452145135,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.21474912017583847,
|
|
"num_tokens": 41870002.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.6977332592010494,
|
|
"epoch": 1.807532621589561,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004677318571117849,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2073204204440117,
|
|
"num_tokens": 41881219.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.648135805130005,
|
|
"epoch": 1.8080268880980626,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046771364496088475,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.20706505477428436,
|
|
"num_tokens": 41893318.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.597618150711059,
|
|
"epoch": 1.8085211546065638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046769542806919913,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21163022220134736,
|
|
"num_tokens": 41904816.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.6681619644165036,
|
|
"epoch": 1.809015421115065,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004676772064371761,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.21015404909849167,
|
|
"num_tokens": 41916293.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.660774803161621,
|
|
"epoch": 1.8095096876235668,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046765898006526384,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.21702121049165726,
|
|
"num_tokens": 41926654.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.609902286529541,
|
|
"epoch": 1.810003954132068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046764074895391084,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.2182338207960129,
|
|
"num_tokens": 41937141.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.677259874343872,
|
|
"epoch": 1.8104982206405693,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046762251310356544,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.20467861592769623,
|
|
"num_tokens": 41947793.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.720065116882324,
|
|
"epoch": 1.8109924871490708,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004676042725146764,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.2136449173092842,
|
|
"num_tokens": 41958524.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.724327087402344,
|
|
"epoch": 1.8114867536575723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046758602718769245,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.20790901333093642,
|
|
"num_tokens": 41969654.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.603501892089843,
|
|
"epoch": 1.8119810201660735,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046756777712306225,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.21563085168600082,
|
|
"num_tokens": 41980881.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.6918388366699215,
|
|
"epoch": 1.8124752866745748,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004675495223212349,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.20594278275966643,
|
|
"num_tokens": 41992490.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.611468935012818,
|
|
"epoch": 1.8129695531830763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004675312627826594,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.22332817167043686,
|
|
"num_tokens": 42001765.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.607533121109009,
|
|
"epoch": 1.8134638196915778,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000467512998507785,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.22148944884538652,
|
|
"num_tokens": 42013122.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.742270851135254,
|
|
"epoch": 1.813958086200079,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046749472949706095,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.20106256902217864,
|
|
"num_tokens": 42023369.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.697535467147827,
|
|
"epoch": 1.8144523527085805,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004674764557509367,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19476296454668046,
|
|
"num_tokens": 42036054.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.646026992797852,
|
|
"epoch": 1.814946619217082,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004674581772698618,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.21507660001516343,
|
|
"num_tokens": 42048782.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.753141736984253,
|
|
"epoch": 1.8154408857255833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046743989405428584,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20294524133205413,
|
|
"num_tokens": 42059438.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.723766183853149,
|
|
"epoch": 1.8159351522340845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004674216061046587,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.20595412850379943,
|
|
"num_tokens": 42070767.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.648732614517212,
|
|
"epoch": 1.816429418742586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004674033134214301,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.21555883139371873,
|
|
"num_tokens": 42081782.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.64431471824646,
|
|
"epoch": 1.8169236852510875,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046738501600505016,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.21295092552900313,
|
|
"num_tokens": 42094402.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.698344612121582,
|
|
"epoch": 1.8174179517595888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000467366713855969,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.20181578695774077,
|
|
"num_tokens": 42106772.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.640494728088379,
|
|
"epoch": 1.81791221826809,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046734840697463685,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.21103611290454866,
|
|
"num_tokens": 42118093.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.6636439800262455,
|
|
"epoch": 1.8184064847765915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046733009536150413,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.20538211315870286,
|
|
"num_tokens": 42130319.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.742032527923584,
|
|
"epoch": 1.818900751285093,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004673117790170211,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.2070443645119667,
|
|
"num_tokens": 42140867.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.659728145599365,
|
|
"epoch": 1.8193950177935942,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046729345794163847,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.2124830737709999,
|
|
"num_tokens": 42151425.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.745584630966187,
|
|
"epoch": 1.8198892843020957,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046727513213580703,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.20191754549741744,
|
|
"num_tokens": 42163553.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.6908916473388675,
|
|
"epoch": 1.8203835508105972,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004672568015999774,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.2024075135588646,
|
|
"num_tokens": 42174968.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.6862578868865965,
|
|
"epoch": 1.8208778173190985,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046723846633460074,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.20933155119419097,
|
|
"num_tokens": 42186944.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.701984071731568,
|
|
"epoch": 1.8213720838275997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046722012634012794,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.2146453857421875,
|
|
"num_tokens": 42198096.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.672878170013428,
|
|
"epoch": 1.8218663503361012,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046720178161701014,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.21260930001735687,
|
|
"num_tokens": 42208782.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.735586786270142,
|
|
"epoch": 1.8223606168446027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004671834321656988,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.203845776617527,
|
|
"num_tokens": 42219925.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.707551336288452,
|
|
"epoch": 1.822854883353104,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046716507798664515,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.21447705030441283,
|
|
"num_tokens": 42231140.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.682097339630127,
|
|
"epoch": 1.8233491498616052,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004671467190803008,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.20727866291999816,
|
|
"num_tokens": 42245025.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.673543071746826,
|
|
"epoch": 1.8238434163701067,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004671283554471174,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.21237177401781082,
|
|
"num_tokens": 42255776.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.6431496143341064,
|
|
"epoch": 1.8243376828786082,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004671099870875465,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.202709598839283,
|
|
"num_tokens": 42268016.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.63979024887085,
|
|
"epoch": 1.8248319493871095,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046709161400204034,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.20984735041856767,
|
|
"num_tokens": 42279521.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.689379596710205,
|
|
"epoch": 1.825326215895611,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046707323619105053,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.21190328449010848,
|
|
"num_tokens": 42290537.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.693030929565429,
|
|
"epoch": 1.8258204824041124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046705485365502926,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.2084565594792366,
|
|
"num_tokens": 42303119.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.714978313446045,
|
|
"epoch": 1.8263147489126137,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046703646639442893,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.21069758534431457,
|
|
"num_tokens": 42314408.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.608600902557373,
|
|
"epoch": 1.826809015421115,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004670180744097017,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.20977841168642045,
|
|
"num_tokens": 42325848.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.644067287445068,
|
|
"epoch": 1.8273032819296164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004669996777013,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20425011664628984,
|
|
"num_tokens": 42337737.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.62424373626709,
|
|
"epoch": 1.827797548438118,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046698127626967645,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.21595388948917388,
|
|
"num_tokens": 42348418.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.682272672653198,
|
|
"epoch": 1.8282918149466192,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004669628701152837,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.2056193083524704,
|
|
"num_tokens": 42358665.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.712541198730468,
|
|
"epoch": 1.8287860814551204,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004669444592385746,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.22162718325853348,
|
|
"num_tokens": 42369030.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.690653610229492,
|
|
"epoch": 1.829280347963622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046692604364000203,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.2087477758526802,
|
|
"num_tokens": 42380751.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.6611542224884035,
|
|
"epoch": 1.8297746144721234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000466907623320019,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.2123103231191635,
|
|
"num_tokens": 42391945.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.683928823471069,
|
|
"epoch": 1.8302688809806247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046688919827907866,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.21199633032083512,
|
|
"num_tokens": 42403346.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.663280296325683,
|
|
"epoch": 1.8307631474891262,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046687076851763433,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.20355056673288346,
|
|
"num_tokens": 42414895.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.585016107559204,
|
|
"epoch": 1.8312574139976276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046685233403613927,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.21453775763511657,
|
|
"num_tokens": 42426951.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.683774995803833,
|
|
"epoch": 1.831751680506129,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046683389483504704,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.20626916885375976,
|
|
"num_tokens": 42438313.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.660834121704101,
|
|
"epoch": 1.8322459470146302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004668154509148112,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.20189391821622849,
|
|
"num_tokens": 42448592.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.680676746368408,
|
|
"epoch": 1.8327402135231317,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046679700227588556,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.20891154408454896,
|
|
"num_tokens": 42460732.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.753837823867798,
|
|
"epoch": 1.8332344800316331,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046677854891872384,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.20590506345033646,
|
|
"num_tokens": 42472862.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.674390077590942,
|
|
"epoch": 1.8337287465401344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004667600908437802,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.21141985058784485,
|
|
"num_tokens": 42483227.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.562748289108276,
|
|
"epoch": 1.8342230130486357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046674162805150843,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.21885784715414047,
|
|
"num_tokens": 42495414.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.6233851432800295,
|
|
"epoch": 1.8347172795571374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046672316054236293,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20670584738254547,
|
|
"num_tokens": 42507908.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.6479075908660885,
|
|
"epoch": 1.8352115460656386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046670468831679795,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.21411996483802795,
|
|
"num_tokens": 42519228.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.62837438583374,
|
|
"epoch": 1.83570581257414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004666862113752679,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.2212498590350151,
|
|
"num_tokens": 42530571.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.64634256362915,
|
|
"epoch": 1.8362000790826414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004666677297182273,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.2108762666583061,
|
|
"num_tokens": 42541781.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.6804839134216305,
|
|
"epoch": 1.8366943455911429,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004666492433461308,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.2066209703683853,
|
|
"num_tokens": 42553912.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.581286811828614,
|
|
"epoch": 1.8371886120996441,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004666307522594332,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.22248194813728334,
|
|
"num_tokens": 42565812.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.690143775939942,
|
|
"epoch": 1.8376828786081454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004666122564585893,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.20642553567886351,
|
|
"num_tokens": 42578177.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.687804460525513,
|
|
"epoch": 1.8381771451166469,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046659375594405427,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.2093749925494194,
|
|
"num_tokens": 42590336.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.713276624679565,
|
|
"epoch": 1.8386714116251484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046657525071628307,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.2119036942720413,
|
|
"num_tokens": 42601438.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.682669544219971,
|
|
"epoch": 1.8391656781336496,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046655674077573104,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.20933985114097595,
|
|
"num_tokens": 42612572.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.68997745513916,
|
|
"epoch": 1.839659944642151,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046653822612285336,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.20551489889621735,
|
|
"num_tokens": 42623138.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.573974132537842,
|
|
"epoch": 1.8401542111506526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046651970675810574,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.21758416295051575,
|
|
"num_tokens": 42635694.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.769328355789185,
|
|
"epoch": 1.8406484776591538,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004665011826819435,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.2073890373110771,
|
|
"num_tokens": 42648371.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.7329682350158695,
|
|
"epoch": 1.841142744167655,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046648265389482245,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20499033480882645,
|
|
"num_tokens": 42659229.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.619436168670655,
|
|
"epoch": 1.8416370106761566,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004664641203971985,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21292126625776292,
|
|
"num_tokens": 42669991.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.5947949409484865,
|
|
"epoch": 1.842131277184658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046644558218952745,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.22172336876392365,
|
|
"num_tokens": 42681091.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.723900842666626,
|
|
"epoch": 1.8426255436931593,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046642703927226534,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21048497706651687,
|
|
"num_tokens": 42691928.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.624897480010986,
|
|
"epoch": 1.8431198102016606,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004664084916458684,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.2127312585711479,
|
|
"num_tokens": 42704611.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.703805923461914,
|
|
"epoch": 1.843614076710162,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004663899393107929,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.21215745955705642,
|
|
"num_tokens": 42715223.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.6283087730407715,
|
|
"epoch": 1.8441083432186636,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004663713822674952,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.21654389500617982,
|
|
"num_tokens": 42728177.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.714989519119262,
|
|
"epoch": 1.8446026097271648,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046635282051643166,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.20245061367750167,
|
|
"num_tokens": 42738469.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.670464706420899,
|
|
"epoch": 1.8450968762356663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004663342540580593,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.21813056021928787,
|
|
"num_tokens": 42749915.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.71905746459961,
|
|
"epoch": 1.8455911427441678,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004663156828928344,
|
|
"loss": 5.1913,
|
|
"mean_token_accuracy": 0.20410557836294174,
|
|
"num_tokens": 42762679.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.731445360183716,
|
|
"epoch": 1.846085409252669,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004662971070212141,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.20890237689018248,
|
|
"num_tokens": 42775351.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.6271484375,
|
|
"epoch": 1.8465796757611703,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046627852644365525,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.20446889102458954,
|
|
"num_tokens": 42785435.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.678062868118286,
|
|
"epoch": 1.8470739422696718,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046625994116061505,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.20561543405056,
|
|
"num_tokens": 42795737.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.727889204025269,
|
|
"epoch": 1.8475682087781733,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004662413511725506,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.2098218560218811,
|
|
"num_tokens": 42806965.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.758443355560303,
|
|
"epoch": 1.8480624752866746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004662227564799192,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.20551977604627608,
|
|
"num_tokens": 42818346.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.618659496307373,
|
|
"epoch": 1.8485567417951758,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046620415708317834,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.2123077318072319,
|
|
"num_tokens": 42829838.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.717202281951904,
|
|
"epoch": 1.8490510083036773,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004661855529827856,
|
|
"loss": 5.1133,
|
|
"mean_token_accuracy": 0.21368440687656404,
|
|
"num_tokens": 42841212.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.645507764816284,
|
|
"epoch": 1.8495452748121788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046616694417919854,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.2163360595703125,
|
|
"num_tokens": 42853237.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.677157402038574,
|
|
"epoch": 1.85003954132068,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046614833067287504,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2071099504828453,
|
|
"num_tokens": 42864000.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.640768146514892,
|
|
"epoch": 1.8505338078291815,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046612971246427293,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.21453907042741777,
|
|
"num_tokens": 42874491.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.711099433898926,
|
|
"epoch": 1.851028074337683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046611108955385024,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.19810796678066253,
|
|
"num_tokens": 42885947.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.67589259147644,
|
|
"epoch": 1.8515223408461843,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004660924619420651,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.20927983969449998,
|
|
"num_tokens": 42897907.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.706653642654419,
|
|
"epoch": 1.8520166073546855,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004660738296293758,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.21465561538934708,
|
|
"num_tokens": 42909332.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.7251753330230715,
|
|
"epoch": 1.852510873863187,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046605519261624055,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.2043725684285164,
|
|
"num_tokens": 42921877.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.6840111255645756,
|
|
"epoch": 1.8530051403716885,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046603655090311796,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.20783186107873916,
|
|
"num_tokens": 42933381.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.726399087905884,
|
|
"epoch": 1.8534994068801898,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004660179044904666,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.20757407397031785,
|
|
"num_tokens": 42944756.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.732462406158447,
|
|
"epoch": 1.853993673388691,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046599925337874516,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.20474471300840377,
|
|
"num_tokens": 42955587.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.723263168334961,
|
|
"epoch": 1.8544879398971925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046598059756841246,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.2011208638548851,
|
|
"num_tokens": 42966150.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.753491973876953,
|
|
"epoch": 1.854982206405694,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004659619370599274,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.20280486792325975,
|
|
"num_tokens": 42978626.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.647647953033447,
|
|
"epoch": 1.8554764729141953,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046594327185374906,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.2186964437365532,
|
|
"num_tokens": 42989194.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.5881565570831295,
|
|
"epoch": 1.8559707394226967,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046592460195033663,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.21590051651000977,
|
|
"num_tokens": 43000589.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.596229076385498,
|
|
"epoch": 1.8564650059311982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004659059273501494,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.21226726621389388,
|
|
"num_tokens": 43011417.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.722276401519776,
|
|
"epoch": 1.8569592724396995,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004658872480536467,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.20348242819309234,
|
|
"num_tokens": 43023178.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.669951963424682,
|
|
"epoch": 1.8574535389482008,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046586856406128805,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.20548654049634935,
|
|
"num_tokens": 43035526.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.645341157913208,
|
|
"epoch": 1.8579478054567022,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004658498753735332,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.21170220524072647,
|
|
"num_tokens": 43046681.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.64978928565979,
|
|
"epoch": 1.8584420719652037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046583118199084177,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.213667394220829,
|
|
"num_tokens": 43058514.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.754199457168579,
|
|
"epoch": 1.858936338473705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004658124839136737,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.20321195274591447,
|
|
"num_tokens": 43069588.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.628097152709961,
|
|
"epoch": 1.8594306049822062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004657937811424889,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.2169813558459282,
|
|
"num_tokens": 43080811.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.707952165603638,
|
|
"epoch": 1.859924871490708,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004657750736777474,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.20623973160982131,
|
|
"num_tokens": 43093506.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.630649757385254,
|
|
"epoch": 1.8604191379992092,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046575636151990955,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.21505729705095292,
|
|
"num_tokens": 43105272.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.670556449890137,
|
|
"epoch": 1.8609134045077105,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046573764466943565,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.20545314699411393,
|
|
"num_tokens": 43116070.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.693999195098877,
|
|
"epoch": 1.861407671016212,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046571892312678606,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.2077165052294731,
|
|
"num_tokens": 43126347.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.735908031463623,
|
|
"epoch": 1.8619019375247134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046570019689242136,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.20493605434894563,
|
|
"num_tokens": 43138752.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.727367496490478,
|
|
"epoch": 1.8623962040332147,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004656814659668023,
|
|
"loss": 5.2126,
|
|
"mean_token_accuracy": 0.19715943932533264,
|
|
"num_tokens": 43151283.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.693686485290527,
|
|
"epoch": 1.862890470541716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046566273035038953,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.20542320609092712,
|
|
"num_tokens": 43161643.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.7128297805786135,
|
|
"epoch": 1.8633847370502175,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046564399004364403,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.20885047316551208,
|
|
"num_tokens": 43171966.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.670362758636474,
|
|
"epoch": 1.863879003558719,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046562524504702683,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20976107120513915,
|
|
"num_tokens": 43183022.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.677827310562134,
|
|
"epoch": 1.8643732700672202,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046560649536099905,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.21197081059217454,
|
|
"num_tokens": 43194927.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.6254034519195555,
|
|
"epoch": 1.8648675365757215,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004655877409860218,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.22275920063257218,
|
|
"num_tokens": 43205519.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.6497483253479,
|
|
"epoch": 1.8653618030842232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046556898192255664,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.2044469192624092,
|
|
"num_tokens": 43217805.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.688298511505127,
|
|
"epoch": 1.8658560695927244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046555021817106494,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.21045214235782622,
|
|
"num_tokens": 43228394.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.648855304718017,
|
|
"epoch": 1.8663503361012257,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046553144973200835,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.207635036110878,
|
|
"num_tokens": 43240204.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.743233585357666,
|
|
"epoch": 1.8668446026097272,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004655126766058485,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.20078975558280945,
|
|
"num_tokens": 43251103.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.6239158630371096,
|
|
"epoch": 1.8673388691182287,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046549389879304724,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.21097054630517958,
|
|
"num_tokens": 43263653.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.647549724578857,
|
|
"epoch": 1.86783313562673,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004654751162940665,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.21010404974222183,
|
|
"num_tokens": 43274893.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.682525110244751,
|
|
"epoch": 1.8683274021352312,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004654563291093684,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.21507300436496735,
|
|
"num_tokens": 43287510.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.70900182723999,
|
|
"epoch": 1.8688216686437327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004654375372394151,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.2097422420978546,
|
|
"num_tokens": 43299735.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.667336940765381,
|
|
"epoch": 1.8693159351522342,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046541874068466876,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.22059192806482314,
|
|
"num_tokens": 43310401.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.646292114257813,
|
|
"epoch": 1.8698102016607354,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046539993944559187,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.20787734240293504,
|
|
"num_tokens": 43321300.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.675187683105468,
|
|
"epoch": 1.870304468169237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000465381133522647,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.2056933343410492,
|
|
"num_tokens": 43332304.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.667923498153686,
|
|
"epoch": 1.8707987346777384,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004653623229162966,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.20950131118297577,
|
|
"num_tokens": 43343524.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.736526155471802,
|
|
"epoch": 1.8712930011862396,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046534350762700354,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.20072523653507232,
|
|
"num_tokens": 43353364.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.607144165039062,
|
|
"epoch": 1.871787267694741,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046532468765523075,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.22626175582408906,
|
|
"num_tokens": 43365660.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.727998828887939,
|
|
"epoch": 1.8722815342032424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046530586300144104,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.20110541135072707,
|
|
"num_tokens": 43376882.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.733039236068725,
|
|
"epoch": 1.8727758007117439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046528703366609757,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.21589444279670716,
|
|
"num_tokens": 43387872.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.69018440246582,
|
|
"epoch": 1.8732700672202451,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046526819964966363,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.20127278566360474,
|
|
"num_tokens": 43399162.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.686466264724731,
|
|
"epoch": 1.8737643337287464,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004652493609526024,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.20425163060426713,
|
|
"num_tokens": 43410163.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.694472455978394,
|
|
"epoch": 1.8742586002372479,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004652305175753774,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.20962063521146773,
|
|
"num_tokens": 43421841.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.668279075622559,
|
|
"epoch": 1.8747528667457494,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004652116695184521,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.21796718686819078,
|
|
"num_tokens": 43432301.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.720820426940918,
|
|
"epoch": 1.8752471332542506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004651928167822903,
|
|
"loss": 5.1307,
|
|
"mean_token_accuracy": 0.20666277259588242,
|
|
"num_tokens": 43443531.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.6045839309692385,
|
|
"epoch": 1.8757413997627521,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004651739593673556,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.2153189867734909,
|
|
"num_tokens": 43455230.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.660484170913696,
|
|
"epoch": 1.8762356662712536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004651550972741121,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.20317342877388,
|
|
"num_tokens": 43466342.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.746299123764038,
|
|
"epoch": 1.8767299327797549,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004651362305030237,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.2019016295671463,
|
|
"num_tokens": 43477962.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.6754625797271725,
|
|
"epoch": 1.8772241992882561,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004651173590545545,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.21061961650848388,
|
|
"num_tokens": 43489252.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.717046117782592,
|
|
"epoch": 1.8777184657967576,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046509848292916877,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.21066354662179948,
|
|
"num_tokens": 43499199.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.639778137207031,
|
|
"epoch": 1.878212732305259,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046507960212733093,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.21050257235765457,
|
|
"num_tokens": 43509812.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.597118711471557,
|
|
"epoch": 1.8787069988137604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046506071664950525,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.21797249764204024,
|
|
"num_tokens": 43521197.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.661090135574341,
|
|
"epoch": 1.8792012653222616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046504182649615664,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.21047366857528688,
|
|
"num_tokens": 43532826.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.712927722930909,
|
|
"epoch": 1.879695531830763,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046502293166774945,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.2056758314371109,
|
|
"num_tokens": 43544617.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.634462213516235,
|
|
"epoch": 1.8801897983392646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004650040321647487,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.22194693684577943,
|
|
"num_tokens": 43556006.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.6871318340301515,
|
|
"epoch": 1.8806840648477658,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004649851279876193,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.20988253206014634,
|
|
"num_tokens": 43567112.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.664251804351807,
|
|
"epoch": 1.8811783313562673,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004649662191368263,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.2093808352947235,
|
|
"num_tokens": 43577974.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.665540027618408,
|
|
"epoch": 1.8816725978647688,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004649473056128349,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.21900418996810914,
|
|
"num_tokens": 43588723.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.626137781143188,
|
|
"epoch": 1.88216686437327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004649283874161102,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21326005905866624,
|
|
"num_tokens": 43599721.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.712900447845459,
|
|
"epoch": 1.8826611308817713,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004649094645471177,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.2057558164000511,
|
|
"num_tokens": 43610517.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.737541532516479,
|
|
"epoch": 1.8831553973902728,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000464890537006323,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20508439391851424,
|
|
"num_tokens": 43622547.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.693411493301392,
|
|
"epoch": 1.8836496638987743,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004648716047941916,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.21420089304447174,
|
|
"num_tokens": 43633982.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.6360736846923825,
|
|
"epoch": 1.8841439304072756,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004648526679111892,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.21348488479852676,
|
|
"num_tokens": 43644888.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.679431056976318,
|
|
"epoch": 1.8846381969157768,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004648337263577818,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.21413121223449708,
|
|
"num_tokens": 43658352.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.6082830905914305,
|
|
"epoch": 1.8851324634242785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046481478013443527,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.2179081454873085,
|
|
"num_tokens": 43669127.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.658367443084717,
|
|
"epoch": 1.8856267299327798,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004647958292416157,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.20512932389974595,
|
|
"num_tokens": 43681504.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.615700578689575,
|
|
"epoch": 1.886120996441281,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004647768736797893,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21081313192844392,
|
|
"num_tokens": 43691396.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.687401819229126,
|
|
"epoch": 1.8866152629497825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046475791344942227,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.21826142072677612,
|
|
"num_tokens": 43703761.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.59323468208313,
|
|
"epoch": 1.887109529458284,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004647389485509812,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.21681876480579376,
|
|
"num_tokens": 43715041.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.695031070709229,
|
|
"epoch": 1.8876037959667853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046471997898493256,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.21198707222938537,
|
|
"num_tokens": 43727060.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.732418203353882,
|
|
"epoch": 1.8880980624752866,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000464701004751743,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.19494557827711106,
|
|
"num_tokens": 43738996.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.644916248321533,
|
|
"epoch": 1.888592328983788,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004646820258518793,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.20847886353731154,
|
|
"num_tokens": 43749415.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.607260894775391,
|
|
"epoch": 1.8890865954922895,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004646630422858083,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.21629607379436494,
|
|
"num_tokens": 43760289.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.660447072982788,
|
|
"epoch": 1.8895808620007908,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046464405405399707,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.21193965077400206,
|
|
"num_tokens": 43771267.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.76099591255188,
|
|
"epoch": 1.890075128509292,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046462506115691274,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.21535208076238632,
|
|
"num_tokens": 43782584.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.7470824241638185,
|
|
"epoch": 1.8905693950177938,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046460606359502237,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.2005769982933998,
|
|
"num_tokens": 43792738.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.700738906860352,
|
|
"epoch": 1.891063661526295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046458706136879354,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.2060956433415413,
|
|
"num_tokens": 43804117.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.731679773330688,
|
|
"epoch": 1.8915579280347963,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004645680544786935,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.20526464581489562,
|
|
"num_tokens": 43817367.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.706391668319702,
|
|
"epoch": 1.8920521945432978,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046454904292518996,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.20857953429222106,
|
|
"num_tokens": 43829213.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.71097617149353,
|
|
"epoch": 1.8925464610517992,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046453002670875055,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.2123314321041107,
|
|
"num_tokens": 43839939.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.682505369186401,
|
|
"epoch": 1.8930407275603005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046451100582984304,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.2108540266752243,
|
|
"num_tokens": 43850411.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.638715410232544,
|
|
"epoch": 1.8935349940688018,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004644919802889354,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.2089805856347084,
|
|
"num_tokens": 43861083.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.703421497344971,
|
|
"epoch": 1.8940292605773033,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046447295008649576,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.2118675008416176,
|
|
"num_tokens": 43871712.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.726370429992675,
|
|
"epoch": 1.8945235270858047,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046445391522299204,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.20526842176914215,
|
|
"num_tokens": 43884617.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.692189741134643,
|
|
"epoch": 1.895017793594306,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046443487569889264,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.20939402431249618,
|
|
"num_tokens": 43895533.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.695067405700684,
|
|
"epoch": 1.8955120601028075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046441583151466586,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.20937955379486084,
|
|
"num_tokens": 43906616.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.680488014221192,
|
|
"epoch": 1.896006326611309,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004643967826707803,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.20724994242191314,
|
|
"num_tokens": 43917389.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.704345798492431,
|
|
"epoch": 1.8965005931198102,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004643777291677045,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.20357723981142045,
|
|
"num_tokens": 43929239.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.740085697174072,
|
|
"epoch": 1.8969948596283115,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004643586710059072,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.20771940499544145,
|
|
"num_tokens": 43940267.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.736715984344483,
|
|
"epoch": 1.897489126136813,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046433960818585717,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.21107553243637084,
|
|
"num_tokens": 43951505.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.642372989654541,
|
|
"epoch": 1.8979833926453145,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046432054070802344,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.212712599337101,
|
|
"num_tokens": 43963669.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.601884126663208,
|
|
"epoch": 1.8984776591538157,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046430146857287497,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.20959969758987426,
|
|
"num_tokens": 43975814.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.6599733352661135,
|
|
"epoch": 1.898971925662317,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046428239178088106,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.2105650171637535,
|
|
"num_tokens": 43987305.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.738140678405761,
|
|
"epoch": 1.8994661921708185,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046426331033251096,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.2130837097764015,
|
|
"num_tokens": 43997441.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.692752265930176,
|
|
"epoch": 1.89996045867932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000464244224228234,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.2100005105137825,
|
|
"num_tokens": 44008718.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.717325687408447,
|
|
"epoch": 1.9004547251878212,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004642251334685199,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.20597219169139863,
|
|
"num_tokens": 44020785.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.64970178604126,
|
|
"epoch": 1.9009489916963227,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046420603805383796,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.21422152668237687,
|
|
"num_tokens": 44031360.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.61028528213501,
|
|
"epoch": 1.9014432582048242,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004641869379846583,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.21404157131910323,
|
|
"num_tokens": 44042510.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.6772873878479,
|
|
"epoch": 1.9019375247133254,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046416783326145065,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.20663723796606065,
|
|
"num_tokens": 44053800.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.632011795043946,
|
|
"epoch": 1.9024317912218267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004641487238846848,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.21318674385547637,
|
|
"num_tokens": 44066727.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.725325632095337,
|
|
"epoch": 1.9029260577303282,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046412960985483105,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.20868173390626907,
|
|
"num_tokens": 44077863.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.634517002105713,
|
|
"epoch": 1.9034203242388297,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004641104911723596,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.22312018126249314,
|
|
"num_tokens": 44088218.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.7625572204589846,
|
|
"epoch": 1.903914590747331,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004640913678377407,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.20671885460615158,
|
|
"num_tokens": 44101236.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.645348453521729,
|
|
"epoch": 1.9044088572558322,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004640722398514448,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.20331116020679474,
|
|
"num_tokens": 44114185.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.616189813613891,
|
|
"epoch": 1.9049031237643337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046405310721394245,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.21146998554468155,
|
|
"num_tokens": 44126060.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.645000743865967,
|
|
"epoch": 1.9053973902728352,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004640339699257044,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.20700879842042924,
|
|
"num_tokens": 44137709.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.684008264541626,
|
|
"epoch": 1.9058916567813364,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004640148279872013,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.20947224646806717,
|
|
"num_tokens": 44150042.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.704849433898926,
|
|
"epoch": 1.906385923289838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046399568139890413,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.20950379073619843,
|
|
"num_tokens": 44162926.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.669223260879517,
|
|
"epoch": 1.9068801897983394,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046397653016128396,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.2183774784207344,
|
|
"num_tokens": 44174211.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.693739604949951,
|
|
"epoch": 1.9073744563068407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004639573742748117,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.20011069476604462,
|
|
"num_tokens": 44187127.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.69809193611145,
|
|
"epoch": 1.907868722815342,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046393821373995884,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.20746659785509108,
|
|
"num_tokens": 44199335.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.679566669464111,
|
|
"epoch": 1.9083629893238434,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046391904855719654,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.22081664502620696,
|
|
"num_tokens": 44209911.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.617990875244141,
|
|
"epoch": 1.908857255832345,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046389987872699637,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.2125635489821434,
|
|
"num_tokens": 44221391.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.663299655914306,
|
|
"epoch": 1.9093515223408462,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046388070424982985,
|
|
"loss": 5.0056,
|
|
"mean_token_accuracy": 0.21765938103199006,
|
|
"num_tokens": 44233138.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.632749366760254,
|
|
"epoch": 1.9098457888493474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004638615251261687,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.21378488689661027,
|
|
"num_tokens": 44244353.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.654253339767456,
|
|
"epoch": 1.910340055357849,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046384234135648475,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.21243773698806762,
|
|
"num_tokens": 44256369.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.684258985519409,
|
|
"epoch": 1.9108343218663504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046382315294124987,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.2088148906826973,
|
|
"num_tokens": 44267958.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.662553930282593,
|
|
"epoch": 1.9113285883748516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004638039598809361,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.21262696832418443,
|
|
"num_tokens": 44279379.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.684934425354004,
|
|
"epoch": 1.9118228548833531,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004637847621760158,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.20224137455224991,
|
|
"num_tokens": 44289655.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.702928972244263,
|
|
"epoch": 1.9123171213918546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046376555982696093,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.20320838838815689,
|
|
"num_tokens": 44301642.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.693377733230591,
|
|
"epoch": 1.9128113879003559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000463746352834244,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.21081688553094863,
|
|
"num_tokens": 44313260.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.705210256576538,
|
|
"epoch": 1.9133056544088571,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004637271411983375,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.2054166615009308,
|
|
"num_tokens": 44325095.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.714215850830078,
|
|
"epoch": 1.9137999209173586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004637079249197141,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.21049583405256272,
|
|
"num_tokens": 44337381.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.6326840877532955,
|
|
"epoch": 1.91429418742586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046368870399884644,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.2196684643626213,
|
|
"num_tokens": 44348487.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.629173707962036,
|
|
"epoch": 1.9147884539343614,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046366947843620737,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21763797253370284,
|
|
"num_tokens": 44358645.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.639835262298584,
|
|
"epoch": 1.9152827204428626,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046365024823226994,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.21895799934864044,
|
|
"num_tokens": 44369924.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.66423659324646,
|
|
"epoch": 1.9157769869513643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004636310133875071,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.207999187707901,
|
|
"num_tokens": 44381684.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.783979892730713,
|
|
"epoch": 1.9162712534598656,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046361177390239204,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.20840117931365967,
|
|
"num_tokens": 44392780.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.70192928314209,
|
|
"epoch": 1.9167655199683669,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004635925297773981,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.20830187052488328,
|
|
"num_tokens": 44405330.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.751723098754883,
|
|
"epoch": 1.9172597864768683,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004635732810129987,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.20631644874811172,
|
|
"num_tokens": 44416307.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.718960618972778,
|
|
"epoch": 1.9177540529853698,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004635540276096673,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.20598903000354768,
|
|
"num_tokens": 44427481.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.610868692398071,
|
|
"epoch": 1.918248319493871,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046353476956787756,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.210893614590168,
|
|
"num_tokens": 44439462.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.680583047866821,
|
|
"epoch": 1.9187425860023724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046351550688810317,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.19955495297908782,
|
|
"num_tokens": 44452206.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.684795331954956,
|
|
"epoch": 1.9192368525108738,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004634962395708182,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.21292051523923874,
|
|
"num_tokens": 44463598.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.673813819885254,
|
|
"epoch": 1.9197311190193753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046347696761649647,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.21660065948963164,
|
|
"num_tokens": 44475606.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.677433204650879,
|
|
"epoch": 1.9202253855278766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000463457691025612,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21167315393686295,
|
|
"num_tokens": 44486948.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.664252758026123,
|
|
"epoch": 1.920719652036378,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046343840979863924,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.213105608522892,
|
|
"num_tokens": 44497408.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.691071081161499,
|
|
"epoch": 1.9212139185448796,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046341912393605225,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.21340717673301696,
|
|
"num_tokens": 44508246.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.594927072525024,
|
|
"epoch": 1.9217081850533808,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004633998334383256,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.21737001687288285,
|
|
"num_tokens": 44520207.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.617666530609131,
|
|
"epoch": 1.922202451561882,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046338053830593384,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.2099496081471443,
|
|
"num_tokens": 44532290.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.692508745193481,
|
|
"epoch": 1.9226967180703836,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004633612385393516,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.20503664761781693,
|
|
"num_tokens": 44544305.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.727007341384888,
|
|
"epoch": 1.923190984578885,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004633419341390537,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.20423349887132644,
|
|
"num_tokens": 44556753.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.733944320678711,
|
|
"epoch": 1.9236852510873863,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000463322625105515,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.2058223381638527,
|
|
"num_tokens": 44567891.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.625531530380249,
|
|
"epoch": 1.9241795175958876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046330331143921045,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.21764454245567322,
|
|
"num_tokens": 44579060.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.648665809631348,
|
|
"epoch": 1.924673784104389,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046328399314061525,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.20786665230989457,
|
|
"num_tokens": 44591748.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.637337875366211,
|
|
"epoch": 1.9251680506128905,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004632646702102046,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.21572076082229613,
|
|
"num_tokens": 44603119.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.71359167098999,
|
|
"epoch": 1.9256623171213918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004632453426484539,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.20505762547254563,
|
|
"num_tokens": 44614391.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.662940645217896,
|
|
"epoch": 1.9261565836298933,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046322601045583863,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.22655795216560365,
|
|
"num_tokens": 44623950.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.595674800872803,
|
|
"epoch": 1.9266508501383948,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004632066736328342,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.2162592738866806,
|
|
"num_tokens": 44635177.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.647982835769653,
|
|
"epoch": 1.927145116646896,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004631873321799164,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.20417763888835908,
|
|
"num_tokens": 44646956.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.7257688522338865,
|
|
"epoch": 1.9276393831553973,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000463167986097561,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.20673205554485322,
|
|
"num_tokens": 44658161.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.634237957000733,
|
|
"epoch": 1.9281336496638988,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046314863538624403,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.211244098842144,
|
|
"num_tokens": 44668823.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.668633222579956,
|
|
"epoch": 1.9286279161724003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004631292800464414,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.20400732457637788,
|
|
"num_tokens": 44682285.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.718524360656739,
|
|
"epoch": 1.9291221826809015,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046310992007862935,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.2118973910808563,
|
|
"num_tokens": 44694031.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.7160358905792235,
|
|
"epoch": 1.9296164491894028,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000463090555483284,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19992041438817978,
|
|
"num_tokens": 44705636.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.6998950958251955,
|
|
"epoch": 1.9301107156979043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046307118626088184,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.20581164807081223,
|
|
"num_tokens": 44716505.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.679389142990113,
|
|
"epoch": 1.9306049822064058,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004630518124118994,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.20373042970895766,
|
|
"num_tokens": 44729298.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.687943172454834,
|
|
"epoch": 1.931099248714907,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046303243393681307,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20766262114048004,
|
|
"num_tokens": 44740456.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.6990865707397464,
|
|
"epoch": 1.9315935152234085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046301305083609973,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.2128683879971504,
|
|
"num_tokens": 44752311.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.741177177429199,
|
|
"epoch": 1.93208778173191,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046299366311023624,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.21049036532640458,
|
|
"num_tokens": 44763704.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.599278593063355,
|
|
"epoch": 1.9325820482404112,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004629742707596994,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.21324600130319596,
|
|
"num_tokens": 44775053.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.730816888809204,
|
|
"epoch": 1.9330763147489125,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046295487378496643,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.20553179383277892,
|
|
"num_tokens": 44786734.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.793850040435791,
|
|
"epoch": 1.933570581257414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046293547218651427,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.20321713536977767,
|
|
"num_tokens": 44798151.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.774808168411255,
|
|
"epoch": 1.9340648477659155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004629160659648204,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.20468598157167434,
|
|
"num_tokens": 44809354.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.692269134521484,
|
|
"epoch": 1.9345591142744167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004628966551203622,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.20411922186613082,
|
|
"num_tokens": 44820994.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.723905992507935,
|
|
"epoch": 1.935053380782918,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046287723965361704,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20268217474222183,
|
|
"num_tokens": 44831486.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.698728942871094,
|
|
"epoch": 1.9355476472914195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004628578195650628,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.20683349967002868,
|
|
"num_tokens": 44844078.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.684786987304688,
|
|
"epoch": 1.936041913799921,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004628383948551769,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.21099505722522735,
|
|
"num_tokens": 44854722.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.664245510101319,
|
|
"epoch": 1.9365361803084222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004628189655244374,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.21270087957382203,
|
|
"num_tokens": 44866337.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.684649133682251,
|
|
"epoch": 1.9370304468169237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004627995315733222,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.20877359807491302,
|
|
"num_tokens": 44878686.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.737878656387329,
|
|
"epoch": 1.9375247133254252,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046278009300230945,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.205269156396389,
|
|
"num_tokens": 44890339.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.784648418426514,
|
|
"epoch": 1.9380189798339265,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004627606498118772,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.20276453346014023,
|
|
"num_tokens": 44902850.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.698237037658691,
|
|
"epoch": 1.9385132463424277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004627412020025039,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21372692584991454,
|
|
"num_tokens": 44914074.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.681797361373901,
|
|
"epoch": 1.9390075128509292,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046272174957466783,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20468156784772873,
|
|
"num_tokens": 44925665.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.730733251571655,
|
|
"epoch": 1.9395017793594307,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004627022925288476,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.2086543157696724,
|
|
"num_tokens": 44936584.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.721788167953491,
|
|
"epoch": 1.939996045867932,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004626828308655219,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.21123915463685988,
|
|
"num_tokens": 44948028.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.627474021911621,
|
|
"epoch": 1.9404903123764332,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046266336458516944,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.21668111085891723,
|
|
"num_tokens": 44959504.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.700573062896728,
|
|
"epoch": 1.940984578884935,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004626438936882691,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.20337452590465546,
|
|
"num_tokens": 44971518.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.629780435562134,
|
|
"epoch": 1.9414788453934362,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046262441817529986,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.2161898598074913,
|
|
"num_tokens": 44982514.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.66630334854126,
|
|
"epoch": 1.9419731119019374,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004626049380467408,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.2151340886950493,
|
|
"num_tokens": 44995198.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.6823629379272464,
|
|
"epoch": 1.942467378410439,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046258545330307124,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.21198004633188247,
|
|
"num_tokens": 45008014.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.680368804931641,
|
|
"epoch": 1.9429616449189404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046256596394477037,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.21359759867191314,
|
|
"num_tokens": 45021169.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.616708564758301,
|
|
"epoch": 1.9434559114274417,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004625464699723177,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.21741574257612228,
|
|
"num_tokens": 45032703.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.6466916561126705,
|
|
"epoch": 1.943950177935943,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004625269713861928,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.21517076194286347,
|
|
"num_tokens": 45044350.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.63430118560791,
|
|
"epoch": 1.9444444444444444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004625074681868753,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.21960160583257676,
|
|
"num_tokens": 45055431.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.681087589263916,
|
|
"epoch": 1.944938710952946,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004624879603748449,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.21286606192588806,
|
|
"num_tokens": 45066801.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.68479642868042,
|
|
"epoch": 1.9454329774614472,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004624684479505817,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.21071429997682573,
|
|
"num_tokens": 45078393.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.6733513355255125,
|
|
"epoch": 1.9459272439699487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004624489309145655,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.2098941206932068,
|
|
"num_tokens": 45090782.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.66185188293457,
|
|
"epoch": 1.9464215104784501,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004624294092672766,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.21607912033796312,
|
|
"num_tokens": 45102079.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.679739761352539,
|
|
"epoch": 1.9469157769869514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004624098830091951,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.22185704559087754,
|
|
"num_tokens": 45112947.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.65932035446167,
|
|
"epoch": 1.9474100434954527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046239035214080146,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.2126736208796501,
|
|
"num_tokens": 45124577.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.676351928710938,
|
|
"epoch": 1.9479043100039541,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004623708166625761,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.2064724400639534,
|
|
"num_tokens": 45135380.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.682094097137451,
|
|
"epoch": 1.9483985765124556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046235127657499945,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.21444472372531892,
|
|
"num_tokens": 45146926.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.63593020439148,
|
|
"epoch": 1.9488928430209569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004623317318785524,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.21371901631355286,
|
|
"num_tokens": 45157662.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.615749979019165,
|
|
"epoch": 1.9493871095294582,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004623121825737158,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.22583201974630357,
|
|
"num_tokens": 45170239.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.68398003578186,
|
|
"epoch": 1.9498813760379596,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046229262866097034,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.20932283848524094,
|
|
"num_tokens": 45180979.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.671893215179443,
|
|
"epoch": 1.9503756425464611,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004622730701407971,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.21492246687412261,
|
|
"num_tokens": 45191160.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.713716602325439,
|
|
"epoch": 1.9508699090549624,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004622535070136774,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.2163281410932541,
|
|
"num_tokens": 45202865.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.699842834472657,
|
|
"epoch": 1.9513641755634639,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046223393928009233,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.2081285908818245,
|
|
"num_tokens": 45214831.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.720073223114014,
|
|
"epoch": 1.9518584420719653,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046221436694052334,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.21235942095518112,
|
|
"num_tokens": 45226453.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.746190977096558,
|
|
"epoch": 1.9523527085804666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046219478999545184,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20575287640094758,
|
|
"num_tokens": 45237292.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.61804313659668,
|
|
"epoch": 1.9528469750889679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004621752084453595,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.21989146620035172,
|
|
"num_tokens": 45248117.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.662950563430786,
|
|
"epoch": 1.9533412415974694,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046215562229072796,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.20973715037107468,
|
|
"num_tokens": 45259120.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.680405616760254,
|
|
"epoch": 1.9538355081059708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046213603153203906,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.2170260354876518,
|
|
"num_tokens": 45269554.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.722486114501953,
|
|
"epoch": 1.954329774614472,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004621164361697748,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.20569131821393966,
|
|
"num_tokens": 45281055.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.646415758132934,
|
|
"epoch": 1.9548240411229734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004620968362044172,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2262939989566803,
|
|
"num_tokens": 45292430.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.61851282119751,
|
|
"epoch": 1.9553183076314749,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004620772316364483,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.21423889994621276,
|
|
"num_tokens": 45303417.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.696473598480225,
|
|
"epoch": 1.9558125741399763,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004620576224663506,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.20053399950265885,
|
|
"num_tokens": 45315243.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.64463176727295,
|
|
"epoch": 1.9563068406484776,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004620380086946063,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.2126850888133049,
|
|
"num_tokens": 45326746.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.65802412033081,
|
|
"epoch": 1.956801107156979,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046201839032169794,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21757504492998123,
|
|
"num_tokens": 45338199.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.6959484100341795,
|
|
"epoch": 1.9572953736654806,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004619987673481082,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.21169678270816802,
|
|
"num_tokens": 45349470.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.683187961578369,
|
|
"epoch": 1.9577896401739818,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046197913977431983,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.20765256136655807,
|
|
"num_tokens": 45359735.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.780264663696289,
|
|
"epoch": 1.958283906682483,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046195950760081556,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.20113771557807922,
|
|
"num_tokens": 45372960.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.730033254623413,
|
|
"epoch": 1.9587781731909846,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004619398708280784,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.2100844293832779,
|
|
"num_tokens": 45385174.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.655494117736817,
|
|
"epoch": 1.959272439699486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004619202294565914,
|
|
"loss": 5.0438,
|
|
"mean_token_accuracy": 0.21626523286104202,
|
|
"num_tokens": 45397013.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.7842559814453125,
|
|
"epoch": 1.9597667062079873,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004619005834868378,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.20158746987581252,
|
|
"num_tokens": 45408863.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.690006399154663,
|
|
"epoch": 1.9602609727164886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004618809329193008,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.21453148126602173,
|
|
"num_tokens": 45420630.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.709689950942993,
|
|
"epoch": 1.96075523922499,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004618612777544639,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21256063580513002,
|
|
"num_tokens": 45431427.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.703120851516724,
|
|
"epoch": 1.9612495057334915,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046184161799281057,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.21591157019138335,
|
|
"num_tokens": 45442649.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.649590539932251,
|
|
"epoch": 1.9617437722419928,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046182195363482444,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.21168902963399888,
|
|
"num_tokens": 45454032.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.655920886993409,
|
|
"epoch": 1.9622380387504943,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046180228468098927,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.20449686497449876,
|
|
"num_tokens": 45464706.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.789444208145142,
|
|
"epoch": 1.9627323052589958,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046178261113178894,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.1988048180937767,
|
|
"num_tokens": 45476292.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.649269104003906,
|
|
"epoch": 1.963226571767497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004617629329877074,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.22186920940876007,
|
|
"num_tokens": 45488189.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.717531967163086,
|
|
"epoch": 1.9637208382759983,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004617432502492287,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.21220097243785857,
|
|
"num_tokens": 45499825.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.635042333602906,
|
|
"epoch": 1.9642151047844998,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004617235629168371,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.21778892278671264,
|
|
"num_tokens": 45511164.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.6711915016174315,
|
|
"epoch": 1.9647093712930013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004617038709910168,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.20508513003587722,
|
|
"num_tokens": 45521506.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.7687084674835205,
|
|
"epoch": 1.9652036378015025,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004616841744722524,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20549910813570021,
|
|
"num_tokens": 45531622.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.7036186218261715,
|
|
"epoch": 1.9656979043100038,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046166447336102836,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.21723143011331558,
|
|
"num_tokens": 45541565.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.691306686401367,
|
|
"epoch": 1.9661921708185055,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046164476765782927,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.21262252181768418,
|
|
"num_tokens": 45552943.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.655617570877075,
|
|
"epoch": 1.9666864373270068,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046162505736313997,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.21326455622911453,
|
|
"num_tokens": 45563914.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.62413010597229,
|
|
"epoch": 1.967180703835508,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004616053424774453,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.21902936995029448,
|
|
"num_tokens": 45575730.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.725116825103759,
|
|
"epoch": 1.9676749703440095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046158562300123023,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.20428133755922318,
|
|
"num_tokens": 45588369.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.633744239807129,
|
|
"epoch": 1.968169236852511,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046156589893498,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.2182771533727646,
|
|
"num_tokens": 45599235.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.655145692825317,
|
|
"epoch": 1.9686635033610123,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046154617027917955,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.22058816403150558,
|
|
"num_tokens": 45610066.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.647213935852051,
|
|
"epoch": 1.9691577698695135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046152643703431447,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.2098646879196167,
|
|
"num_tokens": 45621543.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.694778728485107,
|
|
"epoch": 1.969652036378015,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046150669920087004,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.20439695119857787,
|
|
"num_tokens": 45634984.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.704848957061768,
|
|
"epoch": 1.9701463028865165,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004614869567793319,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.21415792107582093,
|
|
"num_tokens": 45646778.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.680993175506591,
|
|
"epoch": 1.9706405693950177,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046146720977018567,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.21424164175987243,
|
|
"num_tokens": 45658103.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.680191135406494,
|
|
"epoch": 1.971134835903519,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004614474581739172,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.21335003823041915,
|
|
"num_tokens": 45669166.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.638544797897339,
|
|
"epoch": 1.9716291024120207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004614277019910123,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.2037629708647728,
|
|
"num_tokens": 45680667.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.677701377868653,
|
|
"epoch": 1.972123368920522,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004614079412219571,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.20004547536373138,
|
|
"num_tokens": 45692347.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.751753902435302,
|
|
"epoch": 1.9726176354290232,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004613881758672375,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.21331748366355896,
|
|
"num_tokens": 45703972.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.661026096343994,
|
|
"epoch": 1.9731119019375247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046136840592733995,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.20983144789934158,
|
|
"num_tokens": 45715446.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.641726446151734,
|
|
"epoch": 1.9736061684460262,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046134863140275066,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.2239527314901352,
|
|
"num_tokens": 45727210.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.735097932815552,
|
|
"epoch": 1.9741004349545275,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046132885229395606,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.20848499089479447,
|
|
"num_tokens": 45738235.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.671850299835205,
|
|
"epoch": 1.9745947014630287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004613090686014429,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.21848011612892151,
|
|
"num_tokens": 45750743.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.677858591079712,
|
|
"epoch": 1.9750889679715302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046128928032569775,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20594858825206758,
|
|
"num_tokens": 45761989.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.651481103897095,
|
|
"epoch": 1.9755832344800317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004612694874672073,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.20553501546382905,
|
|
"num_tokens": 45775046.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.789968538284302,
|
|
"epoch": 1.976077500988533,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004612496900264586,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.20658429861068725,
|
|
"num_tokens": 45786776.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.7063140869140625,
|
|
"epoch": 1.9765717674970344,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004612298880039387,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.21162472814321517,
|
|
"num_tokens": 45797675.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.678570127487182,
|
|
"epoch": 1.977066034005536,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004612100814001346,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.20350463539361954,
|
|
"num_tokens": 45809897.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.741326141357422,
|
|
"epoch": 1.9775603005140372,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004611902702155336,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.2049441695213318,
|
|
"num_tokens": 45822330.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.721708869934082,
|
|
"epoch": 1.9780545670225385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004611704544506232,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.2142978385090828,
|
|
"num_tokens": 45834705.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.726143741607666,
|
|
"epoch": 1.97854883353104,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004611506341058906,
|
|
"loss": 5.1215,
|
|
"mean_token_accuracy": 0.20422052443027497,
|
|
"num_tokens": 45846646.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.640376138687134,
|
|
"epoch": 1.9790431000395414,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046113080918182346,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.2192317470908165,
|
|
"num_tokens": 45857252.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.630357789993286,
|
|
"epoch": 1.9795373665480427,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046111097967890975,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.21955931782722474,
|
|
"num_tokens": 45867780.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.751022434234619,
|
|
"epoch": 1.980031633056544,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004610911455976369,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.19844427108764648,
|
|
"num_tokens": 45878998.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.6657631397247314,
|
|
"epoch": 1.9805258995650454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046107130693849303,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.21315255165100097,
|
|
"num_tokens": 45889685.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.684873914718628,
|
|
"epoch": 1.981020166073547,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004610514637019662,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.21360464841127397,
|
|
"num_tokens": 45900887.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.648508501052857,
|
|
"epoch": 1.9815144325820482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004610316158885444,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.20470312982797623,
|
|
"num_tokens": 45913860.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.660742282867432,
|
|
"epoch": 1.9820086990905497,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004610117634987161,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.2091463714838028,
|
|
"num_tokens": 45924669.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.651709079742432,
|
|
"epoch": 1.9825029655990511,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046099190653296946,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.211758154630661,
|
|
"num_tokens": 45937013.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.66717939376831,
|
|
"epoch": 1.9829972321075524,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004609720449917932,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.2120351031422615,
|
|
"num_tokens": 45950063.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.680777311325073,
|
|
"epoch": 1.9834914986160537,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046095217887567565,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.2092955619096756,
|
|
"num_tokens": 45962136.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.687870264053345,
|
|
"epoch": 1.9839857651245552,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004609323081851057,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.21102404594421387,
|
|
"num_tokens": 45974712.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.659638404846191,
|
|
"epoch": 1.9844800316330566,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004609124329205721,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.21544581055641174,
|
|
"num_tokens": 45985670.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.7283885955810545,
|
|
"epoch": 1.984974298141558,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004608925530825638,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.2022799715399742,
|
|
"num_tokens": 45997215.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.66595687866211,
|
|
"epoch": 1.9854685646500592,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046087266867156997,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21404301524162292,
|
|
"num_tokens": 46008479.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.691586971282959,
|
|
"epoch": 1.9859628311585606,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046085277968807955,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.21575601696968078,
|
|
"num_tokens": 46019504.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.690830135345459,
|
|
"epoch": 1.9864570976670621,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004608328861325819,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.20711578130722047,
|
|
"num_tokens": 46030218.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.683977508544922,
|
|
"epoch": 1.9869513641755634,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004608129880055665,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.20919976085424424,
|
|
"num_tokens": 46041767.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.666064596176147,
|
|
"epoch": 1.9874456306840649,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046079308530752274,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.2236934244632721,
|
|
"num_tokens": 46052792.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.745473623275757,
|
|
"epoch": 1.9879398971925664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046077317803894024,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.20583725422620774,
|
|
"num_tokens": 46064609.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.636377668380737,
|
|
"epoch": 1.9884341637010676,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046075326620030876,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2145010396838188,
|
|
"num_tokens": 46075624.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.666275691986084,
|
|
"epoch": 1.9889284302095689,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046073334979211813,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.21353914439678193,
|
|
"num_tokens": 46086455.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.751636409759522,
|
|
"epoch": 1.9894226967180704,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004607134288148582,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.2095244288444519,
|
|
"num_tokens": 46097362.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.62841830253601,
|
|
"epoch": 1.9899169632265719,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046069350326901915,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.21789303421974182,
|
|
"num_tokens": 46107811.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.723340845108032,
|
|
"epoch": 1.9904112297350731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004606735731550912,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.19757847338914872,
|
|
"num_tokens": 46120178.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.7393505573272705,
|
|
"epoch": 1.9909054962435744,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046065363847356443,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.20278926342725753,
|
|
"num_tokens": 46131416.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.694263172149658,
|
|
"epoch": 1.991399762752076,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046063369922492943,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.21905182301998138,
|
|
"num_tokens": 46142195.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.681416940689087,
|
|
"epoch": 1.9918940292605773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004606137554096766,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.20777338594198227,
|
|
"num_tokens": 46154537.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.699371337890625,
|
|
"epoch": 1.9923882957690786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004605938070282965,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.21119799017906188,
|
|
"num_tokens": 46166711.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.625368070602417,
|
|
"epoch": 1.99288256227758,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046057385408128013,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.21661234200000762,
|
|
"num_tokens": 46178509.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.6767253398895265,
|
|
"epoch": 1.9933768287860816,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000460553896569118,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.2115548461675644,
|
|
"num_tokens": 46188413.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.680219984054565,
|
|
"epoch": 1.9938710952945828,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004605339344923014,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.2084210142493248,
|
|
"num_tokens": 46199708.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.656156444549561,
|
|
"epoch": 1.994365361803084,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046051396785132113,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.21721094399690627,
|
|
"num_tokens": 46210670.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.68513765335083,
|
|
"epoch": 1.9948596283115856,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004604939966466684,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.20860487520694732,
|
|
"num_tokens": 46220935.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.646271896362305,
|
|
"epoch": 1.995353894820087,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004604740208788347,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.21356969624757766,
|
|
"num_tokens": 46232651.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.721328020095825,
|
|
"epoch": 1.9958481613285883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046045404054831124,
|
|
"loss": 5.0571,
|
|
"mean_token_accuracy": 0.21079475432634354,
|
|
"num_tokens": 46244308.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.777426815032959,
|
|
"epoch": 1.9963424278370896,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046043405565558964,
|
|
"loss": 5.15,
|
|
"mean_token_accuracy": 0.20589957535266876,
|
|
"num_tokens": 46256941.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.649097633361817,
|
|
"epoch": 1.9968366943455913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046041406620116144,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.2058628022670746,
|
|
"num_tokens": 46270557.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.719938039779663,
|
|
"epoch": 1.9973309608540926,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004603940721855185,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.2115815117955208,
|
|
"num_tokens": 46280940.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.684565496444702,
|
|
"epoch": 1.9978252273625938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004603740736091527,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.2111126735806465,
|
|
"num_tokens": 46292358.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.715559577941894,
|
|
"epoch": 1.9983194938710953,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004603540704725558,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.20936446636915207,
|
|
"num_tokens": 46303210.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.641305637359619,
|
|
"epoch": 1.9988137603795968,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004603340627762201,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.2137761265039444,
|
|
"num_tokens": 46315152.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.650291013717651,
|
|
"epoch": 1.999308026888098,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046031405052063756,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.21806330531835555,
|
|
"num_tokens": 46325776.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.661906433105469,
|
|
"epoch": 1.9998022933965993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046029403370630086,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.2172844797372818,
|
|
"num_tokens": 46336797.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.715367221832276,
|
|
"epoch": 2.000296559905101,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046027401233370203,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2159995913505554,
|
|
"num_tokens": 46346327.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.618159532546997,
|
|
"epoch": 2.0007908264136023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046025398640333373,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.2159489393234253,
|
|
"num_tokens": 46358056.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.631726455688477,
|
|
"epoch": 2.0012850929221035,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046023395591568867,
|
|
"loss": 4.9711,
|
|
"mean_token_accuracy": 0.2205471619963646,
|
|
"num_tokens": 46369792.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.682785272598267,
|
|
"epoch": 2.001779359430605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046021392087125957,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21919948011636733,
|
|
"num_tokens": 46381224.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.696166896820069,
|
|
"epoch": 2.0022736259391065,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004601938812705393,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.21001268327236175,
|
|
"num_tokens": 46393788.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.649038028717041,
|
|
"epoch": 2.002767892447608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046017383711402076,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.2129268929362297,
|
|
"num_tokens": 46405742.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.70607099533081,
|
|
"epoch": 2.003262158956109,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004601537884021972,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.21240628957748414,
|
|
"num_tokens": 46417276.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.609369516372681,
|
|
"epoch": 2.0037564254646103,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004601337351355617,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.22350422590970992,
|
|
"num_tokens": 46427950.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.618157243728637,
|
|
"epoch": 2.004250691973112,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004601136773146075,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2215016484260559,
|
|
"num_tokens": 46439200.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.719138050079346,
|
|
"epoch": 2.0047449584816133,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004600936149398282,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.20863528847694396,
|
|
"num_tokens": 46451176.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.683300018310547,
|
|
"epoch": 2.0052392249901145,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046007354801171725,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2164921298623085,
|
|
"num_tokens": 46462798.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.6921593189239506,
|
|
"epoch": 2.0057334914986162,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004600534765307682,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21626923829317093,
|
|
"num_tokens": 46473914.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.722663545608521,
|
|
"epoch": 2.0062277580071175,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046003340049747513,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.2131647601723671,
|
|
"num_tokens": 46485089.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.675890588760376,
|
|
"epoch": 2.0067220245156188,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004600133199123316,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.21926066428422927,
|
|
"num_tokens": 46497115.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.548769998550415,
|
|
"epoch": 2.00721629102412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004599932347758316,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.2288316711783409,
|
|
"num_tokens": 46508845.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.598067331314087,
|
|
"epoch": 2.0077105575326217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004599731450884694,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21953921169042587,
|
|
"num_tokens": 46520105.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.635143804550171,
|
|
"epoch": 2.008204824041123,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004599530508507392,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.21585515439510344,
|
|
"num_tokens": 46530701.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.645169258117676,
|
|
"epoch": 2.0086990905496243,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004599329520631351,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.21708461046218872,
|
|
"num_tokens": 46542614.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.650245523452758,
|
|
"epoch": 2.009193357058126,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045991284872615184,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.2193365216255188,
|
|
"num_tokens": 46553624.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.6613799095153805,
|
|
"epoch": 2.0096876235666272,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045989274084028375,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.21151267737150192,
|
|
"num_tokens": 46565599.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.644386243820191,
|
|
"epoch": 2.0101818900751285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004598726284060256,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.2207090973854065,
|
|
"num_tokens": 46576730.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.6647871971130375,
|
|
"epoch": 2.0106761565836297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000459852511423872,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.21312300562858583,
|
|
"num_tokens": 46587435.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.587189722061157,
|
|
"epoch": 2.0111704230921315,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004598323898943181,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.22213633805513383,
|
|
"num_tokens": 46598431.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.673926448822021,
|
|
"epoch": 2.0116646896006327,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004598122638178586,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.21271133720874785,
|
|
"num_tokens": 46609343.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.729203748703003,
|
|
"epoch": 2.012158956109134,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045979213319498883,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.2160341262817383,
|
|
"num_tokens": 46621844.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.628833293914795,
|
|
"epoch": 2.0126532226176352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004597719980262039,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.21663610637187958,
|
|
"num_tokens": 46633278.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.6560827732086185,
|
|
"epoch": 2.013147489126137,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004597518583119991,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.21496931761503218,
|
|
"num_tokens": 46644375.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.74820237159729,
|
|
"epoch": 2.013641755634638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004597317140528699,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.21078250259160997,
|
|
"num_tokens": 46655631.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.594955158233643,
|
|
"epoch": 2.0141360221431395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045971156524931195,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.22754027247428893,
|
|
"num_tokens": 46667095.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.669883155822754,
|
|
"epoch": 2.014630288651641,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004596914119018209,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.2126537874341011,
|
|
"num_tokens": 46678524.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.68853120803833,
|
|
"epoch": 2.0151245551601424,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045967125401089233,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.21361470222473145,
|
|
"num_tokens": 46689785.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.663337182998657,
|
|
"epoch": 2.0156188216686437,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004596510915770223,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.21044505387544632,
|
|
"num_tokens": 46701109.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.657110166549683,
|
|
"epoch": 2.016113088177145,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004596309246007068,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.21716320216655732,
|
|
"num_tokens": 46711381.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.753578948974609,
|
|
"epoch": 2.0166073546856467,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004596107530824419,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21694085747003555,
|
|
"num_tokens": 46722237.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.638413715362549,
|
|
"epoch": 2.017101621194148,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045959057702272383,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.22121070176362992,
|
|
"num_tokens": 46733679.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.662168073654175,
|
|
"epoch": 2.017595887702649,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004595703964220489,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.20533768832683563,
|
|
"num_tokens": 46746207.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.704695224761963,
|
|
"epoch": 2.0180901542111505,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004595502112809137,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.2115277111530304,
|
|
"num_tokens": 46756607.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.669324064254761,
|
|
"epoch": 2.018584420719652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004595300215998145,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.2160011723637581,
|
|
"num_tokens": 46768383.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.734667873382568,
|
|
"epoch": 2.0190786872281534,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004595098273792482,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.207054041326046,
|
|
"num_tokens": 46779511.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.693780088424683,
|
|
"epoch": 2.0195729537366547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004594896286197116,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2152336671948433,
|
|
"num_tokens": 46791281.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.664788818359375,
|
|
"epoch": 2.0200672202451564,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045946942532170147,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.22228609174489974,
|
|
"num_tokens": 46802090.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.594156312942505,
|
|
"epoch": 2.0205614867536577,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004594492174857149,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.22026713341474533,
|
|
"num_tokens": 46814688.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.720065355300903,
|
|
"epoch": 2.021055753262159,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045942900511224886,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.2147608980536461,
|
|
"num_tokens": 46826212.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.658379364013672,
|
|
"epoch": 2.02155001977066,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004594087882018008,
|
|
"loss": 4.9793,
|
|
"mean_token_accuracy": 0.22108548432588576,
|
|
"num_tokens": 46836583.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.645122432708741,
|
|
"epoch": 2.022044286279162,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004593885667548679,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.21453700214624405,
|
|
"num_tokens": 46847973.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.61444878578186,
|
|
"epoch": 2.022538552787663,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045936834077194754,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.21722497344017028,
|
|
"num_tokens": 46860113.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.766012811660767,
|
|
"epoch": 2.0230328192961644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004593481102535375,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.21979404091835023,
|
|
"num_tokens": 46871578.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.677948093414306,
|
|
"epoch": 2.0235270858046657,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045932787520013533,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.2161948025226593,
|
|
"num_tokens": 46883701.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.601521253585815,
|
|
"epoch": 2.0240213523131674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004593076356122389,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.21890998631715775,
|
|
"num_tokens": 46895107.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.631842947006225,
|
|
"epoch": 2.0245156188216686,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000459287391490346,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.23060783445835115,
|
|
"num_tokens": 46906984.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.697120094299317,
|
|
"epoch": 2.02500988533017,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045926714283495466,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.2160445675253868,
|
|
"num_tokens": 46918582.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.666937923431396,
|
|
"epoch": 2.0255041518386716,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045924688964656303,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.2217430830001831,
|
|
"num_tokens": 46930799.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.668531370162964,
|
|
"epoch": 2.025998418347173,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045922663192566926,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.22027683705091478,
|
|
"num_tokens": 46941517.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.671516799926758,
|
|
"epoch": 2.026492684855674,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045920636967277187,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.21205419450998306,
|
|
"num_tokens": 46953160.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.645624494552612,
|
|
"epoch": 2.0269869513641754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045918610288836915,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.2243179053068161,
|
|
"num_tokens": 46964284.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.698209810256958,
|
|
"epoch": 2.027481217872677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004591658315729598,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.21062007397413254,
|
|
"num_tokens": 46975402.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.711695051193237,
|
|
"epoch": 2.0279754843811784,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004591455557270423,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.217771477997303,
|
|
"num_tokens": 46988629.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.674247360229492,
|
|
"epoch": 2.0284697508896796,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045912527535111567,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.21682387441396714,
|
|
"num_tokens": 47000497.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.667401361465454,
|
|
"epoch": 2.028964017398181,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045910499044567865,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.20941581577062607,
|
|
"num_tokens": 47010841.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.623434400558471,
|
|
"epoch": 2.0294582839066826,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004590847010112303,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.21733448505401612,
|
|
"num_tokens": 47023131.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.7029438495635985,
|
|
"epoch": 2.029952550415184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045906440704826973,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.21916961520910264,
|
|
"num_tokens": 47034363.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.653840970993042,
|
|
"epoch": 2.030446816923685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004590441085572962,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.21096257865428925,
|
|
"num_tokens": 47045584.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.694814872741699,
|
|
"epoch": 2.030941083432187,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045902380553880913,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.21447319239377977,
|
|
"num_tokens": 47056245.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.656255102157592,
|
|
"epoch": 2.031435349940688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004590034979933078,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.21830471456050873,
|
|
"num_tokens": 47067856.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.612227058410644,
|
|
"epoch": 2.0319296164491893,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045898318592129197,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.22526390999555587,
|
|
"num_tokens": 47079316.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.681221961975098,
|
|
"epoch": 2.0324238829576906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045896286932326115,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.20761357992887497,
|
|
"num_tokens": 47090268.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.675450801849365,
|
|
"epoch": 2.0329181494661923,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004589425481997152,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.2192302852869034,
|
|
"num_tokens": 47100980.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.69634222984314,
|
|
"epoch": 2.0334124159746936,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000458922222551154,
|
|
"loss": 4.9658,
|
|
"mean_token_accuracy": 0.21679438650608063,
|
|
"num_tokens": 47112548.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.683189058303833,
|
|
"epoch": 2.033906682483195,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004589018923780777,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21059519946575164,
|
|
"num_tokens": 47123378.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.684381055831909,
|
|
"epoch": 2.0344009489916965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004588815576809862,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.20461406856775283,
|
|
"num_tokens": 47135279.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.750810623168945,
|
|
"epoch": 2.034895215500198,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045886121846037996,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.21417458206415177,
|
|
"num_tokens": 47146510.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.677541732788086,
|
|
"epoch": 2.035389482008699,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045884087471675917,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.22137399315834044,
|
|
"num_tokens": 47158275.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.655041933059692,
|
|
"epoch": 2.0358837485172003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045882052645062433,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.21295645833015442,
|
|
"num_tokens": 47170530.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.6674426078796385,
|
|
"epoch": 2.036378015025702,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000458800173662476,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.2109129920601845,
|
|
"num_tokens": 47182092.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.746099519729614,
|
|
"epoch": 2.0368722815342033,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045877981635281497,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21244132071733474,
|
|
"num_tokens": 47193184.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.685303401947022,
|
|
"epoch": 2.0373665480427046,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045875945452214186,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.20750230103731154,
|
|
"num_tokens": 47205032.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.723717737197876,
|
|
"epoch": 2.037860814551206,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045873908817095773,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.21041948050260545,
|
|
"num_tokens": 47217553.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.7051280498504635,
|
|
"epoch": 2.0383550810597075,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004587187172997635,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.21467075645923614,
|
|
"num_tokens": 47230625.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.655072021484375,
|
|
"epoch": 2.038849347568209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004586983419090603,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.21669741868972778,
|
|
"num_tokens": 47240703.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.632168531417847,
|
|
"epoch": 2.03934361407671,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045867796199934943,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.2220626801252365,
|
|
"num_tokens": 47253768.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.732367897033692,
|
|
"epoch": 2.0398378805852118,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004586575775711322,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.21415303498506547,
|
|
"num_tokens": 47264226.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.627647638320923,
|
|
"epoch": 2.040332147093713,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045863718862491,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.21747655421495438,
|
|
"num_tokens": 47276675.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.7111187934875485,
|
|
"epoch": 2.0408264136022143,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045861679516118447,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.21150697767734528,
|
|
"num_tokens": 47288876.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.685536432266235,
|
|
"epoch": 2.0413206801107155,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004585963971804574,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.21317038387060167,
|
|
"num_tokens": 47300430.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.634823989868164,
|
|
"epoch": 2.0418149466192173,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004585759946832304,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.21519629955291747,
|
|
"num_tokens": 47310822.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.648880577087402,
|
|
"epoch": 2.0423092131277185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045855558767000546,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.20947837680578232,
|
|
"num_tokens": 47323042.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.654583311080932,
|
|
"epoch": 2.0428034796362198,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004585351761412846,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21402914673089982,
|
|
"num_tokens": 47334003.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.623824977874756,
|
|
"epoch": 2.043297746144721,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004585147600975699,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21470932811498641,
|
|
"num_tokens": 47346279.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.661670303344726,
|
|
"epoch": 2.0437920126532227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004584943395393637,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.213410447537899,
|
|
"num_tokens": 47357655.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.650173950195312,
|
|
"epoch": 2.044286279161724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045847391446716826,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.21399174332618714,
|
|
"num_tokens": 47369494.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.660252475738526,
|
|
"epoch": 2.0447805456702253,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000458453484881486,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.21785142719745637,
|
|
"num_tokens": 47380221.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.595717525482177,
|
|
"epoch": 2.045274812178727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004584330507828196,
|
|
"loss": 4.9313,
|
|
"mean_token_accuracy": 0.22405217587947845,
|
|
"num_tokens": 47391119.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.71578950881958,
|
|
"epoch": 2.0457690786872282,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004584126121716717,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.22136372178792954,
|
|
"num_tokens": 47401828.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.60136604309082,
|
|
"epoch": 2.0462633451957295,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004583921690485451,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2168480008840561,
|
|
"num_tokens": 47412921.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.6782105445861815,
|
|
"epoch": 2.0467576117042308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004583717214139427,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.21185654997825623,
|
|
"num_tokens": 47424117.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.676736211776733,
|
|
"epoch": 2.0472518782127325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045835126926836744,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.21861087679862976,
|
|
"num_tokens": 47434457.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.678697633743286,
|
|
"epoch": 2.0477461447212337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004583308126123225,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.213051737844944,
|
|
"num_tokens": 47446108.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.592248439788818,
|
|
"epoch": 2.048240411229735,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045831035144631115,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.22291632294654845,
|
|
"num_tokens": 47458735.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.746953773498535,
|
|
"epoch": 2.0487346777382363,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045828988577083674,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.22030461877584456,
|
|
"num_tokens": 47471726.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.746368026733398,
|
|
"epoch": 2.049228944246738,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004582694155864027,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.21278312802314758,
|
|
"num_tokens": 47483940.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.574789190292359,
|
|
"epoch": 2.0497232107552392,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045824894089351265,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2213670313358307,
|
|
"num_tokens": 47494723.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.633314418792724,
|
|
"epoch": 2.0502174772637405,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004582284616926702,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.2120853915810585,
|
|
"num_tokens": 47506454.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.713232517242432,
|
|
"epoch": 2.050711743772242,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004582079779843791,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20890644937753677,
|
|
"num_tokens": 47518366.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.6306623935699465,
|
|
"epoch": 2.0512060102807435,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004581874897691434,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.21563552021980287,
|
|
"num_tokens": 47530635.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.710493040084839,
|
|
"epoch": 2.0517002767892447,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000458166997047467,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.21193100810050963,
|
|
"num_tokens": 47541158.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.73265814781189,
|
|
"epoch": 2.052194543297746,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045814649981985406,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.208854079246521,
|
|
"num_tokens": 47552392.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.693927145004272,
|
|
"epoch": 2.0526888098062477,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004581259980868088,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.2132966548204422,
|
|
"num_tokens": 47565079.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.670985555648803,
|
|
"epoch": 2.053183076314749,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004581054918488356,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.2139470621943474,
|
|
"num_tokens": 47575529.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.641596364974975,
|
|
"epoch": 2.05367734282325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045808498110643886,
|
|
"loss": 4.9498,
|
|
"mean_token_accuracy": 0.21649311482906342,
|
|
"num_tokens": 47587289.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.666541051864624,
|
|
"epoch": 2.0541716093317515,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045806446586012326,
|
|
"loss": 5.0076,
|
|
"mean_token_accuracy": 0.21796323657035827,
|
|
"num_tokens": 47599184.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.635496950149536,
|
|
"epoch": 2.054665875840253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004580439461103933,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.23004308640956878,
|
|
"num_tokens": 47609651.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.657304191589356,
|
|
"epoch": 2.0551601423487544,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004580234218577539,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.21652598828077316,
|
|
"num_tokens": 47621138.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.643387699127198,
|
|
"epoch": 2.0556544088572557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045800289310270995,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21922110319137572,
|
|
"num_tokens": 47631492.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.655768823623657,
|
|
"epoch": 2.0561486753657574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004579823598457664,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.22255292385816575,
|
|
"num_tokens": 47643088.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.613609266281128,
|
|
"epoch": 2.0566429418742587,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045796182208742846,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.22949917763471603,
|
|
"num_tokens": 47653393.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.643861436843872,
|
|
"epoch": 2.05713720838276,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004579412798282013,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.22513114511966706,
|
|
"num_tokens": 47665879.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.585993385314941,
|
|
"epoch": 2.057631474891261,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004579207330685902,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.22056273072957994,
|
|
"num_tokens": 47678339.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.6660998344421385,
|
|
"epoch": 2.058125741399763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004579001818091009,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.21907689720392226,
|
|
"num_tokens": 47688867.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.661335802078247,
|
|
"epoch": 2.058620007908264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004578796260502385,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.21339231878519058,
|
|
"num_tokens": 47700265.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.705745124816895,
|
|
"epoch": 2.0591142744167654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004578590657925091,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.2031018316745758,
|
|
"num_tokens": 47711539.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.728035926818848,
|
|
"epoch": 2.059608540925267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004578385010364182,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.21309321969747544,
|
|
"num_tokens": 47722433.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.645641231536866,
|
|
"epoch": 2.0601028074337684,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045781793178247194,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.21877609193325043,
|
|
"num_tokens": 47734001.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.597643423080444,
|
|
"epoch": 2.0605970739422697,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004577973580311761,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.2276684746146202,
|
|
"num_tokens": 47744903.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.711612129211426,
|
|
"epoch": 2.061091340450771,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004577767797830369,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.21969857960939407,
|
|
"num_tokens": 47756571.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.6362952709198,
|
|
"epoch": 2.0615856069592726,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045775619703856057,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.21824547201395034,
|
|
"num_tokens": 47767555.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.709694957733154,
|
|
"epoch": 2.062079873467774,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045773560979825347,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.21963334679603577,
|
|
"num_tokens": 47779577.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.715613603591919,
|
|
"epoch": 2.062574139976275,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045771501806262196,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.21323318779468536,
|
|
"num_tokens": 47790898.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.644003105163574,
|
|
"epoch": 2.0630684064847764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045769442183217273,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.2171536549925804,
|
|
"num_tokens": 47802008.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.636333084106445,
|
|
"epoch": 2.063562672993278,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004576738211074123,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.22091972678899766,
|
|
"num_tokens": 47813544.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.742989206314087,
|
|
"epoch": 2.0640569395017794,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004576532158888476,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21415594667196275,
|
|
"num_tokens": 47824313.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.744692754745484,
|
|
"epoch": 2.0645512060102806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004576326061769854,
|
|
"loss": 4.9764,
|
|
"mean_token_accuracy": 0.21722126007080078,
|
|
"num_tokens": 47836653.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.671329498291016,
|
|
"epoch": 2.065045472518782,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045761199197233285,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.21625828891992568,
|
|
"num_tokens": 47848237.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.6366846561431885,
|
|
"epoch": 2.0655397390272836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045759137327539684,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.21029420346021652,
|
|
"num_tokens": 47859686.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.662865161895752,
|
|
"epoch": 2.066034005535785,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004575707500866848,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.21711523234844207,
|
|
"num_tokens": 47871730.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.755568504333496,
|
|
"epoch": 2.066528272044286,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045755012240670395,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.21258346736431122,
|
|
"num_tokens": 47883927.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.596585464477539,
|
|
"epoch": 2.067022538552788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004575294902359618,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.22992324233055114,
|
|
"num_tokens": 47894885.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.72910623550415,
|
|
"epoch": 2.067516805061289,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045750885357496583,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.20886144042015076,
|
|
"num_tokens": 47906183.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.646014022827148,
|
|
"epoch": 2.0680110715697904,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004574882124242238,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.21325428634881974,
|
|
"num_tokens": 47918002.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.614262819290161,
|
|
"epoch": 2.0685053380782916,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045746756678424343,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.2229419842362404,
|
|
"num_tokens": 47928300.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.6232648372650145,
|
|
"epoch": 2.0689996045867933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045744691665553254,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.22022929191589355,
|
|
"num_tokens": 47939591.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.72723503112793,
|
|
"epoch": 2.0694938710952946,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004574262620385993,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.2103950262069702,
|
|
"num_tokens": 47953075.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.748756837844849,
|
|
"epoch": 2.069988137603796,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045740560293395166,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.2062777176499367,
|
|
"num_tokens": 47964795.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.62108793258667,
|
|
"epoch": 2.0704824041122976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004573849393420979,
|
|
"loss": 4.915,
|
|
"mean_token_accuracy": 0.23102890104055404,
|
|
"num_tokens": 47975175.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.661827087402344,
|
|
"epoch": 2.070976670620799,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004573642712635463,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.21689056903123854,
|
|
"num_tokens": 47986548.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.734865951538086,
|
|
"epoch": 2.0714709371293,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045734359869880535,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.20465439260005952,
|
|
"num_tokens": 47998759.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.644789123535157,
|
|
"epoch": 2.0719652036378013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004573229216483836,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.2198326826095581,
|
|
"num_tokens": 48010404.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.615933084487915,
|
|
"epoch": 2.072459470146303,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004573022401127897,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.22380543053150176,
|
|
"num_tokens": 48019729.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.680324983596802,
|
|
"epoch": 2.0729537366548043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045728155409253236,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.20856280624866486,
|
|
"num_tokens": 48031142.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.708774042129517,
|
|
"epoch": 2.0734480031633056,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004572608635881206,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.22196649014949799,
|
|
"num_tokens": 48043051.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.619117307662964,
|
|
"epoch": 2.073942269671807,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004572401686000633,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.22599214613437651,
|
|
"num_tokens": 48053721.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.537456607818603,
|
|
"epoch": 2.0744365361803085,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045721946912886957,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.22657636404037476,
|
|
"num_tokens": 48065208.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.7224202156066895,
|
|
"epoch": 2.07493080268881,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004571987651750486,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.2142981082201004,
|
|
"num_tokens": 48076416.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.724152517318726,
|
|
"epoch": 2.075425069197311,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004571780567391098,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21085721701383592,
|
|
"num_tokens": 48087496.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.698615264892578,
|
|
"epoch": 2.0759193357058128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045715734382156245,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.2153531491756439,
|
|
"num_tokens": 48098920.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0759193357058128,
|
|
"eval_entropy": 5.408183826643603,
|
|
"eval_loss": 5.097185134887695,
|
|
"eval_mean_token_accuracy": 0.21930308469180546,
|
|
"eval_num_tokens": 48098920.0,
|
|
"eval_runtime": 20.5359,
|
|
"eval_samples_per_second": 1583.229,
|
|
"eval_steps_per_second": 197.946,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.650296068191528,
|
|
"epoch": 2.076413602214314,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004571366264229162,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.209500552713871,
|
|
"num_tokens": 48109813.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.687859916687012,
|
|
"epoch": 2.0769078687228153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004571159045436807,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.21917393058538437,
|
|
"num_tokens": 48120736.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.669516611099243,
|
|
"epoch": 2.0774021352313166,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004570951781843657,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.21941807270050048,
|
|
"num_tokens": 48131631.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.605395174026489,
|
|
"epoch": 2.0778964017398183,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045707444734548116,
|
|
"loss": 4.9318,
|
|
"mean_token_accuracy": 0.21855298727750777,
|
|
"num_tokens": 48141662.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.576294994354248,
|
|
"epoch": 2.0783906682483195,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004570537120275369,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.22089688628911971,
|
|
"num_tokens": 48152752.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.715353870391846,
|
|
"epoch": 2.078884934756821,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000457032972231043,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.21621995121240617,
|
|
"num_tokens": 48163510.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.666709327697754,
|
|
"epoch": 2.079379201265322,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004570122279565098,
|
|
"loss": 5.0593,
|
|
"mean_token_accuracy": 0.21032652258872986,
|
|
"num_tokens": 48174241.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.649996376037597,
|
|
"epoch": 2.0798734677738238,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045699147920444757,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.21020580381155013,
|
|
"num_tokens": 48186062.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.678539085388183,
|
|
"epoch": 2.080367734282325,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004569707259753667,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.22569281458854676,
|
|
"num_tokens": 48197108.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.601124715805054,
|
|
"epoch": 2.0808620007908263,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004569499682697778,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.23140249252319336,
|
|
"num_tokens": 48208780.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.624329519271851,
|
|
"epoch": 2.081356267299328,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004569292060881914,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.21942928582429885,
|
|
"num_tokens": 48223164.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.642107200622559,
|
|
"epoch": 2.0818505338078293,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045690843943111824,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.2210210919380188,
|
|
"num_tokens": 48234402.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.70615234375,
|
|
"epoch": 2.0823448003163305,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045688766829906936,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.2125357761979103,
|
|
"num_tokens": 48245147.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.6813191890716555,
|
|
"epoch": 2.0828390668248318,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004568668926925556,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.20433513820171356,
|
|
"num_tokens": 48256787.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.641712093353272,
|
|
"epoch": 2.0833333333333335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000456846112612088,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.20761062800884247,
|
|
"num_tokens": 48267648.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.633345365524292,
|
|
"epoch": 2.0838275998418347,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045682532805817796,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.21266216784715652,
|
|
"num_tokens": 48279274.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.661918449401855,
|
|
"epoch": 2.084321866350336,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004568045390313365,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.21515525579452516,
|
|
"num_tokens": 48290849.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.693440961837768,
|
|
"epoch": 2.0848161328588377,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045678374553207525,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.21023352742195128,
|
|
"num_tokens": 48301271.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.689974641799926,
|
|
"epoch": 2.085310399367339,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045676294756090565,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.2119367703795433,
|
|
"num_tokens": 48311869.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.709160661697387,
|
|
"epoch": 2.0858046658758402,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004567421451183393,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.2208578795194626,
|
|
"num_tokens": 48324907.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.67872257232666,
|
|
"epoch": 2.0862989323843415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000456721338204888,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.22490611374378205,
|
|
"num_tokens": 48335887.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.677862071990967,
|
|
"epoch": 2.086793198892843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004567005268210636,
|
|
"loss": 4.9658,
|
|
"mean_token_accuracy": 0.21953608840703964,
|
|
"num_tokens": 48348190.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.7027459144592285,
|
|
"epoch": 2.0872874654013445,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045667971096737805,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.20537387430667878,
|
|
"num_tokens": 48360113.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.742707967758179,
|
|
"epoch": 2.0877817319098457,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004566588906443434,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.2094676077365875,
|
|
"num_tokens": 48371463.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.708125400543213,
|
|
"epoch": 2.088275998418347,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004566380658524719,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.20396397411823272,
|
|
"num_tokens": 48383969.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.660898494720459,
|
|
"epoch": 2.0887702649268487,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004566172365922758,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.22343368381261824,
|
|
"num_tokens": 48395551.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.679444742202759,
|
|
"epoch": 2.08926453143535,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004565964028642675,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.2181533932685852,
|
|
"num_tokens": 48408154.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.5739013671875,
|
|
"epoch": 2.089758797943851,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004565755646689595,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.22656984776258468,
|
|
"num_tokens": 48420060.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.651965856552124,
|
|
"epoch": 2.0902530644523525,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004565547220068644,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.21775846928358078,
|
|
"num_tokens": 48432347.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.789418888092041,
|
|
"epoch": 2.090747330960854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004565338748784951,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.20186013877391815,
|
|
"num_tokens": 48443177.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.730132389068603,
|
|
"epoch": 2.0912415974693555,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004565130232843642,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.20903053730726243,
|
|
"num_tokens": 48453605.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.672862911224366,
|
|
"epoch": 2.0917358639778567,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004564921672249848,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.21242832392454147,
|
|
"num_tokens": 48465364.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.647468137741089,
|
|
"epoch": 2.0922301304863584,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045647130670086996,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.21843489557504653,
|
|
"num_tokens": 48477255.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.6594264030456545,
|
|
"epoch": 2.0927243969948597,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004564504417125328,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.21427309811115264,
|
|
"num_tokens": 48487551.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.703998708724976,
|
|
"epoch": 2.093218663503361,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045642957226048667,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.21171430945396424,
|
|
"num_tokens": 48500422.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.645060873031616,
|
|
"epoch": 2.093712930011862,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045640869834524486,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.22154406160116197,
|
|
"num_tokens": 48511588.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.6666006565094,
|
|
"epoch": 2.094207196520364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004563878199673209,
|
|
"loss": 5.0739,
|
|
"mean_token_accuracy": 0.21622838377952575,
|
|
"num_tokens": 48522700.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.758858680725098,
|
|
"epoch": 2.094701463028865,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004563669371272285,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.21748532205820084,
|
|
"num_tokens": 48534253.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.631289958953857,
|
|
"epoch": 2.0951957295373664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045634604982548125,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.21752068847417833,
|
|
"num_tokens": 48545543.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.712238836288452,
|
|
"epoch": 2.095689996045868,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045632515806259306,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.21065617650747298,
|
|
"num_tokens": 48557433.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.72247085571289,
|
|
"epoch": 2.0961842625543694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045630426183907786,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.21358831375837325,
|
|
"num_tokens": 48570271.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.660365915298462,
|
|
"epoch": 2.0966785290628707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004562833611554497,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.21491242647171022,
|
|
"num_tokens": 48582376.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.674399662017822,
|
|
"epoch": 2.097172795571372,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004562624560122227,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.21207524538040162,
|
|
"num_tokens": 48595188.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.6678670883178714,
|
|
"epoch": 2.0976670620798736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004562415464099112,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.222423654794693,
|
|
"num_tokens": 48606093.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.665777206420898,
|
|
"epoch": 2.098161328588375,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004562206323490295,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.21252509951591492,
|
|
"num_tokens": 48618163.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.712373304367065,
|
|
"epoch": 2.098655595096876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045619971383009216,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.2176179140806198,
|
|
"num_tokens": 48629771.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.685916566848755,
|
|
"epoch": 2.0991498616053774,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004561787908536138,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.2110289976000786,
|
|
"num_tokens": 48640409.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.641875267028809,
|
|
"epoch": 2.099644128113879,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045615786342010896,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.21897058337926864,
|
|
"num_tokens": 48652223.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.700195837020874,
|
|
"epoch": 2.1001383946223804,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045613693153009264,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.22600506246089935,
|
|
"num_tokens": 48663667.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.7253851890563965,
|
|
"epoch": 2.1006326611308817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004561159951840797,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.21265184730291367,
|
|
"num_tokens": 48674691.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.6713849067687985,
|
|
"epoch": 2.1011269276393834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004560950543825852,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.20996796190738679,
|
|
"num_tokens": 48686888.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.666545391082764,
|
|
"epoch": 2.1016211941478846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045607410912612426,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.21562628746032714,
|
|
"num_tokens": 48698666.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.661928462982178,
|
|
"epoch": 2.102115460656386,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004560531594152121,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.222325836122036,
|
|
"num_tokens": 48709793.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.62381067276001,
|
|
"epoch": 2.102609727164887,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004560322052503642,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.22393170297145842,
|
|
"num_tokens": 48720835.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.723797273635864,
|
|
"epoch": 2.103103993673389,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004560112466320959,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.20789227783679962,
|
|
"num_tokens": 48732990.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.671847248077393,
|
|
"epoch": 2.10359826018189,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045599028356092293,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.2153536394238472,
|
|
"num_tokens": 48744985.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.600727558135986,
|
|
"epoch": 2.1040925266903914,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004559693160373608,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.22514446824789047,
|
|
"num_tokens": 48755328.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.617312622070313,
|
|
"epoch": 2.1045867931988926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004559483440619255,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.21868060827255248,
|
|
"num_tokens": 48766666.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.70514497756958,
|
|
"epoch": 2.1050810597073943,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045592736763513285,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.21363993287086486,
|
|
"num_tokens": 48779134.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.725298452377319,
|
|
"epoch": 2.1055753262158956,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004559063867574989,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.20539577156305314,
|
|
"num_tokens": 48791338.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.640329647064209,
|
|
"epoch": 2.106069592724397,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045588540142953973,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.22048145085573195,
|
|
"num_tokens": 48802711.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.638490676879883,
|
|
"epoch": 2.1065638592328986,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004558644116517717,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.22329133301973342,
|
|
"num_tokens": 48815219.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.618303966522217,
|
|
"epoch": 2.1070581257414,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045584341742471095,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.21336278766393663,
|
|
"num_tokens": 48826075.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.625316572189331,
|
|
"epoch": 2.107552392249901,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004558224187488742,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.217760668694973,
|
|
"num_tokens": 48837375.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.702776527404785,
|
|
"epoch": 2.1080466587584024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045580141562477785,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.20832032561302186,
|
|
"num_tokens": 48849205.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.637407398223877,
|
|
"epoch": 2.108540925266904,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045578040805293864,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.21831342428922654,
|
|
"num_tokens": 48861700.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.7121563911437985,
|
|
"epoch": 2.1090351917754053,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045575939603387336,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.20496477633714677,
|
|
"num_tokens": 48873510.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.723335647583008,
|
|
"epoch": 2.1095294582839066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004557383795680988,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.21332503110170364,
|
|
"num_tokens": 48885011.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.676425504684448,
|
|
"epoch": 2.1100237247924083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045571735865613215,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.21984738260507583,
|
|
"num_tokens": 48895767.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.691645002365112,
|
|
"epoch": 2.1105179913009096,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045569633329849043,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20697356313467025,
|
|
"num_tokens": 48906616.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.679794025421143,
|
|
"epoch": 2.111012257809411,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004556753034956909,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.2145752102136612,
|
|
"num_tokens": 48916841.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.647846508026123,
|
|
"epoch": 2.111506524317912,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004556542692482508,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.21998891681432725,
|
|
"num_tokens": 48928798.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.641065835952759,
|
|
"epoch": 2.112000790826414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004556332305566877,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.22036895751953126,
|
|
"num_tokens": 48940235.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.6534929275512695,
|
|
"epoch": 2.112495057334915,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004556121874215191,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.22152170538902283,
|
|
"num_tokens": 48951718.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.672334098815918,
|
|
"epoch": 2.1129893238434163,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004555911398432627,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.2210202246904373,
|
|
"num_tokens": 48963215.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.733951616287231,
|
|
"epoch": 2.1134835903519176,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045557008782243626,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.21473779529333115,
|
|
"num_tokens": 48975761.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.641482305526734,
|
|
"epoch": 2.1139778568604193,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004555490313595575,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.223097625374794,
|
|
"num_tokens": 48987192.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.612545394897461,
|
|
"epoch": 2.1144721233689205,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004555279704551447,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.2221687227487564,
|
|
"num_tokens": 48999503.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.66132755279541,
|
|
"epoch": 2.114966389877422,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004555069051097158,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.20904601067304612,
|
|
"num_tokens": 49010046.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.6712218761444095,
|
|
"epoch": 2.115460656385923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045548583532378903,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2185022011399269,
|
|
"num_tokens": 49021028.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.722016286849976,
|
|
"epoch": 2.1159549228944248,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004554647610978827,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.21127742528915405,
|
|
"num_tokens": 49034522.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.744274997711182,
|
|
"epoch": 2.116449189402926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004554436824325152,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.21956152319908143,
|
|
"num_tokens": 49045034.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.615834331512451,
|
|
"epoch": 2.1169434559114273,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045542259932820515,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.2161223918199539,
|
|
"num_tokens": 49056350.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.687479496002197,
|
|
"epoch": 2.117437722419929,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004554015117854712,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.21975050419569014,
|
|
"num_tokens": 49067362.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.6801290035247805,
|
|
"epoch": 2.1179319889284303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004553804198048321,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.21779961735010148,
|
|
"num_tokens": 49078067.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.63741626739502,
|
|
"epoch": 2.1184262554369315,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045535932338680655,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.22106690406799318,
|
|
"num_tokens": 49090205.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.609007883071899,
|
|
"epoch": 2.118920521945433,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004553382225319138,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21885061264038086,
|
|
"num_tokens": 49101134.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.7151782512664795,
|
|
"epoch": 2.1194147884539345,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004553171172406728,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.20899778753519058,
|
|
"num_tokens": 49112282.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.671550369262695,
|
|
"epoch": 2.1199090549624358,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004552960075136027,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.21144363582134246,
|
|
"num_tokens": 49123228.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.62641453742981,
|
|
"epoch": 2.120403321470937,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045527489335122284,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.21978760808706282,
|
|
"num_tokens": 49134769.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.607322549819946,
|
|
"epoch": 2.1208975879794387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045525377475405266,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22754495292901994,
|
|
"num_tokens": 49146096.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.665983247756958,
|
|
"epoch": 2.12139185448794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045523265172261155,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.20969967246055604,
|
|
"num_tokens": 49156829.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.657736968994141,
|
|
"epoch": 2.1218861209964412,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045521152425741934,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.21390421092510223,
|
|
"num_tokens": 49167364.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.730755424499511,
|
|
"epoch": 2.1223803875049425,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045519039235899573,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.21303328424692153,
|
|
"num_tokens": 49178283.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.79849796295166,
|
|
"epoch": 2.122874654013444,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045516925602786043,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.21029277443885802,
|
|
"num_tokens": 49190466.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.703871345520019,
|
|
"epoch": 2.1233689205219455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004551481152645335,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.21805175095796586,
|
|
"num_tokens": 49202601.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.5718859195709225,
|
|
"epoch": 2.1238631870304467,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045512697006953504,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.2257145881652832,
|
|
"num_tokens": 49214228.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.58619065284729,
|
|
"epoch": 2.124357453538948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045510582044338513,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.2104465052485466,
|
|
"num_tokens": 49225495.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.6865123271942135,
|
|
"epoch": 2.1248517200474497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000455084666386604,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.2183225452899933,
|
|
"num_tokens": 49237348.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.697784900665283,
|
|
"epoch": 2.125345986555951,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045506350789971227,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.20518922954797744,
|
|
"num_tokens": 49247691.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.633681201934815,
|
|
"epoch": 2.1258402530644522,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004550423449832302,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.22406365275382994,
|
|
"num_tokens": 49259191.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.675106954574585,
|
|
"epoch": 2.126334519572954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004550211776376787,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.21764902472496034,
|
|
"num_tokens": 49271760.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.6905358791351315,
|
|
"epoch": 2.126828786081455,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045500000586357807,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.21133720725774766,
|
|
"num_tokens": 49283918.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.6472405910491945,
|
|
"epoch": 2.1273230525899565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045497882966144955,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.22142320722341538,
|
|
"num_tokens": 49294313.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.601295280456543,
|
|
"epoch": 2.1278173190984577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004549576490318138,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.21830862313508986,
|
|
"num_tokens": 49305213.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.629416513442993,
|
|
"epoch": 2.1283115856069594,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000454936463975192,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.22252366095781326,
|
|
"num_tokens": 49317245.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.7379249095916744,
|
|
"epoch": 2.1288058521154607,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004549152744921053,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.20591568499803542,
|
|
"num_tokens": 49328400.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.755444049835205,
|
|
"epoch": 2.129300118623962,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004548940805830749,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.20803329348564148,
|
|
"num_tokens": 49341094.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.65848741531372,
|
|
"epoch": 2.129794385132463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045487288224862224,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.2134752482175827,
|
|
"num_tokens": 49352472.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.582034015655518,
|
|
"epoch": 2.130288651640965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045485167948926876,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.21736062616109847,
|
|
"num_tokens": 49362432.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.608698177337646,
|
|
"epoch": 2.130782918149466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000454830472305536,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.22124118208885193,
|
|
"num_tokens": 49373857.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.721438312530518,
|
|
"epoch": 2.1312771846579674,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004548092606979458,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.21645084619522095,
|
|
"num_tokens": 49387545.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.710677528381348,
|
|
"epoch": 2.131771451166469,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045478804466701984,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.21961295157670974,
|
|
"num_tokens": 49398273.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.6636727809906,
|
|
"epoch": 2.1322657176749704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045476682421328015,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.2123141959309578,
|
|
"num_tokens": 49408662.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.679003763198852,
|
|
"epoch": 2.1327599841834717,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045474559933724866,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.21603399962186814,
|
|
"num_tokens": 49421189.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.72951488494873,
|
|
"epoch": 2.133254250691973,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045472437003944753,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.21037341952323912,
|
|
"num_tokens": 49432878.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.696219968795776,
|
|
"epoch": 2.1337485172004746,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004547031363203991,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.21649140268564224,
|
|
"num_tokens": 49444058.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.665451335906982,
|
|
"epoch": 2.134242783708976,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045468189818062554,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.20561412125825881,
|
|
"num_tokens": 49456602.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.671263551712036,
|
|
"epoch": 2.134737050217477,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004546606556206494,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.2113035202026367,
|
|
"num_tokens": 49467287.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.670231199264526,
|
|
"epoch": 2.135231316725979,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004546394086409933,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.21564057022333144,
|
|
"num_tokens": 49478662.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.657781505584717,
|
|
"epoch": 2.13572558323448,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045461815724217984,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.21552485674619676,
|
|
"num_tokens": 49489365.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.719663667678833,
|
|
"epoch": 2.1362198497429814,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045459690142473193,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.2098734810948372,
|
|
"num_tokens": 49501318.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.705675888061523,
|
|
"epoch": 2.1367141162514827,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004545756411891723,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.20505027025938033,
|
|
"num_tokens": 49512138.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.7037523746490475,
|
|
"epoch": 2.1372083827599844,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004545543765360241,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.21258124113082885,
|
|
"num_tokens": 49523325.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.632678031921387,
|
|
"epoch": 2.1377026492684856,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045453310746581036,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.22172578126192094,
|
|
"num_tokens": 49535382.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.652568531036377,
|
|
"epoch": 2.138196915776987,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004545118339790543,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.22377882152795792,
|
|
"num_tokens": 49546151.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.595573616027832,
|
|
"epoch": 2.138691182285488,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004544905560762793,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.2198541983962059,
|
|
"num_tokens": 49558617.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.6624613285064695,
|
|
"epoch": 2.13918544879399,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045446927375800876,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.22603626251220704,
|
|
"num_tokens": 49568494.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.696228122711181,
|
|
"epoch": 2.139679715302491,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045444798702476625,
|
|
"loss": 5.0104,
|
|
"mean_token_accuracy": 0.22291962653398514,
|
|
"num_tokens": 49579763.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.605453586578369,
|
|
"epoch": 2.1401739818109924,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004544266958770755,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.21980197578668595,
|
|
"num_tokens": 49591631.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.662349462509155,
|
|
"epoch": 2.1406682483194936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045440540031546004,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.21075187772512435,
|
|
"num_tokens": 49603458.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.663685321807861,
|
|
"epoch": 2.1411625148279954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045438410034044397,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.2196357324719429,
|
|
"num_tokens": 49614076.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.701815557479859,
|
|
"epoch": 2.1416567813364966,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045436279595255125,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.21169036626815796,
|
|
"num_tokens": 49624982.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.6367738246917725,
|
|
"epoch": 2.142151047844998,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004543414871523059,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21861060410737992,
|
|
"num_tokens": 49635897.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.661371278762817,
|
|
"epoch": 2.1426453143534996,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004543201739402321,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.22130238860845566,
|
|
"num_tokens": 49647023.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.693820858001709,
|
|
"epoch": 2.143139580862001,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045429885631685424,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.20628563612699508,
|
|
"num_tokens": 49658578.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.669672632217408,
|
|
"epoch": 2.143633847370502,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004542775342826967,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.21763622909784316,
|
|
"num_tokens": 49670978.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.599813556671142,
|
|
"epoch": 2.1441281138790034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045425620783828396,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.21933725327253342,
|
|
"num_tokens": 49682553.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.688272523880005,
|
|
"epoch": 2.144622380387505,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004542348769841407,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.2153347611427307,
|
|
"num_tokens": 49694589.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.7083094120025635,
|
|
"epoch": 2.1451166468960063,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045421354172079173,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.21681129634380342,
|
|
"num_tokens": 49706530.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.617859315872193,
|
|
"epoch": 2.1456109134045076,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045419220204876175,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.21920625418424605,
|
|
"num_tokens": 49718524.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.658264780044556,
|
|
"epoch": 2.1461051799130093,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045417085796857596,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2170478031039238,
|
|
"num_tokens": 49729555.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.72885947227478,
|
|
"epoch": 2.1465994464215106,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045414950948075906,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.21782120317220688,
|
|
"num_tokens": 49739708.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.707045221328736,
|
|
"epoch": 2.147093712930012,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045412815658583657,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.2147676795721054,
|
|
"num_tokens": 49750997.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.630479431152343,
|
|
"epoch": 2.147587979438513,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004541067992843336,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.22202005237340927,
|
|
"num_tokens": 49761508.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.696569776535034,
|
|
"epoch": 2.148082245947015,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045408543757677555,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.22115105986595154,
|
|
"num_tokens": 49772821.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.591461229324341,
|
|
"epoch": 2.148576512455516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000454064071463688,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.2261551722884178,
|
|
"num_tokens": 49783932.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.645427799224853,
|
|
"epoch": 2.1490707789640173,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004540427009455965,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.21319205760955812,
|
|
"num_tokens": 49795126.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.676718044281006,
|
|
"epoch": 2.1495650454725186,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004540213260230267,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.21294891685247422,
|
|
"num_tokens": 49806110.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.7491905212402346,
|
|
"epoch": 2.1500593119810203,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004539999466965046,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.2089319184422493,
|
|
"num_tokens": 49818879.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.682772493362426,
|
|
"epoch": 2.1505535784895216,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045397856296655603,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.22046666890382766,
|
|
"num_tokens": 49828986.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.679441642761231,
|
|
"epoch": 2.151047844998023,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045395717483370703,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.21458420902490616,
|
|
"num_tokens": 49841987.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.671192693710327,
|
|
"epoch": 2.1515421115065245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045393578229848373,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.21076978445053102,
|
|
"num_tokens": 49854151.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.690689420700073,
|
|
"epoch": 2.152036378015026,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045391438536141257,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.21620922535657883,
|
|
"num_tokens": 49866531.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.649730777740478,
|
|
"epoch": 2.152530644523527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045389298402301965,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.2213156208395958,
|
|
"num_tokens": 49877737.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.756574296951294,
|
|
"epoch": 2.1530249110320283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004538715782838316,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.204083414375782,
|
|
"num_tokens": 49889214.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.7010244846344,
|
|
"epoch": 2.15351917754053,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045385016814437494,
|
|
"loss": 5.0317,
|
|
"mean_token_accuracy": 0.2199822947382927,
|
|
"num_tokens": 49900293.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.730643320083618,
|
|
"epoch": 2.1540134440490313,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045382875360517645,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.20311021208763122,
|
|
"num_tokens": 49912193.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.722182703018189,
|
|
"epoch": 2.1545077105575325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004538073346667628,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.21897727400064468,
|
|
"num_tokens": 49922780.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.660122394561768,
|
|
"epoch": 2.155001977066034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045378591132966105,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.21952902376651764,
|
|
"num_tokens": 49934551.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.679895639419556,
|
|
"epoch": 2.1554962435745355,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004537644835943982,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21226985901594161,
|
|
"num_tokens": 49945779.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.614342927932739,
|
|
"epoch": 2.1559905100830368,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004537430514615012,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.22672014236450194,
|
|
"num_tokens": 49957127.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.637734317779541,
|
|
"epoch": 2.156484776591538,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045372161493149746,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.21884865015745164,
|
|
"num_tokens": 49968679.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.659509658813477,
|
|
"epoch": 2.1569790431000397,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004537001740049142,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.22233585715293885,
|
|
"num_tokens": 49979924.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.702066564559937,
|
|
"epoch": 2.157473309608541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000453678728682279,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.21362146139144897,
|
|
"num_tokens": 49991318.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.518225479125976,
|
|
"epoch": 2.1579675761170423,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004536572789641193,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.2263866752386093,
|
|
"num_tokens": 50003096.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.624046802520752,
|
|
"epoch": 2.1584618426255435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045363582485096295,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.22103070318698884,
|
|
"num_tokens": 50013953.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.6637674331665036,
|
|
"epoch": 2.1589561091340452,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004536143663433375,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22121310383081436,
|
|
"num_tokens": 50025696.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.693082857131958,
|
|
"epoch": 2.1594503756425465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045359290344177094,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.22216037064790725,
|
|
"num_tokens": 50036880.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.658318185806275,
|
|
"epoch": 2.1599446421510478,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004535714361467913,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.21381282508373262,
|
|
"num_tokens": 50048746.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.63101544380188,
|
|
"epoch": 2.1604389086595495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004535499644589266,
|
|
"loss": 4.9771,
|
|
"mean_token_accuracy": 0.22471747994422914,
|
|
"num_tokens": 50060711.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.6767068862915036,
|
|
"epoch": 2.1609331751680507,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045352848837870496,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.21947458982467652,
|
|
"num_tokens": 50071878.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.715390396118164,
|
|
"epoch": 2.161427441676552,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000453507007906655,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21452721506357192,
|
|
"num_tokens": 50084600.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.564010906219482,
|
|
"epoch": 2.1619217081850532,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004534855230433048,
|
|
"loss": 4.9002,
|
|
"mean_token_accuracy": 0.22306875437498092,
|
|
"num_tokens": 50095814.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.611167240142822,
|
|
"epoch": 2.162415974693555,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045346403378918314,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.2177370086312294,
|
|
"num_tokens": 50108390.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.655351877212524,
|
|
"epoch": 2.162910241202056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004534425401448185,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.21423005312681198,
|
|
"num_tokens": 50118939.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.650758361816406,
|
|
"epoch": 2.1634045077105575,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004534210421107397,
|
|
"loss": 4.9639,
|
|
"mean_token_accuracy": 0.22554995268583297,
|
|
"num_tokens": 50129510.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.66246771812439,
|
|
"epoch": 2.1638987742190587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004533995396874756,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.21990277171134948,
|
|
"num_tokens": 50140611.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.650850677490235,
|
|
"epoch": 2.1643930407275604,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045337803287555525,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.21397680193185806,
|
|
"num_tokens": 50152214.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.767504405975342,
|
|
"epoch": 2.1648873072360617,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004533565216755075,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.2041615813970566,
|
|
"num_tokens": 50164201.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.656232643127441,
|
|
"epoch": 2.165381573744563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004533350060878615,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.22097525149583816,
|
|
"num_tokens": 50176515.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.711996603012085,
|
|
"epoch": 2.1658758402530642,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004533134861131469,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.21349685788154601,
|
|
"num_tokens": 50187624.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.540691089630127,
|
|
"epoch": 2.166370106761566,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004532919617518929,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.22471041828393937,
|
|
"num_tokens": 50199549.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.697504234313965,
|
|
"epoch": 2.166864373270067,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045327043300462887,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.21573407649993898,
|
|
"num_tokens": 50210920.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.6719162940979,
|
|
"epoch": 2.1673586397785685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004532488998718846,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.22538520991802216,
|
|
"num_tokens": 50221335.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.645465660095215,
|
|
"epoch": 2.16785290628707,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045322736235418973,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.210878449678421,
|
|
"num_tokens": 50235138.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.7132649421691895,
|
|
"epoch": 2.1683471727955714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045320582045207405,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.21945931166410446,
|
|
"num_tokens": 50246454.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.721777439117432,
|
|
"epoch": 2.1688414393040727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004531842741660675,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.21189993619918823,
|
|
"num_tokens": 50257591.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.699546670913696,
|
|
"epoch": 2.169335705812574,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004531627234967003,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.21910217851400376,
|
|
"num_tokens": 50268557.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.735510158538818,
|
|
"epoch": 2.1698299723210757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004531411684445024,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20600184351205825,
|
|
"num_tokens": 50280617.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.642502927780152,
|
|
"epoch": 2.170324238829577,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045311960901000403,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21564667373895646,
|
|
"num_tokens": 50292071.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.652326011657715,
|
|
"epoch": 2.170818505338078,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004530980451937358,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.2144598111510277,
|
|
"num_tokens": 50303389.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.670426654815674,
|
|
"epoch": 2.17131277184658,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004530764769962279,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2122088611125946,
|
|
"num_tokens": 50315088.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.674012470245361,
|
|
"epoch": 2.171807038355081,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004530549044180111,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.22129662632942199,
|
|
"num_tokens": 50326177.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.655090379714966,
|
|
"epoch": 2.1723013048635824,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045303332745961605,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.220781672000885,
|
|
"num_tokens": 50337333.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.686314630508423,
|
|
"epoch": 2.1727955713720837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045301174612157345,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.22145062536001206,
|
|
"num_tokens": 50348406.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.637266969680786,
|
|
"epoch": 2.1732898378805854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004529901604044143,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.2269187942147255,
|
|
"num_tokens": 50360057.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.709635448455811,
|
|
"epoch": 2.1737841043890866,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004529685703086697,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.2261491596698761,
|
|
"num_tokens": 50370355.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.669628047943116,
|
|
"epoch": 2.174278370897588,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045294697583487056,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.21288039833307265,
|
|
"num_tokens": 50382193.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.6328973293304445,
|
|
"epoch": 2.174772637406089,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045292537698354824,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.21765660643577575,
|
|
"num_tokens": 50394383.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.627808237075806,
|
|
"epoch": 2.175266903914591,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000452903773755234,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.22593719214200975,
|
|
"num_tokens": 50405006.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.702607917785644,
|
|
"epoch": 2.175761170423092,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004528821661504594,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.21421063542366028,
|
|
"num_tokens": 50416940.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.63926362991333,
|
|
"epoch": 2.1762554369315934,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004528605541697558,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.21788471192121506,
|
|
"num_tokens": 50428506.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.7090311527252195,
|
|
"epoch": 2.176749703440095,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045283893781365513,
|
|
"loss": 5.054,
|
|
"mean_token_accuracy": 0.2127472087740898,
|
|
"num_tokens": 50440421.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.694029521942139,
|
|
"epoch": 2.1772439699485964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004528173170826889,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.21045078486204147,
|
|
"num_tokens": 50451819.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.810104274749756,
|
|
"epoch": 2.1777382364570976,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004527956919773891,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.20480873733758925,
|
|
"num_tokens": 50464382.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.72567572593689,
|
|
"epoch": 2.178232502965599,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004527740624982877,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.21660586148500444,
|
|
"num_tokens": 50474773.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.655304861068726,
|
|
"epoch": 2.1787267694741006,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045275242864591683,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2212412714958191,
|
|
"num_tokens": 50485626.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.694558429718017,
|
|
"epoch": 2.179221035982602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045273079042080854,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.2177233040332794,
|
|
"num_tokens": 50496130.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.682359313964843,
|
|
"epoch": 2.179715302491103,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045270914782349534,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.21738297194242479,
|
|
"num_tokens": 50506578.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.678047370910645,
|
|
"epoch": 2.1802095689996044,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045268750085450946,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20233904719352722,
|
|
"num_tokens": 50517398.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.623337078094482,
|
|
"epoch": 2.180703835508106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004526658495143835,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.2294995129108429,
|
|
"num_tokens": 50528577.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.682349824905396,
|
|
"epoch": 2.1811981020166074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004526441938036501,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.22720635831356048,
|
|
"num_tokens": 50539118.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.651153516769409,
|
|
"epoch": 2.1816923685251086,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045262253372284193,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.21403884291648864,
|
|
"num_tokens": 50549934.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.664872312545777,
|
|
"epoch": 2.1821866350336103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045260086927249193,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.22008953094482422,
|
|
"num_tokens": 50560661.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.6892153263092045,
|
|
"epoch": 2.1826809015421116,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000452579200453133,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.21079075187444687,
|
|
"num_tokens": 50573304.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.693763399124146,
|
|
"epoch": 2.183175168050613,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004525575272652981,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.20983985513448716,
|
|
"num_tokens": 50584166.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.765702724456787,
|
|
"epoch": 2.183669434559114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004525358497095206,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.2062061011791229,
|
|
"num_tokens": 50596425.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.66849193572998,
|
|
"epoch": 2.184163701067616,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045251416778633354,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.2282855287194252,
|
|
"num_tokens": 50607483.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.651926755905151,
|
|
"epoch": 2.184657967576117,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045249248149627046,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.22374370992183684,
|
|
"num_tokens": 50619655.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.706148624420166,
|
|
"epoch": 2.1851522340846183,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045247079083986485,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.20685858875513077,
|
|
"num_tokens": 50631323.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.646940469741821,
|
|
"epoch": 2.18564650059312,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004524490958176502,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.22318165600299836,
|
|
"num_tokens": 50642931.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.589934921264648,
|
|
"epoch": 2.1861407671016213,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004524273964301603,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.22583849728107452,
|
|
"num_tokens": 50655396.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.639464855194092,
|
|
"epoch": 2.1866350336101226,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045240569267792887,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.21836257725954056,
|
|
"num_tokens": 50667264.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.5817564010620115,
|
|
"epoch": 2.187129300118624,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045238398456148995,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.22699138820171355,
|
|
"num_tokens": 50679073.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.684965133666992,
|
|
"epoch": 2.1876235666271255,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045236227208137744,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.21740833222866057,
|
|
"num_tokens": 50689554.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.735178709030151,
|
|
"epoch": 2.188117833135627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004523405552381256,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.2134220153093338,
|
|
"num_tokens": 50702419.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.682103157043457,
|
|
"epoch": 2.188612099644128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004523188340322685,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.21832867860794067,
|
|
"num_tokens": 50713016.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.699271869659424,
|
|
"epoch": 2.1891063661526293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004522971084643406,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21184080988168716,
|
|
"num_tokens": 50723936.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.682348394393921,
|
|
"epoch": 2.189600632661131,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045227537853487627,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.21901579648256303,
|
|
"num_tokens": 50734339.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.75082426071167,
|
|
"epoch": 2.1900948991696323,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045225364424441016,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.20260730981826783,
|
|
"num_tokens": 50746262.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.698929786682129,
|
|
"epoch": 2.1905891656781336,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000452231905593477,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.22087409794330598,
|
|
"num_tokens": 50758218.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.749433374404907,
|
|
"epoch": 2.191083432186635,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004522101625826113,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20996861308813095,
|
|
"num_tokens": 50769263.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.582195472717285,
|
|
"epoch": 2.1915776986951365,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004521884152123482,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.23170056194067,
|
|
"num_tokens": 50780049.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.616878795623779,
|
|
"epoch": 2.192071965203638,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004521666634832227,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.21520345360040666,
|
|
"num_tokens": 50791817.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.665956497192383,
|
|
"epoch": 2.192566231712139,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004521449073957697,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21643973290920257,
|
|
"num_tokens": 50802669.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.730605936050415,
|
|
"epoch": 2.1930604982206408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045212314695052447,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.2178683876991272,
|
|
"num_tokens": 50813920.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.71940655708313,
|
|
"epoch": 2.193554764729142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045210138214802227,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21486475467681884,
|
|
"num_tokens": 50825828.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.6866209506988525,
|
|
"epoch": 2.1940490312376433,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045207961298879875,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.20854361355304718,
|
|
"num_tokens": 50837425.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.681218957901001,
|
|
"epoch": 2.1945432977461445,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004520578394733892,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.21816277503967285,
|
|
"num_tokens": 50848720.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.6503190994262695,
|
|
"epoch": 2.1950375642546462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045203606160232936,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2152488574385643,
|
|
"num_tokens": 50860304.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.691532707214355,
|
|
"epoch": 2.1955318307631475,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004520142793761549,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21251154243946074,
|
|
"num_tokens": 50872099.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.7910911560058596,
|
|
"epoch": 2.1960260972716488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004519924927954017,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20451939702033997,
|
|
"num_tokens": 50884116.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.649617338180542,
|
|
"epoch": 2.1965203637801505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004519707018606059,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.22153560668230057,
|
|
"num_tokens": 50896293.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.61067419052124,
|
|
"epoch": 2.1970146302886517,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045194890657230315,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.22966085225343705,
|
|
"num_tokens": 50908633.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.636182498931885,
|
|
"epoch": 2.197508896797153,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045192710693103,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2224552571773529,
|
|
"num_tokens": 50919524.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.672965431213379,
|
|
"epoch": 2.1980031633056543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004519053029373224,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.2110559046268463,
|
|
"num_tokens": 50930157.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.742501592636108,
|
|
"epoch": 2.198497429814156,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000451883494591717,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.20912256389856337,
|
|
"num_tokens": 50942474.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.7372496128082275,
|
|
"epoch": 2.1989916963226572,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045186168189475026,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.20857156813144684,
|
|
"num_tokens": 50954847.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.687530612945556,
|
|
"epoch": 2.1994859628311585,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004518398648469586,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.2188659906387329,
|
|
"num_tokens": 50966446.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.614317083358765,
|
|
"epoch": 2.1999802293396598,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045181804344887887,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.21999270766973494,
|
|
"num_tokens": 50977949.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.664126253128051,
|
|
"epoch": 2.2004744958481615,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045179621770104786,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.21553430706262589,
|
|
"num_tokens": 50989297.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.691448163986206,
|
|
"epoch": 2.2009687623566627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045177438760400244,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.21469613611698152,
|
|
"num_tokens": 51001616.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.703028678894043,
|
|
"epoch": 2.201463028865164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004517525531582797,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.21347023248672486,
|
|
"num_tokens": 51012870.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.641374254226685,
|
|
"epoch": 2.2019572953736652,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045173071436441665,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.22387326806783675,
|
|
"num_tokens": 51025368.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.675304126739502,
|
|
"epoch": 2.202451561882167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004517088712229507,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.22088173478841783,
|
|
"num_tokens": 51035964.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.693119049072266,
|
|
"epoch": 2.202945828390668,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045168702373441904,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.21184033304452896,
|
|
"num_tokens": 51048313.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.647491025924682,
|
|
"epoch": 2.2034400948991695,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045166517189935924,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.2226567327976227,
|
|
"num_tokens": 51060503.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.638196420669556,
|
|
"epoch": 2.203934361407671,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045164331571830875,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.222506020963192,
|
|
"num_tokens": 51070865.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.666767644882202,
|
|
"epoch": 2.2044286279161724,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045162145519180534,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.21257597357034683,
|
|
"num_tokens": 51081158.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.591541528701782,
|
|
"epoch": 2.2049228944246737,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004515995903203867,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.23046351969242096,
|
|
"num_tokens": 51090661.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.607682752609253,
|
|
"epoch": 2.205417160933175,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004515777211045908,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.21829446852207185,
|
|
"num_tokens": 51101825.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.65821795463562,
|
|
"epoch": 2.2059114274416767,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045155584754495546,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.22002317905426025,
|
|
"num_tokens": 51114546.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.711731672286987,
|
|
"epoch": 2.206405693950178,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004515339696420189,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.21424951255321503,
|
|
"num_tokens": 51124888.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.593837881088257,
|
|
"epoch": 2.206899960458679,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004515120873963194,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.2243323102593422,
|
|
"num_tokens": 51135892.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.665636205673218,
|
|
"epoch": 2.207394226967181,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004514902008083951,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.2126334860920906,
|
|
"num_tokens": 51147513.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.708343553543091,
|
|
"epoch": 2.207888493475682,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004514683098787845,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.21924553513526918,
|
|
"num_tokens": 51159514.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.719173097610474,
|
|
"epoch": 2.2083827599841834,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004514464146080261,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.21159352958202363,
|
|
"num_tokens": 51171245.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.645319032669067,
|
|
"epoch": 2.2088770264926847,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045142451499665846,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.21902304589748384,
|
|
"num_tokens": 51182763.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.706423234939575,
|
|
"epoch": 2.2093712930011864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045140261104522044,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.21056655943393707,
|
|
"num_tokens": 51193811.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.636297130584717,
|
|
"epoch": 2.2098655595096877,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004513807027542508,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.2234930083155632,
|
|
"num_tokens": 51203963.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.636875200271606,
|
|
"epoch": 2.210359826018189,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004513587901242886,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.22789134681224824,
|
|
"num_tokens": 51215128.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.602320766448974,
|
|
"epoch": 2.21085409252669,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045133687315587263,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22642624974250794,
|
|
"num_tokens": 51226773.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.609581708908081,
|
|
"epoch": 2.211348359035192,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004513149518495424,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.21632274836301804,
|
|
"num_tokens": 51238226.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.688904905319214,
|
|
"epoch": 2.211842625543693,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045129302620583683,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.22244412451982498,
|
|
"num_tokens": 51249096.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.732726526260376,
|
|
"epoch": 2.2123368920521944,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045127109622529563,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.2212379679083824,
|
|
"num_tokens": 51259709.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.6275547504425045,
|
|
"epoch": 2.212831158560696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045124916190845797,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.2238454207777977,
|
|
"num_tokens": 51271787.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.676040697097778,
|
|
"epoch": 2.2133254250691974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045122722325586373,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.21753086298704147,
|
|
"num_tokens": 51284093.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.719811677932739,
|
|
"epoch": 2.2138196915776986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045120528026805235,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.2212701141834259,
|
|
"num_tokens": 51295659.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.707357597351074,
|
|
"epoch": 2.2143139580862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045118333294556377,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.20969756692647934,
|
|
"num_tokens": 51307960.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.615570735931397,
|
|
"epoch": 2.2148082245947016,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004511613812889379,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.22497417032718658,
|
|
"num_tokens": 51319366.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.642349672317505,
|
|
"epoch": 2.215302491103203,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045113942529871473,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.21884201020002364,
|
|
"num_tokens": 51332445.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.640856552124023,
|
|
"epoch": 2.215796757611704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004511174649754343,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.22297832369804382,
|
|
"num_tokens": 51342900.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.615917634963989,
|
|
"epoch": 2.2162910241202054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000451095500319637,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.22067887783050538,
|
|
"num_tokens": 51354437.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.600045680999756,
|
|
"epoch": 2.216785290628707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000451073531331863,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.22387824356555938,
|
|
"num_tokens": 51364630.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.685436391830445,
|
|
"epoch": 2.2172795571372084,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004510515580126528,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.2097620040178299,
|
|
"num_tokens": 51376547.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.752695035934448,
|
|
"epoch": 2.2177738236457096,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000451029580362547,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.22155168503522873,
|
|
"num_tokens": 51388704.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.8351866722106935,
|
|
"epoch": 2.2182680901542113,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004510075983820862,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.19838051348924637,
|
|
"num_tokens": 51400884.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.635405206680298,
|
|
"epoch": 2.2187623566627126,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045098561207181114,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.2275451213121414,
|
|
"num_tokens": 51412946.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.662896299362183,
|
|
"epoch": 2.219256623171214,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004509636214322628,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.21676404774188995,
|
|
"num_tokens": 51425860.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.705865955352783,
|
|
"epoch": 2.219750889679715,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004509416264639821,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.2161942318081856,
|
|
"num_tokens": 51438812.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.7193882942199705,
|
|
"epoch": 2.220245156188217,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004509196271675101,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.21055757105350495,
|
|
"num_tokens": 51449881.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.614821338653565,
|
|
"epoch": 2.220739422696718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045089762354338784,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.22074348777532576,
|
|
"num_tokens": 51460403.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.697412395477295,
|
|
"epoch": 2.2212336892052194,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045087561559215683,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.21104186475276948,
|
|
"num_tokens": 51471414.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.601916837692261,
|
|
"epoch": 2.221727955713721,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045085360331435835,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.2218962848186493,
|
|
"num_tokens": 51482855.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.72335376739502,
|
|
"epoch": 2.2222222222222223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000450831586710534,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21442992389202117,
|
|
"num_tokens": 51495363.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.674115180969238,
|
|
"epoch": 2.2227164887307236,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045080956578122535,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.2135403946042061,
|
|
"num_tokens": 51506678.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.700314617156982,
|
|
"epoch": 2.223210755239225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045078754052697406,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.2191697046160698,
|
|
"num_tokens": 51518596.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.752384519577026,
|
|
"epoch": 2.2237050217477266,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045076551094832206,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.20221661925315856,
|
|
"num_tokens": 51531292.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.674378252029419,
|
|
"epoch": 2.224199288256228,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045074347704581114,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.22457479536533356,
|
|
"num_tokens": 51542507.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.643131828308105,
|
|
"epoch": 2.224693554764729,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045072143881998345,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.21815322190523148,
|
|
"num_tokens": 51553895.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.690120029449463,
|
|
"epoch": 2.2251878212732303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004506993962713812,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.21139990538358688,
|
|
"num_tokens": 51566533.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.728049468994141,
|
|
"epoch": 2.225682087781732,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045067734940054644,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.21251696795225145,
|
|
"num_tokens": 51576308.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.662898159027099,
|
|
"epoch": 2.2261763542902333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045065529820802165,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.2218948110938072,
|
|
"num_tokens": 51589844.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.639301919937134,
|
|
"epoch": 2.2266706207987346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045063324269434924,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.2232772395014763,
|
|
"num_tokens": 51601685.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.701422595977784,
|
|
"epoch": 2.227164887307236,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004506111828600719,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.22477250844240187,
|
|
"num_tokens": 51613258.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.747844505310058,
|
|
"epoch": 2.2276591538157375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004505891187057322,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.22189033925533294,
|
|
"num_tokens": 51624088.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.68549542427063,
|
|
"epoch": 2.228153420324239,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004505670502318729,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.22499199211597443,
|
|
"num_tokens": 51636617.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.70145583152771,
|
|
"epoch": 2.22864768683274,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045054497743903687,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.20768143683671952,
|
|
"num_tokens": 51647777.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.683493566513062,
|
|
"epoch": 2.2291419533412418,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004505229003277673,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20870109498500825,
|
|
"num_tokens": 51660505.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.730178594589233,
|
|
"epoch": 2.229636219849743,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045050081889860713,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.22540943026542665,
|
|
"num_tokens": 51672296.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.650163269042968,
|
|
"epoch": 2.2301304863582443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045047873315209945,
|
|
"loss": 5.0213,
|
|
"mean_token_accuracy": 0.22351315766572952,
|
|
"num_tokens": 51684437.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.599716711044311,
|
|
"epoch": 2.2306247528667456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004504566430887878,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.2340442344546318,
|
|
"num_tokens": 51694919.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.6593451499938965,
|
|
"epoch": 2.2311190193752473,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045043454870921553,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.2194284200668335,
|
|
"num_tokens": 51705273.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.703883695602417,
|
|
"epoch": 2.2316132858837485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004504124500139261,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.21367145627737044,
|
|
"num_tokens": 51717048.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.718654680252075,
|
|
"epoch": 2.23210755239225,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004503903470034632,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.20823822766542435,
|
|
"num_tokens": 51729208.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.5936203956604,
|
|
"epoch": 2.2326018189007515,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045036823967837066,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.22665866762399672,
|
|
"num_tokens": 51740393.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.6753825664520265,
|
|
"epoch": 2.2330960854092528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004503461280391921,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21936925649642944,
|
|
"num_tokens": 51751044.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.692008113861084,
|
|
"epoch": 2.233590351917754,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004503240120864716,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.2134673535823822,
|
|
"num_tokens": 51761969.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.66832275390625,
|
|
"epoch": 2.2340846184262553,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004503018918207532,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21148513704538346,
|
|
"num_tokens": 51774185.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.706737947463989,
|
|
"epoch": 2.234578884934757,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004502797672425811,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.22073792815208435,
|
|
"num_tokens": 51786155.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.672430419921875,
|
|
"epoch": 2.2350731514432582,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045025763835249957,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.2145986184477806,
|
|
"num_tokens": 51797125.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.751372575759888,
|
|
"epoch": 2.2355674179517595,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004502355051510528,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.21077884137630462,
|
|
"num_tokens": 51809046.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.753048229217529,
|
|
"epoch": 2.2360616844602608,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045021336763878555,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.2004881262779236,
|
|
"num_tokens": 51821857.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.726709079742432,
|
|
"epoch": 2.2365559509687625,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045019122581624224,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.2191958338022232,
|
|
"num_tokens": 51833504.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.617403650283814,
|
|
"epoch": 2.2370502174772637,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045016907968396764,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.21488860100507737,
|
|
"num_tokens": 51844166.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.6753013134002686,
|
|
"epoch": 2.237544483985765,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004501469292425064,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.2175396665930748,
|
|
"num_tokens": 51855674.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.638219404220581,
|
|
"epoch": 2.2380387504942667,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045012477449240363,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.2164605215191841,
|
|
"num_tokens": 51866128.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.679204511642456,
|
|
"epoch": 2.238533017002768,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045010261543420416,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.21784630417823792,
|
|
"num_tokens": 51877036.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.698066759109497,
|
|
"epoch": 2.2390272835112692,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004500804520684532,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.22097880095243455,
|
|
"num_tokens": 51888331.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.729745197296142,
|
|
"epoch": 2.2395215500197705,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045005828439569594,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.21344051212072374,
|
|
"num_tokens": 51899843.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.7472278594970705,
|
|
"epoch": 2.240015816528272,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045003611241647783,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.2084558129310608,
|
|
"num_tokens": 51911429.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.676789999008179,
|
|
"epoch": 2.2405100830367735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045001393613134413,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2173532083630562,
|
|
"num_tokens": 51923154.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.713173866271973,
|
|
"epoch": 2.2410043495452747,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004499917555408405,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.21408035904169082,
|
|
"num_tokens": 51935126.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.688978290557861,
|
|
"epoch": 2.241498616053776,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044996957064551244,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.21319541335105896,
|
|
"num_tokens": 51947629.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.693309640884399,
|
|
"epoch": 2.2419928825622777,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004499473814459059,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.21482918411493301,
|
|
"num_tokens": 51957631.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.719139814376831,
|
|
"epoch": 2.242487149070779,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044992518794256657,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.21509247422218322,
|
|
"num_tokens": 51969854.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.74778299331665,
|
|
"epoch": 2.24298141557928,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044990299013604045,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.21321891248226166,
|
|
"num_tokens": 51980501.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.676448202133178,
|
|
"epoch": 2.243475682087782,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044988078802687373,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.2137457773089409,
|
|
"num_tokens": 51991336.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.705523872375489,
|
|
"epoch": 2.243969948596283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004498585816156124,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.21265614181756973,
|
|
"num_tokens": 52003215.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.753480052947998,
|
|
"epoch": 2.2444642151047844,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004498363709028029,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.21478519290685655,
|
|
"num_tokens": 52014772.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.7069189071655275,
|
|
"epoch": 2.2449584816132857,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044981415588899153,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.20979753285646438,
|
|
"num_tokens": 52025808.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.695060539245605,
|
|
"epoch": 2.2454527481217874,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004497919365747248,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.2127516359090805,
|
|
"num_tokens": 52037397.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.6413736820220945,
|
|
"epoch": 2.2459470146302887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044976971296054936,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.22446622401475907,
|
|
"num_tokens": 52048874.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.718465566635132,
|
|
"epoch": 2.24644128113879,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004497474850470118,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.2092381790280342,
|
|
"num_tokens": 52061180.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.72221565246582,
|
|
"epoch": 2.2469355476472916,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000449725252834659,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.21246058791875838,
|
|
"num_tokens": 52073400.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.694234085083008,
|
|
"epoch": 2.247429814155793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044970301632403796,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.21970780938863754,
|
|
"num_tokens": 52084737.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.628676223754883,
|
|
"epoch": 2.247924080664294,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044968077551569554,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.21977199018001556,
|
|
"num_tokens": 52096044.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.687891912460327,
|
|
"epoch": 2.2484183471727954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000449658530410179,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.22497704327106477,
|
|
"num_tokens": 52108701.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.714768028259277,
|
|
"epoch": 2.248912613681297,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004496362810080354,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.21947241127490996,
|
|
"num_tokens": 52119797.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.6833827018737795,
|
|
"epoch": 2.2494068801897984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004496140273098123,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.21265851855278015,
|
|
"num_tokens": 52132557.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.608319425582886,
|
|
"epoch": 2.2499011466982997,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044959176931605704,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.22188480347394943,
|
|
"num_tokens": 52144058.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.70881028175354,
|
|
"epoch": 2.250395413206801,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044956950702731714,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.22054446935653688,
|
|
"num_tokens": 52155432.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.662421846389771,
|
|
"epoch": 2.2508896797153026,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004495472404441403,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.2186515137553215,
|
|
"num_tokens": 52166925.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.6225813865661625,
|
|
"epoch": 2.251383946223804,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004495249695670742,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.212876757979393,
|
|
"num_tokens": 52177452.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.677905416488647,
|
|
"epoch": 2.251878212732305,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004495026943966669,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.21327440887689592,
|
|
"num_tokens": 52189288.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.629843854904175,
|
|
"epoch": 2.2523724792408064,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044948041493346615,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.220742130279541,
|
|
"num_tokens": 52199963.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.635707569122315,
|
|
"epoch": 2.252866745749308,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004494581311780202,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.21408036053180696,
|
|
"num_tokens": 52210727.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.710407638549805,
|
|
"epoch": 2.2533610122578094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044943584313087705,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.21765277087688445,
|
|
"num_tokens": 52222211.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.729773807525635,
|
|
"epoch": 2.2538552787663106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044941355079258517,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.2111378252506256,
|
|
"num_tokens": 52234453.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.637953567504883,
|
|
"epoch": 2.2543495452748123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004493912541636928,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.22029542028903962,
|
|
"num_tokens": 52246324.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.72339768409729,
|
|
"epoch": 2.2548438117833136,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004493689532447486,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.2144623577594757,
|
|
"num_tokens": 52258223.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.67529296875,
|
|
"epoch": 2.255338078291815,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004493466480363011,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.22118455171585083,
|
|
"num_tokens": 52270066.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.78153395652771,
|
|
"epoch": 2.255832344800316,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044932433853889903,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.20846378803253174,
|
|
"num_tokens": 52281366.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.686095094680786,
|
|
"epoch": 2.256326611308818,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004493020247530912,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.21414400786161422,
|
|
"num_tokens": 52292109.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.609932804107666,
|
|
"epoch": 2.256820877817319,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004492797066794264,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.2312849536538124,
|
|
"num_tokens": 52302707.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.658918380737305,
|
|
"epoch": 2.2573151443258204,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044925738431845385,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.22031792849302292,
|
|
"num_tokens": 52313715.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.710073566436767,
|
|
"epoch": 2.257809410834322,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044923505767072267,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.20963357537984847,
|
|
"num_tokens": 52325612.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.582243824005127,
|
|
"epoch": 2.2583036773428233,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044921272673678197,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.22864942252635956,
|
|
"num_tokens": 52338233.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.662897539138794,
|
|
"epoch": 2.2587979438513246,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004491903915171812,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.22055939882993697,
|
|
"num_tokens": 52348792.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.681028079986572,
|
|
"epoch": 2.259292210359826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044916805201246975,
|
|
"loss": 5.0738,
|
|
"mean_token_accuracy": 0.2128281518816948,
|
|
"num_tokens": 52359334.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.719241952896118,
|
|
"epoch": 2.2597864768683276,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044914570822319723,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2072407752275467,
|
|
"num_tokens": 52370600.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.708096027374268,
|
|
"epoch": 2.260280743376829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004491233601499132,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.21664016395807267,
|
|
"num_tokens": 52382783.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.638728761672974,
|
|
"epoch": 2.26077500988533,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044910100779316757,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.22957417666912078,
|
|
"num_tokens": 52393372.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.631084680557251,
|
|
"epoch": 2.261269276393832,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004490786511535102,
|
|
"loss": 4.9734,
|
|
"mean_token_accuracy": 0.2170527011156082,
|
|
"num_tokens": 52405181.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.6507344245910645,
|
|
"epoch": 2.261763542902333,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044905629023149084,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.2128605991601944,
|
|
"num_tokens": 52417371.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.716310596466064,
|
|
"epoch": 2.2622578094108343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004490339250276598,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.2118415728211403,
|
|
"num_tokens": 52428712.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.671646356582642,
|
|
"epoch": 2.2627520759193356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004490115555425672,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.21647128611803054,
|
|
"num_tokens": 52439764.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.636702299118042,
|
|
"epoch": 2.263246342427837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004489891817767634,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.2117112770676613,
|
|
"num_tokens": 52451409.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.706080055236816,
|
|
"epoch": 2.2637406089363385,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044896680373079874,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21242875158786773,
|
|
"num_tokens": 52461471.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.6779533386230465,
|
|
"epoch": 2.26423487544484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044894442140522365,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.2137769341468811,
|
|
"num_tokens": 52472693.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.64128270149231,
|
|
"epoch": 2.264729141953341,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004489220348005889,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.21976672112941742,
|
|
"num_tokens": 52483449.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.636235332489013,
|
|
"epoch": 2.265223408461843,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000448899643917445,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.21751079708337784,
|
|
"num_tokens": 52494048.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.715504455566406,
|
|
"epoch": 2.265717674970344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004488772487563429,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.2083883136510849,
|
|
"num_tokens": 52506224.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.6978295803070065,
|
|
"epoch": 2.2662119414788453,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004488548493178336,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.21202306300401688,
|
|
"num_tokens": 52517157.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.6975850582122805,
|
|
"epoch": 2.2667062079873466,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044883244560246793,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.2150995299220085,
|
|
"num_tokens": 52528826.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.684078025817871,
|
|
"epoch": 2.2672004744958483,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004488100376107972,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.2266093224287033,
|
|
"num_tokens": 52540068.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.632140398025513,
|
|
"epoch": 2.2676947410043495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004487876253433726,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.22181721329689025,
|
|
"num_tokens": 52552611.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.6190532684326175,
|
|
"epoch": 2.268189007512851,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004487652088007454,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.2166075587272644,
|
|
"num_tokens": 52564532.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.740961790084839,
|
|
"epoch": 2.2686832740213525,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004487427879834671,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20927091240882872,
|
|
"num_tokens": 52576110.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.7315624237060545,
|
|
"epoch": 2.2691775405298538,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044872036289208926,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.21775861829519272,
|
|
"num_tokens": 52586890.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.667583560943603,
|
|
"epoch": 2.269671807038355,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004486979335271635,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.22180592864751816,
|
|
"num_tokens": 52598597.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.639960241317749,
|
|
"epoch": 2.2701660735468563,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044867549988924176,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.22313950955867767,
|
|
"num_tokens": 52609361.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.741444158554077,
|
|
"epoch": 2.270660340055358,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044865306197887573,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.21177972853183746,
|
|
"num_tokens": 52620954.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.71704511642456,
|
|
"epoch": 2.2711546065638593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044863061979661745,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.21156969368457795,
|
|
"num_tokens": 52631944.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.733975982666015,
|
|
"epoch": 2.2716488730723605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004486081733430189,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.2120288148522377,
|
|
"num_tokens": 52642517.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.701702499389649,
|
|
"epoch": 2.2721431395808622,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044858572261863245,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.21623460054397584,
|
|
"num_tokens": 52653654.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.692103004455566,
|
|
"epoch": 2.2726374060893635,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004485632676240102,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.21682728528976442,
|
|
"num_tokens": 52666068.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.727848291397095,
|
|
"epoch": 2.2731316725978647,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004485408083597047,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.21564664840698242,
|
|
"num_tokens": 52677797.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.688394403457641,
|
|
"epoch": 2.273625939106366,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004485183448262684,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.22105617672204972,
|
|
"num_tokens": 52688947.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.648006820678711,
|
|
"epoch": 2.2741202056148677,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004484958770242538,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.20803418457508088,
|
|
"num_tokens": 52700357.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.735352659225464,
|
|
"epoch": 2.274614472123369,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044847340495421384,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.20366864949464797,
|
|
"num_tokens": 52712602.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.727027416229248,
|
|
"epoch": 2.2751087386318702,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044845092861670114,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.2190770536661148,
|
|
"num_tokens": 52723480.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.654927158355713,
|
|
"epoch": 2.2756030051403715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004484284480122688,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.21196895688772202,
|
|
"num_tokens": 52735418.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.628233957290649,
|
|
"epoch": 2.276097271648873,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044840596314146955,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.22278324514627457,
|
|
"num_tokens": 52746308.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.594630908966065,
|
|
"epoch": 2.2765915381573745,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004483834740048568,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.23119399845600128,
|
|
"num_tokens": 52756834.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.67337474822998,
|
|
"epoch": 2.2770858046658757,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004483609806029837,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21497540175914764,
|
|
"num_tokens": 52768398.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.735830783843994,
|
|
"epoch": 2.277580071174377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044833848293640354,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.2108389377593994,
|
|
"num_tokens": 52780062.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.700595808029175,
|
|
"epoch": 2.2780743376828787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044831598100566984,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.218555223941803,
|
|
"num_tokens": 52791760.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.651475191116333,
|
|
"epoch": 2.27856860419138,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044829347481133613,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.22268069088459014,
|
|
"num_tokens": 52802638.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.631056690216065,
|
|
"epoch": 2.2790628706998812,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000448270964353956,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.21831170916557313,
|
|
"num_tokens": 52813590.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.660090780258178,
|
|
"epoch": 2.279557137208383,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004482484496340833,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.2164960280060768,
|
|
"num_tokens": 52824177.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.814073991775513,
|
|
"epoch": 2.280051403716884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004482259306522719,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20324424505233765,
|
|
"num_tokens": 52834637.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.721695852279663,
|
|
"epoch": 2.2805456702253855,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044820340740907565,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.21495870649814605,
|
|
"num_tokens": 52847893.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.69823145866394,
|
|
"epoch": 2.2810399367338867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004481808799050488,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.2143731027841568,
|
|
"num_tokens": 52859339.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.716180229187012,
|
|
"epoch": 2.2815342032423884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044815834814074544,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.21188420355319976,
|
|
"num_tokens": 52872405.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.654378461837768,
|
|
"epoch": 2.2820284697508897,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004481358121167198,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.2271616891026497,
|
|
"num_tokens": 52882187.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.648568820953369,
|
|
"epoch": 2.282522736259391,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044811327183352627,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.22084983736276625,
|
|
"num_tokens": 52894004.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.763744783401489,
|
|
"epoch": 2.2830170027678927,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004480907272917195,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21307190358638764,
|
|
"num_tokens": 52904749.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.638816595077515,
|
|
"epoch": 2.283511269276394,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004480681784918539,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2152424305677414,
|
|
"num_tokens": 52915794.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.6871199131011965,
|
|
"epoch": 2.284005535784895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044804562543448436,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.2138795405626297,
|
|
"num_tokens": 52926695.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.663855695724488,
|
|
"epoch": 2.2844998022933964,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004480230681201655,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.21976750791072847,
|
|
"num_tokens": 52937824.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.634802293777466,
|
|
"epoch": 2.284994068801898,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044800050654945233,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.21329197734594346,
|
|
"num_tokens": 52949174.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.68503885269165,
|
|
"epoch": 2.2854883353103994,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044797794072289987,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.21012507528066635,
|
|
"num_tokens": 52960675.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.712743139266967,
|
|
"epoch": 2.2859826018189007,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044795537064106335,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.2165724068880081,
|
|
"num_tokens": 52971705.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.705541610717773,
|
|
"epoch": 2.2864768683274024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044793279630449777,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.21343256086111068,
|
|
"num_tokens": 52983025.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.710432624816894,
|
|
"epoch": 2.2869711348359036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004479102177137586,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.20440847426652908,
|
|
"num_tokens": 52993810.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.70296835899353,
|
|
"epoch": 2.287465401344405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004478876348694012,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.20884255170822144,
|
|
"num_tokens": 53005902.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.688646745681763,
|
|
"epoch": 2.287959667852906,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004478650477719812,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.21161330193281175,
|
|
"num_tokens": 53017511.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.599677610397339,
|
|
"epoch": 2.2884539343614074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004478424564220542,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.22579682469367982,
|
|
"num_tokens": 53028514.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.6960084438323975,
|
|
"epoch": 2.288948200869909,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044781986082017595,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.21880811154842378,
|
|
"num_tokens": 53039338.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.681038236618042,
|
|
"epoch": 2.2894424673784104,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044779726096690227,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.22350631207227706,
|
|
"num_tokens": 53050877.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.694847822189331,
|
|
"epoch": 2.2899367338869117,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004477746568627892,
|
|
"loss": 5.0104,
|
|
"mean_token_accuracy": 0.21236397475004196,
|
|
"num_tokens": 53062819.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.7100687503814695,
|
|
"epoch": 2.2904310003954134,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044775204850839277,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.21225139647722244,
|
|
"num_tokens": 53073486.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.647610902786255,
|
|
"epoch": 2.2909252669039146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004477294359042692,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.22147968411445618,
|
|
"num_tokens": 53084499.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.6587401866912845,
|
|
"epoch": 2.291419533412416,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004477068190509747,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.2131115734577179,
|
|
"num_tokens": 53097181.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.73638424873352,
|
|
"epoch": 2.291913799920917,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044768419794906556,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.21377201974391938,
|
|
"num_tokens": 53108586.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.742063236236572,
|
|
"epoch": 2.292408066429419,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044766157259909853,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.21430430114269255,
|
|
"num_tokens": 53119481.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.6958447933197025,
|
|
"epoch": 2.29290233293792,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004476389430016299,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.2223695084452629,
|
|
"num_tokens": 53129482.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.614659070968628,
|
|
"epoch": 2.2933965994464214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044761630915721645,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.21895683258771897,
|
|
"num_tokens": 53142311.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.679651975631714,
|
|
"epoch": 2.293890865954923,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004475936710664151,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.21591575741767882,
|
|
"num_tokens": 53153485.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.666842269897461,
|
|
"epoch": 2.2943851324634243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004475710287297826,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.21228787153959275,
|
|
"num_tokens": 53164121.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.702724456787109,
|
|
"epoch": 2.2948793989719256,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004475483821478761,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.2163947731256485,
|
|
"num_tokens": 53174949.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.6245036125183105,
|
|
"epoch": 2.295373665480427,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044752573132125263,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.22054691910743712,
|
|
"num_tokens": 53186762.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.681869459152222,
|
|
"epoch": 2.2958679319889286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004475030762504694,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.21575143486261367,
|
|
"num_tokens": 53198261.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.586990928649902,
|
|
"epoch": 2.29636219849743,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004474804169360836,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.22699526101350784,
|
|
"num_tokens": 53209143.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.733219146728516,
|
|
"epoch": 2.296856465005931,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044745775337865293,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.21018125414848327,
|
|
"num_tokens": 53222619.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.680987453460693,
|
|
"epoch": 2.297350731514433,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044743508557873473,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.22305282354354858,
|
|
"num_tokens": 53233829.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.671728515625,
|
|
"epoch": 2.297844998022934,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044741241353688665,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.20802544802427292,
|
|
"num_tokens": 53244248.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.719701433181763,
|
|
"epoch": 2.2983392645314353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004473897372536665,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.21471018195152283,
|
|
"num_tokens": 53255638.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.734069061279297,
|
|
"epoch": 2.2988335310399366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447367056729632,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.2135075718164444,
|
|
"num_tokens": 53265798.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.668795919418335,
|
|
"epoch": 2.2993277975484383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004473443719653412,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.22370714992284774,
|
|
"num_tokens": 53278001.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.68076343536377,
|
|
"epoch": 2.2998220640569396,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044732168296135217,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.21044055372476578,
|
|
"num_tokens": 53289742.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.71370940208435,
|
|
"epoch": 2.300316330565441,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044729898971822296,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.21935127973556517,
|
|
"num_tokens": 53301285.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.642543125152588,
|
|
"epoch": 2.300810597073942,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004472762922365118,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.22366938591003419,
|
|
"num_tokens": 53312883.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.71660270690918,
|
|
"epoch": 2.301304863582444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004472535905167773,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.20965449810028075,
|
|
"num_tokens": 53325215.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.706032562255859,
|
|
"epoch": 2.301799130090945,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004472308845595776,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.2081302061676979,
|
|
"num_tokens": 53337104.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.691897392272949,
|
|
"epoch": 2.3022933965994463,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004472081743654715,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.21492475569248198,
|
|
"num_tokens": 53348097.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.680724287033081,
|
|
"epoch": 2.3027876631079476,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044718545993501754,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.22704749703407287,
|
|
"num_tokens": 53358405.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.70723066329956,
|
|
"epoch": 2.3032819296164493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004471627412687745,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.21774028688669206,
|
|
"num_tokens": 53370012.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.749528264999389,
|
|
"epoch": 2.3037761961249505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044714001836730145,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.21145770251750945,
|
|
"num_tokens": 53383214.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.708898210525513,
|
|
"epoch": 2.304270462633452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044711729123115716,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.2096566990017891,
|
|
"num_tokens": 53395672.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.666447734832763,
|
|
"epoch": 2.3047647291419535,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044709455986090084,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21555528938770294,
|
|
"num_tokens": 53407577.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.657599449157715,
|
|
"epoch": 2.305258995650455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004470718242570916,
|
|
"loss": 4.9618,
|
|
"mean_token_accuracy": 0.2172285199165344,
|
|
"num_tokens": 53417772.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.733635711669922,
|
|
"epoch": 2.305753262158956,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004470490844202889,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.2115627944469452,
|
|
"num_tokens": 53429675.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.678607559204101,
|
|
"epoch": 2.3062475286674573,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004470263403510519,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.2096492677927017,
|
|
"num_tokens": 53442352.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.74375319480896,
|
|
"epoch": 2.306741795175959,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044700359204994034,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.20670633018016815,
|
|
"num_tokens": 53453710.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.695979833602905,
|
|
"epoch": 2.3072360616844603,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044698083951751365,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.22462694644927977,
|
|
"num_tokens": 53464764.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.678501272201538,
|
|
"epoch": 2.3077303281929615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004469580827543318,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.22243524640798568,
|
|
"num_tokens": 53476495.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.688408613204956,
|
|
"epoch": 2.3082245947014632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004469353217609542,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.2108292043209076,
|
|
"num_tokens": 53488613.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.722078561782837,
|
|
"epoch": 2.3087188612099645,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004469125565379411,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.2090960457921028,
|
|
"num_tokens": 53501851.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.712436819076538,
|
|
"epoch": 2.3092131277184658,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004468897870858525,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20903616696596145,
|
|
"num_tokens": 53514325.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.742020940780639,
|
|
"epoch": 2.309707394226967,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044686701340524836,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.22027665376663208,
|
|
"num_tokens": 53525717.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.6945885181427,
|
|
"epoch": 2.3102016607354687,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004468442354966891,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.21449732035398483,
|
|
"num_tokens": 53536488.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.761054563522339,
|
|
"epoch": 2.31069592724397,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000446821453360735,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.20337573438882828,
|
|
"num_tokens": 53547230.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.737098264694214,
|
|
"epoch": 2.3111901937524713,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044679866699794644,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.20744367837905883,
|
|
"num_tokens": 53558673.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.6743306636810305,
|
|
"epoch": 2.311684460260973,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004467758764088841,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.22115942388772963,
|
|
"num_tokens": 53570088.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.682835292816162,
|
|
"epoch": 2.3121787267694742,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004467530815941085,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.22157259583473204,
|
|
"num_tokens": 53582115.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.6456841945648195,
|
|
"epoch": 2.3126729932779755,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044673028255418047,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.2149854138493538,
|
|
"num_tokens": 53594719.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.5851655960083,
|
|
"epoch": 2.3131672597864767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004467074792896608,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.22980525642633437,
|
|
"num_tokens": 53606453.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.679275846481323,
|
|
"epoch": 2.313661526294978,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044668467180111054,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.21826194524765014,
|
|
"num_tokens": 53617038.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.769206428527832,
|
|
"epoch": 2.3141557928034797,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044666186008909077,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.2195906400680542,
|
|
"num_tokens": 53627230.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.722536039352417,
|
|
"epoch": 2.314650059311981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044663904415416245,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.21001044809818267,
|
|
"num_tokens": 53638247.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.722390794754029,
|
|
"epoch": 2.3151443258204822,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004466162239968871,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.21694618314504624,
|
|
"num_tokens": 53648643.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.6543860912323,
|
|
"epoch": 2.315638592328984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004465933996178261,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.22980217337608339,
|
|
"num_tokens": 53659715.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.623960304260254,
|
|
"epoch": 2.316132858837485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044657057101754073,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.21481255441904068,
|
|
"num_tokens": 53671119.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.69827880859375,
|
|
"epoch": 2.3166271253459865,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044654773819659277,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.22371531575918197,
|
|
"num_tokens": 53682145.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.732368278503418,
|
|
"epoch": 2.3171213918544877,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044652490115554386,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.22277864664793015,
|
|
"num_tokens": 53693882.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.6837279319763185,
|
|
"epoch": 2.3176156583629894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004465020598949557,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.21185367107391356,
|
|
"num_tokens": 53706010.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.680853462219238,
|
|
"epoch": 2.3181099248714907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004464792144153903,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.2140778586268425,
|
|
"num_tokens": 53717657.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.709449005126953,
|
|
"epoch": 2.318604191379992,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004464563647174096,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.21985059678554536,
|
|
"num_tokens": 53729181.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.651836824417114,
|
|
"epoch": 2.3190984578884937,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004464335108015757,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.2277241140604019,
|
|
"num_tokens": 53740864.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.63017258644104,
|
|
"epoch": 2.319592724396995,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004464106526684509,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.21748261004686356,
|
|
"num_tokens": 53751726.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.732248973846436,
|
|
"epoch": 2.320086990905496,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004463877903185974,
|
|
"loss": 5.0404,
|
|
"mean_token_accuracy": 0.21556512415409088,
|
|
"num_tokens": 53763629.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.6761658668518065,
|
|
"epoch": 2.3205812574139975,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004463649237525777,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.22481902986764907,
|
|
"num_tokens": 53774814.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.711197137832642,
|
|
"epoch": 2.321075523922499,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004463420529709543,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.21792300343513488,
|
|
"num_tokens": 53786298.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.693343448638916,
|
|
"epoch": 2.3215697904310004,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044631917797428985,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.21814027726650237,
|
|
"num_tokens": 53798509.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.717051982879639,
|
|
"epoch": 2.3220640569395017,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000446296298763147,
|
|
"loss": 5.0907,
|
|
"mean_token_accuracy": 0.21217311918735504,
|
|
"num_tokens": 53810689.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.710059881210327,
|
|
"epoch": 2.3225583234480034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004462734153380886,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.2131557583808899,
|
|
"num_tokens": 53822432.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.678190469741821,
|
|
"epoch": 2.3230525899565047,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044625052769967766,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21896739453077316,
|
|
"num_tokens": 53833701.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.6734034538269045,
|
|
"epoch": 2.323546856465006,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044622763584847716,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.2222059339284897,
|
|
"num_tokens": 53844413.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.642414093017578,
|
|
"epoch": 2.324041122973507,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044620473978505023,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.22081330567598342,
|
|
"num_tokens": 53856392.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.727092456817627,
|
|
"epoch": 2.324535389482009,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044618183950996017,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.21695526838302612,
|
|
"num_tokens": 53867938.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.622947311401367,
|
|
"epoch": 2.32502965599051,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004461589350237702,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.22543786615133285,
|
|
"num_tokens": 53878153.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.611142873764038,
|
|
"epoch": 2.3255239224990114,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000446136026327044,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.220254085958004,
|
|
"num_tokens": 53889090.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.6422473907470705,
|
|
"epoch": 2.3260181890075127,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044611311342034494,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.22219029664993287,
|
|
"num_tokens": 53900459.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.6777183532714846,
|
|
"epoch": 2.3265124555160144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004460901963042368,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.22414757311344147,
|
|
"num_tokens": 53912815.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.603401374816895,
|
|
"epoch": 2.3270067220245156,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044606727497928324,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.22347140461206436,
|
|
"num_tokens": 53924387.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.711576795578003,
|
|
"epoch": 2.327500988533017,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044604434944604826,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.21276316344738005,
|
|
"num_tokens": 53936147.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.67951922416687,
|
|
"epoch": 2.327995255041518,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004460214197050956,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.21447852700948716,
|
|
"num_tokens": 53948102.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.727203416824341,
|
|
"epoch": 2.32848952155002,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004459984857569896,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.20715589970350265,
|
|
"num_tokens": 53959721.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.674393892288208,
|
|
"epoch": 2.328983788058521,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044597554760229433,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.215665203332901,
|
|
"num_tokens": 53970302.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.774135255813599,
|
|
"epoch": 2.3294780545670224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000445952605241574,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.21364330649375915,
|
|
"num_tokens": 53982198.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.734185457229614,
|
|
"epoch": 2.329972321075524,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044592965867539306,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.21166161596775054,
|
|
"num_tokens": 53994443.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.682979011535645,
|
|
"epoch": 2.3304665875840254,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044590670790431604,
|
|
"loss": 4.9948,
|
|
"mean_token_accuracy": 0.2171334832906723,
|
|
"num_tokens": 54005666.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.7016603469848635,
|
|
"epoch": 2.3309608540925266,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004458837529289074,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.22118810266256334,
|
|
"num_tokens": 54016173.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.636428022384644,
|
|
"epoch": 2.331455120601028,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004458607937497321,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.21214968711137772,
|
|
"num_tokens": 54027743.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.735698270797729,
|
|
"epoch": 2.3319493871095296,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004458378303673546,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.21122650057077408,
|
|
"num_tokens": 54039804.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.7199584484100345,
|
|
"epoch": 2.332443653618031,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004458148627823401,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.21671708226203917,
|
|
"num_tokens": 54050202.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.712037563323975,
|
|
"epoch": 2.332937920126532,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044579189099525334,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21777575165033342,
|
|
"num_tokens": 54061088.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.61924147605896,
|
|
"epoch": 2.333432186635034,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044576891500665967,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.22296383529901503,
|
|
"num_tokens": 54072524.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.677139186859131,
|
|
"epoch": 2.333926453143535,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004457459348171242,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.21721460968255996,
|
|
"num_tokens": 54083265.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.676045751571655,
|
|
"epoch": 2.3344207196520363,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044572295042721215,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.2307722568511963,
|
|
"num_tokens": 54093848.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.637051725387574,
|
|
"epoch": 2.3349149861605376,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044569996183748913,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.22925136387348174,
|
|
"num_tokens": 54104595.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.568222713470459,
|
|
"epoch": 2.3354092526690393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044567696904852057,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.22692091315984725,
|
|
"num_tokens": 54115577.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.682089757919312,
|
|
"epoch": 2.3359035191775406,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000445653972060872,
|
|
"loss": 4.968,
|
|
"mean_token_accuracy": 0.22168441265821456,
|
|
"num_tokens": 54125579.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.692544603347779,
|
|
"epoch": 2.336397785686042,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044563097087510934,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.21008388847112655,
|
|
"num_tokens": 54137895.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.720218563079834,
|
|
"epoch": 2.3368920521945435,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044560796549179826,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.21132448464632034,
|
|
"num_tokens": 54149423.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.793787670135498,
|
|
"epoch": 2.337386318703045,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004455849559115048,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.2149218052625656,
|
|
"num_tokens": 54160743.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.726458597183227,
|
|
"epoch": 2.337880585211546,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004455619421347949,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.21330489069223404,
|
|
"num_tokens": 54171517.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.6738362312316895,
|
|
"epoch": 2.3383748517200473,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044553892416223485,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.22007000148296357,
|
|
"num_tokens": 54182959.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.687151384353638,
|
|
"epoch": 2.3388691182285486,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044551590199439075,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.21805785745382308,
|
|
"num_tokens": 54194577.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.744302225112915,
|
|
"epoch": 2.3393633847370503,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000445492875631829,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.20234737694263458,
|
|
"num_tokens": 54207423.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.688050079345703,
|
|
"epoch": 2.3398576512455516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004454698450751161,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.21903806328773498,
|
|
"num_tokens": 54218776.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.724394989013672,
|
|
"epoch": 2.340351917754053,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004454468103248186,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.22351094335317612,
|
|
"num_tokens": 54229508.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.748839378356934,
|
|
"epoch": 2.3408461842625545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000445423771381503,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.21015447229146958,
|
|
"num_tokens": 54240546.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.686213541030884,
|
|
"epoch": 2.341340450771056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004454007282457364,
|
|
"loss": 5.031,
|
|
"mean_token_accuracy": 0.2186095595359802,
|
|
"num_tokens": 54252486.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.735169792175293,
|
|
"epoch": 2.341834717279557,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044537768091808516,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.2164394363760948,
|
|
"num_tokens": 54264240.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.7081934928894045,
|
|
"epoch": 2.3423289837880583,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004453546293991168,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.22104554027318954,
|
|
"num_tokens": 54275894.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.708915424346924,
|
|
"epoch": 2.34282325029656,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000445331573689398,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.21392490863800048,
|
|
"num_tokens": 54287697.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.636246824264527,
|
|
"epoch": 2.3433175168050613,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000445308513789496,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.2331737145781517,
|
|
"num_tokens": 54300327.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.723508310317993,
|
|
"epoch": 2.3438117833135625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044528544969997823,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.21122708916664124,
|
|
"num_tokens": 54311949.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.672755527496338,
|
|
"epoch": 2.3443060498220643,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044526238142141196,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.21691982001066207,
|
|
"num_tokens": 54322134.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.7213561058044435,
|
|
"epoch": 2.3448003163305655,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044523930895436475,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.20234075784683228,
|
|
"num_tokens": 54334579.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.708582639694214,
|
|
"epoch": 2.3452945828390668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044521623229940407,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.21302523016929625,
|
|
"num_tokens": 54346624.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.661236333847046,
|
|
"epoch": 2.345788849347568,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044519315145709765,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.21953872889280318,
|
|
"num_tokens": 54356455.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.748168277740478,
|
|
"epoch": 2.3462831158560697,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004451700664280133,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.20701320618391036,
|
|
"num_tokens": 54368141.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.7215172290802006,
|
|
"epoch": 2.346777382364571,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000445146977212719,
|
|
"loss": 5.0402,
|
|
"mean_token_accuracy": 0.21474129110574722,
|
|
"num_tokens": 54379304.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.691365194320679,
|
|
"epoch": 2.3472716488730723,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004451238838117826,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.22139421552419664,
|
|
"num_tokens": 54391462.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.669318914413452,
|
|
"epoch": 2.347765915381574,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004451007862257723,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.22784819453954697,
|
|
"num_tokens": 54402325.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.628589725494384,
|
|
"epoch": 2.3482601818900752,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004450776844552562,
|
|
"loss": 4.9341,
|
|
"mean_token_accuracy": 0.22085167318582535,
|
|
"num_tokens": 54413874.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.66631121635437,
|
|
"epoch": 2.3487544483985765,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004450545785008027,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.21492263227701186,
|
|
"num_tokens": 54426266.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.673762607574463,
|
|
"epoch": 2.3492487149070778,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044503146836298026,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.21731659173965454,
|
|
"num_tokens": 54436682.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.676106309890747,
|
|
"epoch": 2.3497429814155795,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044500835404235727,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.2167414680123329,
|
|
"num_tokens": 54447462.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.733704996109009,
|
|
"epoch": 2.3502372479240807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004449852355395024,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.2226727545261383,
|
|
"num_tokens": 54460116.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.747341918945312,
|
|
"epoch": 2.350731514432582,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044496211285498434,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.223288856446743,
|
|
"num_tokens": 54471016.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.659575176239014,
|
|
"epoch": 2.3512257809410833,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000444938985989372,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.22074017971754073,
|
|
"num_tokens": 54482410.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.628712892532349,
|
|
"epoch": 2.351720047449585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044491585494323415,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.2154706358909607,
|
|
"num_tokens": 54495555.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.74377293586731,
|
|
"epoch": 2.3522143139580862,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044489271971713995,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.21765593737363814,
|
|
"num_tokens": 54505658.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.601878261566162,
|
|
"epoch": 2.3527085804665875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044486958031165856,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.22546352595090866,
|
|
"num_tokens": 54518633.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.768847370147705,
|
|
"epoch": 2.3532028469750887,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044484643672735907,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.2091477856040001,
|
|
"num_tokens": 54531451.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.695329332351685,
|
|
"epoch": 2.3536971134835905,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004448232889648109,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.22564560920000076,
|
|
"num_tokens": 54542798.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.666089820861816,
|
|
"epoch": 2.3541913799920917,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004448001370245835,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.21576445549726486,
|
|
"num_tokens": 54554551.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.756264543533325,
|
|
"epoch": 2.354685646500593,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044477698090724635,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.21258767545223237,
|
|
"num_tokens": 54564711.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.723188209533691,
|
|
"epoch": 2.3551799130090947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044475382061336913,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.2124479278922081,
|
|
"num_tokens": 54576096.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.703089952468872,
|
|
"epoch": 2.355674179517596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004447306561435215,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.21234242171049117,
|
|
"num_tokens": 54587939.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.748182487487793,
|
|
"epoch": 2.356168446026097,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044470748749827354,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.21989842057228087,
|
|
"num_tokens": 54598470.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.721365165710449,
|
|
"epoch": 2.3566627125345985,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044468431467819505,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.21920582354068757,
|
|
"num_tokens": 54608840.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.669226837158203,
|
|
"epoch": 2.3571569790431,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000444661137683856,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.21371020376682281,
|
|
"num_tokens": 54619319.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.658643198013306,
|
|
"epoch": 2.3576512455516014,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004446379565158268,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.21837828308343887,
|
|
"num_tokens": 54630410.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.732089853286743,
|
|
"epoch": 2.3581455120601027,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004446147711746774,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.20949156284332277,
|
|
"num_tokens": 54642376.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.691869592666626,
|
|
"epoch": 2.3586397785686044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004445915816609784,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2172745794057846,
|
|
"num_tokens": 54654378.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.6832562446594235,
|
|
"epoch": 2.3591340450771057,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044456838797530006,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.2149462953209877,
|
|
"num_tokens": 54664879.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.670623445510865,
|
|
"epoch": 2.359628311585607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004445451901182132,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.2199103444814682,
|
|
"num_tokens": 54677251.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.68749098777771,
|
|
"epoch": 2.360122578094108,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004445219880902884,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.21702411472797395,
|
|
"num_tokens": 54688827.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.641295766830444,
|
|
"epoch": 2.36061684460261,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004444987818920963,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.2122592329978943,
|
|
"num_tokens": 54701046.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.727259969711303,
|
|
"epoch": 2.361111111111111,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004444755715242078,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.21145299673080445,
|
|
"num_tokens": 54713254.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.681588983535766,
|
|
"epoch": 2.3616053776196124,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044445235698719406,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.22435097098350526,
|
|
"num_tokens": 54723734.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.747234439849853,
|
|
"epoch": 2.362099644128114,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000444429138281626,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.21391547918319703,
|
|
"num_tokens": 54735080.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.647678279876709,
|
|
"epoch": 2.3625939106366154,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044440591540807496,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.2227100908756256,
|
|
"num_tokens": 54745164.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.641484117507934,
|
|
"epoch": 2.3630881771451167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000444382688367112,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.21475329995155334,
|
|
"num_tokens": 54757350.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.66078634262085,
|
|
"epoch": 2.363582443653618,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044435945715930864,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.221308571100235,
|
|
"num_tokens": 54768290.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.708400821685791,
|
|
"epoch": 2.364076710162119,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004443362217852364,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.21427827179431916,
|
|
"num_tokens": 54779053.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.7770191669464115,
|
|
"epoch": 2.364570976670621,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004443129822454668,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.2033746436238289,
|
|
"num_tokens": 54789787.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.745732545852661,
|
|
"epoch": 2.365065243179122,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044428973854057164,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.2150130569934845,
|
|
"num_tokens": 54802036.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.737455129623413,
|
|
"epoch": 2.3655595096876234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044426649067112257,
|
|
"loss": 5.0552,
|
|
"mean_token_accuracy": 0.21968555450439453,
|
|
"num_tokens": 54811765.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.650635242462158,
|
|
"epoch": 2.366053776196125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004442432386376916,
|
|
"loss": 4.9908,
|
|
"mean_token_accuracy": 0.22027362883090973,
|
|
"num_tokens": 54823057.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.684525966644287,
|
|
"epoch": 2.3665480427046264,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044421998244085066,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.21251795589923858,
|
|
"num_tokens": 54834070.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.664101791381836,
|
|
"epoch": 2.3670423092131276,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044419672208117204,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.21255804896354674,
|
|
"num_tokens": 54845913.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.688136768341065,
|
|
"epoch": 2.367536575721629,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004441734575592276,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.21540898233652114,
|
|
"num_tokens": 54856721.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.762500858306884,
|
|
"epoch": 2.3680308422301306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044415018887559,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.20872692316770552,
|
|
"num_tokens": 54868652.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.653864479064941,
|
|
"epoch": 2.368525108738632,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004441269160308315,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.22462428659200667,
|
|
"num_tokens": 54880753.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.574725770950318,
|
|
"epoch": 2.369019375247133,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044410363902552466,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.23104054778814315,
|
|
"num_tokens": 54891724.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.682564353942871,
|
|
"epoch": 2.369513641755635,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000444080357860242,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.21701662838459015,
|
|
"num_tokens": 54902516.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.714620351791382,
|
|
"epoch": 2.370007908264136,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044405707253555626,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.2138836920261383,
|
|
"num_tokens": 54914392.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.665670776367188,
|
|
"epoch": 2.3705021747726374,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004440337830520404,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.22086611539125442,
|
|
"num_tokens": 54925209.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.692057657241821,
|
|
"epoch": 2.3709964412811386,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044401048941026725,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.21360094398260115,
|
|
"num_tokens": 54935972.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.698579454421997,
|
|
"epoch": 2.3714907077896403,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004439871916108098,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.2243943527340889,
|
|
"num_tokens": 54945631.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.675301218032837,
|
|
"epoch": 2.3719849742981416,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044396388965424124,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.21650419235229493,
|
|
"num_tokens": 54955734.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.659920406341553,
|
|
"epoch": 2.372479240806643,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004439405835411348,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.21386342942714692,
|
|
"num_tokens": 54968506.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.372479240806643,
|
|
"eval_entropy": 5.509411944733041,
|
|
"eval_loss": 5.077908992767334,
|
|
"eval_mean_token_accuracy": 0.221356893383049,
|
|
"eval_num_tokens": 54968506.0,
|
|
"eval_runtime": 20.5482,
|
|
"eval_samples_per_second": 1582.278,
|
|
"eval_steps_per_second": 197.827,
|
|
"step": 24000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 101150,
|
|
"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": 1.275532438634496e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|