34ce47b2b0
Model: fpadovani/isl-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.29655990510083036,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.469703674316406,
|
|
"epoch": 0.0004942665085013839,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.3039,
|
|
"mean_token_accuracy": 0.08914985954761505,
|
|
"num_tokens": 11289.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.451202011108398,
|
|
"epoch": 0.0009885330170027679,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.2923,
|
|
"mean_token_accuracy": 0.09169483110308647,
|
|
"num_tokens": 21541.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.475129747390747,
|
|
"epoch": 0.0014827995255041518,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.2709,
|
|
"mean_token_accuracy": 0.09598705545067787,
|
|
"num_tokens": 32257.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.492884302139283,
|
|
"epoch": 0.0019770660340055358,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.2938,
|
|
"mean_token_accuracy": 0.09161478653550148,
|
|
"num_tokens": 44176.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.503809309005737,
|
|
"epoch": 0.0024713325425069197,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.2106,
|
|
"mean_token_accuracy": 0.0929027833044529,
|
|
"num_tokens": 56115.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.537404775619507,
|
|
"epoch": 0.0029655990510083037,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.0948231890797615,
|
|
"num_tokens": 68828.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.524669170379639,
|
|
"epoch": 0.0034598655595096876,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.2556,
|
|
"mean_token_accuracy": 0.09147608950734139,
|
|
"num_tokens": 80097.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.5563098907470705,
|
|
"epoch": 0.0039541320680110716,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.2372,
|
|
"mean_token_accuracy": 0.09377887398004532,
|
|
"num_tokens": 91510.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.577905559539795,
|
|
"epoch": 0.004448398576512456,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.2791,
|
|
"mean_token_accuracy": 0.09560152813792229,
|
|
"num_tokens": 103443.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.562246513366699,
|
|
"epoch": 0.0049426650850138395,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.3081,
|
|
"mean_token_accuracy": 0.08996103182435036,
|
|
"num_tokens": 114629.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.533729696273804,
|
|
"epoch": 0.005436931593515224,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.306,
|
|
"mean_token_accuracy": 0.09244225695729255,
|
|
"num_tokens": 125012.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.58353476524353,
|
|
"epoch": 0.005931198102016607,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.2392,
|
|
"mean_token_accuracy": 0.09736663252115249,
|
|
"num_tokens": 135834.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.575706529617309,
|
|
"epoch": 0.006425464610517992,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.1391,
|
|
"mean_token_accuracy": 0.10104931369423867,
|
|
"num_tokens": 147413.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.567987012863159,
|
|
"epoch": 0.006919731119019375,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.328,
|
|
"mean_token_accuracy": 0.09703772887587547,
|
|
"num_tokens": 158046.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.553958082199097,
|
|
"epoch": 0.00741399762752076,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.2398,
|
|
"mean_token_accuracy": 0.09700576439499856,
|
|
"num_tokens": 168564.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.556397438049316,
|
|
"epoch": 0.007908264136022143,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.2517,
|
|
"mean_token_accuracy": 0.09499543234705925,
|
|
"num_tokens": 181168.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.5417234897613525,
|
|
"epoch": 0.008402530644523527,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.2216,
|
|
"mean_token_accuracy": 0.0979242317378521,
|
|
"num_tokens": 192666.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.562561988830566,
|
|
"epoch": 0.008896797153024912,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.2863,
|
|
"mean_token_accuracy": 0.09055893197655678,
|
|
"num_tokens": 203688.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.481156682968139,
|
|
"epoch": 0.009391063661526295,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.1426,
|
|
"mean_token_accuracy": 0.10065646544098854,
|
|
"num_tokens": 214399.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.469635391235352,
|
|
"epoch": 0.009885330170027679,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.2347,
|
|
"mean_token_accuracy": 0.09190195500850677,
|
|
"num_tokens": 227549.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.503566455841065,
|
|
"epoch": 0.010379596678529062,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.1392,
|
|
"mean_token_accuracy": 0.10797618925571442,
|
|
"num_tokens": 239612.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.572363758087159,
|
|
"epoch": 0.010873863187030448,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.2757,
|
|
"mean_token_accuracy": 0.09476120248436928,
|
|
"num_tokens": 251163.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.461998224258423,
|
|
"epoch": 0.011368129695531831,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.1332,
|
|
"mean_token_accuracy": 0.1059160701930523,
|
|
"num_tokens": 263995.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.588790702819824,
|
|
"epoch": 0.011862396204033215,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.3141,
|
|
"mean_token_accuracy": 0.08305804803967476,
|
|
"num_tokens": 275103.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.536360836029052,
|
|
"epoch": 0.012356662712534598,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.2092,
|
|
"mean_token_accuracy": 0.09603819251060486,
|
|
"num_tokens": 286838.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.514512634277343,
|
|
"epoch": 0.012850929221035983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.237,
|
|
"mean_token_accuracy": 0.0946768917143345,
|
|
"num_tokens": 298750.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.4676471710205075,
|
|
"epoch": 0.013345195729537367,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.1196,
|
|
"mean_token_accuracy": 0.10568102300167084,
|
|
"num_tokens": 310451.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.508374309539795,
|
|
"epoch": 0.01383946223803875,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.2575,
|
|
"mean_token_accuracy": 0.09567514508962631,
|
|
"num_tokens": 321232.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.625961065292358,
|
|
"epoch": 0.014333728746540134,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.1811,
|
|
"mean_token_accuracy": 0.09812303707003593,
|
|
"num_tokens": 332531.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.4815513610839846,
|
|
"epoch": 0.01482799525504152,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.1754,
|
|
"mean_token_accuracy": 0.09771352261304855,
|
|
"num_tokens": 346002.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.486629390716553,
|
|
"epoch": 0.015322261763542903,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.1493,
|
|
"mean_token_accuracy": 0.09570263773202896,
|
|
"num_tokens": 356691.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.513840389251709,
|
|
"epoch": 0.015816528272044286,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.1711,
|
|
"mean_token_accuracy": 0.09991738945245743,
|
|
"num_tokens": 368749.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.455194139480591,
|
|
"epoch": 0.01631079478054567,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.1046,
|
|
"mean_token_accuracy": 0.10521886423230171,
|
|
"num_tokens": 379484.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.511811923980713,
|
|
"epoch": 0.016805061289047053,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.1474,
|
|
"mean_token_accuracy": 0.09446320682764053,
|
|
"num_tokens": 389751.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.460206699371338,
|
|
"epoch": 0.017299327797548437,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.1648,
|
|
"mean_token_accuracy": 0.09561898037791253,
|
|
"num_tokens": 400771.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.551068878173828,
|
|
"epoch": 0.017793594306049824,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.1854,
|
|
"mean_token_accuracy": 0.09663412421941757,
|
|
"num_tokens": 413575.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.459692096710205,
|
|
"epoch": 0.018287860814551207,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.1186,
|
|
"mean_token_accuracy": 0.09810871481895447,
|
|
"num_tokens": 424825.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.612393522262574,
|
|
"epoch": 0.01878212732305259,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1832,
|
|
"mean_token_accuracy": 0.10366637259721756,
|
|
"num_tokens": 435610.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.4823657989501955,
|
|
"epoch": 0.019276393831553974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1995,
|
|
"mean_token_accuracy": 0.09689589515328408,
|
|
"num_tokens": 445855.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.4008557319641115,
|
|
"epoch": 0.019770660340055358,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.078,
|
|
"mean_token_accuracy": 0.10040710046887398,
|
|
"num_tokens": 456895.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.558928728103638,
|
|
"epoch": 0.02026492684855674,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.226,
|
|
"mean_token_accuracy": 0.09527792558073997,
|
|
"num_tokens": 467446.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.542035818099976,
|
|
"epoch": 0.020759193357058125,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1408,
|
|
"mean_token_accuracy": 0.09867265969514846,
|
|
"num_tokens": 478988.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.445913553237915,
|
|
"epoch": 0.02125345986555951,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1245,
|
|
"mean_token_accuracy": 0.10041875392198563,
|
|
"num_tokens": 491053.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.589331150054932,
|
|
"epoch": 0.021747726374060895,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2108,
|
|
"mean_token_accuracy": 0.09277821779251098,
|
|
"num_tokens": 502279.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.351877689361572,
|
|
"epoch": 0.02224199288256228,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0907,
|
|
"mean_token_accuracy": 0.10218187943100929,
|
|
"num_tokens": 513470.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.563132953643799,
|
|
"epoch": 0.022736259391063662,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1604,
|
|
"mean_token_accuracy": 0.09525467976927757,
|
|
"num_tokens": 524380.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.478720617294312,
|
|
"epoch": 0.023230525899565046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1638,
|
|
"mean_token_accuracy": 0.09922493025660514,
|
|
"num_tokens": 535798.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.49151644706726,
|
|
"epoch": 0.02372479240806643,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.1082,
|
|
"mean_token_accuracy": 0.10218137353658677,
|
|
"num_tokens": 545720.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.510548734664917,
|
|
"epoch": 0.024219058916567813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1354,
|
|
"mean_token_accuracy": 0.10085964500904084,
|
|
"num_tokens": 557110.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.368914556503296,
|
|
"epoch": 0.024713325425069196,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0898,
|
|
"mean_token_accuracy": 0.10415727794170379,
|
|
"num_tokens": 568966.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.4961333751678465,
|
|
"epoch": 0.02520759193357058,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1273,
|
|
"mean_token_accuracy": 0.10322419255971908,
|
|
"num_tokens": 580441.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.495905208587646,
|
|
"epoch": 0.025701858442071967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1237,
|
|
"mean_token_accuracy": 0.09592118486762047,
|
|
"num_tokens": 592698.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.46055006980896,
|
|
"epoch": 0.02619612495057335,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1033,
|
|
"mean_token_accuracy": 0.10308752283453941,
|
|
"num_tokens": 604787.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.470848751068115,
|
|
"epoch": 0.026690391459074734,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0865,
|
|
"mean_token_accuracy": 0.0982378177344799,
|
|
"num_tokens": 616445.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.464596509933472,
|
|
"epoch": 0.027184657967576117,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1405,
|
|
"mean_token_accuracy": 0.10080643817782402,
|
|
"num_tokens": 627723.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.526458120346069,
|
|
"epoch": 0.0276789244760775,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1866,
|
|
"mean_token_accuracy": 0.09936180636286736,
|
|
"num_tokens": 638987.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.4703020572662355,
|
|
"epoch": 0.028173190984578884,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.10166787654161454,
|
|
"num_tokens": 650626.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.38916015625,
|
|
"epoch": 0.028667457493080268,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0269,
|
|
"mean_token_accuracy": 0.1108930952847004,
|
|
"num_tokens": 661911.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.406114387512207,
|
|
"epoch": 0.02916172400158165,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0953,
|
|
"mean_token_accuracy": 0.1046306237578392,
|
|
"num_tokens": 674298.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.434783887863159,
|
|
"epoch": 0.02965599051008304,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0246,
|
|
"mean_token_accuracy": 0.1099107675254345,
|
|
"num_tokens": 686000.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.457195472717285,
|
|
"epoch": 0.030150257018584422,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0606,
|
|
"mean_token_accuracy": 0.10334300473332406,
|
|
"num_tokens": 698464.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.388035774230957,
|
|
"epoch": 0.030644523527085805,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0749,
|
|
"mean_token_accuracy": 0.10073440000414849,
|
|
"num_tokens": 709702.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.647989797592163,
|
|
"epoch": 0.03113879003558719,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1756,
|
|
"mean_token_accuracy": 0.09775948747992516,
|
|
"num_tokens": 722234.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.324582767486572,
|
|
"epoch": 0.03163305654408857,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1208,
|
|
"mean_token_accuracy": 0.10032215490937232,
|
|
"num_tokens": 733001.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.522441816329956,
|
|
"epoch": 0.03212732305258996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0869,
|
|
"mean_token_accuracy": 0.1011140413582325,
|
|
"num_tokens": 743315.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.429833459854126,
|
|
"epoch": 0.03262158956109134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0304,
|
|
"mean_token_accuracy": 0.10157204046845436,
|
|
"num_tokens": 754386.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.433870887756347,
|
|
"epoch": 0.033115856069592726,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1433,
|
|
"mean_token_accuracy": 0.10339019373059273,
|
|
"num_tokens": 766504.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.289975929260254,
|
|
"epoch": 0.033610122578094107,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9711,
|
|
"mean_token_accuracy": 0.11004318147897721,
|
|
"num_tokens": 777039.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.508639812469482,
|
|
"epoch": 0.034104389086595494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0737,
|
|
"mean_token_accuracy": 0.10165267884731292,
|
|
"num_tokens": 787890.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.268938064575195,
|
|
"epoch": 0.034598655595096874,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0296,
|
|
"mean_token_accuracy": 0.10082691311836242,
|
|
"num_tokens": 800129.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.4750524997711185,
|
|
"epoch": 0.03509292210359826,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1229,
|
|
"mean_token_accuracy": 0.09419984817504883,
|
|
"num_tokens": 812517.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.386541795730591,
|
|
"epoch": 0.03558718861209965,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.0536,
|
|
"mean_token_accuracy": 0.10280298069119453,
|
|
"num_tokens": 824570.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.37411732673645,
|
|
"epoch": 0.03608145512060103,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0507,
|
|
"mean_token_accuracy": 0.10352159217000008,
|
|
"num_tokens": 836506.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.47959794998169,
|
|
"epoch": 0.036575721629102415,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0444,
|
|
"mean_token_accuracy": 0.10556175038218499,
|
|
"num_tokens": 846841.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.415268468856811,
|
|
"epoch": 0.037069988137603795,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0936,
|
|
"mean_token_accuracy": 0.10685667470097542,
|
|
"num_tokens": 858770.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.34727110862732,
|
|
"epoch": 0.03756425464610518,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.944,
|
|
"mean_token_accuracy": 0.10581078305840493,
|
|
"num_tokens": 870184.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.387606573104859,
|
|
"epoch": 0.03805852115460656,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.996,
|
|
"mean_token_accuracy": 0.10772442370653153,
|
|
"num_tokens": 881843.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.415964269638062,
|
|
"epoch": 0.03855278766310795,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.0285,
|
|
"mean_token_accuracy": 0.10454590618610382,
|
|
"num_tokens": 893453.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.4321942806243895,
|
|
"epoch": 0.03904705417160933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0785,
|
|
"mean_token_accuracy": 0.09805944114923477,
|
|
"num_tokens": 904417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.339347553253174,
|
|
"epoch": 0.039541320680110716,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.0135,
|
|
"mean_token_accuracy": 0.10153622105717659,
|
|
"num_tokens": 915134.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.397016334533691,
|
|
"epoch": 0.0400355871886121,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0317,
|
|
"mean_token_accuracy": 0.10312987342476845,
|
|
"num_tokens": 926361.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.307787704467773,
|
|
"epoch": 0.04052985369711348,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9558,
|
|
"mean_token_accuracy": 0.10188485085964202,
|
|
"num_tokens": 937474.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.432948350906372,
|
|
"epoch": 0.04102412020561487,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.021,
|
|
"mean_token_accuracy": 0.1049279622733593,
|
|
"num_tokens": 948897.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.335451555252075,
|
|
"epoch": 0.04151838671411625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.0438,
|
|
"mean_token_accuracy": 0.10066490024328231,
|
|
"num_tokens": 960669.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.3269850730896,
|
|
"epoch": 0.04201265322261764,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8868,
|
|
"mean_token_accuracy": 0.10576090738177299,
|
|
"num_tokens": 973001.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.289369392395019,
|
|
"epoch": 0.04250691973111902,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.957,
|
|
"mean_token_accuracy": 0.10359662398695946,
|
|
"num_tokens": 986214.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.209768915176392,
|
|
"epoch": 0.043001186239620404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9765,
|
|
"mean_token_accuracy": 0.10080774426460266,
|
|
"num_tokens": 997363.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.378287410736084,
|
|
"epoch": 0.04349545274812179,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.89,
|
|
"mean_token_accuracy": 0.11189188435673714,
|
|
"num_tokens": 1009543.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.301484727859497,
|
|
"epoch": 0.04398971925662317,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.984,
|
|
"mean_token_accuracy": 0.10262056440114975,
|
|
"num_tokens": 1020561.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.333764362335205,
|
|
"epoch": 0.04448398576512456,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.9396,
|
|
"mean_token_accuracy": 0.1044077455997467,
|
|
"num_tokens": 1032587.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.36834979057312,
|
|
"epoch": 0.04497825227362594,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.949,
|
|
"mean_token_accuracy": 0.10236429199576377,
|
|
"num_tokens": 1044249.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.328242921829224,
|
|
"epoch": 0.045472518782127325,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.9932,
|
|
"mean_token_accuracy": 0.10464346408843994,
|
|
"num_tokens": 1055415.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.299544954299927,
|
|
"epoch": 0.045966785290628705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.9773,
|
|
"mean_token_accuracy": 0.10330140814185143,
|
|
"num_tokens": 1066593.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.335889530181885,
|
|
"epoch": 0.04646105179913009,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.9728,
|
|
"mean_token_accuracy": 0.1081781692802906,
|
|
"num_tokens": 1076966.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.278144025802613,
|
|
"epoch": 0.04695531830763147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.0076,
|
|
"mean_token_accuracy": 0.10260550826787948,
|
|
"num_tokens": 1089927.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.320434522628784,
|
|
"epoch": 0.04744958481613286,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.9523,
|
|
"mean_token_accuracy": 0.10259445980191231,
|
|
"num_tokens": 1101920.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.355521011352539,
|
|
"epoch": 0.047943851324634246,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.0105,
|
|
"mean_token_accuracy": 0.10701147764921189,
|
|
"num_tokens": 1115078.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.400402402877807,
|
|
"epoch": 0.048438117833135626,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0944,
|
|
"mean_token_accuracy": 0.0997918725013733,
|
|
"num_tokens": 1127138.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.240495920181274,
|
|
"epoch": 0.04893238434163701,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8923,
|
|
"mean_token_accuracy": 0.1018766038119793,
|
|
"num_tokens": 1138390.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.1997147560119625,
|
|
"epoch": 0.04942665085013839,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.8512,
|
|
"mean_token_accuracy": 0.11121880635619164,
|
|
"num_tokens": 1149124.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.302788877487183,
|
|
"epoch": 0.04992091735863978,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9238,
|
|
"mean_token_accuracy": 0.1091496266424656,
|
|
"num_tokens": 1161091.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.353948354721069,
|
|
"epoch": 0.05041518386714116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.893,
|
|
"mean_token_accuracy": 0.10641072243452072,
|
|
"num_tokens": 1171919.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.2228254795074465,
|
|
"epoch": 0.05090945037564255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.9246,
|
|
"mean_token_accuracy": 0.10590804591774941,
|
|
"num_tokens": 1183688.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.212153196334839,
|
|
"epoch": 0.051403716884143934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.8462,
|
|
"mean_token_accuracy": 0.10454064607620239,
|
|
"num_tokens": 1195323.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.319693851470947,
|
|
"epoch": 0.051897983392645314,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.9631,
|
|
"mean_token_accuracy": 0.10184277668595314,
|
|
"num_tokens": 1206782.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.154052352905273,
|
|
"epoch": 0.0523922499011467,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.8618,
|
|
"mean_token_accuracy": 0.11248803958296776,
|
|
"num_tokens": 1218102.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.168608140945435,
|
|
"epoch": 0.05288651640964808,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8305,
|
|
"mean_token_accuracy": 0.11310576722025871,
|
|
"num_tokens": 1230199.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.333725214004517,
|
|
"epoch": 0.05338078291814947,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.9599,
|
|
"mean_token_accuracy": 0.10180617794394493,
|
|
"num_tokens": 1242127.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.257206916809082,
|
|
"epoch": 0.05387504942665085,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.8219,
|
|
"mean_token_accuracy": 0.10760059282183647,
|
|
"num_tokens": 1252329.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.028431701660156,
|
|
"epoch": 0.054369315935152235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.8242,
|
|
"mean_token_accuracy": 0.11318544000387191,
|
|
"num_tokens": 1264832.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.242120885848999,
|
|
"epoch": 0.054863582443653615,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9013,
|
|
"mean_token_accuracy": 0.1043594166636467,
|
|
"num_tokens": 1276708.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.267107915878296,
|
|
"epoch": 0.055357848952155,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7969,
|
|
"mean_token_accuracy": 0.11708691790699959,
|
|
"num_tokens": 1288089.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.195605134963989,
|
|
"epoch": 0.05585211546065639,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.9462,
|
|
"mean_token_accuracy": 0.10276999175548554,
|
|
"num_tokens": 1299411.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.24189248085022,
|
|
"epoch": 0.05634638196915777,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.10456405952572823,
|
|
"num_tokens": 1311368.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.220668077468872,
|
|
"epoch": 0.056840648477659156,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.8516,
|
|
"mean_token_accuracy": 0.11227458119392394,
|
|
"num_tokens": 1321962.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.196398830413818,
|
|
"epoch": 0.057334914986160536,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.8289,
|
|
"mean_token_accuracy": 0.11454056426882744,
|
|
"num_tokens": 1335150.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.223259687423706,
|
|
"epoch": 0.05782918149466192,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.11283383145928383,
|
|
"num_tokens": 1346986.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.1827106952667235,
|
|
"epoch": 0.0583234480031633,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8096,
|
|
"mean_token_accuracy": 0.11008091494441033,
|
|
"num_tokens": 1357820.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.12157974243164,
|
|
"epoch": 0.05881771451166469,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.7996,
|
|
"mean_token_accuracy": 0.11600334495306015,
|
|
"num_tokens": 1368269.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.093701171875,
|
|
"epoch": 0.05931198102016608,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.8325,
|
|
"mean_token_accuracy": 0.10474282503128052,
|
|
"num_tokens": 1380364.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.230424165725708,
|
|
"epoch": 0.05980624752866746,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.7834,
|
|
"mean_token_accuracy": 0.11662303283810616,
|
|
"num_tokens": 1390667.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.1123291015625,
|
|
"epoch": 0.060300514037168844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.74,
|
|
"mean_token_accuracy": 0.11314672902226448,
|
|
"num_tokens": 1401452.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.08479061126709,
|
|
"epoch": 0.060794780545670224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.738,
|
|
"mean_token_accuracy": 0.10963475927710534,
|
|
"num_tokens": 1412947.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.127987480163574,
|
|
"epoch": 0.06128904705417161,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8109,
|
|
"mean_token_accuracy": 0.10360400006175041,
|
|
"num_tokens": 1425123.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.153063583374023,
|
|
"epoch": 0.06178331356267299,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.7645,
|
|
"mean_token_accuracy": 0.11070188730955124,
|
|
"num_tokens": 1436538.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.101979494094849,
|
|
"epoch": 0.06227758007117438,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.8117,
|
|
"mean_token_accuracy": 0.10509998053312301,
|
|
"num_tokens": 1448269.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.106948661804199,
|
|
"epoch": 0.06277184657967576,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.788,
|
|
"mean_token_accuracy": 0.11462685242295265,
|
|
"num_tokens": 1459729.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.1686571598052975,
|
|
"epoch": 0.06326611308817714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.11152929291129113,
|
|
"num_tokens": 1470684.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.013633441925049,
|
|
"epoch": 0.06376037959667853,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.7587,
|
|
"mean_token_accuracy": 0.1101705864071846,
|
|
"num_tokens": 1483571.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.109546422958374,
|
|
"epoch": 0.06425464610517992,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7362,
|
|
"mean_token_accuracy": 0.11758828014135361,
|
|
"num_tokens": 1494671.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.0959288597106935,
|
|
"epoch": 0.06474891261368129,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.7585,
|
|
"mean_token_accuracy": 0.11675207242369652,
|
|
"num_tokens": 1505435.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.204699468612671,
|
|
"epoch": 0.06524317912218268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8475,
|
|
"mean_token_accuracy": 0.11172165870666503,
|
|
"num_tokens": 1518510.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.068896198272705,
|
|
"epoch": 0.06573744563068407,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.7641,
|
|
"mean_token_accuracy": 0.11413847506046296,
|
|
"num_tokens": 1530218.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.1204170227050785,
|
|
"epoch": 0.06623171213918545,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.8049,
|
|
"mean_token_accuracy": 0.11596491858363152,
|
|
"num_tokens": 1542486.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.062425327301026,
|
|
"epoch": 0.06672597864768683,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.8047,
|
|
"mean_token_accuracy": 0.1089675173163414,
|
|
"num_tokens": 1553873.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.1306592464447025,
|
|
"epoch": 0.06722024515618821,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.7547,
|
|
"mean_token_accuracy": 0.11543979942798614,
|
|
"num_tokens": 1565343.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.066051483154297,
|
|
"epoch": 0.0677145116646896,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.8026,
|
|
"mean_token_accuracy": 0.11002968549728394,
|
|
"num_tokens": 1577061.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.14155158996582,
|
|
"epoch": 0.06820877817319099,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.8113,
|
|
"mean_token_accuracy": 0.1125007539987564,
|
|
"num_tokens": 1588083.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.073976802825928,
|
|
"epoch": 0.06870304468169237,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.7554,
|
|
"mean_token_accuracy": 0.10692217722535133,
|
|
"num_tokens": 1599796.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.1110053062438965,
|
|
"epoch": 0.06919731119019375,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.8121,
|
|
"mean_token_accuracy": 0.11048990935087204,
|
|
"num_tokens": 1611994.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.0139154434204105,
|
|
"epoch": 0.06969157769869513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.7507,
|
|
"mean_token_accuracy": 0.10957834497094154,
|
|
"num_tokens": 1623280.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.106026649475098,
|
|
"epoch": 0.07018584420719652,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.808,
|
|
"mean_token_accuracy": 0.11340730711817741,
|
|
"num_tokens": 1634989.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.131832885742187,
|
|
"epoch": 0.07068011071569791,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.8305,
|
|
"mean_token_accuracy": 0.10883578062057495,
|
|
"num_tokens": 1647042.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.011553001403809,
|
|
"epoch": 0.0711743772241993,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.7172,
|
|
"mean_token_accuracy": 0.11980939731001854,
|
|
"num_tokens": 1659245.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.99677586555481,
|
|
"epoch": 0.07166864373270067,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7013,
|
|
"mean_token_accuracy": 0.11443367972970009,
|
|
"num_tokens": 1670271.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.0444377899169925,
|
|
"epoch": 0.07216291024120206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.7708,
|
|
"mean_token_accuracy": 0.11387339234352112,
|
|
"num_tokens": 1682648.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.0597460746765135,
|
|
"epoch": 0.07265717674970344,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7893,
|
|
"mean_token_accuracy": 0.10786014571785926,
|
|
"num_tokens": 1694542.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.062112951278687,
|
|
"epoch": 0.07315144325820483,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6807,
|
|
"mean_token_accuracy": 0.11052479296922683,
|
|
"num_tokens": 1705737.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.024798059463501,
|
|
"epoch": 0.0736457097667062,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.11467356607317924,
|
|
"num_tokens": 1718474.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.036571741104126,
|
|
"epoch": 0.07413997627520759,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7323,
|
|
"mean_token_accuracy": 0.11398957073688507,
|
|
"num_tokens": 1729360.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.9887631893157955,
|
|
"epoch": 0.07463424278370898,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7255,
|
|
"mean_token_accuracy": 0.11519158333539962,
|
|
"num_tokens": 1739654.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.033215522766113,
|
|
"epoch": 0.07512850929221036,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.7387,
|
|
"mean_token_accuracy": 0.1136898435652256,
|
|
"num_tokens": 1752158.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.069390344619751,
|
|
"epoch": 0.07562277580071175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.7168,
|
|
"mean_token_accuracy": 0.11647839024662972,
|
|
"num_tokens": 1764545.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.947335958480835,
|
|
"epoch": 0.07611704230921312,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.7149,
|
|
"mean_token_accuracy": 0.11350835710763932,
|
|
"num_tokens": 1775422.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.006612300872803,
|
|
"epoch": 0.07661130881771451,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7434,
|
|
"mean_token_accuracy": 0.10612287968397141,
|
|
"num_tokens": 1787833.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.998319816589356,
|
|
"epoch": 0.0771055753262159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6043,
|
|
"mean_token_accuracy": 0.12429658696055412,
|
|
"num_tokens": 1798508.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.004573345184326,
|
|
"epoch": 0.07759984183471728,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.659,
|
|
"mean_token_accuracy": 0.1183803491294384,
|
|
"num_tokens": 1809873.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.007242250442505,
|
|
"epoch": 0.07809410834321866,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7413,
|
|
"mean_token_accuracy": 0.11312813088297843,
|
|
"num_tokens": 1820876.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.948212289810181,
|
|
"epoch": 0.07858837485172004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.699,
|
|
"mean_token_accuracy": 0.10882346406579017,
|
|
"num_tokens": 1833233.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.106487035751343,
|
|
"epoch": 0.07908264136022143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.778,
|
|
"mean_token_accuracy": 0.10910732001066208,
|
|
"num_tokens": 1844520.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.8816266536712645,
|
|
"epoch": 0.07957690786872282,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.6648,
|
|
"mean_token_accuracy": 0.12200288325548173,
|
|
"num_tokens": 1856814.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.97114930152893,
|
|
"epoch": 0.0800711743772242,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.6628,
|
|
"mean_token_accuracy": 0.12218885123729706,
|
|
"num_tokens": 1867581.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.999241828918457,
|
|
"epoch": 0.08056544088572558,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.7072,
|
|
"mean_token_accuracy": 0.10921736285090447,
|
|
"num_tokens": 1879302.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.969866561889648,
|
|
"epoch": 0.08105970739422697,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.6885,
|
|
"mean_token_accuracy": 0.10975500419735909,
|
|
"num_tokens": 1891697.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.910426378250122,
|
|
"epoch": 0.08155397390272835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.6127,
|
|
"mean_token_accuracy": 0.11688940823078156,
|
|
"num_tokens": 1903544.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.008802366256714,
|
|
"epoch": 0.08204824041122974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6874,
|
|
"mean_token_accuracy": 0.11403921097517014,
|
|
"num_tokens": 1915286.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.882919025421143,
|
|
"epoch": 0.08254250691973111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.11978555917739868,
|
|
"num_tokens": 1926361.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.969589138031006,
|
|
"epoch": 0.0830367734282325,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.6586,
|
|
"mean_token_accuracy": 0.11664789393544198,
|
|
"num_tokens": 1938540.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.94748272895813,
|
|
"epoch": 0.08353103993673389,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.6722,
|
|
"mean_token_accuracy": 0.1142181321978569,
|
|
"num_tokens": 1950532.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.009950017929077,
|
|
"epoch": 0.08402530644523527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.688,
|
|
"mean_token_accuracy": 0.11444820910692215,
|
|
"num_tokens": 1960899.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.877012252807617,
|
|
"epoch": 0.08451957295373666,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6664,
|
|
"mean_token_accuracy": 0.11932071298360825,
|
|
"num_tokens": 1972278.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.944576215744019,
|
|
"epoch": 0.08501383946223803,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6772,
|
|
"mean_token_accuracy": 0.11343410313129425,
|
|
"num_tokens": 1985079.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.87914719581604,
|
|
"epoch": 0.08550810597073942,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.717,
|
|
"mean_token_accuracy": 0.10890110954642296,
|
|
"num_tokens": 1996467.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.0112952709198,
|
|
"epoch": 0.08600237247924081,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5965,
|
|
"mean_token_accuracy": 0.11732956543564796,
|
|
"num_tokens": 2007339.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.880322694778442,
|
|
"epoch": 0.0864966389877422,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.6191,
|
|
"mean_token_accuracy": 0.12273732423782349,
|
|
"num_tokens": 2019962.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.9337687492370605,
|
|
"epoch": 0.08699090549624358,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5968,
|
|
"mean_token_accuracy": 0.12427836582064629,
|
|
"num_tokens": 2031251.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.820502090454101,
|
|
"epoch": 0.08748517200474495,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.6173,
|
|
"mean_token_accuracy": 0.1142122581601143,
|
|
"num_tokens": 2042412.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.907873010635376,
|
|
"epoch": 0.08797943851324634,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6431,
|
|
"mean_token_accuracy": 0.11822873800992965,
|
|
"num_tokens": 2054423.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.863052892684936,
|
|
"epoch": 0.08847370502174773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.11389594078063965,
|
|
"num_tokens": 2065657.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.908948945999145,
|
|
"epoch": 0.08896797153024912,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.5882,
|
|
"mean_token_accuracy": 0.12156546339392663,
|
|
"num_tokens": 2076305.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.855497550964356,
|
|
"epoch": 0.08946223803875049,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6008,
|
|
"mean_token_accuracy": 0.1167502075433731,
|
|
"num_tokens": 2087734.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.798408842086792,
|
|
"epoch": 0.08995650454725188,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.5,
|
|
"mean_token_accuracy": 0.12408471554517746,
|
|
"num_tokens": 2098016.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.817918014526367,
|
|
"epoch": 0.09045077105575326,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.6752,
|
|
"mean_token_accuracy": 0.11778675690293312,
|
|
"num_tokens": 2110293.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.892794036865235,
|
|
"epoch": 0.09094503756425465,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4743,
|
|
"mean_token_accuracy": 0.12243440523743629,
|
|
"num_tokens": 2120441.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.797029685974121,
|
|
"epoch": 0.09143930407275604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.5657,
|
|
"mean_token_accuracy": 0.12534191459417343,
|
|
"num_tokens": 2131520.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.813828420639038,
|
|
"epoch": 0.09193357058125741,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.11672990769147873,
|
|
"num_tokens": 2145005.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.872094964981079,
|
|
"epoch": 0.0924278370897588,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5506,
|
|
"mean_token_accuracy": 0.12510338500142099,
|
|
"num_tokens": 2156608.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.760220718383789,
|
|
"epoch": 0.09292210359826018,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.5463,
|
|
"mean_token_accuracy": 0.1284232459962368,
|
|
"num_tokens": 2168341.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.826963710784912,
|
|
"epoch": 0.09341637010676157,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.5516,
|
|
"mean_token_accuracy": 0.114336409419775,
|
|
"num_tokens": 2178704.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.916041135787964,
|
|
"epoch": 0.09391063661526294,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.7081,
|
|
"mean_token_accuracy": 0.11039185151457787,
|
|
"num_tokens": 2190884.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.903425168991089,
|
|
"epoch": 0.09440490312376433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6124,
|
|
"mean_token_accuracy": 0.11909380853176117,
|
|
"num_tokens": 2201822.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.817460918426514,
|
|
"epoch": 0.09489916963226572,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6002,
|
|
"mean_token_accuracy": 0.11638330668210983,
|
|
"num_tokens": 2213362.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.884056949615479,
|
|
"epoch": 0.0953934361407671,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6144,
|
|
"mean_token_accuracy": 0.1184050552546978,
|
|
"num_tokens": 2224366.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.7438822269439695,
|
|
"epoch": 0.09588770264926849,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.1230374664068222,
|
|
"num_tokens": 2234645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.803455400466919,
|
|
"epoch": 0.09638196915776986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.12610765993595124,
|
|
"num_tokens": 2245904.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.681088209152222,
|
|
"epoch": 0.09687623566627125,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4954,
|
|
"mean_token_accuracy": 0.12240897715091706,
|
|
"num_tokens": 2257753.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.754433631896973,
|
|
"epoch": 0.09737050217477264,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5155,
|
|
"mean_token_accuracy": 0.12655969709157944,
|
|
"num_tokens": 2269009.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.843816947937012,
|
|
"epoch": 0.09786476868327403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.11670292690396308,
|
|
"num_tokens": 2279840.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.755049037933349,
|
|
"epoch": 0.0983590351917754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.11820845976471901,
|
|
"num_tokens": 2290577.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.765120506286621,
|
|
"epoch": 0.09885330170027679,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.12245884612202644,
|
|
"num_tokens": 2301341.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.746102571487427,
|
|
"epoch": 0.09934756820877817,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999982287888,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.12232246473431588,
|
|
"num_tokens": 2312505.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.866240930557251,
|
|
"epoch": 0.09984183471727956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999910332434,
|
|
"loss": 6.5172,
|
|
"mean_token_accuracy": 0.11665143966674804,
|
|
"num_tokens": 2323443.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.745142984390259,
|
|
"epoch": 0.10033610122578095,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999783026635,
|
|
"loss": 6.5361,
|
|
"mean_token_accuracy": 0.11963617578148841,
|
|
"num_tokens": 2335686.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.703868341445923,
|
|
"epoch": 0.10083036773428232,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999600370491,
|
|
"loss": 6.517,
|
|
"mean_token_accuracy": 0.11855524033308029,
|
|
"num_tokens": 2347273.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.730478429794312,
|
|
"epoch": 0.1013246342427837,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999362364008,
|
|
"loss": 6.4405,
|
|
"mean_token_accuracy": 0.13110232651233672,
|
|
"num_tokens": 2358011.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.7004495620727536,
|
|
"epoch": 0.1018189007512851,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999069007191,
|
|
"loss": 6.5822,
|
|
"mean_token_accuracy": 0.1172802321612835,
|
|
"num_tokens": 2371390.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.794222068786621,
|
|
"epoch": 0.10231316725978648,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999998720300048,
|
|
"loss": 6.5474,
|
|
"mean_token_accuracy": 0.12140254527330399,
|
|
"num_tokens": 2381887.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.795210361480713,
|
|
"epoch": 0.10280743376828787,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999998316242589,
|
|
"loss": 6.4809,
|
|
"mean_token_accuracy": 0.12476008459925651,
|
|
"num_tokens": 2393632.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.711300373077393,
|
|
"epoch": 0.10330170027678924,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999997856834821,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.12174365520477295,
|
|
"num_tokens": 2405686.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.642526435852051,
|
|
"epoch": 0.10379596678529063,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999997342076757,
|
|
"loss": 6.458,
|
|
"mean_token_accuracy": 0.12098277881741523,
|
|
"num_tokens": 2417459.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.810392236709594,
|
|
"epoch": 0.10429023329379201,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999996771968408,
|
|
"loss": 6.5135,
|
|
"mean_token_accuracy": 0.12017063796520233,
|
|
"num_tokens": 2428689.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.64630160331726,
|
|
"epoch": 0.1047844998022934,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999996146509791,
|
|
"loss": 6.5336,
|
|
"mean_token_accuracy": 0.11422798931598663,
|
|
"num_tokens": 2439437.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.869584083557129,
|
|
"epoch": 0.10527876631079477,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999995465700919,
|
|
"loss": 6.5124,
|
|
"mean_token_accuracy": 0.12146430611610412,
|
|
"num_tokens": 2450576.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.80404257774353,
|
|
"epoch": 0.10577303281929616,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999994729541809,
|
|
"loss": 6.6452,
|
|
"mean_token_accuracy": 0.11663848459720612,
|
|
"num_tokens": 2462684.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.779199504852295,
|
|
"epoch": 0.10626729932779755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999993938032481,
|
|
"loss": 6.5343,
|
|
"mean_token_accuracy": 0.12712442725896836,
|
|
"num_tokens": 2474193.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.629879188537598,
|
|
"epoch": 0.10676156583629894,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999993091172952,
|
|
"loss": 6.4598,
|
|
"mean_token_accuracy": 0.12284933924674987,
|
|
"num_tokens": 2486264.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.699342727661133,
|
|
"epoch": 0.10725583234480032,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999992188963245,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.1300704911351204,
|
|
"num_tokens": 2497668.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.698151445388794,
|
|
"epoch": 0.1077500988533017,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499999123140338,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.11959851160645485,
|
|
"num_tokens": 2509635.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.730442905426026,
|
|
"epoch": 0.10824436536180308,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999990218493382,
|
|
"loss": 6.5092,
|
|
"mean_token_accuracy": 0.12682930305600165,
|
|
"num_tokens": 2521980.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.709285688400269,
|
|
"epoch": 0.10873863187030447,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999989150233276,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.12090066596865653,
|
|
"num_tokens": 2533750.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.731018304824829,
|
|
"epoch": 0.10923289837880586,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999988026623088,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.11578204408288002,
|
|
"num_tokens": 2545620.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.651696014404297,
|
|
"epoch": 0.10972716488730723,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999986847662843,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.13319482430815696,
|
|
"num_tokens": 2556463.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.734298992156982,
|
|
"epoch": 0.11022143139580862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985613352576,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.12397273704409599,
|
|
"num_tokens": 2567396.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.686400699615478,
|
|
"epoch": 0.11071569790431,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999984323692311,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.12991662919521332,
|
|
"num_tokens": 2579208.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.661752843856812,
|
|
"epoch": 0.11120996441281139,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999982978682085,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.12975354716181756,
|
|
"num_tokens": 2590940.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.747511720657348,
|
|
"epoch": 0.11170423092131278,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999981578321927,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.1310792900621891,
|
|
"num_tokens": 2602491.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.611108875274658,
|
|
"epoch": 0.11219849742981415,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999980122611874,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.1327824428677559,
|
|
"num_tokens": 2612139.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.693927431106568,
|
|
"epoch": 0.11269276393831554,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499997861155196,
|
|
"loss": 6.5011,
|
|
"mean_token_accuracy": 0.1247858576476574,
|
|
"num_tokens": 2624906.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.6354106903076175,
|
|
"epoch": 0.11318703044681692,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999977045142223,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.12271838635206223,
|
|
"num_tokens": 2636046.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.691875314712524,
|
|
"epoch": 0.11368129695531831,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999975423382703,
|
|
"loss": 6.4263,
|
|
"mean_token_accuracy": 0.13008476421236992,
|
|
"num_tokens": 2645617.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.7659107685089115,
|
|
"epoch": 0.11417556346381968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999973746273438,
|
|
"loss": 6.4566,
|
|
"mean_token_accuracy": 0.1254364877939224,
|
|
"num_tokens": 2656780.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.659218263626099,
|
|
"epoch": 0.11466982997232107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997201381447,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.1278814695775509,
|
|
"num_tokens": 2668078.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.662109756469727,
|
|
"epoch": 0.11516409648082246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999970226005841,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.12168930992484092,
|
|
"num_tokens": 2679049.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.731383752822876,
|
|
"epoch": 0.11565836298932385,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999968382847595,
|
|
"loss": 6.4737,
|
|
"mean_token_accuracy": 0.1280827172100544,
|
|
"num_tokens": 2690165.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.73934531211853,
|
|
"epoch": 0.11615262949782523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966484339778,
|
|
"loss": 6.503,
|
|
"mean_token_accuracy": 0.11856682375073432,
|
|
"num_tokens": 2701965.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.5927499294281,
|
|
"epoch": 0.1166468960063266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999964530482437,
|
|
"loss": 6.4146,
|
|
"mean_token_accuracy": 0.12625361010432243,
|
|
"num_tokens": 2713479.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.668395376205444,
|
|
"epoch": 0.11714116251482799,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999962521275619,
|
|
"loss": 6.4271,
|
|
"mean_token_accuracy": 0.12376236468553543,
|
|
"num_tokens": 2725629.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.4717286109924315,
|
|
"epoch": 0.11763542902332938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999960456719374,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.123749740421772,
|
|
"num_tokens": 2736620.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.62722806930542,
|
|
"epoch": 0.11812969553183077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999958336813753,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.13400673493742943,
|
|
"num_tokens": 2747118.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.557834100723267,
|
|
"epoch": 0.11862396204033215,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999956161558807,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12897140979766847,
|
|
"num_tokens": 2758371.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.586788654327393,
|
|
"epoch": 0.11911822854883353,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999953930954591,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.12413987889885902,
|
|
"num_tokens": 2770575.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.63907904624939,
|
|
"epoch": 0.11961249505733491,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999951645001159,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.12998759970068932,
|
|
"num_tokens": 2783103.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.585193490982055,
|
|
"epoch": 0.1201067615658363,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999949303698568,
|
|
"loss": 6.4645,
|
|
"mean_token_accuracy": 0.12690217643976212,
|
|
"num_tokens": 2796636.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.638331365585327,
|
|
"epoch": 0.12060102807433769,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999946907046875,
|
|
"loss": 6.3222,
|
|
"mean_token_accuracy": 0.13736142292618753,
|
|
"num_tokens": 2807798.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.535335206985474,
|
|
"epoch": 0.12109529458283906,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999944455046139,
|
|
"loss": 6.4524,
|
|
"mean_token_accuracy": 0.12832500115036966,
|
|
"num_tokens": 2819255.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.663571977615357,
|
|
"epoch": 0.12158956109134045,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499994194769642,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.1270384594798088,
|
|
"num_tokens": 2829952.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.701180505752563,
|
|
"epoch": 0.12208382759984183,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499993938499778,
|
|
"loss": 6.476,
|
|
"mean_token_accuracy": 0.1340859904885292,
|
|
"num_tokens": 2841056.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.587615871429444,
|
|
"epoch": 0.12257809410834322,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999936766950283,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.1331305004656315,
|
|
"num_tokens": 2852045.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.603626489639282,
|
|
"epoch": 0.12307236061684461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999934093553992,
|
|
"loss": 6.4274,
|
|
"mean_token_accuracy": 0.1284114196896553,
|
|
"num_tokens": 2863440.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.648584413528442,
|
|
"epoch": 0.12356662712534598,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999931364808972,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.12790528684854507,
|
|
"num_tokens": 2874017.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.594161510467529,
|
|
"epoch": 0.12406089363384737,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999928580715293,
|
|
"loss": 6.3586,
|
|
"mean_token_accuracy": 0.13108654990792273,
|
|
"num_tokens": 2885677.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.574838018417358,
|
|
"epoch": 0.12455516014234876,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499992574127302,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.12673256024718285,
|
|
"num_tokens": 2897825.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.713541269302368,
|
|
"epoch": 0.12504942665085014,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999922846482226,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.12139986976981162,
|
|
"num_tokens": 2909304.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.6441412448883055,
|
|
"epoch": 0.12554369315935152,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999919896342981,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.12221642285585403,
|
|
"num_tokens": 2920918.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.6605743885040285,
|
|
"epoch": 0.12603795966785292,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999916890855358,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.12975434139370917,
|
|
"num_tokens": 2932294.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.561512088775634,
|
|
"epoch": 0.1265322261763543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999913830019431,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.13787687346339225,
|
|
"num_tokens": 2943372.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.464610910415649,
|
|
"epoch": 0.12702649268485566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999910713835272,
|
|
"loss": 6.2922,
|
|
"mean_token_accuracy": 0.1328001670539379,
|
|
"num_tokens": 2953807.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.581829261779785,
|
|
"epoch": 0.12752075919335706,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999907542302962,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.14087910503149031,
|
|
"num_tokens": 2964372.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.564945030212402,
|
|
"epoch": 0.12801502570185844,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999904315422577,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.1339232198894024,
|
|
"num_tokens": 2975537.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.499995517730713,
|
|
"epoch": 0.12850929221035984,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999901033194198,
|
|
"loss": 6.3155,
|
|
"mean_token_accuracy": 0.12768632620573045,
|
|
"num_tokens": 2986094.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.646216011047363,
|
|
"epoch": 0.1290035587188612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999897695617904,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.12920272648334502,
|
|
"num_tokens": 2996023.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.6123514652252195,
|
|
"epoch": 0.12949782522736258,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999894302693778,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.1242698810994625,
|
|
"num_tokens": 3007584.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.681271362304687,
|
|
"epoch": 0.12999209173586398,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999890854421902,
|
|
"loss": 6.459,
|
|
"mean_token_accuracy": 0.1226358100771904,
|
|
"num_tokens": 3018995.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.480655765533447,
|
|
"epoch": 0.13048635824436536,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999887350802362,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.13495219945907594,
|
|
"num_tokens": 3030576.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.501480150222778,
|
|
"epoch": 0.13098062475286676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999883791835246,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.13001331686973572,
|
|
"num_tokens": 3040765.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.589521598815918,
|
|
"epoch": 0.13147489126136813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999880177520637,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.12722131982445717,
|
|
"num_tokens": 3053912.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.452705240249633,
|
|
"epoch": 0.1319691577698695,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999876507858628,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.1288708493113518,
|
|
"num_tokens": 3065921.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.664311170578003,
|
|
"epoch": 0.1324634242783709,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999872782849308,
|
|
"loss": 6.3949,
|
|
"mean_token_accuracy": 0.12616097629070283,
|
|
"num_tokens": 3078643.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.459210395812988,
|
|
"epoch": 0.13295769078687228,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999869002492768,
|
|
"loss": 6.3291,
|
|
"mean_token_accuracy": 0.12967689260840415,
|
|
"num_tokens": 3090300.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.512746524810791,
|
|
"epoch": 0.13345195729537365,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999865166789102,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.13676148131489754,
|
|
"num_tokens": 3102307.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.59787917137146,
|
|
"epoch": 0.13394622380387505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999861275738404,
|
|
"loss": 6.3986,
|
|
"mean_token_accuracy": 0.12524239718914032,
|
|
"num_tokens": 3113817.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.543708562850952,
|
|
"epoch": 0.13444049031237643,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999857329340769,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.13055241033434867,
|
|
"num_tokens": 3124719.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.411153316497803,
|
|
"epoch": 0.13493475682087783,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999853327596295,
|
|
"loss": 6.2897,
|
|
"mean_token_accuracy": 0.13201832994818688,
|
|
"num_tokens": 3136136.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.56207914352417,
|
|
"epoch": 0.1354290233293792,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499984927050508,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.13325023874640465,
|
|
"num_tokens": 3148977.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.551389932632446,
|
|
"epoch": 0.13592328983788057,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999845158067223,
|
|
"loss": 6.3633,
|
|
"mean_token_accuracy": 0.12621287032961845,
|
|
"num_tokens": 3160520.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.536664581298828,
|
|
"epoch": 0.13641755634638197,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999840990282828,
|
|
"loss": 6.3349,
|
|
"mean_token_accuracy": 0.13194907903671266,
|
|
"num_tokens": 3172895.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.496895885467529,
|
|
"epoch": 0.13691182285488335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999836767151994,
|
|
"loss": 6.3416,
|
|
"mean_token_accuracy": 0.13204838037490846,
|
|
"num_tokens": 3183960.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.522651672363281,
|
|
"epoch": 0.13740608936338475,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999832488674827,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.12837577536702155,
|
|
"num_tokens": 3194276.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.513303756713867,
|
|
"epoch": 0.13790035587188612,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999828154851432,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.13473956882953644,
|
|
"num_tokens": 3206084.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.524267959594726,
|
|
"epoch": 0.1383946223803875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999823765681915,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.13728717863559722,
|
|
"num_tokens": 3217941.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.480133390426635,
|
|
"epoch": 0.1388888888888889,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999819321166385,
|
|
"loss": 6.2548,
|
|
"mean_token_accuracy": 0.13228702992200853,
|
|
"num_tokens": 3229088.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.4318465232849125,
|
|
"epoch": 0.13938315539739027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499981482130495,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.13228484094142914,
|
|
"num_tokens": 3240708.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.46836485862732,
|
|
"epoch": 0.13987742190589167,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999810266097721,
|
|
"loss": 6.3368,
|
|
"mean_token_accuracy": 0.12805040180683136,
|
|
"num_tokens": 3251040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.476617431640625,
|
|
"epoch": 0.14037168841439304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999805655544811,
|
|
"loss": 6.278,
|
|
"mean_token_accuracy": 0.1379806451499462,
|
|
"num_tokens": 3262655.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.446955060958862,
|
|
"epoch": 0.14086595492289442,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999800989646333,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.13916653543710708,
|
|
"num_tokens": 3273160.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.492981576919556,
|
|
"epoch": 0.14136022143139582,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999796268402401,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.13187761902809142,
|
|
"num_tokens": 3285932.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.438924407958984,
|
|
"epoch": 0.1418544879398972,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999791491813132,
|
|
"loss": 6.295,
|
|
"mean_token_accuracy": 0.1294438548386097,
|
|
"num_tokens": 3298834.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.521294736862183,
|
|
"epoch": 0.1423487544483986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999786659878643,
|
|
"loss": 6.2684,
|
|
"mean_token_accuracy": 0.1286303736269474,
|
|
"num_tokens": 3310473.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.372927856445313,
|
|
"epoch": 0.14284302095689996,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999781772599055,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.1356230579316616,
|
|
"num_tokens": 3322662.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.60296220779419,
|
|
"epoch": 0.14333728746540134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999776829974484,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.13732139021158218,
|
|
"num_tokens": 3334321.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.441670370101929,
|
|
"epoch": 0.14383155397390274,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999771832005055,
|
|
"loss": 6.2298,
|
|
"mean_token_accuracy": 0.13349530473351479,
|
|
"num_tokens": 3345130.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.440216207504273,
|
|
"epoch": 0.1443258204824041,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499976677869089,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.1323176234960556,
|
|
"num_tokens": 3355601.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.415243005752563,
|
|
"epoch": 0.14482008699090548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999761670032115,
|
|
"loss": 6.2209,
|
|
"mean_token_accuracy": 0.13547109439969063,
|
|
"num_tokens": 3367075.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.440726089477539,
|
|
"epoch": 0.14531435349940688,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999756506028851,
|
|
"loss": 6.2086,
|
|
"mean_token_accuracy": 0.13799653053283692,
|
|
"num_tokens": 3378888.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.460967779159546,
|
|
"epoch": 0.14580862000790826,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999751286681229,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.13389106541872026,
|
|
"num_tokens": 3390705.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.470330762863159,
|
|
"epoch": 0.14630288651640966,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999746011989376,
|
|
"loss": 6.2469,
|
|
"mean_token_accuracy": 0.141701989620924,
|
|
"num_tokens": 3401710.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.501716089248657,
|
|
"epoch": 0.14679715302491103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999740681953422,
|
|
"loss": 6.3595,
|
|
"mean_token_accuracy": 0.12875558733940123,
|
|
"num_tokens": 3413467.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.460022449493408,
|
|
"epoch": 0.1472914195334124,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999735296573499,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.14054137468338013,
|
|
"num_tokens": 3425885.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.471263265609741,
|
|
"epoch": 0.1477856860419138,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999729855849738,
|
|
"loss": 6.3169,
|
|
"mean_token_accuracy": 0.12381748557090759,
|
|
"num_tokens": 3437952.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.476200199127197,
|
|
"epoch": 0.14827995255041518,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999724359782274,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.15090513229370117,
|
|
"num_tokens": 3449680.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.451878356933594,
|
|
"epoch": 0.14877421905891658,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999718808371241,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.12572553679347037,
|
|
"num_tokens": 3460699.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.50455265045166,
|
|
"epoch": 0.14926848556741795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999713201616776,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.13989587351679802,
|
|
"num_tokens": 3471919.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.361866235733032,
|
|
"epoch": 0.14976275207591933,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499970753951902,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.1308351695537567,
|
|
"num_tokens": 3484110.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.533850765228271,
|
|
"epoch": 0.15025701858442073,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999701822078107,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.1353417955338955,
|
|
"num_tokens": 3496103.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.473228120803833,
|
|
"epoch": 0.1507512850929221,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499969604929418,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.13488239124417306,
|
|
"num_tokens": 3507291.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.454948472976684,
|
|
"epoch": 0.1512455516014235,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999690221167382,
|
|
"loss": 6.3017,
|
|
"mean_token_accuracy": 0.12805337607860565,
|
|
"num_tokens": 3519564.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.356312274932861,
|
|
"epoch": 0.15173981810992487,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999684337697855,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.14256911277770995,
|
|
"num_tokens": 3530679.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.445040559768676,
|
|
"epoch": 0.15223408461842625,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999678398885746,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.13545068502426147,
|
|
"num_tokens": 3542662.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.442259311676025,
|
|
"epoch": 0.15272835112692765,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999672404731197,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.13151721879839898,
|
|
"num_tokens": 3554760.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.390431261062622,
|
|
"epoch": 0.15322261763542902,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499966635523436,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14151813611388206,
|
|
"num_tokens": 3565604.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.489778709411621,
|
|
"epoch": 0.1537168841439304,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999660250395381,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.13059073835611343,
|
|
"num_tokens": 3577535.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.454697751998902,
|
|
"epoch": 0.1542111506524318,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499965409021441,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.13098583221435547,
|
|
"num_tokens": 3590458.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.460421705245972,
|
|
"epoch": 0.15470541716093317,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049996478746916,
|
|
"loss": 6.2659,
|
|
"mean_token_accuracy": 0.13603687211871146,
|
|
"num_tokens": 3600916.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.387070751190185,
|
|
"epoch": 0.15519968366943457,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999641603827104,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.13124272525310515,
|
|
"num_tokens": 3612794.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.422871780395508,
|
|
"epoch": 0.15569395017793594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999635277621073,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.14298698604106902,
|
|
"num_tokens": 3624186.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.386454057693482,
|
|
"epoch": 0.15618821668643731,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999628896073668,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.13735796883702278,
|
|
"num_tokens": 3636041.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.462503433227539,
|
|
"epoch": 0.15668248319493872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999622459185042,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.13020889237523078,
|
|
"num_tokens": 3646859.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.398414373397827,
|
|
"epoch": 0.1571767497034401,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999615966955354,
|
|
"loss": 6.1157,
|
|
"mean_token_accuracy": 0.14551621302962303,
|
|
"num_tokens": 3657853.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.463107538223267,
|
|
"epoch": 0.1576710162119415,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999609419384764,
|
|
"loss": 6.2214,
|
|
"mean_token_accuracy": 0.13310921415686608,
|
|
"num_tokens": 3668341.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.392400121688842,
|
|
"epoch": 0.15816528272044286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999602816473434,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.1410088613629341,
|
|
"num_tokens": 3679020.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.408904552459717,
|
|
"epoch": 0.15865954922894424,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999596158221526,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14006651043891907,
|
|
"num_tokens": 3691121.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.385823917388916,
|
|
"epoch": 0.15915381573744564,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999589444629203,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.1411613941192627,
|
|
"num_tokens": 3702584.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.3845240592956545,
|
|
"epoch": 0.159648082245947,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999582675696631,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.13805127739906312,
|
|
"num_tokens": 3713085.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.46448073387146,
|
|
"epoch": 0.1601423487544484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999575851423976,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.12872665300965308,
|
|
"num_tokens": 3724318.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.464413785934449,
|
|
"epoch": 0.16063661526294978,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999568971811407,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.1430479533970356,
|
|
"num_tokens": 3734288.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.328683185577392,
|
|
"epoch": 0.16113088177145116,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499956203685909,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.13233742043375968,
|
|
"num_tokens": 3744645.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.442096281051636,
|
|
"epoch": 0.16162514827995256,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049995550465672,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.14003336429595947,
|
|
"num_tokens": 3755660.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.326750326156616,
|
|
"epoch": 0.16211941478845393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999548000935906,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.1436133176088333,
|
|
"num_tokens": 3767614.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.386001491546631,
|
|
"epoch": 0.16261368129695533,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999540899965383,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.13778984621167184,
|
|
"num_tokens": 3780750.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.425701570510864,
|
|
"epoch": 0.1631079478054567,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999533743655803,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.1312929518520832,
|
|
"num_tokens": 3793195.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.375810956954956,
|
|
"epoch": 0.16360221431395808,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999526532007346,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.14021370857954024,
|
|
"num_tokens": 3804256.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.400203657150269,
|
|
"epoch": 0.16409648082245948,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999519265020187,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.13381656855344773,
|
|
"num_tokens": 3815403.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.297303676605225,
|
|
"epoch": 0.16459074733096085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999511942694504,
|
|
"loss": 6.1146,
|
|
"mean_token_accuracy": 0.1449520155787468,
|
|
"num_tokens": 3826682.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.372660064697266,
|
|
"epoch": 0.16508501383946222,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999504565030479,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.13841361403465272,
|
|
"num_tokens": 3837780.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.417489624023437,
|
|
"epoch": 0.16557928034796363,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999497132028293,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.13504983931779863,
|
|
"num_tokens": 3848782.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.337214994430542,
|
|
"epoch": 0.166073546856465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999489643688127,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14474000558257102,
|
|
"num_tokens": 3859220.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.308086252212524,
|
|
"epoch": 0.1665678133649664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999482100010169,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1455448277294636,
|
|
"num_tokens": 3869794.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.305660057067871,
|
|
"epoch": 0.16706207987346777,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999474500994601,
|
|
"loss": 6.21,
|
|
"mean_token_accuracy": 0.13534921333193778,
|
|
"num_tokens": 3881133.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.372439575195313,
|
|
"epoch": 0.16755634638196915,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999466846641611,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.1381655864417553,
|
|
"num_tokens": 3891600.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.324881887435913,
|
|
"epoch": 0.16805061289047055,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999459136951389,
|
|
"loss": 6.2368,
|
|
"mean_token_accuracy": 0.1343551091849804,
|
|
"num_tokens": 3903287.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.367248630523681,
|
|
"epoch": 0.16854487939897192,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999451371924123,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.14270353838801383,
|
|
"num_tokens": 3914497.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.32606315612793,
|
|
"epoch": 0.16903914590747332,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999443551560003,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.13897614777088166,
|
|
"num_tokens": 3925536.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.3809061527252195,
|
|
"epoch": 0.1695334124159747,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999435675859224,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.1441777989268303,
|
|
"num_tokens": 3936705.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.315342855453491,
|
|
"epoch": 0.17002767892447607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999427744821977,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.14600003734230996,
|
|
"num_tokens": 3948422.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.263158702850342,
|
|
"epoch": 0.17052194543297747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499941975844846,
|
|
"loss": 6.0986,
|
|
"mean_token_accuracy": 0.14980924874544144,
|
|
"num_tokens": 3958697.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.321331548690796,
|
|
"epoch": 0.17101621194147884,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999411716738866,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.13610462471842766,
|
|
"num_tokens": 3970255.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.3515236377716064,
|
|
"epoch": 0.17151047844998024,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999403619693397,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.13452404960989953,
|
|
"num_tokens": 3980892.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.215304851531982,
|
|
"epoch": 0.17200474495848161,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999395467312249,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.13866710513830185,
|
|
"num_tokens": 3991375.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.409534502029419,
|
|
"epoch": 0.172499011466983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999387259595623,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.1355798661708832,
|
|
"num_tokens": 4003352.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.323182249069214,
|
|
"epoch": 0.1729932779754844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999378996543723,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.13970827013254167,
|
|
"num_tokens": 4014429.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.331288051605225,
|
|
"epoch": 0.17348754448398576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999370678156749,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.14578365832567214,
|
|
"num_tokens": 4025213.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.292533731460571,
|
|
"epoch": 0.17398181099248716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999362304434909,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.14500001072883606,
|
|
"num_tokens": 4036244.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.346677541732788,
|
|
"epoch": 0.17447607750098854,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999353875378406,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.14193734377622605,
|
|
"num_tokens": 4047944.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.283301496505738,
|
|
"epoch": 0.1749703440094899,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499934539098745,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.14384573325514793,
|
|
"num_tokens": 4058865.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.257331275939942,
|
|
"epoch": 0.1754646105179913,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999336851262247,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.1391538202762604,
|
|
"num_tokens": 4070627.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.394286632537842,
|
|
"epoch": 0.17595887702649268,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999328256203009,
|
|
"loss": 6.1895,
|
|
"mean_token_accuracy": 0.1373151198029518,
|
|
"num_tokens": 4081406.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.353554725646973,
|
|
"epoch": 0.17645314353499406,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999319605809947,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.13284853249788284,
|
|
"num_tokens": 4092957.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.333940410614014,
|
|
"epoch": 0.17694741004349546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999310900083274,
|
|
"loss": 6.1955,
|
|
"mean_token_accuracy": 0.1371501013636589,
|
|
"num_tokens": 4104381.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.325356578826904,
|
|
"epoch": 0.17744167655199683,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999302139023204,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.1423741340637207,
|
|
"num_tokens": 4117190.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.260775136947632,
|
|
"epoch": 0.17793594306049823,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999293322629951,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.14984049201011657,
|
|
"num_tokens": 4127870.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.272122192382812,
|
|
"epoch": 0.1784302095689996,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999284450903736,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.1465057462453842,
|
|
"num_tokens": 4139240.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.317811346054077,
|
|
"epoch": 0.17892447607750098,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999275523844772,
|
|
"loss": 6.082,
|
|
"mean_token_accuracy": 0.14482868909835817,
|
|
"num_tokens": 4149885.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.389834928512573,
|
|
"epoch": 0.17941874258600238,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999266541453283,
|
|
"loss": 6.2447,
|
|
"mean_token_accuracy": 0.13586108312010764,
|
|
"num_tokens": 4161824.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.320416498184204,
|
|
"epoch": 0.17991300909450375,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999257503729487,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.13344803750514983,
|
|
"num_tokens": 4173581.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.351769924163818,
|
|
"epoch": 0.18040727560300515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999248410673607,
|
|
"loss": 6.0812,
|
|
"mean_token_accuracy": 0.1483595296740532,
|
|
"num_tokens": 4184843.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.358120441436768,
|
|
"epoch": 0.18090154211150652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999239262285869,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.13489353209733962,
|
|
"num_tokens": 4195016.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.332878112792969,
|
|
"epoch": 0.1813958086200079,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999230058566495,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.14574753791093825,
|
|
"num_tokens": 4206798.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.3394999504089355,
|
|
"epoch": 0.1818900751285093,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999220799515713,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.13963396325707436,
|
|
"num_tokens": 4218784.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.299774408340454,
|
|
"epoch": 0.18238434163701067,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499921148513375,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.1387876182794571,
|
|
"num_tokens": 4229875.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.221422624588013,
|
|
"epoch": 0.18287860814551207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999202115420836,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.1441081039607525,
|
|
"num_tokens": 4241801.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.324825763702393,
|
|
"epoch": 0.18337287465401345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999192690377201,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.14329453259706498,
|
|
"num_tokens": 4253168.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.309213781356812,
|
|
"epoch": 0.18386714116251482,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999183210003076,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.13910027593374252,
|
|
"num_tokens": 4264791.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.258148193359375,
|
|
"epoch": 0.18436140767101622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999173674298696,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.14661507308483124,
|
|
"num_tokens": 4275816.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.368045091629028,
|
|
"epoch": 0.1848556741795176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999164083264294,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.13778545409440995,
|
|
"num_tokens": 4287806.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.267383623123169,
|
|
"epoch": 0.185349940688019,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999154436900108,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.14197772592306138,
|
|
"num_tokens": 4300319.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.316354417800904,
|
|
"epoch": 0.18584420719652037,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999144735206373,
|
|
"loss": 6.1769,
|
|
"mean_token_accuracy": 0.13574445396661758,
|
|
"num_tokens": 4310987.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.323000907897949,
|
|
"epoch": 0.18633847370502174,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999134978183328,
|
|
"loss": 6.1294,
|
|
"mean_token_accuracy": 0.14480389952659606,
|
|
"num_tokens": 4322438.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.3687646865844725,
|
|
"epoch": 0.18683274021352314,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999125165831215,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.14540814906358718,
|
|
"num_tokens": 4333242.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.235511398315429,
|
|
"epoch": 0.1873270067220245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999115298150273,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.1450972318649292,
|
|
"num_tokens": 4343660.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.31268277168274,
|
|
"epoch": 0.1878212732305259,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999105375140746,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14088804945349692,
|
|
"num_tokens": 4353382.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.274864387512207,
|
|
"epoch": 0.1883155397390273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999095396802878,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.13407786786556244,
|
|
"num_tokens": 4364614.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.314316892623902,
|
|
"epoch": 0.18880980624752866,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999085363136913,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.13962836787104607,
|
|
"num_tokens": 4376001.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.306294870376587,
|
|
"epoch": 0.18930407275603006,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049990752741431,
|
|
"loss": 6.1602,
|
|
"mean_token_accuracy": 0.13340804651379584,
|
|
"num_tokens": 4387083.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.270431327819824,
|
|
"epoch": 0.18979833926453143,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999065129821687,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.14158050566911698,
|
|
"num_tokens": 4399977.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.206098794937134,
|
|
"epoch": 0.1902926057730328,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999054930172923,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.14246447533369064,
|
|
"num_tokens": 4411609.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.359363842010498,
|
|
"epoch": 0.1907868722815342,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999044675197058,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.14360579550266267,
|
|
"num_tokens": 4423567.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.191033506393433,
|
|
"epoch": 0.19128113879003558,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999034364894345,
|
|
"loss": 6.1078,
|
|
"mean_token_accuracy": 0.14449855983257293,
|
|
"num_tokens": 4435410.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.402541160583496,
|
|
"epoch": 0.19177540529853698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999023999265039,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.14298228770494462,
|
|
"num_tokens": 4445279.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.226133203506469,
|
|
"epoch": 0.19226967180703836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999013578309392,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.14651723206043243,
|
|
"num_tokens": 4456017.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.2588560581207275,
|
|
"epoch": 0.19276393831553973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999003102027663,
|
|
"loss": 6.0097,
|
|
"mean_token_accuracy": 0.14699807465076448,
|
|
"num_tokens": 4466759.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.213010692596436,
|
|
"epoch": 0.19325820482404113,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499899257042011,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.1432296924293041,
|
|
"num_tokens": 4478316.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.35000696182251,
|
|
"epoch": 0.1937524713325425,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998981983486988,
|
|
"loss": 6.1573,
|
|
"mean_token_accuracy": 0.13669586628675462,
|
|
"num_tokens": 4490775.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.219941663742065,
|
|
"epoch": 0.1942467378410439,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998971341228563,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.1470404416322708,
|
|
"num_tokens": 4501622.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.287500047683716,
|
|
"epoch": 0.19474100434954528,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998960643645093,
|
|
"loss": 6.1098,
|
|
"mean_token_accuracy": 0.14525135159492492,
|
|
"num_tokens": 4512279.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.271857500076294,
|
|
"epoch": 0.19523527085804665,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998949890736841,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.14391626492142678,
|
|
"num_tokens": 4524087.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.265537738800049,
|
|
"epoch": 0.19572953736654805,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998939082504075,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.1437728226184845,
|
|
"num_tokens": 4534816.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.251546621322632,
|
|
"epoch": 0.19622380387504942,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998928218947057,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.1464489668607712,
|
|
"num_tokens": 4545725.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.367499351501465,
|
|
"epoch": 0.1967180703835508,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998917300066056,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.13893528208136557,
|
|
"num_tokens": 4557003.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.190875053405762,
|
|
"epoch": 0.1972123368920522,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998906325861342,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.14024949371814727,
|
|
"num_tokens": 4568768.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.2134082317352295,
|
|
"epoch": 0.19770660340055357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998895296333183,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.15064804553985595,
|
|
"num_tokens": 4581116.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.283394813537598,
|
|
"epoch": 0.19820086990905497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499888421148185,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.14467725306749343,
|
|
"num_tokens": 4592660.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.260604429244995,
|
|
"epoch": 0.19869513641755635,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998873071307617,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.14113724008202552,
|
|
"num_tokens": 4603057.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.200288867950439,
|
|
"epoch": 0.19918940292605772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998861875810758,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15196106284856797,
|
|
"num_tokens": 4613546.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.246992015838623,
|
|
"epoch": 0.19968366943455912,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998850624991548,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.14428235441446305,
|
|
"num_tokens": 4624613.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.230186557769775,
|
|
"epoch": 0.2001779359430605,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998839318850263,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.1460937425494194,
|
|
"num_tokens": 4636004.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.193474054336548,
|
|
"epoch": 0.2006722024515619,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998827957387182,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.15042401626706123,
|
|
"num_tokens": 4646450.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.244450569152832,
|
|
"epoch": 0.20116646896006327,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998816540602584,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.14856441468000411,
|
|
"num_tokens": 4658928.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.227334880828858,
|
|
"epoch": 0.20166073546856464,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998805068496752,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.14230842441320418,
|
|
"num_tokens": 4670392.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.30333456993103,
|
|
"epoch": 0.20215500197706604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998793541069964,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.14288742393255233,
|
|
"num_tokens": 4680605.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.180010843276977,
|
|
"epoch": 0.2026492684855674,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998781958322507,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.14871413111686707,
|
|
"num_tokens": 4694250.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.281947135925293,
|
|
"epoch": 0.20314353499406881,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998770320254666,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.14538564309477806,
|
|
"num_tokens": 4705754.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.2580322265625,
|
|
"epoch": 0.2036378015025702,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998758626866725,
|
|
"loss": 6.0149,
|
|
"mean_token_accuracy": 0.1483184352517128,
|
|
"num_tokens": 4716393.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.154084968566894,
|
|
"epoch": 0.20413206801107156,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998746878158973,
|
|
"loss": 6.0146,
|
|
"mean_token_accuracy": 0.1491061344742775,
|
|
"num_tokens": 4726894.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.207609033584594,
|
|
"epoch": 0.20462633451957296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998735074131699,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.1427217200398445,
|
|
"num_tokens": 4737488.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.279056692123413,
|
|
"epoch": 0.20512060102807433,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998723214785194,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.1388081707060337,
|
|
"num_tokens": 4749131.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.210673522949219,
|
|
"epoch": 0.20561486753657574,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998711300119749,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.1441672131419182,
|
|
"num_tokens": 4760503.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.266996288299561,
|
|
"epoch": 0.2061091340450771,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998699330135656,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.14080554991960526,
|
|
"num_tokens": 4771965.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.194011402130127,
|
|
"epoch": 0.20660340055357848,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998687304833212,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.14432893693447113,
|
|
"num_tokens": 4784215.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.1993388652801515,
|
|
"epoch": 0.20709766706207988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499867522421271,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.14703067466616632,
|
|
"num_tokens": 4796410.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.164281129837036,
|
|
"epoch": 0.20759193357058126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499866308827445,
|
|
"loss": 6.0026,
|
|
"mean_token_accuracy": 0.15248948186635972,
|
|
"num_tokens": 4806990.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.228803062438965,
|
|
"epoch": 0.20808620007908263,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998650897018729,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.1467735067009926,
|
|
"num_tokens": 4818903.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.225046968460083,
|
|
"epoch": 0.20858046658758403,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998638650445847,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.15080888271331788,
|
|
"num_tokens": 4829130.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.200888967514038,
|
|
"epoch": 0.2090747330960854,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998626348556105,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.15483116656541823,
|
|
"num_tokens": 4840424.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.197483348846435,
|
|
"epoch": 0.2095689996045868,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998613991349807,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.1491863876581192,
|
|
"num_tokens": 4851674.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.074605512619018,
|
|
"epoch": 0.21006326611308818,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998601578827255,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.1571485087275505,
|
|
"num_tokens": 4863884.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.180933475494385,
|
|
"epoch": 0.21055753262158955,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998589110988755,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.15155385658144951,
|
|
"num_tokens": 4875582.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.2378441333770756,
|
|
"epoch": 0.21105179913009095,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998576587834614,
|
|
"loss": 6.0372,
|
|
"mean_token_accuracy": 0.14390906766057016,
|
|
"num_tokens": 4888325.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.167991065979004,
|
|
"epoch": 0.21154606563859232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499856400936514,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.14813374429941178,
|
|
"num_tokens": 4899631.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.222489881515503,
|
|
"epoch": 0.21204033214709372,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998551375580643,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.14445801451802254,
|
|
"num_tokens": 4910954.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.200428104400634,
|
|
"epoch": 0.2125345986555951,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998538686481435,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.14709079191088675,
|
|
"num_tokens": 4921952.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.1896810054779055,
|
|
"epoch": 0.21302886516409647,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998525942067824,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.15096844732761383,
|
|
"num_tokens": 4933984.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.227153158187866,
|
|
"epoch": 0.21352313167259787,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998513142340128,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.14837369918823243,
|
|
"num_tokens": 4945926.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.1681867122650145,
|
|
"epoch": 0.21401739818109924,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998500287298657,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.15544141232967376,
|
|
"num_tokens": 4958123.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.295369386672974,
|
|
"epoch": 0.21451166468960065,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998487376943733,
|
|
"loss": 6.1066,
|
|
"mean_token_accuracy": 0.14306268021464347,
|
|
"num_tokens": 4970409.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.205995368957519,
|
|
"epoch": 0.21500593119810202,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499847441127567,
|
|
"loss": 6.0043,
|
|
"mean_token_accuracy": 0.14616703540086745,
|
|
"num_tokens": 4980429.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.177132654190063,
|
|
"epoch": 0.2155001977066034,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998461390294787,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.14917071387171746,
|
|
"num_tokens": 4991790.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.220096111297607,
|
|
"epoch": 0.2159944642151048,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998448314001405,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.14717172235250472,
|
|
"num_tokens": 5003611.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.254109907150268,
|
|
"epoch": 0.21648873072360617,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998435182395845,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.13986384347081185,
|
|
"num_tokens": 5014824.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.227781105041504,
|
|
"epoch": 0.21698299723210757,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998421995478432,
|
|
"loss": 6.0503,
|
|
"mean_token_accuracy": 0.148946550488472,
|
|
"num_tokens": 5026937.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.244038105010986,
|
|
"epoch": 0.21747726374060894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998408753249489,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.13694722205400467,
|
|
"num_tokens": 5037996.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.237607145309449,
|
|
"epoch": 0.2179715302491103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998395455709342,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.1504923239350319,
|
|
"num_tokens": 5050944.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.243500423431397,
|
|
"epoch": 0.2184657967576117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998382102858317,
|
|
"loss": 6.0655,
|
|
"mean_token_accuracy": 0.1380969375371933,
|
|
"num_tokens": 5062129.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.214231157302857,
|
|
"epoch": 0.2189600632661131,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998368694696743,
|
|
"loss": 6.0638,
|
|
"mean_token_accuracy": 0.14710126519203187,
|
|
"num_tokens": 5073318.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.157390117645264,
|
|
"epoch": 0.21945432977461446,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998355231224952,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.13977600187063216,
|
|
"num_tokens": 5084607.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.260241842269897,
|
|
"epoch": 0.21994859628311586,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998341712443273,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.14976139664649962,
|
|
"num_tokens": 5096004.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.157348537445069,
|
|
"epoch": 0.22044286279161723,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499832813835204,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.14522008523344992,
|
|
"num_tokens": 5107171.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.131589794158936,
|
|
"epoch": 0.22093712930011863,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998314508951584,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.15599283277988435,
|
|
"num_tokens": 5119249.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.141232109069824,
|
|
"epoch": 0.22143139580862,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998300824242244,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.146238474547863,
|
|
"num_tokens": 5130798.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.232096910476685,
|
|
"epoch": 0.22192566231712138,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998287084224353,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.13696300685405732,
|
|
"num_tokens": 5141376.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.146618509292603,
|
|
"epoch": 0.22241992882562278,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998273288898252,
|
|
"loss": 5.9091,
|
|
"mean_token_accuracy": 0.15360306277871133,
|
|
"num_tokens": 5152888.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.065787649154663,
|
|
"epoch": 0.22291419533412415,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499825943826428,
|
|
"loss": 6.0166,
|
|
"mean_token_accuracy": 0.14354098588228226,
|
|
"num_tokens": 5165720.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.176988172531128,
|
|
"epoch": 0.22340846184262556,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998245532322776,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.15421061739325523,
|
|
"num_tokens": 5177345.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.1588715553283695,
|
|
"epoch": 0.22390272835112693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998231571074083,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.1537886306643486,
|
|
"num_tokens": 5187385.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.167546176910401,
|
|
"epoch": 0.2243969948596283,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998217554518545,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.14182861372828484,
|
|
"num_tokens": 5199552.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.146705436706543,
|
|
"epoch": 0.2248912613681297,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998203482656507,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.15320322513580323,
|
|
"num_tokens": 5210316.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.161525392532349,
|
|
"epoch": 0.22538552787663108,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998189355488314,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.15011645257472991,
|
|
"num_tokens": 5221595.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.221466970443726,
|
|
"epoch": 0.22587979438513248,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998175173014313,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.14501310810446738,
|
|
"num_tokens": 5232882.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.196228265762329,
|
|
"epoch": 0.22637406089363385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998160935234857,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.14222247898578644,
|
|
"num_tokens": 5244841.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.162954092025757,
|
|
"epoch": 0.22686832740213522,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499814664215029,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.1541356138885021,
|
|
"num_tokens": 5256162.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.1496068954467775,
|
|
"epoch": 0.22736259391063662,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998132293760968,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.1593697711825371,
|
|
"num_tokens": 5267130.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.999020719528199,
|
|
"epoch": 0.227856860419138,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998117890067243,
|
|
"loss": 5.9811,
|
|
"mean_token_accuracy": 0.1474272921681404,
|
|
"num_tokens": 5279394.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.163106775283813,
|
|
"epoch": 0.22835112692763937,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998103431069469,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.15263054817914962,
|
|
"num_tokens": 5291068.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.195495080947876,
|
|
"epoch": 0.22884539343614077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998088916768002,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.15293610841035843,
|
|
"num_tokens": 5300924.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.081633424758911,
|
|
"epoch": 0.22933965994464214,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998074347163199,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.15552001297473908,
|
|
"num_tokens": 5311998.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.198126602172851,
|
|
"epoch": 0.22983392645314354,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998059722255418,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.1518368422985077,
|
|
"num_tokens": 5322163.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.083274698257446,
|
|
"epoch": 0.23032819296164492,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998045042045019,
|
|
"loss": 5.9524,
|
|
"mean_token_accuracy": 0.15333037078380585,
|
|
"num_tokens": 5331638.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.1572568893432615,
|
|
"epoch": 0.2308224594701463,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998030306532363,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.15855043828487397,
|
|
"num_tokens": 5342399.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.137854766845703,
|
|
"epoch": 0.2313167259786477,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998015515717813,
|
|
"loss": 5.9965,
|
|
"mean_token_accuracy": 0.14803121536970137,
|
|
"num_tokens": 5353481.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.154527091979981,
|
|
"epoch": 0.23181099248714906,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998000669601733,
|
|
"loss": 5.9314,
|
|
"mean_token_accuracy": 0.15086086690425873,
|
|
"num_tokens": 5365167.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.123769855499267,
|
|
"epoch": 0.23230525899565047,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997985768184488,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.15256110429763795,
|
|
"num_tokens": 5375809.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.056447267532349,
|
|
"epoch": 0.23279952550415184,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997970811466443,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.15769713670015334,
|
|
"num_tokens": 5387372.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.282668924331665,
|
|
"epoch": 0.2332937920126532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997955799447969,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.14419636502861977,
|
|
"num_tokens": 5399210.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.112582731246948,
|
|
"epoch": 0.2337880585211546,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997940732129432,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.14607637226581574,
|
|
"num_tokens": 5410969.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.07240662574768,
|
|
"epoch": 0.23428232502965599,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997925609511205,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.15724605768918992,
|
|
"num_tokens": 5422569.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.12368426322937,
|
|
"epoch": 0.2347765915381574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997910431593659,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.1551958680152893,
|
|
"num_tokens": 5434592.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.1067907333374025,
|
|
"epoch": 0.23527085804665876,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997895198377168,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15322967916727065,
|
|
"num_tokens": 5446525.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.143498849868775,
|
|
"epoch": 0.23576512455516013,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997879909862105,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.15008583962917327,
|
|
"num_tokens": 5457327.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.232042026519776,
|
|
"epoch": 0.23625939106366153,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499786456604885,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.14592731818556787,
|
|
"num_tokens": 5468533.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.09161491394043,
|
|
"epoch": 0.2367536575721629,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997849166937776,
|
|
"loss": 5.8926,
|
|
"mean_token_accuracy": 0.15270923376083373,
|
|
"num_tokens": 5480652.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.1551309585571286,
|
|
"epoch": 0.2372479240806643,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997833712529265,
|
|
"loss": 5.9233,
|
|
"mean_token_accuracy": 0.1461702197790146,
|
|
"num_tokens": 5491446.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.084803724288941,
|
|
"epoch": 0.23774219058916568,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997818202823695,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.15715935975313186,
|
|
"num_tokens": 5502886.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.133616352081299,
|
|
"epoch": 0.23823645709766705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997802637821449,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.14540450945496558,
|
|
"num_tokens": 5514305.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.08673734664917,
|
|
"epoch": 0.23873072360616845,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997787017522909,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.1596880927681923,
|
|
"num_tokens": 5525913.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.006779384613037,
|
|
"epoch": 0.23922499011466983,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997771341928459,
|
|
"loss": 5.8859,
|
|
"mean_token_accuracy": 0.16061815544962882,
|
|
"num_tokens": 5537069.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.104032278060913,
|
|
"epoch": 0.2397192566231712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997755611038487,
|
|
"loss": 5.9961,
|
|
"mean_token_accuracy": 0.144280281662941,
|
|
"num_tokens": 5547988.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.207238817214966,
|
|
"epoch": 0.2402135231316726,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997739824853378,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.14740365296602248,
|
|
"num_tokens": 5560400.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.095962429046631,
|
|
"epoch": 0.24070778964017397,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997723983373519,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.1554897114634514,
|
|
"num_tokens": 5572291.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.167290544509887,
|
|
"epoch": 0.24120205614867538,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997708086599303,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.1484512284398079,
|
|
"num_tokens": 5583583.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.183183908462524,
|
|
"epoch": 0.24169632265717675,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997692134531119,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.14650021344423295,
|
|
"num_tokens": 5595499.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.089758729934692,
|
|
"epoch": 0.24219058916567812,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499767612716936,
|
|
"loss": 5.8875,
|
|
"mean_token_accuracy": 0.16020604968070984,
|
|
"num_tokens": 5606745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.070741653442383,
|
|
"epoch": 0.24268485567417952,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997660064514419,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.14979561567306518,
|
|
"num_tokens": 5618226.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.241481876373291,
|
|
"epoch": 0.2431791221826809,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997643946566691,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.14858949631452562,
|
|
"num_tokens": 5628941.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.038295078277588,
|
|
"epoch": 0.2436733886911823,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997627773326574,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.16433235108852387,
|
|
"num_tokens": 5641077.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.130333995819091,
|
|
"epoch": 0.24416765519968367,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997611544794465,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.14532085955142976,
|
|
"num_tokens": 5652156.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.220878314971924,
|
|
"epoch": 0.24466192170818504,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997595260970764,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.14606670886278153,
|
|
"num_tokens": 5663988.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.095632934570313,
|
|
"epoch": 0.24515618821668644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499757892185587,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.15061840713024138,
|
|
"num_tokens": 5676302.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.133012342453003,
|
|
"epoch": 0.24565045472518782,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997562527450187,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.14953794404864312,
|
|
"num_tokens": 5686686.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.10685167312622,
|
|
"epoch": 0.24614472123368922,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997546077754116,
|
|
"loss": 5.8971,
|
|
"mean_token_accuracy": 0.1646903246641159,
|
|
"num_tokens": 5698379.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.1061577796936035,
|
|
"epoch": 0.2466389877421906,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997529572768063,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.1544343575835228,
|
|
"num_tokens": 5708891.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.052794504165649,
|
|
"epoch": 0.24713325425069196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997513012492434,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.15541503578424454,
|
|
"num_tokens": 5720326.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.1182698726654055,
|
|
"epoch": 0.24762752075919336,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997496396927636,
|
|
"loss": 5.8705,
|
|
"mean_token_accuracy": 0.1567327544093132,
|
|
"num_tokens": 5731121.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.115647983551026,
|
|
"epoch": 0.24812178726769474,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997479726074077,
|
|
"loss": 5.9047,
|
|
"mean_token_accuracy": 0.1568905934691429,
|
|
"num_tokens": 5741637.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.159960174560547,
|
|
"epoch": 0.24861605377619614,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499746299993217,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15289734974503516,
|
|
"num_tokens": 5752659.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.045699405670166,
|
|
"epoch": 0.2491103202846975,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997446218502324,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.15085340589284896,
|
|
"num_tokens": 5763829.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.149063539505005,
|
|
"epoch": 0.24960458679319888,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997429381784952,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.14978117346763611,
|
|
"num_tokens": 5775848.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.088855504989624,
|
|
"epoch": 0.2500988533017003,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997412489780469,
|
|
"loss": 5.9458,
|
|
"mean_token_accuracy": 0.15962931662797927,
|
|
"num_tokens": 5786595.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.095394515991211,
|
|
"epoch": 0.25059311981020166,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499739554248929,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.16231104359030724,
|
|
"num_tokens": 5797841.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.014609241485596,
|
|
"epoch": 0.25108738631870303,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997378539911832,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.15764168053865432,
|
|
"num_tokens": 5809106.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.036460590362549,
|
|
"epoch": 0.2515816528272044,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997361482048513,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.15573886185884475,
|
|
"num_tokens": 5820316.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.130526161193847,
|
|
"epoch": 0.25207591933570583,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997344368899753,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.1489880457520485,
|
|
"num_tokens": 5833137.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.140044546127319,
|
|
"epoch": 0.2525701858442072,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997327200465972,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.1543002173304558,
|
|
"num_tokens": 5844088.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.110529088973999,
|
|
"epoch": 0.2530644523527086,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997309976747594,
|
|
"loss": 5.9042,
|
|
"mean_token_accuracy": 0.1501915216445923,
|
|
"num_tokens": 5854546.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.13458662033081,
|
|
"epoch": 0.25355871886120995,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997292697745042,
|
|
"loss": 5.9112,
|
|
"mean_token_accuracy": 0.15691982805728913,
|
|
"num_tokens": 5865326.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.1010185241699215,
|
|
"epoch": 0.2540529853697113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997275363458741,
|
|
"loss": 5.8117,
|
|
"mean_token_accuracy": 0.15828278064727783,
|
|
"num_tokens": 5876487.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.987020254135132,
|
|
"epoch": 0.25454725187821275,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997257973889118,
|
|
"loss": 5.9125,
|
|
"mean_token_accuracy": 0.15327198207378387,
|
|
"num_tokens": 5887846.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.149021959304809,
|
|
"epoch": 0.25504151838671413,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997240529036599,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.16193937510252,
|
|
"num_tokens": 5898572.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.05965838432312,
|
|
"epoch": 0.2555357848952155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997223028901615,
|
|
"loss": 5.9338,
|
|
"mean_token_accuracy": 0.15329011231660844,
|
|
"num_tokens": 5908927.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.08336501121521,
|
|
"epoch": 0.2560300514037169,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997205473484596,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.15567793250083922,
|
|
"num_tokens": 5919807.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.05651478767395,
|
|
"epoch": 0.25652431791221825,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997187862785974,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.15435239002108575,
|
|
"num_tokens": 5931160.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.133126735687256,
|
|
"epoch": 0.2570185844207197,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997170196806181,
|
|
"loss": 5.9697,
|
|
"mean_token_accuracy": 0.14922844171524047,
|
|
"num_tokens": 5943694.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.10101637840271,
|
|
"epoch": 0.25751285092922105,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997152475545652,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.1568847507238388,
|
|
"num_tokens": 5954543.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.032856464385986,
|
|
"epoch": 0.2580071174377224,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997134699004825,
|
|
"loss": 5.9138,
|
|
"mean_token_accuracy": 0.15866148322820664,
|
|
"num_tokens": 5965080.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.100453948974609,
|
|
"epoch": 0.2585013839462238,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997116867184136,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.1504710793495178,
|
|
"num_tokens": 5975314.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.156487703323364,
|
|
"epoch": 0.25899565045472517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997098980084022,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.1572839215397835,
|
|
"num_tokens": 5985927.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.053633785247802,
|
|
"epoch": 0.2594899169632266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997081037704926,
|
|
"loss": 5.9358,
|
|
"mean_token_accuracy": 0.15075213015079497,
|
|
"num_tokens": 5997311.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.047173976898193,
|
|
"epoch": 0.25998418347172797,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997063040047288,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.14865972250699996,
|
|
"num_tokens": 6008595.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.14096417427063,
|
|
"epoch": 0.26047844998022934,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997044987111548,
|
|
"loss": 5.8857,
|
|
"mean_token_accuracy": 0.15375734716653824,
|
|
"num_tokens": 6019055.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.093348121643066,
|
|
"epoch": 0.2609727164887307,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997026878898155,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.14476267546415328,
|
|
"num_tokens": 6030029.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.12502155303955,
|
|
"epoch": 0.2614669829972321,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997008715407552,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.1483074575662613,
|
|
"num_tokens": 6041495.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.122032976150512,
|
|
"epoch": 0.2619612495057335,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996990496640185,
|
|
"loss": 5.8544,
|
|
"mean_token_accuracy": 0.1526714891195297,
|
|
"num_tokens": 6052307.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.993034410476684,
|
|
"epoch": 0.2624555160142349,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996972222596505,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.15812475681304933,
|
|
"num_tokens": 6062550.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.990975999832154,
|
|
"epoch": 0.26294978252273626,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996953893276958,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.15025542229413985,
|
|
"num_tokens": 6074450.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.081708335876465,
|
|
"epoch": 0.26344404903123764,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996935508681997,
|
|
"loss": 5.9066,
|
|
"mean_token_accuracy": 0.155532006919384,
|
|
"num_tokens": 6085749.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.05987777709961,
|
|
"epoch": 0.263938315539739,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996917068812075,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.16070664674043655,
|
|
"num_tokens": 6096438.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.030507278442383,
|
|
"epoch": 0.26443258204824044,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996898573667643,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.14768243730068206,
|
|
"num_tokens": 6108386.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.0277626514434814,
|
|
"epoch": 0.2649268485567418,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996880023249158,
|
|
"loss": 5.7815,
|
|
"mean_token_accuracy": 0.16615237444639205,
|
|
"num_tokens": 6118771.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.110533952713013,
|
|
"epoch": 0.2654211150652432,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996861417557076,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15228350311517716,
|
|
"num_tokens": 6130718.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.002656650543213,
|
|
"epoch": 0.26591538157374456,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996842756591855,
|
|
"loss": 5.9056,
|
|
"mean_token_accuracy": 0.1509190857410431,
|
|
"num_tokens": 6142086.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.003255558013916,
|
|
"epoch": 0.26640964808224593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996824040353953,
|
|
"loss": 5.8815,
|
|
"mean_token_accuracy": 0.15629380643367768,
|
|
"num_tokens": 6153857.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.225221776962281,
|
|
"epoch": 0.2669039145907473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996805268843832,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.14962111189961433,
|
|
"num_tokens": 6166796.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.044892978668213,
|
|
"epoch": 0.26739818109924873,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996786442061952,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.15803508460521698,
|
|
"num_tokens": 6178046.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.045975303649902,
|
|
"epoch": 0.2678924476077501,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996767560008777,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.15712593793869017,
|
|
"num_tokens": 6190455.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.0375689506530765,
|
|
"epoch": 0.2683867141162515,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996748622684771,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.16150919497013091,
|
|
"num_tokens": 6201659.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.969774627685547,
|
|
"epoch": 0.26888098062475285,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996729630090401,
|
|
"loss": 5.8917,
|
|
"mean_token_accuracy": 0.15097161531448364,
|
|
"num_tokens": 6213870.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.122914266586304,
|
|
"epoch": 0.2693752471332542,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996710582226133,
|
|
"loss": 5.8313,
|
|
"mean_token_accuracy": 0.16073371469974518,
|
|
"num_tokens": 6224237.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.037442827224732,
|
|
"epoch": 0.26986951364175565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996691479092437,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.1519405834376812,
|
|
"num_tokens": 6235868.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.088305044174194,
|
|
"epoch": 0.270363780150257,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996672320689782,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.15224603563547134,
|
|
"num_tokens": 6247994.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.923361682891846,
|
|
"epoch": 0.2708580466587584,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996653107018638,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.16427244246006012,
|
|
"num_tokens": 6259654.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.050891637802124,
|
|
"epoch": 0.2713523131672598,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499663383807948,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.1583833247423172,
|
|
"num_tokens": 6270582.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.075754547119141,
|
|
"epoch": 0.27184657967576115,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996614513872781,
|
|
"loss": 5.8355,
|
|
"mean_token_accuracy": 0.15854936242103576,
|
|
"num_tokens": 6281088.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.093008613586425,
|
|
"epoch": 0.2723408461842626,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996595134399017,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.1467800997197628,
|
|
"num_tokens": 6292920.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.052947187423706,
|
|
"epoch": 0.27283511269276395,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996575699658664,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.156585992872715,
|
|
"num_tokens": 6304980.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.028429698944092,
|
|
"epoch": 0.2733293792012653,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996556209652199,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.16182130724191665,
|
|
"num_tokens": 6316175.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.074451160430908,
|
|
"epoch": 0.2738236457097667,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996536664380104,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.159360608458519,
|
|
"num_tokens": 6327590.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.015805959701538,
|
|
"epoch": 0.27431791221826807,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996517063842859,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.15416058599948884,
|
|
"num_tokens": 6339066.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.061740112304688,
|
|
"epoch": 0.2748121787267695,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996497408040944,
|
|
"loss": 5.8339,
|
|
"mean_token_accuracy": 0.15957537293434143,
|
|
"num_tokens": 6349485.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.976840829849243,
|
|
"epoch": 0.27530644523527087,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996477696974845,
|
|
"loss": 5.7903,
|
|
"mean_token_accuracy": 0.16120934933423997,
|
|
"num_tokens": 6360775.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.0038059711456295,
|
|
"epoch": 0.27580071174377224,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996457930645046,
|
|
"loss": 5.797,
|
|
"mean_token_accuracy": 0.15618587732315065,
|
|
"num_tokens": 6371645.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.965744543075561,
|
|
"epoch": 0.2762949782522736,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996438109052034,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.1584193930029869,
|
|
"num_tokens": 6383877.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.05974178314209,
|
|
"epoch": 0.276789244760775,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996418232196296,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.14770453348755835,
|
|
"num_tokens": 6394488.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.052662467956543,
|
|
"epoch": 0.2772835112692764,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996398300078321,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.156643283367157,
|
|
"num_tokens": 6404948.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.078036880493164,
|
|
"epoch": 0.2777777777777778,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996378312698598,
|
|
"loss": 5.8659,
|
|
"mean_token_accuracy": 0.15740013867616653,
|
|
"num_tokens": 6416273.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.047493886947632,
|
|
"epoch": 0.27827204428627916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996358270057622,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.15248379707336426,
|
|
"num_tokens": 6427091.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.046441507339478,
|
|
"epoch": 0.27876631079478054,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996338172155883,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.1569639503955841,
|
|
"num_tokens": 6438254.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.973606586456299,
|
|
"epoch": 0.2792605773032819,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996318018993876,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.1562727063894272,
|
|
"num_tokens": 6450618.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.033926391601563,
|
|
"epoch": 0.27975484381178334,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996297810572098,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.15667466074228287,
|
|
"num_tokens": 6462467.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.983758878707886,
|
|
"epoch": 0.2802491103202847,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996277546891045,
|
|
"loss": 5.8044,
|
|
"mean_token_accuracy": 0.16479460895061493,
|
|
"num_tokens": 6474206.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.020964288711548,
|
|
"epoch": 0.2807433768287861,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996257227951216,
|
|
"loss": 5.888,
|
|
"mean_token_accuracy": 0.15300803631544113,
|
|
"num_tokens": 6486405.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.05193862915039,
|
|
"epoch": 0.28123764333728746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499623685375311,
|
|
"loss": 5.8497,
|
|
"mean_token_accuracy": 0.15643176138401033,
|
|
"num_tokens": 6496949.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.958805656433105,
|
|
"epoch": 0.28173190984578883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499621642429723,
|
|
"loss": 5.8017,
|
|
"mean_token_accuracy": 0.15794066339731216,
|
|
"num_tokens": 6508913.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.015378046035766,
|
|
"epoch": 0.28222617635429026,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996195939584078,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.15706655457615853,
|
|
"num_tokens": 6519837.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.01123013496399,
|
|
"epoch": 0.28272044286279163,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996175399614156,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.15670203119516374,
|
|
"num_tokens": 6531409.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.018320989608765,
|
|
"epoch": 0.283214709371293,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996154804387972,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.15969696193933486,
|
|
"num_tokens": 6543433.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.009840059280395,
|
|
"epoch": 0.2837089758797944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499613415390603,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.14991554468870164,
|
|
"num_tokens": 6554511.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.046218013763427,
|
|
"epoch": 0.28420324238829575,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499611344816884,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.15823389291763307,
|
|
"num_tokens": 6564591.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.01461706161499,
|
|
"epoch": 0.2846975088967972,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499609268717691,
|
|
"loss": 5.8225,
|
|
"mean_token_accuracy": 0.1623471572995186,
|
|
"num_tokens": 6575684.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.017358875274658,
|
|
"epoch": 0.28519177540529855,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996071870930753,
|
|
"loss": 5.9406,
|
|
"mean_token_accuracy": 0.15425658077001572,
|
|
"num_tokens": 6588504.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.959894227981567,
|
|
"epoch": 0.2856860419137999,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996050999430878,
|
|
"loss": 5.7635,
|
|
"mean_token_accuracy": 0.16143444627523423,
|
|
"num_tokens": 6599969.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.0251145362854,
|
|
"epoch": 0.2861803084223013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996030072677802,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.16413614600896836,
|
|
"num_tokens": 6611430.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.97908205986023,
|
|
"epoch": 0.2866745749308027,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996009090672037,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.1551106110215187,
|
|
"num_tokens": 6623247.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.029708385467529,
|
|
"epoch": 0.28716884143930405,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995988053414098,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.149957475066185,
|
|
"num_tokens": 6635508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.988954877853393,
|
|
"epoch": 0.2876631079478055,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995966960904506,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.15391170904040335,
|
|
"num_tokens": 6646020.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.052160787582397,
|
|
"epoch": 0.28815737445630685,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995945813143778,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.1489527091383934,
|
|
"num_tokens": 6658194.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.05843505859375,
|
|
"epoch": 0.2886516409648082,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995924610132435,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.158658966422081,
|
|
"num_tokens": 6670582.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.010510683059692,
|
|
"epoch": 0.2891459074733096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995903351870998,
|
|
"loss": 5.7942,
|
|
"mean_token_accuracy": 0.15778048932552338,
|
|
"num_tokens": 6680836.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.075353288650513,
|
|
"epoch": 0.28964017398181097,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499588203835999,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.15145400837063788,
|
|
"num_tokens": 6693045.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.051756286621094,
|
|
"epoch": 0.2901344404903124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995860669599935,
|
|
"loss": 5.8502,
|
|
"mean_token_accuracy": 0.15376394540071486,
|
|
"num_tokens": 6704006.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.9235528945922855,
|
|
"epoch": 0.29062870699881377,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499583924559136,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.15702625140547752,
|
|
"num_tokens": 6717027.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.067442607879639,
|
|
"epoch": 0.29112297350731514,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499581776633479,
|
|
"loss": 5.7958,
|
|
"mean_token_accuracy": 0.1589622288942337,
|
|
"num_tokens": 6728107.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.924325895309448,
|
|
"epoch": 0.2916172400158165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995796231830756,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.15883112251758574,
|
|
"num_tokens": 6738628.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.967429113388062,
|
|
"epoch": 0.2921115065243179,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995774642079786,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.16689376384019852,
|
|
"num_tokens": 6749416.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.94444088935852,
|
|
"epoch": 0.2926057730328193,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499575299708241,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.14967955350875856,
|
|
"num_tokens": 6761663.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.0701212882995605,
|
|
"epoch": 0.2931000395413207,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995731296839163,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.16118715405464173,
|
|
"num_tokens": 6773557.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.85501708984375,
|
|
"epoch": 0.29359430604982206,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995709541350578,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.16694540828466414,
|
|
"num_tokens": 6782832.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.010708570480347,
|
|
"epoch": 0.29408857255832344,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499568773061719,
|
|
"loss": 5.8681,
|
|
"mean_token_accuracy": 0.15356052964925765,
|
|
"num_tokens": 6795165.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.066813945770264,
|
|
"epoch": 0.2945828390668248,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995665864639534,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.15979506969451904,
|
|
"num_tokens": 6807054.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.903352069854736,
|
|
"epoch": 0.29507710557532624,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995643943418149,
|
|
"loss": 5.6685,
|
|
"mean_token_accuracy": 0.16543218046426772,
|
|
"num_tokens": 6817681.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.982229900360108,
|
|
"epoch": 0.2955713720838276,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995621966953576,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.15782412886619568,
|
|
"num_tokens": 6829387.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.967217683792114,
|
|
"epoch": 0.296065638592329,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004995599935246355,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.15736720860004424,
|
|
"num_tokens": 6842023.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.993825960159302,
|
|
"epoch": 0.29655990510083036,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995577848297026,
|
|
"loss": 5.824,
|
|
"mean_token_accuracy": 0.15770515501499177,
|
|
"num_tokens": 6853189.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.29655990510083036,
|
|
"eval_entropy": 5.832319829502082,
|
|
"eval_loss": 5.858894348144531,
|
|
"eval_mean_token_accuracy": 0.1635531999793953,
|
|
"eval_num_tokens": 6853189.0,
|
|
"eval_runtime": 20.5029,
|
|
"eval_samples_per_second": 1585.78,
|
|
"eval_steps_per_second": 198.265,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"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": 1590050377728000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|