6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.357355568790947,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742183494567872,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8347,
|
|
"mean_token_accuracy": 6.570302066393197e-05,
|
|
"num_tokens": 14043.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742181587219239,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8184,
|
|
"mean_token_accuracy": 5.6306307669728994e-05,
|
|
"num_tokens": 27431.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742227840423585,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.792,
|
|
"mean_token_accuracy": 0.00015279132057912647,
|
|
"num_tokens": 41546.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742228794097901,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7654,
|
|
"mean_token_accuracy": 5.235602147877216e-05,
|
|
"num_tokens": 55610.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742142009735108,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 4.25,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6461,
|
|
"mean_token_accuracy": 0.0007188191404566169,
|
|
"num_tokens": 67719.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741945934295654,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 3.4375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5819,
|
|
"mean_token_accuracy": 0.0071188481757417325,
|
|
"num_tokens": 82309.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.741309547424317,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.436,
|
|
"mean_token_accuracy": 0.025534892454743385,
|
|
"num_tokens": 95752.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.739977741241455,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.3101,
|
|
"mean_token_accuracy": 0.027164995670318604,
|
|
"num_tokens": 109473.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.73803424835205,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.2408,
|
|
"mean_token_accuracy": 0.03164031654596329,
|
|
"num_tokens": 124193.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.736229801177979,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.1299,
|
|
"mean_token_accuracy": 0.033015350252389906,
|
|
"num_tokens": 136870.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.7350643157959,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.0889,
|
|
"mean_token_accuracy": 0.035209237970411776,
|
|
"num_tokens": 150613.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.733927249908447,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.0142,
|
|
"mean_token_accuracy": 0.03481624573469162,
|
|
"num_tokens": 164213.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.732409286499024,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9266,
|
|
"mean_token_accuracy": 0.03644208796322346,
|
|
"num_tokens": 177408.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.730414295196534,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8609,
|
|
"mean_token_accuracy": 0.035931960307061674,
|
|
"num_tokens": 190273.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.727591800689698,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7942,
|
|
"mean_token_accuracy": 0.036602536030113694,
|
|
"num_tokens": 203323.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.723168182373048,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7562,
|
|
"mean_token_accuracy": 0.035238896124064924,
|
|
"num_tokens": 218647.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.717996406555176,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6793,
|
|
"mean_token_accuracy": 0.03231475837528706,
|
|
"num_tokens": 232910.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.712448978424073,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5914,
|
|
"mean_token_accuracy": 0.034204628132283685,
|
|
"num_tokens": 246683.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.703381633758545,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5074,
|
|
"mean_token_accuracy": 0.0348433218896389,
|
|
"num_tokens": 260150.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.688982582092285,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.431,
|
|
"mean_token_accuracy": 0.034749519638717176,
|
|
"num_tokens": 273788.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.672309303283692,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.3078,
|
|
"mean_token_accuracy": 0.03429920971393585,
|
|
"num_tokens": 287625.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.650675106048585,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.2221,
|
|
"mean_token_accuracy": 0.0347648523747921,
|
|
"num_tokens": 302938.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.61922378540039,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0864,
|
|
"mean_token_accuracy": 0.03500578422099352,
|
|
"num_tokens": 316905.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.572606658935547,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.924,
|
|
"mean_token_accuracy": 0.03559151701629162,
|
|
"num_tokens": 331131.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.516113567352296,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8249,
|
|
"mean_token_accuracy": 0.032901805639266965,
|
|
"num_tokens": 344995.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.453802871704102,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6582,
|
|
"mean_token_accuracy": 0.03676526509225368,
|
|
"num_tokens": 361057.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.370664405822755,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5228,
|
|
"mean_token_accuracy": 0.03370327036827803,
|
|
"num_tokens": 375037.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.266613578796386,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3958,
|
|
"mean_token_accuracy": 0.03396179284900427,
|
|
"num_tokens": 389797.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.141527652740479,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2779,
|
|
"mean_token_accuracy": 0.03149167206138372,
|
|
"num_tokens": 403743.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.992219924926758,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1645,
|
|
"mean_token_accuracy": 0.030641537345945834,
|
|
"num_tokens": 417337.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.80675220489502,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9755,
|
|
"mean_token_accuracy": 0.035594462603330615,
|
|
"num_tokens": 430106.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.583033466339112,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9146,
|
|
"mean_token_accuracy": 0.034621411561965944,
|
|
"num_tokens": 444654.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.349032878875732,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.849,
|
|
"mean_token_accuracy": 0.029788750410079955,
|
|
"num_tokens": 457837.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.113014602661133,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6894,
|
|
"mean_token_accuracy": 0.03679767306894064,
|
|
"num_tokens": 472006.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.845180225372314,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6327,
|
|
"mean_token_accuracy": 0.03697254229336977,
|
|
"num_tokens": 486155.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.680907440185546,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6678,
|
|
"mean_token_accuracy": 0.041565592586994174,
|
|
"num_tokens": 501152.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.531956195831299,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5695,
|
|
"mean_token_accuracy": 0.04552752338349819,
|
|
"num_tokens": 514856.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.419017887115478,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5451,
|
|
"mean_token_accuracy": 0.04798501394689083,
|
|
"num_tokens": 529356.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.345262050628662,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.4986,
|
|
"mean_token_accuracy": 0.04905890300869942,
|
|
"num_tokens": 542876.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.245842933654785,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.468,
|
|
"mean_token_accuracy": 0.05098759308457375,
|
|
"num_tokens": 557245.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.199878883361816,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3793,
|
|
"mean_token_accuracy": 0.055880747735500336,
|
|
"num_tokens": 571458.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.144281673431397,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.3802,
|
|
"mean_token_accuracy": 0.054352150112390515,
|
|
"num_tokens": 588000.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.136652183532714,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4053,
|
|
"mean_token_accuracy": 0.06009378880262375,
|
|
"num_tokens": 602302.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.131936168670654,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4315,
|
|
"mean_token_accuracy": 0.05938838943839073,
|
|
"num_tokens": 616708.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.018897008895873,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.2856,
|
|
"mean_token_accuracy": 0.05857427380979061,
|
|
"num_tokens": 629236.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.098274040222169,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.3467,
|
|
"mean_token_accuracy": 0.06362572610378266,
|
|
"num_tokens": 642934.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.013978528976441,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2145,
|
|
"mean_token_accuracy": 0.06474445015192032,
|
|
"num_tokens": 656008.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.028218317031861,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.4327,
|
|
"mean_token_accuracy": 0.06487233191728592,
|
|
"num_tokens": 668843.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.044657325744629,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3194,
|
|
"mean_token_accuracy": 0.06946417763829231,
|
|
"num_tokens": 681883.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.010096073150635,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2913,
|
|
"mean_token_accuracy": 0.06887354739010335,
|
|
"num_tokens": 694282.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.946925401687622,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.21,
|
|
"mean_token_accuracy": 0.07376883625984192,
|
|
"num_tokens": 708158.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.903460550308227,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2194,
|
|
"mean_token_accuracy": 0.06968091353774071,
|
|
"num_tokens": 722083.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.88522777557373,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.2204,
|
|
"mean_token_accuracy": 0.07137699350714684,
|
|
"num_tokens": 737806.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.816258811950684,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.07385070994496346,
|
|
"num_tokens": 754100.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.8969801902771,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1976,
|
|
"mean_token_accuracy": 0.07308120429515838,
|
|
"num_tokens": 769128.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.8850123405456545,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.2051,
|
|
"mean_token_accuracy": 0.07497966662049294,
|
|
"num_tokens": 781259.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.812098693847656,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1031,
|
|
"mean_token_accuracy": 0.07991473153233528,
|
|
"num_tokens": 796152.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.7976302146911625,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1463,
|
|
"mean_token_accuracy": 0.07945740520954132,
|
|
"num_tokens": 809686.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.7539088249206545,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1006,
|
|
"mean_token_accuracy": 0.08280241340398789,
|
|
"num_tokens": 824500.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.737009906768799,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0368,
|
|
"mean_token_accuracy": 0.0804534487426281,
|
|
"num_tokens": 840643.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.828617763519287,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0918,
|
|
"mean_token_accuracy": 0.08342065252363681,
|
|
"num_tokens": 853207.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.701815795898438,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1476,
|
|
"mean_token_accuracy": 0.07626047655940056,
|
|
"num_tokens": 867735.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.727453899383545,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0593,
|
|
"mean_token_accuracy": 0.08431698828935623,
|
|
"num_tokens": 881237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.756283855438232,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.0628,
|
|
"mean_token_accuracy": 0.08603817000985145,
|
|
"num_tokens": 894288.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.698923826217651,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0176,
|
|
"mean_token_accuracy": 0.08519366085529327,
|
|
"num_tokens": 907492.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.638896846771241,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9325,
|
|
"mean_token_accuracy": 0.08895694315433503,
|
|
"num_tokens": 922255.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.63583927154541,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9871,
|
|
"mean_token_accuracy": 0.08658753335475922,
|
|
"num_tokens": 937055.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.590744733810425,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8883,
|
|
"mean_token_accuracy": 0.0914541356265545,
|
|
"num_tokens": 951248.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.55070309638977,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8828,
|
|
"mean_token_accuracy": 0.091338162869215,
|
|
"num_tokens": 965211.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.525717115402221,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.09259014204144478,
|
|
"num_tokens": 979787.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.50576491355896,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8776,
|
|
"mean_token_accuracy": 0.09012275263667106,
|
|
"num_tokens": 993412.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.547108888626099,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8638,
|
|
"mean_token_accuracy": 0.0968759037554264,
|
|
"num_tokens": 1006819.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.480889987945557,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8627,
|
|
"mean_token_accuracy": 0.09363154023885727,
|
|
"num_tokens": 1022287.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.4811498641967775,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8544,
|
|
"mean_token_accuracy": 0.0976115770637989,
|
|
"num_tokens": 1034908.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.450716018676758,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.894,
|
|
"mean_token_accuracy": 0.09215271174907684,
|
|
"num_tokens": 1051506.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.386427736282348,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.7631,
|
|
"mean_token_accuracy": 0.0934596985578537,
|
|
"num_tokens": 1066382.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.438938188552856,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8572,
|
|
"mean_token_accuracy": 0.08746511340141297,
|
|
"num_tokens": 1082030.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.481917047500611,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.09139562249183655,
|
|
"num_tokens": 1095926.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.349998188018799,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7656,
|
|
"mean_token_accuracy": 0.0982861079275608,
|
|
"num_tokens": 1110579.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.378432703018189,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.09419288635253906,
|
|
"num_tokens": 1124001.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.473501968383789,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8251,
|
|
"mean_token_accuracy": 0.09458990395069122,
|
|
"num_tokens": 1138316.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.333215761184692,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7328,
|
|
"mean_token_accuracy": 0.09874959588050843,
|
|
"num_tokens": 1150055.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.342270565032959,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8506,
|
|
"mean_token_accuracy": 0.09371097683906555,
|
|
"num_tokens": 1163645.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.368842363357544,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6872,
|
|
"mean_token_accuracy": 0.10014689564704896,
|
|
"num_tokens": 1176660.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.309666538238526,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7961,
|
|
"mean_token_accuracy": 0.09248664155602455,
|
|
"num_tokens": 1193169.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.347740602493286,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.74,
|
|
"mean_token_accuracy": 0.09651226848363877,
|
|
"num_tokens": 1208484.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.2615007877349855,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.0988834910094738,
|
|
"num_tokens": 1222925.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.298656797409057,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.09822965413331985,
|
|
"num_tokens": 1237949.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.3722340106964115,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.1032131403684616,
|
|
"num_tokens": 1251535.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.26842737197876,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6426,
|
|
"mean_token_accuracy": 0.1049805611371994,
|
|
"num_tokens": 1265453.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.230884599685669,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6627,
|
|
"mean_token_accuracy": 0.1022911824285984,
|
|
"num_tokens": 1280662.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.22289514541626,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7295,
|
|
"mean_token_accuracy": 0.09482937082648277,
|
|
"num_tokens": 1294980.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.170809268951416,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6079,
|
|
"mean_token_accuracy": 0.09827929437160492,
|
|
"num_tokens": 1309686.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.160658168792724,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.5961,
|
|
"mean_token_accuracy": 0.10312132835388184,
|
|
"num_tokens": 1324815.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.259875392913818,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.10013843029737472,
|
|
"num_tokens": 1337829.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.098458099365234,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6612,
|
|
"mean_token_accuracy": 0.10124345347285271,
|
|
"num_tokens": 1352163.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.205197191238403,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.5936,
|
|
"mean_token_accuracy": 0.10394150242209435,
|
|
"num_tokens": 1364954.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.174849510192871,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.09912089258432388,
|
|
"num_tokens": 1379414.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.093812608718872,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.10558257475495339,
|
|
"num_tokens": 1393515.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.065914583206177,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.10575130134820938,
|
|
"num_tokens": 1408986.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.068597936630249,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.1057064950466156,
|
|
"num_tokens": 1423176.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.180021667480469,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6594,
|
|
"mean_token_accuracy": 0.101287080347538,
|
|
"num_tokens": 1436802.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.107086324691773,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5323,
|
|
"mean_token_accuracy": 0.1064387544989586,
|
|
"num_tokens": 1449212.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.067509412765503,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.5942,
|
|
"mean_token_accuracy": 0.10407756939530373,
|
|
"num_tokens": 1463357.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.188254976272583,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5773,
|
|
"mean_token_accuracy": 0.10477585569024087,
|
|
"num_tokens": 1477494.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.07730622291565,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.5115,
|
|
"mean_token_accuracy": 0.10843904837965965,
|
|
"num_tokens": 1491687.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.918906593322754,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.11039169207215309,
|
|
"num_tokens": 1506656.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.066193056106568,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.10977512747049331,
|
|
"num_tokens": 1519336.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.121071767807007,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.637,
|
|
"mean_token_accuracy": 0.10029823333024979,
|
|
"num_tokens": 1535204.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.026650047302246,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4435,
|
|
"mean_token_accuracy": 0.11559138372540474,
|
|
"num_tokens": 1547876.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.059904098510742,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5566,
|
|
"mean_token_accuracy": 0.10418016389012337,
|
|
"num_tokens": 1560315.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.000280284881592,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6114,
|
|
"mean_token_accuracy": 0.10283819288015365,
|
|
"num_tokens": 1576379.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.1294999599456785,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4815,
|
|
"mean_token_accuracy": 0.1085024543106556,
|
|
"num_tokens": 1590480.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.918955373764038,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5464,
|
|
"mean_token_accuracy": 0.10271873772144317,
|
|
"num_tokens": 1605328.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.0181163311004635,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4882,
|
|
"mean_token_accuracy": 0.10755092278122902,
|
|
"num_tokens": 1619814.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.944701337814331,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.10893059074878693,
|
|
"num_tokens": 1632561.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.987877702713012,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5072,
|
|
"mean_token_accuracy": 0.10601216182112694,
|
|
"num_tokens": 1645669.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.988888740539551,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.454,
|
|
"mean_token_accuracy": 0.10420122295618058,
|
|
"num_tokens": 1660479.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.946523141860962,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4849,
|
|
"mean_token_accuracy": 0.1114343523979187,
|
|
"num_tokens": 1673966.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.8098907470703125,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.11343350037932395,
|
|
"num_tokens": 1688866.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.852885770797729,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.11477320343255996,
|
|
"num_tokens": 1703810.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.044281244277954,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5907,
|
|
"mean_token_accuracy": 0.10320461988449096,
|
|
"num_tokens": 1719308.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.940822982788086,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.1170460619032383,
|
|
"num_tokens": 1734508.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.8789849281311035,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.3345,
|
|
"mean_token_accuracy": 0.11990054100751876,
|
|
"num_tokens": 1745999.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.763300085067749,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.11457164734601974,
|
|
"num_tokens": 1761083.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.822115707397461,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.11405027881264687,
|
|
"num_tokens": 1774948.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.937965774536133,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.10521830841898919,
|
|
"num_tokens": 1787897.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.7878087043762205,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3098,
|
|
"mean_token_accuracy": 0.11155571267008782,
|
|
"num_tokens": 1801208.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.7966279029846195,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3072,
|
|
"mean_token_accuracy": 0.11627824008464813,
|
|
"num_tokens": 1815439.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.812145853042603,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3388,
|
|
"mean_token_accuracy": 0.11540080681443214,
|
|
"num_tokens": 1828177.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.74655556678772,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3067,
|
|
"mean_token_accuracy": 0.11337784305214882,
|
|
"num_tokens": 1844854.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.742314243316651,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.11590223461389541,
|
|
"num_tokens": 1858245.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.87442831993103,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4123,
|
|
"mean_token_accuracy": 0.10785512253642082,
|
|
"num_tokens": 1872167.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.815114450454712,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.11168409660458564,
|
|
"num_tokens": 1885376.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.842722368240357,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.10913070514798165,
|
|
"num_tokens": 1899318.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.785850381851196,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4205,
|
|
"mean_token_accuracy": 0.10894930735230446,
|
|
"num_tokens": 1914028.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.8544024467468265,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.11298043429851531,
|
|
"num_tokens": 1927653.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.788467264175415,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.10948711559176445,
|
|
"num_tokens": 1941397.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.758484315872193,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3168,
|
|
"mean_token_accuracy": 0.11713797152042389,
|
|
"num_tokens": 1955941.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.817478275299072,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.11794802024960518,
|
|
"num_tokens": 1970440.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.679837894439697,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2517,
|
|
"mean_token_accuracy": 0.11665802001953125,
|
|
"num_tokens": 1985770.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.776376962661743,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.10708962306380272,
|
|
"num_tokens": 1999314.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.668450260162354,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.12091019451618194,
|
|
"num_tokens": 2014578.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.739320993423462,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.11275363117456436,
|
|
"num_tokens": 2027650.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.798482942581177,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2793,
|
|
"mean_token_accuracy": 0.1181432731449604,
|
|
"num_tokens": 2042215.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.676054430007935,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.11466208919882774,
|
|
"num_tokens": 2055818.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.653960132598877,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.11222518086433411,
|
|
"num_tokens": 2069040.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.682643699645996,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.11789485588669776,
|
|
"num_tokens": 2085085.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.727219772338867,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.11351984664797783,
|
|
"num_tokens": 2100780.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.862605714797974,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.112281883507967,
|
|
"num_tokens": 2116317.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.620303583145142,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2802,
|
|
"mean_token_accuracy": 0.11524079740047455,
|
|
"num_tokens": 2130865.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.664459180831909,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.11343947649002076,
|
|
"num_tokens": 2145791.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.749904727935791,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2298,
|
|
"mean_token_accuracy": 0.12268061265349388,
|
|
"num_tokens": 2158750.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.6750328063964846,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3118,
|
|
"mean_token_accuracy": 0.11220015361905097,
|
|
"num_tokens": 2175026.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.596572732925415,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.11250628605484962,
|
|
"num_tokens": 2189597.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.779586124420166,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4,
|
|
"mean_token_accuracy": 0.11090977415442467,
|
|
"num_tokens": 2203663.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.60975866317749,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2014,
|
|
"mean_token_accuracy": 0.1156569704413414,
|
|
"num_tokens": 2218784.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.622003269195557,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2237,
|
|
"mean_token_accuracy": 0.11353443339467048,
|
|
"num_tokens": 2233256.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.63480863571167,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2379,
|
|
"mean_token_accuracy": 0.11858787089586258,
|
|
"num_tokens": 2247689.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.557226371765137,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.12291062027215957,
|
|
"num_tokens": 2261158.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.518621158599854,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.13050554171204568,
|
|
"num_tokens": 2274013.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.6024250984191895,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3208,
|
|
"mean_token_accuracy": 0.11554502844810485,
|
|
"num_tokens": 2287471.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.5365015983581545,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.1233399897813797,
|
|
"num_tokens": 2302536.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.640579080581665,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.337,
|
|
"mean_token_accuracy": 0.11535090804100037,
|
|
"num_tokens": 2315235.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.747769975662232,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.11088532656431198,
|
|
"num_tokens": 2329010.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.591479730606079,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2125,
|
|
"mean_token_accuracy": 0.1245424821972847,
|
|
"num_tokens": 2342862.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.614097547531128,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.12870702892541885,
|
|
"num_tokens": 2354680.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.493401050567627,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.11563577875494957,
|
|
"num_tokens": 2369251.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.510954999923706,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.11866097152233124,
|
|
"num_tokens": 2382880.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.579282760620117,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.1205758735537529,
|
|
"num_tokens": 2397627.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.6060676097869875,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.12276405319571496,
|
|
"num_tokens": 2411923.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.614116859436035,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2741,
|
|
"mean_token_accuracy": 0.11239862740039826,
|
|
"num_tokens": 2426253.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.549399185180664,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.12170327082276344,
|
|
"num_tokens": 2440887.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.552827501296997,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.12400813326239586,
|
|
"num_tokens": 2453556.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.546022272109985,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2013,
|
|
"mean_token_accuracy": 0.12121366187930108,
|
|
"num_tokens": 2467374.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.5050191402435305,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.11917331218719482,
|
|
"num_tokens": 2481106.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.468537712097168,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.1258152939379215,
|
|
"num_tokens": 2495431.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.5304240703582765,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.11701044365763665,
|
|
"num_tokens": 2511312.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.55829701423645,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.12205464690923691,
|
|
"num_tokens": 2524960.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.500060653686523,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.12649419754743577,
|
|
"num_tokens": 2537965.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.5613710403442385,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.12154769822955132,
|
|
"num_tokens": 2550802.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.482674026489258,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.12224112898111343,
|
|
"num_tokens": 2565844.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.567696285247803,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1645,
|
|
"mean_token_accuracy": 0.12145803570747375,
|
|
"num_tokens": 2580049.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.474516153335571,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.12551279589533806,
|
|
"num_tokens": 2594516.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.357745122909546,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.11735675930976867,
|
|
"num_tokens": 2610528.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.500650882720947,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.12276835590600968,
|
|
"num_tokens": 2624357.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.390538358688355,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.12950707823038102,
|
|
"num_tokens": 2640422.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.3502476692199705,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.005,
|
|
"mean_token_accuracy": 0.1270424395799637,
|
|
"num_tokens": 2653573.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.450726938247681,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.1256076291203499,
|
|
"num_tokens": 2667746.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.3469545364379885,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.12623366490006446,
|
|
"num_tokens": 2681158.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.49516339302063,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.12307176068425178,
|
|
"num_tokens": 2693093.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.446919965744018,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.1252012223005295,
|
|
"num_tokens": 2704664.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.3282310962677,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.12134386375546455,
|
|
"num_tokens": 2718495.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.422227954864502,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1294598400592804,
|
|
"num_tokens": 2731529.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.311568117141723,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.13299588859081268,
|
|
"num_tokens": 2745382.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.468044996261597,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0841,
|
|
"mean_token_accuracy": 0.12702603191137313,
|
|
"num_tokens": 2758291.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.341191387176513,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.13111869767308235,
|
|
"num_tokens": 2771179.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.383563899993897,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.12788205072283745,
|
|
"num_tokens": 2784172.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.4522544860839846,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.12667660266160966,
|
|
"num_tokens": 2798402.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.364996814727784,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.12513912171125413,
|
|
"num_tokens": 2813371.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.334622097015381,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.1293714627623558,
|
|
"num_tokens": 2825837.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.454077196121216,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.12313304245471954,
|
|
"num_tokens": 2837988.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.282851886749268,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 5.9817,
|
|
"mean_token_accuracy": 0.13360010832548141,
|
|
"num_tokens": 2851396.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.294692039489746,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.12635651752352714,
|
|
"num_tokens": 2863958.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.461576080322265,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.1211632639169693,
|
|
"num_tokens": 2876179.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.367428874969482,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.12488003447651863,
|
|
"num_tokens": 2890023.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.351331377029419,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 6.0051,
|
|
"mean_token_accuracy": 0.13282816261053085,
|
|
"num_tokens": 2902345.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.4046485900878904,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.12030059173703193,
|
|
"num_tokens": 2916310.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.236508560180664,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 5.9271,
|
|
"mean_token_accuracy": 0.13164182603359223,
|
|
"num_tokens": 2928523.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.436446762084961,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.12325587049126625,
|
|
"num_tokens": 2943367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.359068441390991,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.12907699570059777,
|
|
"num_tokens": 2956995.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.286796140670776,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.12894436493515968,
|
|
"num_tokens": 2971380.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.278202724456787,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.12432756423950195,
|
|
"num_tokens": 2986048.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.425439739227295,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.1325755976140499,
|
|
"num_tokens": 2997058.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.28617296218872,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.0221,
|
|
"mean_token_accuracy": 0.12454378306865692,
|
|
"num_tokens": 3011844.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.313051700592041,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 5.9951,
|
|
"mean_token_accuracy": 0.13137999251484872,
|
|
"num_tokens": 3024648.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.2854513168334964,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 5.9666,
|
|
"mean_token_accuracy": 0.12976680919528008,
|
|
"num_tokens": 3038533.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.290816593170166,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.12990044206380844,
|
|
"num_tokens": 3052531.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.258984231948853,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.12387203425168991,
|
|
"num_tokens": 3066526.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.306193065643311,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1295250229537487,
|
|
"num_tokens": 3080729.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.284939384460449,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.13003896847367286,
|
|
"num_tokens": 3093776.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.197756433486939,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.13206810057163237,
|
|
"num_tokens": 3107005.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.382076263427734,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.12192723751068116,
|
|
"num_tokens": 3120840.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.247245407104492,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 5.9423,
|
|
"mean_token_accuracy": 0.13738912492990493,
|
|
"num_tokens": 3134894.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.403128004074096,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.12629491686820984,
|
|
"num_tokens": 3146917.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.3133220195770265,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 6.0041,
|
|
"mean_token_accuracy": 0.12788599953055382,
|
|
"num_tokens": 3162161.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.192528200149536,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.13294726982712746,
|
|
"num_tokens": 3176627.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.281828927993774,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.12526661157608032,
|
|
"num_tokens": 3190139.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.122537755966187,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 5.7922,
|
|
"mean_token_accuracy": 0.13596827089786528,
|
|
"num_tokens": 3202312.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.275762701034546,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.1306569755077362,
|
|
"num_tokens": 3219052.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.147595548629761,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.8729,
|
|
"mean_token_accuracy": 0.13916604742407798,
|
|
"num_tokens": 3233706.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.3489350318908695,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.12903773859143258,
|
|
"num_tokens": 3249947.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.191387891769409,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.13957050070166588,
|
|
"num_tokens": 3264308.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.211583471298217,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.14119818210601806,
|
|
"num_tokens": 3277171.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.219825363159179,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.13040691390633583,
|
|
"num_tokens": 3290445.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.152277088165283,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.13456293493509291,
|
|
"num_tokens": 3304850.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.18782114982605,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.1308791384100914,
|
|
"num_tokens": 3318765.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.285896110534668,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.12730536982417107,
|
|
"num_tokens": 3330403.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.243529176712036,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.1316504694521427,
|
|
"num_tokens": 3346420.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.200117015838623,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.12813543006777764,
|
|
"num_tokens": 3361853.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.207744121551514,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.1302527032792568,
|
|
"num_tokens": 3375907.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.263318586349487,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 5.9602,
|
|
"mean_token_accuracy": 0.1266719475388527,
|
|
"num_tokens": 3390151.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.158126878738403,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.9592,
|
|
"mean_token_accuracy": 0.12761132046580315,
|
|
"num_tokens": 3405151.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.298018312454223,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 5.9751,
|
|
"mean_token_accuracy": 0.13020757883787154,
|
|
"num_tokens": 3420510.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.109394550323486,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.13398747742176056,
|
|
"num_tokens": 3435162.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.261184501647949,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.1259373977780342,
|
|
"num_tokens": 3450923.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.163080024719238,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.13199557438492776,
|
|
"num_tokens": 3464575.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.13615665435791,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.13966626226902007,
|
|
"num_tokens": 3477494.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.3183629512786865,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 6.0528,
|
|
"mean_token_accuracy": 0.12290267571806908,
|
|
"num_tokens": 3492314.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.17548680305481,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.8749,
|
|
"mean_token_accuracy": 0.13766821697354317,
|
|
"num_tokens": 3504913.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.311449909210205,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.12477483078837395,
|
|
"num_tokens": 3519758.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.139519739151001,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.14197972118854524,
|
|
"num_tokens": 3531268.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.2304911613464355,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.12250895500183105,
|
|
"num_tokens": 3546560.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.161889743804932,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.13964627236127852,
|
|
"num_tokens": 3560602.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.108182716369629,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.12805922999978064,
|
|
"num_tokens": 3575611.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.155970811843872,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.1279609300196171,
|
|
"num_tokens": 3589933.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.128014087677002,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.8852,
|
|
"mean_token_accuracy": 0.1352235957980156,
|
|
"num_tokens": 3602513.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.215742731094361,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.1263606384396553,
|
|
"num_tokens": 3615488.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.0860411643981935,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.13899177685379982,
|
|
"num_tokens": 3629292.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.102784109115601,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1349021963775158,
|
|
"num_tokens": 3647010.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.094648599624634,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14222987964749337,
|
|
"num_tokens": 3661994.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.2444103240966795,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.1391028083860874,
|
|
"num_tokens": 3676789.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.099581623077393,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1327517084777355,
|
|
"num_tokens": 3689598.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.126536417007446,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.13856274411082267,
|
|
"num_tokens": 3703597.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.202872657775879,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1350098006427288,
|
|
"num_tokens": 3717312.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.095597791671753,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.13469851538538932,
|
|
"num_tokens": 3731677.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.175401449203491,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.13118114992976188,
|
|
"num_tokens": 3746648.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.046168470382691,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.8116,
|
|
"mean_token_accuracy": 0.13979229629039763,
|
|
"num_tokens": 3760859.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.1087652206420895,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.14346203953027725,
|
|
"num_tokens": 3774743.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.108399534225464,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.13659733533859253,
|
|
"num_tokens": 3789566.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.125910091400146,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.13647732883691788,
|
|
"num_tokens": 3802875.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.075304651260376,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.1374050907790661,
|
|
"num_tokens": 3816197.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.018436431884766,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.8232,
|
|
"mean_token_accuracy": 0.14218598753213882,
|
|
"num_tokens": 3829196.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.249544095993042,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.13307114019989968,
|
|
"num_tokens": 3842618.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.1407723903656,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.1387593887746334,
|
|
"num_tokens": 3854833.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.195996522903442,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.14503343403339386,
|
|
"num_tokens": 3867971.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.054100847244262,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.14200711995363235,
|
|
"num_tokens": 3881555.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.100306701660156,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.14153566658496858,
|
|
"num_tokens": 3894717.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.075147581100464,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.8292,
|
|
"mean_token_accuracy": 0.13094881400465966,
|
|
"num_tokens": 3909381.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.10245189666748,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.1395154632627964,
|
|
"num_tokens": 3923828.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.967838907241822,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.14525343626737594,
|
|
"num_tokens": 3936901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.132982015609741,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.14513242095708848,
|
|
"num_tokens": 3949052.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.045504951477051,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.8714,
|
|
"mean_token_accuracy": 0.13704032599925994,
|
|
"num_tokens": 3963099.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.16231861114502,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.8014,
|
|
"mean_token_accuracy": 0.1322947271168232,
|
|
"num_tokens": 3977598.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.128900623321533,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.13798302561044692,
|
|
"num_tokens": 3989995.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.172013568878174,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.13327042013406754,
|
|
"num_tokens": 4002971.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.017853879928589,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7647,
|
|
"mean_token_accuracy": 0.13795410469174385,
|
|
"num_tokens": 4017380.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.001563310623169,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.13615191131830215,
|
|
"num_tokens": 4031125.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.0987037181854244,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8352,
|
|
"mean_token_accuracy": 0.1364310458302498,
|
|
"num_tokens": 4046416.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.109888076782227,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.8641,
|
|
"mean_token_accuracy": 0.1359500080347061,
|
|
"num_tokens": 4061024.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.057561159133911,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.1439843602478504,
|
|
"num_tokens": 4074753.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.0372072696685795,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.13691218346357345,
|
|
"num_tokens": 4089954.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.042539405822754,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.7714,
|
|
"mean_token_accuracy": 0.14127889573574065,
|
|
"num_tokens": 4105220.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.025610017776489,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.14062938392162322,
|
|
"num_tokens": 4117578.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.0217842102050785,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.13991036266088486,
|
|
"num_tokens": 4131113.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.923555183410644,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.14742299616336824,
|
|
"num_tokens": 4145029.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.077828407287598,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.14328548908233643,
|
|
"num_tokens": 4157227.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.968223714828492,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.14207359179854392,
|
|
"num_tokens": 4171172.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.060792303085327,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7271,
|
|
"mean_token_accuracy": 0.1467897191643715,
|
|
"num_tokens": 4184219.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.948859405517578,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1476665310561657,
|
|
"num_tokens": 4199317.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.105476236343383,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.13571951538324356,
|
|
"num_tokens": 4213905.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.026069593429566,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.7593,
|
|
"mean_token_accuracy": 0.1381727173924446,
|
|
"num_tokens": 4228123.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0289146900177,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.14089103564620017,
|
|
"num_tokens": 4243024.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.97723650932312,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7316,
|
|
"mean_token_accuracy": 0.14283815920352935,
|
|
"num_tokens": 4259061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.053089904785156,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.13426867201924325,
|
|
"num_tokens": 4273010.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.069848442077637,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.705,
|
|
"mean_token_accuracy": 0.14787458628416061,
|
|
"num_tokens": 4286515.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.92649474143982,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.14708176404237747,
|
|
"num_tokens": 4300125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.960150051116943,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.1453533485531807,
|
|
"num_tokens": 4313962.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.9575080394744875,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.7541,
|
|
"mean_token_accuracy": 0.14509638547897338,
|
|
"num_tokens": 4328776.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.06169753074646,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.1447771780192852,
|
|
"num_tokens": 4340933.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.044741296768189,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.13476346135139466,
|
|
"num_tokens": 4355463.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.017773771286011,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.14227432161569595,
|
|
"num_tokens": 4369717.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.01103105545044,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.14884234070777894,
|
|
"num_tokens": 4383713.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.982986640930176,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.14456475526094437,
|
|
"num_tokens": 4396487.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.072724056243897,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.8018,
|
|
"mean_token_accuracy": 0.14579196870326996,
|
|
"num_tokens": 4408762.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.907863330841065,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.14011288806796074,
|
|
"num_tokens": 4422871.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.988130187988281,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.14636473283171653,
|
|
"num_tokens": 4436399.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.935398817062378,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.14530467391014099,
|
|
"num_tokens": 4450799.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.8840916633605955,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.6902,
|
|
"mean_token_accuracy": 0.15209779292345046,
|
|
"num_tokens": 4464567.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.023315811157227,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.7492,
|
|
"mean_token_accuracy": 0.1440256230533123,
|
|
"num_tokens": 4478461.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.8960765361785885,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.1430221252143383,
|
|
"num_tokens": 4493252.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.975708055496216,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.1421280398964882,
|
|
"num_tokens": 4507716.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.9918951988220215,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.14283654913306237,
|
|
"num_tokens": 4520903.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.9884819984436035,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.757,
|
|
"mean_token_accuracy": 0.14660940766334535,
|
|
"num_tokens": 4534939.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.941656112670898,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.14215019568800927,
|
|
"num_tokens": 4547502.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.985489463806152,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.1540282890200615,
|
|
"num_tokens": 4560531.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.896367597579956,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.14529286175966263,
|
|
"num_tokens": 4573678.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.953095293045044,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.15338113605976106,
|
|
"num_tokens": 4586313.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.876391077041626,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.14725659191608428,
|
|
"num_tokens": 4600030.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.9935619831085205,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.14525030702352523,
|
|
"num_tokens": 4613289.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.943365240097046,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.6493,
|
|
"mean_token_accuracy": 0.14853100031614302,
|
|
"num_tokens": 4626642.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.986563062667846,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.14294660985469818,
|
|
"num_tokens": 4639750.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.8959746837615965,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.14631985872983932,
|
|
"num_tokens": 4656894.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.864677000045776,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.5882,
|
|
"mean_token_accuracy": 0.15125427693128585,
|
|
"num_tokens": 4670229.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.917145919799805,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.1474950507283211,
|
|
"num_tokens": 4683754.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.861428308486938,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.14484547674655915,
|
|
"num_tokens": 4697824.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.056915712356568,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.14596075415611268,
|
|
"num_tokens": 4711004.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.886464977264405,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.1506524845957756,
|
|
"num_tokens": 4724992.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.93082103729248,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.14679386615753173,
|
|
"num_tokens": 4737770.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.982219123840332,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.6381,
|
|
"mean_token_accuracy": 0.1514803260564804,
|
|
"num_tokens": 4753807.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.760978889465332,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.15484319478273392,
|
|
"num_tokens": 4766294.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.888656377792358,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.15029520839452742,
|
|
"num_tokens": 4780143.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.906369304656982,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6624,
|
|
"mean_token_accuracy": 0.14471479430794715,
|
|
"num_tokens": 4793717.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.035571956634522,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.1430202305316925,
|
|
"num_tokens": 4808925.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.839449691772461,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.1487026743590832,
|
|
"num_tokens": 4821439.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.922779560089111,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.15140777006745337,
|
|
"num_tokens": 4835511.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.826804113388062,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.1572335720062256,
|
|
"num_tokens": 4849500.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.848100852966309,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.1487742006778717,
|
|
"num_tokens": 4863372.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.968707418441772,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.13946339711546898,
|
|
"num_tokens": 4876643.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.929504442214966,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.14708083271980285,
|
|
"num_tokens": 4890274.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.810866594314575,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.15671751648187637,
|
|
"num_tokens": 4905643.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.809827089309692,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.14416072219610215,
|
|
"num_tokens": 4920106.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.933014345169068,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.1499159552156925,
|
|
"num_tokens": 4934498.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.884340429306031,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.142864453792572,
|
|
"num_tokens": 4947562.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.923207092285156,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.6892,
|
|
"mean_token_accuracy": 0.14773986637592315,
|
|
"num_tokens": 4962375.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.941981983184815,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.1469015933573246,
|
|
"num_tokens": 4975683.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.880807876586914,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.14753714501857756,
|
|
"num_tokens": 4989662.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.906244277954102,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.155949142575264,
|
|
"num_tokens": 5003778.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.878344297409058,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.14796825796365737,
|
|
"num_tokens": 5016556.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.8604559898376465,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.15356758683919908,
|
|
"num_tokens": 5029732.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.7357566356658936,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.15466021448373796,
|
|
"num_tokens": 5042123.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.880379962921142,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.14878395795822144,
|
|
"num_tokens": 5055537.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.866318416595459,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.15060170888900756,
|
|
"num_tokens": 5068795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.895635652542114,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.6534,
|
|
"mean_token_accuracy": 0.1463247373700142,
|
|
"num_tokens": 5083149.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.872237825393677,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.15161531865596772,
|
|
"num_tokens": 5096879.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.839275884628296,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.15384691804647446,
|
|
"num_tokens": 5110692.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.84959192276001,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.14749133214354515,
|
|
"num_tokens": 5125981.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.854062128067016,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.6106,
|
|
"mean_token_accuracy": 0.15050003081560134,
|
|
"num_tokens": 5138755.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.971685457229614,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.14192944541573524,
|
|
"num_tokens": 5154208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.9124468803405765,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1436879187822342,
|
|
"num_tokens": 5169633.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.902647590637207,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.6791,
|
|
"mean_token_accuracy": 0.1411766916513443,
|
|
"num_tokens": 5186213.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.956612014770508,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.6828,
|
|
"mean_token_accuracy": 0.15168982446193696,
|
|
"num_tokens": 5201171.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.78167986869812,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15614613145589828,
|
|
"num_tokens": 5216669.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.015679883956909,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.1417037233710289,
|
|
"num_tokens": 5229774.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.945243072509766,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.14587639272212982,
|
|
"num_tokens": 5241862.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.823768424987793,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15290849953889846,
|
|
"num_tokens": 5255768.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.861085605621338,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.15960920006036758,
|
|
"num_tokens": 5268472.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.774131011962891,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.15801258087158204,
|
|
"num_tokens": 5284309.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.877685642242431,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.1461619719862938,
|
|
"num_tokens": 5298559.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.879857110977173,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.1536956936120987,
|
|
"num_tokens": 5312024.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.802623462677002,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15076420307159424,
|
|
"num_tokens": 5326848.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.7987607479095455,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.15402921885252,
|
|
"num_tokens": 5341382.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.8349268436431885,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.14886656552553176,
|
|
"num_tokens": 5355477.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.873121738433838,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.1476642370223999,
|
|
"num_tokens": 5369271.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.8935792446136475,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.14571685194969178,
|
|
"num_tokens": 5385016.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.773671102523804,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.15096244364976882,
|
|
"num_tokens": 5398838.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.834370851516724,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.15553368628025055,
|
|
"num_tokens": 5413297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.883207702636719,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.14447153508663177,
|
|
"num_tokens": 5428013.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.853828191757202,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.15532859563827514,
|
|
"num_tokens": 5442252.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.853962182998657,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.1507514476776123,
|
|
"num_tokens": 5455919.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.824535846710205,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.15193421691656112,
|
|
"num_tokens": 5469615.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.766221046447754,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.15433768928050995,
|
|
"num_tokens": 5483955.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.896716499328614,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.14598566442728042,
|
|
"num_tokens": 5498304.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.828017234802246,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.15394308418035507,
|
|
"num_tokens": 5512674.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.840755033493042,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.14422297328710557,
|
|
"num_tokens": 5527553.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.782053375244141,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16121405810117723,
|
|
"num_tokens": 5539818.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.727403783798218,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.14863491505384446,
|
|
"num_tokens": 5554619.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.792196273803711,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.15689422488212584,
|
|
"num_tokens": 5568539.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.7989184856414795,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.15792766064405442,
|
|
"num_tokens": 5581476.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.7262804985046385,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.15621651336550713,
|
|
"num_tokens": 5593774.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.837261819839478,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1490989312529564,
|
|
"num_tokens": 5606425.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.868685674667359,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.1526150196790695,
|
|
"num_tokens": 5620472.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.746627140045166,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.15095988661050797,
|
|
"num_tokens": 5634744.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.820336484909058,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.15817087292671203,
|
|
"num_tokens": 5648555.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.654189109802246,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.16331421136856078,
|
|
"num_tokens": 5661780.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.810167264938355,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.6237,
|
|
"mean_token_accuracy": 0.14594944566488266,
|
|
"num_tokens": 5674713.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.8684288501739506,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.1581734761595726,
|
|
"num_tokens": 5689152.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.821078968048096,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15297086387872696,
|
|
"num_tokens": 5704097.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.846594524383545,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.1534001722931862,
|
|
"num_tokens": 5716579.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.791203594207763,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.15501691848039628,
|
|
"num_tokens": 5731114.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.8727644920349125,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.5935,
|
|
"mean_token_accuracy": 0.14780626967549323,
|
|
"num_tokens": 5744843.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.789867162704468,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.14191780239343643,
|
|
"num_tokens": 5759277.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.836066865921021,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.1461949788033962,
|
|
"num_tokens": 5774754.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.824730443954468,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.1531083270907402,
|
|
"num_tokens": 5788524.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.784889554977417,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.15846714973449708,
|
|
"num_tokens": 5800617.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.729056930541992,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.4642,
|
|
"mean_token_accuracy": 0.16036854833364486,
|
|
"num_tokens": 5812433.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.788734769821167,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.15883542001247405,
|
|
"num_tokens": 5825507.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.766335344314575,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.15552578046917914,
|
|
"num_tokens": 5841214.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.7235047817230225,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.15404129177331924,
|
|
"num_tokens": 5854788.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.7752213954925535,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.15705669671297073,
|
|
"num_tokens": 5870241.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.706209516525268,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.15873096585273744,
|
|
"num_tokens": 5883245.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.771699523925781,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1555697053670883,
|
|
"num_tokens": 5896103.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.774951791763305,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.15437076538801192,
|
|
"num_tokens": 5909633.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.741052532196045,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.16289055198431016,
|
|
"num_tokens": 5924211.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.732291650772095,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.16250183135271073,
|
|
"num_tokens": 5937484.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.767012739181519,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.1622129425406456,
|
|
"num_tokens": 5951224.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.752144432067871,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.158035908639431,
|
|
"num_tokens": 5964762.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.766765213012695,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.1441946767270565,
|
|
"num_tokens": 5978215.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.777844858169556,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.15517966747283934,
|
|
"num_tokens": 5992951.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.805502128601074,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.14943464547395707,
|
|
"num_tokens": 6005853.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.670528078079224,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.1550400286912918,
|
|
"num_tokens": 6021502.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.797346067428589,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.1466439701616764,
|
|
"num_tokens": 6038098.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.75105504989624,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.14942799955606462,
|
|
"num_tokens": 6053957.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.843917989730835,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.15020484626293182,
|
|
"num_tokens": 6069018.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.713776731491089,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.1559767708182335,
|
|
"num_tokens": 6085202.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.730500555038452,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.15834935307502745,
|
|
"num_tokens": 6098351.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.7543556690216064,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.16555993407964706,
|
|
"num_tokens": 6111322.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.680195426940918,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.15907896757125856,
|
|
"num_tokens": 6124438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.830910491943359,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.15566118210554122,
|
|
"num_tokens": 6139409.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.772664499282837,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.1510126292705536,
|
|
"num_tokens": 6156678.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.804413557052612,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1492897093296051,
|
|
"num_tokens": 6171149.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.7141624927520756,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.1593698337674141,
|
|
"num_tokens": 6184179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.700485420227051,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.16164242178201677,
|
|
"num_tokens": 6197564.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.78814730644226,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.1535431906580925,
|
|
"num_tokens": 6211018.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.642172718048096,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.165253446996212,
|
|
"num_tokens": 6223129.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.822677659988403,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.5354,
|
|
"mean_token_accuracy": 0.15645369738340378,
|
|
"num_tokens": 6238236.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.727661037445069,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.15571245178580284,
|
|
"num_tokens": 6251285.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.695922613143921,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.1628317266702652,
|
|
"num_tokens": 6266221.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.682155513763428,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.16071774065494537,
|
|
"num_tokens": 6278991.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.702351808547974,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.16429808586835862,
|
|
"num_tokens": 6293095.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.6871805667877195,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.16122872084379197,
|
|
"num_tokens": 6306162.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.756260251998901,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.15692074596881866,
|
|
"num_tokens": 6318636.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.667980194091797,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.1623864531517029,
|
|
"num_tokens": 6332815.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.671984720230102,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.16339942216873168,
|
|
"num_tokens": 6346887.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.691684865951538,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.1576998472213745,
|
|
"num_tokens": 6360688.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.664248991012573,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.16118588149547577,
|
|
"num_tokens": 6376560.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.816897964477539,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.15335736498236657,
|
|
"num_tokens": 6390434.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.632402467727661,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.3763,
|
|
"mean_token_accuracy": 0.16879032105207442,
|
|
"num_tokens": 6403585.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.759318161010742,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.15672422498464583,
|
|
"num_tokens": 6414663.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.7544502258300785,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.159070248901844,
|
|
"num_tokens": 6428655.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.731297779083252,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.1552168533205986,
|
|
"num_tokens": 6443494.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.734210968017578,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.15551268607378005,
|
|
"num_tokens": 6456078.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.755726957321167,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.15114115923643112,
|
|
"num_tokens": 6469805.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.635595083236694,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.1549799308180809,
|
|
"num_tokens": 6484209.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.6775514602661135,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.16016292721033096,
|
|
"num_tokens": 6498471.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.741027402877807,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.15452294647693635,
|
|
"num_tokens": 6513558.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.737386846542359,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.15471736043691636,
|
|
"num_tokens": 6527538.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.6719869613647464,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.1682674691081047,
|
|
"num_tokens": 6542188.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.707267141342163,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.15894713550806044,
|
|
"num_tokens": 6557774.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.768304443359375,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.15813593566417694,
|
|
"num_tokens": 6571868.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.61864128112793,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.5054,
|
|
"mean_token_accuracy": 0.15922000110149384,
|
|
"num_tokens": 6585534.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.707316255569458,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.16243680715560913,
|
|
"num_tokens": 6599855.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.691481971740723,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.15631041526794434,
|
|
"num_tokens": 6615496.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.758702373504638,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.15837289094924928,
|
|
"num_tokens": 6629993.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.624302387237549,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.16616827994585037,
|
|
"num_tokens": 6644076.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.614185571670532,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1681667983531952,
|
|
"num_tokens": 6656924.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.625910329818725,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.15688778311014176,
|
|
"num_tokens": 6670350.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.731524658203125,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.16615445613861085,
|
|
"num_tokens": 6683174.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.764780712127686,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.15738168507814407,
|
|
"num_tokens": 6699648.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.643772602081299,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.1589035451412201,
|
|
"num_tokens": 6712174.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.632435894012451,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.16203927099704743,
|
|
"num_tokens": 6725376.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.524544143676758,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.17558714896440505,
|
|
"num_tokens": 6738177.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.681800365447998,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.16042183339595795,
|
|
"num_tokens": 6751521.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.704955530166626,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.15936244279146194,
|
|
"num_tokens": 6765901.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.600447654724121,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.17559294402599335,
|
|
"num_tokens": 6778473.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.718362140655517,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.5413,
|
|
"mean_token_accuracy": 0.15127855092287062,
|
|
"num_tokens": 6792067.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.664472007751465,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.16567944288253783,
|
|
"num_tokens": 6807534.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.632346487045288,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.15765434131026268,
|
|
"num_tokens": 6821600.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.686599826812744,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16716605424880981,
|
|
"num_tokens": 6835044.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.648890161514283,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.1567879304289818,
|
|
"num_tokens": 6847745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.643044281005859,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.16371610164642333,
|
|
"num_tokens": 6861403.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.605740261077881,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.16381412744522095,
|
|
"num_tokens": 6874418.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.801210021972656,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15529614984989165,
|
|
"num_tokens": 6890166.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.690111064910889,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.15613416135311126,
|
|
"num_tokens": 6904569.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.6721052646636965,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.16279612928628923,
|
|
"num_tokens": 6918562.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.740928030014038,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.15916131287813187,
|
|
"num_tokens": 6934751.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.646144247055053,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.16374265253543854,
|
|
"num_tokens": 6947669.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.775876522064209,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.1609296530485153,
|
|
"num_tokens": 6959993.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.636061096191407,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1665743112564087,
|
|
"num_tokens": 6974637.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.56963996887207,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.167204912006855,
|
|
"num_tokens": 6989182.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.60927939414978,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.1643602266907692,
|
|
"num_tokens": 7003681.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.634929227828979,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.16805891692638397,
|
|
"num_tokens": 7017919.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.7103218078613285,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.15703504979610444,
|
|
"num_tokens": 7033405.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.591740942001342,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.16865961104631425,
|
|
"num_tokens": 7046938.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.639147329330444,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.15662651062011718,
|
|
"num_tokens": 7059708.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.636305665969848,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16775305718183517,
|
|
"num_tokens": 7074554.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.607331466674805,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.1624634951353073,
|
|
"num_tokens": 7089654.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.636829471588134,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.1580259993672371,
|
|
"num_tokens": 7103137.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.598562431335449,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.17140354141592978,
|
|
"num_tokens": 7114857.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.650972557067871,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16446297764778137,
|
|
"num_tokens": 7128243.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.6322792053222654,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.15940468907356262,
|
|
"num_tokens": 7142505.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.5690161228179935,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.16011220663785936,
|
|
"num_tokens": 7157877.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.614592552185059,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.15924295634031296,
|
|
"num_tokens": 7170819.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.662329292297363,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.4602,
|
|
"mean_token_accuracy": 0.16824824064970018,
|
|
"num_tokens": 7183013.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.577002477645874,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.15459822118282318,
|
|
"num_tokens": 7196530.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.81734299659729,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.1522914230823517,
|
|
"num_tokens": 7210657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.577762269973755,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.16126917749643327,
|
|
"num_tokens": 7224450.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.6173646450042725,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.1648561418056488,
|
|
"num_tokens": 7238767.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.692874526977539,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.1685239166021347,
|
|
"num_tokens": 7253326.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.512430953979492,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.16743609309196472,
|
|
"num_tokens": 7268256.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.612433052062988,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.16665096580982208,
|
|
"num_tokens": 7281561.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.645188856124878,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.1619505003094673,
|
|
"num_tokens": 7294302.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.5982451915740965,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.16281116455793382,
|
|
"num_tokens": 7309257.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.6211920261383055,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.1656322419643402,
|
|
"num_tokens": 7322797.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.624097919464111,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.17238076776266098,
|
|
"num_tokens": 7336913.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.646049451828003,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.16334831714630127,
|
|
"num_tokens": 7350267.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.671913194656372,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.16798181235790252,
|
|
"num_tokens": 7365592.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.570678615570069,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16728129982948303,
|
|
"num_tokens": 7380045.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.649079751968384,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.16623117178678512,
|
|
"num_tokens": 7392487.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.6728575229644775,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.158479180932045,
|
|
"num_tokens": 7405578.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.6485189437866214,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.16377977579832076,
|
|
"num_tokens": 7418940.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.57572226524353,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.16576361954212188,
|
|
"num_tokens": 7432688.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.7026293754577635,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.1577007867395878,
|
|
"num_tokens": 7446238.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.701103448867798,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.15402617454528808,
|
|
"num_tokens": 7460781.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.595748519897461,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.15443253070116042,
|
|
"num_tokens": 7475041.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.6993509292602536,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.15144548565149307,
|
|
"num_tokens": 7491027.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.692638921737671,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.16102027893066406,
|
|
"num_tokens": 7503070.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.569590759277344,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.1691955015063286,
|
|
"num_tokens": 7515553.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.538298177719116,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.16621797084808348,
|
|
"num_tokens": 7529603.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.663971900939941,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.15859650075435638,
|
|
"num_tokens": 7543320.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.619390296936035,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.16396857649087906,
|
|
"num_tokens": 7556413.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.6256359100341795,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.4322,
|
|
"mean_token_accuracy": 0.16423783004283904,
|
|
"num_tokens": 7570427.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.631426906585693,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.15992715656757356,
|
|
"num_tokens": 7585143.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.692942667007446,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1656443104147911,
|
|
"num_tokens": 7597429.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.517695045471191,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.17762928754091262,
|
|
"num_tokens": 7610203.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.570860481262207,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.15536038130521773,
|
|
"num_tokens": 7625343.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.617734956741333,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.3592,
|
|
"mean_token_accuracy": 0.16593704372644424,
|
|
"num_tokens": 7637850.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.564725017547607,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.1703445553779602,
|
|
"num_tokens": 7651877.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.695179843902588,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.466,
|
|
"mean_token_accuracy": 0.15940675437450408,
|
|
"num_tokens": 7666457.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.567157411575318,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.1676443710923195,
|
|
"num_tokens": 7678979.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.558333110809326,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.16749558895826339,
|
|
"num_tokens": 7692357.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.686964607238769,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.15954697579145433,
|
|
"num_tokens": 7707537.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.519318008422852,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.16792828291654588,
|
|
"num_tokens": 7719737.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.609381437301636,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.16744615286588668,
|
|
"num_tokens": 7734612.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.634121942520141,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.1555524453520775,
|
|
"num_tokens": 7749109.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.515996646881104,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.16647806912660598,
|
|
"num_tokens": 7761972.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.628909635543823,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1572790265083313,
|
|
"num_tokens": 7777769.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.622025060653686,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.16501683443784715,
|
|
"num_tokens": 7792576.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.502942609786987,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.16594948321580888,
|
|
"num_tokens": 7805997.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.557144498825073,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.16462566703557968,
|
|
"num_tokens": 7819548.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.550113344192505,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.16538318544626235,
|
|
"num_tokens": 7832786.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.638032674789429,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.1630851998925209,
|
|
"num_tokens": 7847524.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.516295433044434,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.17548558712005616,
|
|
"num_tokens": 7861783.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.532091665267944,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.1643317773938179,
|
|
"num_tokens": 7875671.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.648615932464599,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.1673572242259979,
|
|
"num_tokens": 7890624.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.561357641220093,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.16167960613965987,
|
|
"num_tokens": 7904296.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.505871915817261,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.16874135732650758,
|
|
"num_tokens": 7918588.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.522439622879029,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.17053997218608857,
|
|
"num_tokens": 7933087.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.587213230133057,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.16668923944234848,
|
|
"num_tokens": 7945477.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.63070592880249,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.1570942744612694,
|
|
"num_tokens": 7961488.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.6248846530914305,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.1757759466767311,
|
|
"num_tokens": 7974533.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.526473426818848,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.16862046271562575,
|
|
"num_tokens": 7988481.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.619885015487671,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.16942613273859025,
|
|
"num_tokens": 8003589.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.52764778137207,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.1693471595644951,
|
|
"num_tokens": 8017560.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.552784109115601,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.1612047329545021,
|
|
"num_tokens": 8032339.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.595651721954345,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.1592611014842987,
|
|
"num_tokens": 8047634.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.5863272190094,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3918,
|
|
"mean_token_accuracy": 0.1652919813990593,
|
|
"num_tokens": 8061267.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.543440198898315,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.166269950568676,
|
|
"num_tokens": 8076225.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.573662137985229,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.16605644524097443,
|
|
"num_tokens": 8089997.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.591129922866822,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.16995038986206054,
|
|
"num_tokens": 8102739.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.587178468704224,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.1624770373106003,
|
|
"num_tokens": 8115435.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.598823881149292,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1697479158639908,
|
|
"num_tokens": 8129833.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.569084024429321,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.3729,
|
|
"mean_token_accuracy": 0.1669548973441124,
|
|
"num_tokens": 8144316.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.578461694717407,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.16917092055082322,
|
|
"num_tokens": 8158927.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.617590284347534,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.16542406380176544,
|
|
"num_tokens": 8172297.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.613320064544678,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.1679888367652893,
|
|
"num_tokens": 8184985.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.588392210006714,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.1678030714392662,
|
|
"num_tokens": 8198936.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.5983302116394045,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.1687172457575798,
|
|
"num_tokens": 8213538.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.59259786605835,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.161647991836071,
|
|
"num_tokens": 8226794.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.527505016326904,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.16996421962976455,
|
|
"num_tokens": 8241671.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.5442180156707765,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.16769520044326783,
|
|
"num_tokens": 8255079.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.5615553855896,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.16994720846414565,
|
|
"num_tokens": 8267958.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.550642204284668,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.1602596029639244,
|
|
"num_tokens": 8281082.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.548654079437256,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.16562802940607071,
|
|
"num_tokens": 8292675.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.510513496398926,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.17679769545793533,
|
|
"num_tokens": 8304481.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.553654766082763,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.16842448115348815,
|
|
"num_tokens": 8318529.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.5886695861816404,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.16488241851329805,
|
|
"num_tokens": 8333181.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.497231817245483,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.17946436256170273,
|
|
"num_tokens": 8346036.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.511769723892212,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.16782039552927017,
|
|
"num_tokens": 8361037.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.55103235244751,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17024607360363006,
|
|
"num_tokens": 8374802.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.33094315484026,
|
|
"eval_loss": 5.315858364105225,
|
|
"eval_mean_token_accuracy": 0.17842997617459036,
|
|
"eval_num_tokens": 8374802.0,
|
|
"eval_runtime": 18.8093,
|
|
"eval_samples_per_second": 1356.401,
|
|
"eval_steps_per_second": 169.597,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"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": 2222324889845760.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|