12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.714711137581894,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.53194375038147,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.17845398634672166,
|
|
"num_tokens": 8389127.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.645079278945923,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.1543111339211464,
|
|
"num_tokens": 8403358.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.578828430175781,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.3537,
|
|
"mean_token_accuracy": 0.1660466119647026,
|
|
"num_tokens": 8418693.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.534197664260864,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.17261601388454437,
|
|
"num_tokens": 8429968.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.526310586929322,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.16782355755567552,
|
|
"num_tokens": 8443700.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.569401836395263,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.381,
|
|
"mean_token_accuracy": 0.16564542949199676,
|
|
"num_tokens": 8457919.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.60796422958374,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.16518213897943496,
|
|
"num_tokens": 8472787.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.532761478424073,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17310683876276017,
|
|
"num_tokens": 8484235.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.460708284378052,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.17374361157417298,
|
|
"num_tokens": 8496971.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.544519662857056,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.16985341310501098,
|
|
"num_tokens": 8510531.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.555769729614258,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.4447,
|
|
"mean_token_accuracy": 0.16951690912246703,
|
|
"num_tokens": 8522492.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.602981996536255,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.3362,
|
|
"mean_token_accuracy": 0.16971496790647506,
|
|
"num_tokens": 8537119.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.464743804931641,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.17136756777763368,
|
|
"num_tokens": 8549899.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.5660888195037845,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.1557522490620613,
|
|
"num_tokens": 8563604.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.648580932617188,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.1666161060333252,
|
|
"num_tokens": 8577948.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.5360502243042,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.1703394889831543,
|
|
"num_tokens": 8591750.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.570601511001587,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17260025888681413,
|
|
"num_tokens": 8604091.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.427626848220825,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17656562775373458,
|
|
"num_tokens": 8617314.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.468297958374023,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.17591919004917145,
|
|
"num_tokens": 8630050.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.4180926322937015,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.17195673286914825,
|
|
"num_tokens": 8643462.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.47792763710022,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.17004989087581635,
|
|
"num_tokens": 8657207.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.579573440551758,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.17448567301034928,
|
|
"num_tokens": 8671129.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.5449652671813965,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.1721959412097931,
|
|
"num_tokens": 8684308.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.509975385665894,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17383912801742554,
|
|
"num_tokens": 8697651.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.543778657913208,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.16248745173215867,
|
|
"num_tokens": 8714559.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.575860786437988,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.1686939001083374,
|
|
"num_tokens": 8729999.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.5252625942230225,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.17304440289735795,
|
|
"num_tokens": 8742503.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.50363187789917,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.16426770389080048,
|
|
"num_tokens": 8755034.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.49028844833374,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.1699514016509056,
|
|
"num_tokens": 8770410.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.5367120742797855,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.17531256079673768,
|
|
"num_tokens": 8784020.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.495750761032104,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17027590200304984,
|
|
"num_tokens": 8797763.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.494180345535279,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.179366996884346,
|
|
"num_tokens": 8810306.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.444682168960571,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.175647334754467,
|
|
"num_tokens": 8822345.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.488202714920044,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.1701683670282364,
|
|
"num_tokens": 8836024.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.539686298370361,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.16921445727348328,
|
|
"num_tokens": 8849994.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.494520139694214,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.17560119926929474,
|
|
"num_tokens": 8863867.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.459944105148315,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17062760442495345,
|
|
"num_tokens": 8878077.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.497016668319702,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.16758826673030852,
|
|
"num_tokens": 8892729.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.513605403900146,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.1787588343024254,
|
|
"num_tokens": 8906242.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.500463771820068,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.16812289208173753,
|
|
"num_tokens": 8919814.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.489879703521728,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.1734540954232216,
|
|
"num_tokens": 8934345.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.469197797775268,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.17496797889471055,
|
|
"num_tokens": 8947825.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.5221010684967045,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.16763191670179367,
|
|
"num_tokens": 8962270.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.516406583786011,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.17425250262022018,
|
|
"num_tokens": 8974453.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.545296716690063,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.1678760230541229,
|
|
"num_tokens": 8991689.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.508287954330444,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.17742977142333985,
|
|
"num_tokens": 9005783.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.489894723892212,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.16761346012353898,
|
|
"num_tokens": 9019733.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.433395004272461,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.16695324182510377,
|
|
"num_tokens": 9035131.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.57075867652893,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.17603086531162263,
|
|
"num_tokens": 9047954.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.458488321304321,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.17589410841464997,
|
|
"num_tokens": 9059945.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.48297004699707,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.17242926508188247,
|
|
"num_tokens": 9074128.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.503276681900024,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.16760232895612717,
|
|
"num_tokens": 9086760.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.555027437210083,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.16785975694656372,
|
|
"num_tokens": 9100632.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.485769939422608,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.16383741348981856,
|
|
"num_tokens": 9115092.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.450682783126831,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.181158210337162,
|
|
"num_tokens": 9127473.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.514653205871582,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.1720754772424698,
|
|
"num_tokens": 9141028.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.4921064376831055,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.17332016676664352,
|
|
"num_tokens": 9154526.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.555002164840698,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.1678193524479866,
|
|
"num_tokens": 9167220.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.562772369384765,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.1711056910455227,
|
|
"num_tokens": 9181648.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.4501426219940186,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.1786603108048439,
|
|
"num_tokens": 9194714.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.426304912567138,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.17161348313093186,
|
|
"num_tokens": 9211467.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.664749717712402,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.16128215342760086,
|
|
"num_tokens": 9226409.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.487881278991699,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.17049567103385926,
|
|
"num_tokens": 9240476.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.454006195068359,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.17328597903251647,
|
|
"num_tokens": 9254020.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.438784456253051,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.17969273924827575,
|
|
"num_tokens": 9269150.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.572743654251099,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.16024698466062545,
|
|
"num_tokens": 9285184.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.513273859024048,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.1805974245071411,
|
|
"num_tokens": 9298622.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.5300816059112545,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16618907749652861,
|
|
"num_tokens": 9314653.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.4713304996490475,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.1765909180045128,
|
|
"num_tokens": 9328428.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.549885082244873,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.1682168647646904,
|
|
"num_tokens": 9341250.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.48319182395935,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.1751708373427391,
|
|
"num_tokens": 9355706.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.614543342590332,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.1599671334028244,
|
|
"num_tokens": 9368562.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.552252292633057,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.16700713187456132,
|
|
"num_tokens": 9383484.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.362362194061279,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.17983500510454178,
|
|
"num_tokens": 9397364.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.38932056427002,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.17546263486146926,
|
|
"num_tokens": 9411738.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.443359327316284,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.17884623557329177,
|
|
"num_tokens": 9426660.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.484179973602295,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.1664903923869133,
|
|
"num_tokens": 9440878.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.4818016529083256,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.16915637701749803,
|
|
"num_tokens": 9455174.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.443004894256592,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1759191244840622,
|
|
"num_tokens": 9467936.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.435940599441528,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.17029665559530258,
|
|
"num_tokens": 9482529.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.501376104354859,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.17074424624443055,
|
|
"num_tokens": 9497141.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.539723205566406,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.1649772733449936,
|
|
"num_tokens": 9509878.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.456761884689331,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.17851642966270448,
|
|
"num_tokens": 9522720.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.46306676864624,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.17651566714048386,
|
|
"num_tokens": 9536418.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.485482597351075,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.18023780584335328,
|
|
"num_tokens": 9552336.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.477826881408691,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17453182190656663,
|
|
"num_tokens": 9565676.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.376121377944946,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.1855195179581642,
|
|
"num_tokens": 9579361.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.407404041290283,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.17755534797906875,
|
|
"num_tokens": 9591779.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.490596723556519,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.17143639475107192,
|
|
"num_tokens": 9608353.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.445445871353149,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.17303474694490434,
|
|
"num_tokens": 9623236.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.431187629699707,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.17017227411270142,
|
|
"num_tokens": 9635746.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.423646306991577,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.17713408172130585,
|
|
"num_tokens": 9650458.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.4576317310333256,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18094676434993745,
|
|
"num_tokens": 9665486.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.521482372283936,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.16958900392055512,
|
|
"num_tokens": 9679977.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.488754367828369,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.16972343921661376,
|
|
"num_tokens": 9695092.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.354253053665161,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.18037663996219636,
|
|
"num_tokens": 9707836.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.510741806030273,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.16598230898380278,
|
|
"num_tokens": 9721936.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.432139110565186,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.17956025302410125,
|
|
"num_tokens": 9734876.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.455330467224121,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.16417320519685746,
|
|
"num_tokens": 9748870.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.569710540771484,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.1703778013586998,
|
|
"num_tokens": 9763605.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.530073738098144,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.17459381520748138,
|
|
"num_tokens": 9779312.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.442477798461914,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.16355077177286148,
|
|
"num_tokens": 9791770.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.451168346405029,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.17671115100383758,
|
|
"num_tokens": 9807341.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.448538446426392,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.17702449560165406,
|
|
"num_tokens": 9821829.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.366397714614868,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.18542798310518266,
|
|
"num_tokens": 9836554.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.446051073074341,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.18016983121633529,
|
|
"num_tokens": 9849904.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.431139087677002,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.17674075067043304,
|
|
"num_tokens": 9863935.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.431934213638305,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.17591250240802764,
|
|
"num_tokens": 9878230.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.410821104049683,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.18137411326169967,
|
|
"num_tokens": 9891411.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.358261919021606,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.17786334007978438,
|
|
"num_tokens": 9904891.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.3938836574554445,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.17019854635000228,
|
|
"num_tokens": 9918920.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.451056623458863,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.17660196423530578,
|
|
"num_tokens": 9932975.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.444226360321045,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.17603071331977843,
|
|
"num_tokens": 9946704.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.416390752792358,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.173039610683918,
|
|
"num_tokens": 9961729.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.4772782802581785,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.17304217368364333,
|
|
"num_tokens": 9976980.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.51420111656189,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.17432699352502823,
|
|
"num_tokens": 9991963.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.472890758514405,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.1745639756321907,
|
|
"num_tokens": 10005323.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.40621337890625,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.17891811579465866,
|
|
"num_tokens": 10018352.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.438979244232177,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.17730545848608018,
|
|
"num_tokens": 10032371.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.524429130554199,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.17437071353197098,
|
|
"num_tokens": 10044221.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.5083776950836185,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.17418865263462066,
|
|
"num_tokens": 10057475.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.439066696166992,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.17699487656354904,
|
|
"num_tokens": 10072272.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.466569089889527,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.16676444858312606,
|
|
"num_tokens": 10086757.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.522718000411987,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.1667618930339813,
|
|
"num_tokens": 10100471.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.505567789077759,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17292843610048295,
|
|
"num_tokens": 10112764.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.445482921600342,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.1857913389801979,
|
|
"num_tokens": 10125830.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.316396999359131,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.18059258460998534,
|
|
"num_tokens": 10140007.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.438551616668701,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.18052507936954498,
|
|
"num_tokens": 10154508.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.468423318862915,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.17988714724779128,
|
|
"num_tokens": 10167832.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.416162157058716,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.1766108751296997,
|
|
"num_tokens": 10182421.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.394202375411988,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.1765,
|
|
"mean_token_accuracy": 0.17946621775627136,
|
|
"num_tokens": 10196210.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.432455539703369,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.17361632287502288,
|
|
"num_tokens": 10210930.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.4363268375396725,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.179244963824749,
|
|
"num_tokens": 10225758.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.476582765579224,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.17901217341423034,
|
|
"num_tokens": 10239924.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.456946849822998,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.17777508199214936,
|
|
"num_tokens": 10254713.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.456771469116211,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.1681886374950409,
|
|
"num_tokens": 10270335.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.4499236106872555,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.1767041116952896,
|
|
"num_tokens": 10286368.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.4764598369598385,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.17117395251989365,
|
|
"num_tokens": 10302073.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.372010898590088,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.1833252027630806,
|
|
"num_tokens": 10317741.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.432416534423828,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.174821637570858,
|
|
"num_tokens": 10331439.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.539056968688965,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.16558377742767333,
|
|
"num_tokens": 10345107.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.499377059936523,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.17398845851421357,
|
|
"num_tokens": 10360078.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.386675119400024,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.17178381532430648,
|
|
"num_tokens": 10373221.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.515303659439087,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.16752853691577912,
|
|
"num_tokens": 10386200.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.400387859344482,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.1776488721370697,
|
|
"num_tokens": 10398680.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.4428901195526125,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1718101069331169,
|
|
"num_tokens": 10414483.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.497593736648559,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.1737542986869812,
|
|
"num_tokens": 10428962.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.584635305404663,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.17216833904385567,
|
|
"num_tokens": 10442273.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.537905216217041,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.17508672028779984,
|
|
"num_tokens": 10456610.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.387487459182739,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.17823742032051088,
|
|
"num_tokens": 10470144.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.4657457828521725,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18805933594703675,
|
|
"num_tokens": 10483866.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.422224617004394,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.17784465104341507,
|
|
"num_tokens": 10497350.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.378564071655274,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1758370280265808,
|
|
"num_tokens": 10510808.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.412915515899658,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.18201710134744645,
|
|
"num_tokens": 10525965.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.467325448989868,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.17504528164863586,
|
|
"num_tokens": 10539900.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.454932785034179,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1722474977374077,
|
|
"num_tokens": 10553653.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.374240446090698,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.18090267479419708,
|
|
"num_tokens": 10568202.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.339132022857666,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.1799025222659111,
|
|
"num_tokens": 10581290.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.394349145889282,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.1787856101989746,
|
|
"num_tokens": 10596697.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.4527936458587645,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.17962846159934998,
|
|
"num_tokens": 10610052.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.407793474197388,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.1826455920934677,
|
|
"num_tokens": 10624268.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.324577283859253,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.18459611386060715,
|
|
"num_tokens": 10636463.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.426402425765991,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.18134627342224122,
|
|
"num_tokens": 10649566.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.405946397781372,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18083360195159912,
|
|
"num_tokens": 10661373.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.371559953689575,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.18358622789382933,
|
|
"num_tokens": 10677008.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.480168676376342,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.17987342029809952,
|
|
"num_tokens": 10690497.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.388162517547608,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.1827029123902321,
|
|
"num_tokens": 10705315.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.373668193817139,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.18545912057161332,
|
|
"num_tokens": 10718536.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.400412559509277,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.17034007608890533,
|
|
"num_tokens": 10735402.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.486510419845581,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.17834403812885286,
|
|
"num_tokens": 10748809.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.331592845916748,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.1848363310098648,
|
|
"num_tokens": 10761935.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.398069715499878,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1697085589170456,
|
|
"num_tokens": 10778252.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.540862083435059,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.17047490328550338,
|
|
"num_tokens": 10792606.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.447160911560059,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.17300592213869095,
|
|
"num_tokens": 10805433.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.388632154464721,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1762865036725998,
|
|
"num_tokens": 10818648.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.432145118713379,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.17859960943460465,
|
|
"num_tokens": 10833089.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.358439779281616,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.17855484187602996,
|
|
"num_tokens": 10847850.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.457101726531983,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.17978406846523284,
|
|
"num_tokens": 10861354.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.506772565841675,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.16890907734632493,
|
|
"num_tokens": 10877986.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.310773229598999,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.18601099401712418,
|
|
"num_tokens": 10891253.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.398805141448975,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.17864535003900528,
|
|
"num_tokens": 10905916.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.414415884017944,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.18294261991977692,
|
|
"num_tokens": 10920038.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.3523149490356445,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.18407817482948302,
|
|
"num_tokens": 10933161.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.384498882293701,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.17449699640274047,
|
|
"num_tokens": 10946573.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.414169502258301,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.17691306173801422,
|
|
"num_tokens": 10960727.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.478633069992066,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.17322907149791716,
|
|
"num_tokens": 10973298.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.416499090194702,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.17739322781562805,
|
|
"num_tokens": 10988214.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.470095634460449,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.17839152961969376,
|
|
"num_tokens": 11003526.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.49106731414795,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.16881988793611527,
|
|
"num_tokens": 11019600.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.332584953308105,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.18336566388607026,
|
|
"num_tokens": 11032591.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.344310665130616,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.18219054490327835,
|
|
"num_tokens": 11045724.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.479485273361206,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.17386580258607864,
|
|
"num_tokens": 11059149.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.420220232009887,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.17556451112031937,
|
|
"num_tokens": 11073489.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.43749771118164,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.17946831583976747,
|
|
"num_tokens": 11086535.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.324299335479736,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18641428798437118,
|
|
"num_tokens": 11100142.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.294971179962158,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.18939329385757447,
|
|
"num_tokens": 11113364.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.502555322647095,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.17518739253282548,
|
|
"num_tokens": 11127127.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.461540746688843,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.17829690128564835,
|
|
"num_tokens": 11139788.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.389543247222901,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.1797940105199814,
|
|
"num_tokens": 11156470.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.365475416183472,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.18815007209777831,
|
|
"num_tokens": 11168923.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.386591386795044,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.1842184230685234,
|
|
"num_tokens": 11181328.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.487314748764038,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.17080096155405045,
|
|
"num_tokens": 11197800.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.52086763381958,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.17595488131046294,
|
|
"num_tokens": 11209862.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.353274869918823,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.17607441693544387,
|
|
"num_tokens": 11223433.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.4463588237762455,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.17377653568983079,
|
|
"num_tokens": 11236975.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.379982042312622,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.17730392664670944,
|
|
"num_tokens": 11250277.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.441099500656128,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.17686755508184432,
|
|
"num_tokens": 11264990.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.46997332572937,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.17195749580860137,
|
|
"num_tokens": 11277496.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.407310247421265,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.17768220603466034,
|
|
"num_tokens": 11290263.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.399970149993896,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.18622722029685973,
|
|
"num_tokens": 11305611.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.459443044662476,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.17523133903741836,
|
|
"num_tokens": 11321216.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.423429250717163,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.18697123378515243,
|
|
"num_tokens": 11335029.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.340970468521118,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1715432271361351,
|
|
"num_tokens": 11349301.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.455768823623657,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.17929711788892747,
|
|
"num_tokens": 11364561.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.359412908554077,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.1832022950053215,
|
|
"num_tokens": 11379470.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.407134914398194,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.1830180376768112,
|
|
"num_tokens": 11393433.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.333357048034668,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.18091286718845367,
|
|
"num_tokens": 11406673.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.341376066207886,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.18248946219682693,
|
|
"num_tokens": 11420395.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.427642154693603,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1790100708603859,
|
|
"num_tokens": 11432866.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.349800157546997,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.17877718955278396,
|
|
"num_tokens": 11447062.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.344159936904907,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.1861804947257042,
|
|
"num_tokens": 11461255.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.463950109481812,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.17237258106470107,
|
|
"num_tokens": 11475711.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.41520471572876,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.17271950989961624,
|
|
"num_tokens": 11491199.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.448308992385864,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.18378346115350724,
|
|
"num_tokens": 11504365.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.420531940460205,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.17314012795686723,
|
|
"num_tokens": 11517969.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.394005966186524,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.17764792740345,
|
|
"num_tokens": 11533203.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.403848791122437,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.1772610768675804,
|
|
"num_tokens": 11547820.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.391172599792481,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.18545330613851546,
|
|
"num_tokens": 11561591.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.346930599212646,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.18011981397867202,
|
|
"num_tokens": 11576722.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.481418132781982,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.1792983591556549,
|
|
"num_tokens": 11590455.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.446556568145752,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.1737887904047966,
|
|
"num_tokens": 11605495.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.380440711975098,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.17735483199357988,
|
|
"num_tokens": 11619692.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.365343761444092,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.18099919259548186,
|
|
"num_tokens": 11633806.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.377055406570435,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.18955023884773253,
|
|
"num_tokens": 11649871.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.34689154624939,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.18082754909992219,
|
|
"num_tokens": 11661472.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.3021033763885494,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.18494856208562852,
|
|
"num_tokens": 11674689.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.301540803909302,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.19291228652000428,
|
|
"num_tokens": 11687867.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.318424558639526,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.18405648320913315,
|
|
"num_tokens": 11704611.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.418560123443603,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.17981443852186202,
|
|
"num_tokens": 11719448.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.359702920913696,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.18143897801637648,
|
|
"num_tokens": 11731160.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.373467493057251,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.1843373268842697,
|
|
"num_tokens": 11744319.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.384470272064209,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.18225540816783906,
|
|
"num_tokens": 11757861.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.320976638793946,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.18314458876848222,
|
|
"num_tokens": 11770707.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.383945560455322,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.18670070469379424,
|
|
"num_tokens": 11785155.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.373613739013672,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.17876102179288864,
|
|
"num_tokens": 11798532.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.24838604927063,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.184522907435894,
|
|
"num_tokens": 11812708.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.42040786743164,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.17628637254238128,
|
|
"num_tokens": 11828844.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.338803482055664,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.18194308876991272,
|
|
"num_tokens": 11845070.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.299670934677124,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.1859847143292427,
|
|
"num_tokens": 11858299.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.412613868713379,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.18599607646465302,
|
|
"num_tokens": 11873805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.316448831558228,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.171941277384758,
|
|
"num_tokens": 11888304.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.3904636859893795,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.18893087059259414,
|
|
"num_tokens": 11901914.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.376463317871094,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.184621000289917,
|
|
"num_tokens": 11913225.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.363157176971436,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.18310361355543137,
|
|
"num_tokens": 11927200.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.332843542098999,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.18536149263381957,
|
|
"num_tokens": 11939826.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.315101099014282,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.18348885625600814,
|
|
"num_tokens": 11951983.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.416784811019897,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.177970851957798,
|
|
"num_tokens": 11965642.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.407585000991821,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.17398284673690795,
|
|
"num_tokens": 11981472.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.348097896575927,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.1831167832016945,
|
|
"num_tokens": 11995739.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.439723157882691,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.17539945840835572,
|
|
"num_tokens": 12007850.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.429744052886963,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1897364154458046,
|
|
"num_tokens": 12022893.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.3463188171386715,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.19170445799827576,
|
|
"num_tokens": 12035520.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.3189493179321286,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.17921495586633682,
|
|
"num_tokens": 12047938.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.3553399562835695,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.1810295581817627,
|
|
"num_tokens": 12061236.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.327606868743897,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.1883678764104843,
|
|
"num_tokens": 12074427.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.333645963668824,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.18838856220245362,
|
|
"num_tokens": 12088128.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.436138057708741,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.1713164508342743,
|
|
"num_tokens": 12100938.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.374925661087036,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.18169915080070495,
|
|
"num_tokens": 12113464.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.333883953094483,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.17713046222925186,
|
|
"num_tokens": 12129113.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.402696943283081,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.17428978979587556,
|
|
"num_tokens": 12142024.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.40776424407959,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.17911534011363983,
|
|
"num_tokens": 12157889.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.397247409820556,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.18019398897886277,
|
|
"num_tokens": 12171527.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.352613306045532,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.1757894992828369,
|
|
"num_tokens": 12186453.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.294702100753784,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.1854909524321556,
|
|
"num_tokens": 12201401.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.316075944900513,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.17699071615934373,
|
|
"num_tokens": 12215219.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.40913577079773,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.17095923721790313,
|
|
"num_tokens": 12229932.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.341264867782593,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.1836489751935005,
|
|
"num_tokens": 12241718.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.404876804351806,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.18075872212648392,
|
|
"num_tokens": 12256395.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.323521566390991,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.1884683221578598,
|
|
"num_tokens": 12269966.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.359594917297363,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.17640553265810013,
|
|
"num_tokens": 12284410.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.29043231010437,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.19154949784278869,
|
|
"num_tokens": 12298931.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.306810569763184,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.184539595246315,
|
|
"num_tokens": 12313857.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.335316228866577,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.18559955060482025,
|
|
"num_tokens": 12327732.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.354093456268311,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.1781379371881485,
|
|
"num_tokens": 12341754.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.340103435516357,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.1820943310856819,
|
|
"num_tokens": 12355656.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.299054861068726,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.19043822437524796,
|
|
"num_tokens": 12368346.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.320931720733642,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.18237759321928024,
|
|
"num_tokens": 12381844.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.412809801101685,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.1745242342352867,
|
|
"num_tokens": 12395432.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.348816967010498,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.1783488169312477,
|
|
"num_tokens": 12408897.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.319600820541382,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.18761228770017624,
|
|
"num_tokens": 12421480.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.38168249130249,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.1767524540424347,
|
|
"num_tokens": 12436931.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.357715749740601,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.1780093342065811,
|
|
"num_tokens": 12451687.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.346804809570313,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.18669354319572448,
|
|
"num_tokens": 12464338.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.342980432510376,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.17993794977664948,
|
|
"num_tokens": 12482520.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.473724365234375,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.1799166440963745,
|
|
"num_tokens": 12495791.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.355010461807251,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.17974822223186493,
|
|
"num_tokens": 12509963.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.381701517105102,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.18136336356401445,
|
|
"num_tokens": 12522825.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.381725168228149,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.1828573077917099,
|
|
"num_tokens": 12536097.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.2805726528167725,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.1897248238325119,
|
|
"num_tokens": 12551441.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.322610759735108,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.18795953691005707,
|
|
"num_tokens": 12566271.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.420116519927978,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.1835271894931793,
|
|
"num_tokens": 12580585.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.267950582504272,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.1915774330496788,
|
|
"num_tokens": 12592389.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.192738819122314,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.19835987836122512,
|
|
"num_tokens": 12606487.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.2980540752410885,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.19084453135728835,
|
|
"num_tokens": 12621036.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.354099130630493,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.1919423371553421,
|
|
"num_tokens": 12634911.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.275477552413941,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.19001434594392777,
|
|
"num_tokens": 12649165.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.313499069213867,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.18552252352237703,
|
|
"num_tokens": 12663803.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.3516298770904545,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.1860592007637024,
|
|
"num_tokens": 12676336.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.264741277694702,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.18942687511444092,
|
|
"num_tokens": 12689619.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.281706666946411,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.18445766866207122,
|
|
"num_tokens": 12703964.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.4037003993988035,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.18617296367883682,
|
|
"num_tokens": 12716832.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.303174543380737,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.1901222810149193,
|
|
"num_tokens": 12729665.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.287974309921265,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.1851668655872345,
|
|
"num_tokens": 12743576.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.258513402938843,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.18396760225296022,
|
|
"num_tokens": 12758511.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.299459743499756,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.18704642951488495,
|
|
"num_tokens": 12771694.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.312016153335572,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.1825407028198242,
|
|
"num_tokens": 12786367.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.245462083816529,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.19003615230321885,
|
|
"num_tokens": 12801177.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.3865326881408695,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.1721171796321869,
|
|
"num_tokens": 12817347.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.3835690975189205,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.1815650701522827,
|
|
"num_tokens": 12830304.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.2819915294647215,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.19441343247890472,
|
|
"num_tokens": 12843813.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.354576063156128,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.1779221698641777,
|
|
"num_tokens": 12857989.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.365860271453857,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.1199,
|
|
"mean_token_accuracy": 0.18672771453857423,
|
|
"num_tokens": 12871529.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.318894243240356,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.18040903359651567,
|
|
"num_tokens": 12884907.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.2730248928070065,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.1864814504981041,
|
|
"num_tokens": 12898403.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.347129392623901,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.18264321535825728,
|
|
"num_tokens": 12913982.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.344757986068726,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.18262473940849305,
|
|
"num_tokens": 12928826.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.261846733093262,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.1848312333226204,
|
|
"num_tokens": 12941905.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.3465046882629395,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1858798533678055,
|
|
"num_tokens": 12955522.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.371321058273315,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.18562092036008834,
|
|
"num_tokens": 12968491.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.297031497955322,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.18115428388118743,
|
|
"num_tokens": 12983258.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.318244791030883,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.18428515195846557,
|
|
"num_tokens": 12996271.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.364977312088013,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.18524766713380814,
|
|
"num_tokens": 13010920.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.25998821258545,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.19228564500808715,
|
|
"num_tokens": 13023499.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.3263512134552,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.1809248998761177,
|
|
"num_tokens": 13040510.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.322596454620362,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.191793230175972,
|
|
"num_tokens": 13053708.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.338529348373413,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.185623100399971,
|
|
"num_tokens": 13068666.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.309015130996704,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.17966341376304626,
|
|
"num_tokens": 13082549.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.444301462173462,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.17759112864732743,
|
|
"num_tokens": 13096685.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.332045364379883,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.18240438550710678,
|
|
"num_tokens": 13110187.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.253191518783569,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.18413471579551696,
|
|
"num_tokens": 13124105.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.359992599487304,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.1873343288898468,
|
|
"num_tokens": 13139675.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.3295289993286135,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.18729310780763625,
|
|
"num_tokens": 13154105.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.251990795135498,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.19008799344301225,
|
|
"num_tokens": 13168473.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.342791795730591,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.18688295781612396,
|
|
"num_tokens": 13182873.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.288819646835327,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.18229663521051406,
|
|
"num_tokens": 13196894.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.283871412277222,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.18293171674013137,
|
|
"num_tokens": 13212285.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.386455345153808,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.18217893838882446,
|
|
"num_tokens": 13227272.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.334987211227417,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.18561779707670212,
|
|
"num_tokens": 13241544.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.294053316116333,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.1810023307800293,
|
|
"num_tokens": 13255605.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.342393112182617,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.1864907681941986,
|
|
"num_tokens": 13269143.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.300639295578003,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.19212037175893784,
|
|
"num_tokens": 13284316.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.246579551696778,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.1949671611189842,
|
|
"num_tokens": 13297714.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.283139991760254,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.18398559838533401,
|
|
"num_tokens": 13311759.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.2232029914855955,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.19327093958854674,
|
|
"num_tokens": 13325966.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.332334375381469,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.18459965735673906,
|
|
"num_tokens": 13340939.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.345418310165405,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.18587302714586257,
|
|
"num_tokens": 13354400.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.482950258255005,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.1716497138142586,
|
|
"num_tokens": 13368819.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.2797523021698,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19408287107944489,
|
|
"num_tokens": 13381106.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.313072156906128,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.1848406746983528,
|
|
"num_tokens": 13394718.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.354447746276856,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.18064648061990737,
|
|
"num_tokens": 13408416.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.339391088485717,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.18296917527914047,
|
|
"num_tokens": 13422287.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.353500032424927,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.18404195755720137,
|
|
"num_tokens": 13438080.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.326828289031982,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.0913,
|
|
"mean_token_accuracy": 0.18155461102724074,
|
|
"num_tokens": 13454781.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.295237302780151,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.179357174038887,
|
|
"num_tokens": 13467021.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.252260828018189,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.18549765646457672,
|
|
"num_tokens": 13479125.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.308937072753906,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.19174055457115174,
|
|
"num_tokens": 13493444.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.319361066818237,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.18553740084171294,
|
|
"num_tokens": 13508261.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.362977313995361,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.18401493281126022,
|
|
"num_tokens": 13521371.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.315124940872193,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.18406408429145812,
|
|
"num_tokens": 13536944.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.33033242225647,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.1895923212170601,
|
|
"num_tokens": 13552281.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.319507026672364,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.182035830616951,
|
|
"num_tokens": 13567376.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.420705127716064,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.17559084743261338,
|
|
"num_tokens": 13580688.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.331259059906006,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.1855834275484085,
|
|
"num_tokens": 13594823.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.27305760383606,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.18907674700021743,
|
|
"num_tokens": 13606702.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.334150218963623,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.18504173457622528,
|
|
"num_tokens": 13620651.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.254895496368408,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.19002680629491805,
|
|
"num_tokens": 13633192.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.223383855819702,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.18796343058347703,
|
|
"num_tokens": 13647082.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.309591293334961,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.18823856562376023,
|
|
"num_tokens": 13662753.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.248241519927978,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.18975120633840561,
|
|
"num_tokens": 13678548.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.326264381408691,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.1870553523302078,
|
|
"num_tokens": 13690969.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.325755167007446,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.0501,
|
|
"mean_token_accuracy": 0.18742039203643798,
|
|
"num_tokens": 13704519.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.270959997177124,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.18990254104137422,
|
|
"num_tokens": 13719664.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.2809583187103275,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 5.0033,
|
|
"mean_token_accuracy": 0.18962556570768357,
|
|
"num_tokens": 13733527.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.363389396667481,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.18534155189990997,
|
|
"num_tokens": 13747788.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.292184972763062,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.1887222185730934,
|
|
"num_tokens": 13761389.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.2499746799469,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.18806459307670592,
|
|
"num_tokens": 13774153.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.300623989105224,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.1648,
|
|
"mean_token_accuracy": 0.18778980821371077,
|
|
"num_tokens": 13788167.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.328409147262573,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.1956685245037079,
|
|
"num_tokens": 13801190.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.269784164428711,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.18476307094097139,
|
|
"num_tokens": 13815744.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.317069387435913,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.19391795843839646,
|
|
"num_tokens": 13829329.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.366438722610473,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.18827635049819946,
|
|
"num_tokens": 13842401.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.246575784683228,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.18482894450426102,
|
|
"num_tokens": 13857156.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.2397401332855225,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.18295381367206573,
|
|
"num_tokens": 13870863.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.38400182723999,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1797648251056671,
|
|
"num_tokens": 13886121.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.38569016456604,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.18728985637426376,
|
|
"num_tokens": 13898928.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.324422311782837,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.18712487518787385,
|
|
"num_tokens": 13911648.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.31566104888916,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.18176639825105667,
|
|
"num_tokens": 13924705.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.28463306427002,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.18167000263929367,
|
|
"num_tokens": 13939495.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.278111171722412,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.1901421144604683,
|
|
"num_tokens": 13952236.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.373788261413575,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.18144380897283555,
|
|
"num_tokens": 13967699.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.328965330123902,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.18640072345733644,
|
|
"num_tokens": 13980619.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.265719652175903,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.18287436813116073,
|
|
"num_tokens": 13995965.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.272796201705932,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.18683422952890397,
|
|
"num_tokens": 14010325.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.371990966796875,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.18376192897558213,
|
|
"num_tokens": 14025368.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.2132796287536625,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.18886683881282806,
|
|
"num_tokens": 14039609.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.362352561950684,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.18064136058092117,
|
|
"num_tokens": 14053680.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.438577604293823,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.17920819520950318,
|
|
"num_tokens": 14067262.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.2425000190734865,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.18719157874584197,
|
|
"num_tokens": 14080821.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.305828285217285,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.18426071256399154,
|
|
"num_tokens": 14093586.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.2797142505645756,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.19537042677402497,
|
|
"num_tokens": 14108138.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.271422624588013,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.19041558653116225,
|
|
"num_tokens": 14122495.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.212626504898071,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.0562,
|
|
"mean_token_accuracy": 0.19054892063140869,
|
|
"num_tokens": 14136838.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.2571022510528564,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19038456231355666,
|
|
"num_tokens": 14150910.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.347372961044312,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.1909787118434906,
|
|
"num_tokens": 14164116.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.306113290786743,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.19805614799261093,
|
|
"num_tokens": 14178549.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.233040475845337,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.19163627922534943,
|
|
"num_tokens": 14191625.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.260637426376343,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.18975056409835817,
|
|
"num_tokens": 14205396.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.2180005550384525,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.18550759553909302,
|
|
"num_tokens": 14216957.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.344973611831665,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.18451027572155,
|
|
"num_tokens": 14232891.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.31133918762207,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.19374196380376815,
|
|
"num_tokens": 14245628.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.25178279876709,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.1899755120277405,
|
|
"num_tokens": 14260164.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.364306306838989,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.1508,
|
|
"mean_token_accuracy": 0.18147098869085312,
|
|
"num_tokens": 14274828.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.312448883056641,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.1832786023616791,
|
|
"num_tokens": 14287779.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.29574728012085,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.18824758976697922,
|
|
"num_tokens": 14300946.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.240840768814087,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.1948929861187935,
|
|
"num_tokens": 14314944.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.325879812240601,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.18817064315080642,
|
|
"num_tokens": 14330069.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.288411235809326,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.18363292664289474,
|
|
"num_tokens": 14344262.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.277113962173462,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.19191761761903764,
|
|
"num_tokens": 14358358.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.2646068096160885,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.1958531767129898,
|
|
"num_tokens": 14371520.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.236413240432739,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.19725024849176406,
|
|
"num_tokens": 14384901.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.1662312030792235,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.2038427323102951,
|
|
"num_tokens": 14397740.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.281447982788086,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.18043904304504393,
|
|
"num_tokens": 14412850.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.375515794754028,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.17840202003717423,
|
|
"num_tokens": 14426174.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.296802282333374,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.1517,
|
|
"mean_token_accuracy": 0.18499358743429184,
|
|
"num_tokens": 14442736.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.3573719501495365,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.185704804956913,
|
|
"num_tokens": 14459631.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.250402545928955,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.18379927724599837,
|
|
"num_tokens": 14472896.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.291708612442017,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.18361558765172958,
|
|
"num_tokens": 14487959.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.193226337432861,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.19897136390209197,
|
|
"num_tokens": 14501420.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.306984567642212,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.19501829594373704,
|
|
"num_tokens": 14514800.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.333307886123658,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.17928817719221116,
|
|
"num_tokens": 14530254.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.341461086273194,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.18351953774690627,
|
|
"num_tokens": 14545635.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.271201133728027,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.18357431441545485,
|
|
"num_tokens": 14558672.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.199121570587158,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.1879173994064331,
|
|
"num_tokens": 14571706.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.277734231948853,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.18633452504873277,
|
|
"num_tokens": 14584732.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.367848539352417,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.1857175350189209,
|
|
"num_tokens": 14598883.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.27206130027771,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.18820749670267106,
|
|
"num_tokens": 14613202.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.373336935043335,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.18176941126585006,
|
|
"num_tokens": 14627267.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.323449230194091,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18643707036972046,
|
|
"num_tokens": 14640300.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.272343254089355,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.18567184656858443,
|
|
"num_tokens": 14655029.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.353311443328858,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.18438043296337128,
|
|
"num_tokens": 14669321.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.245241308212281,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.1966283231973648,
|
|
"num_tokens": 14682280.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.279285287857055,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.1925666868686676,
|
|
"num_tokens": 14693761.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.280442380905152,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 5.0315,
|
|
"mean_token_accuracy": 0.18646539449691774,
|
|
"num_tokens": 14706024.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.276974725723266,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.185473270714283,
|
|
"num_tokens": 14721273.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.251651430130005,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.1818856731057167,
|
|
"num_tokens": 14737033.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.289854955673218,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.18851457685232162,
|
|
"num_tokens": 14751881.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.2588685035705565,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.18895655870437622,
|
|
"num_tokens": 14764866.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.31620454788208,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18956113755702972,
|
|
"num_tokens": 14777703.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.286112213134766,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19186916798353196,
|
|
"num_tokens": 14792819.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.162862968444824,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.1927088439464569,
|
|
"num_tokens": 14806612.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.255834531784058,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1965508595108986,
|
|
"num_tokens": 14820313.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.3676141738891605,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.19088566452264785,
|
|
"num_tokens": 14832874.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.289055967330933,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.1893642857670784,
|
|
"num_tokens": 14845021.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.354841327667236,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.1890455886721611,
|
|
"num_tokens": 14860928.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.321168708801269,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.19722183495759965,
|
|
"num_tokens": 14874709.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.305152034759521,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.1784098356962204,
|
|
"num_tokens": 14888323.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.282805728912353,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.18615499436855315,
|
|
"num_tokens": 14901410.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.317856025695801,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.1873985543847084,
|
|
"num_tokens": 14915335.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.339862203598022,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.18458202034235,
|
|
"num_tokens": 14931549.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.212453603744507,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.19202922731637956,
|
|
"num_tokens": 14943745.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.331994152069091,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.18600480407476425,
|
|
"num_tokens": 14957662.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.329409265518189,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.18402229696512223,
|
|
"num_tokens": 14970175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.280200862884522,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.18674208521842955,
|
|
"num_tokens": 14983901.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.393907308578491,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.18259987682104112,
|
|
"num_tokens": 14997637.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.292523717880249,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.17948938757181168,
|
|
"num_tokens": 15014576.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.300879335403442,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.1831787794828415,
|
|
"num_tokens": 15031049.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.242600154876709,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.18616707921028136,
|
|
"num_tokens": 15044632.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.245788955688477,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.1916586220264435,
|
|
"num_tokens": 15057500.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.317418622970581,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.18928124904632568,
|
|
"num_tokens": 15070994.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.212126159667969,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.18696680516004563,
|
|
"num_tokens": 15085824.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.252003908157349,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.19138366281986235,
|
|
"num_tokens": 15101263.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.278714513778686,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.1978074014186859,
|
|
"num_tokens": 15113830.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.297952508926391,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.18746108710765838,
|
|
"num_tokens": 15128427.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.286092758178711,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.1954586461186409,
|
|
"num_tokens": 15143790.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.283107757568359,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.18880869448184967,
|
|
"num_tokens": 15157533.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.229476737976074,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.18911298513412475,
|
|
"num_tokens": 15172164.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.279301691055298,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.19701821953058243,
|
|
"num_tokens": 15184334.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.191413354873657,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.0468,
|
|
"mean_token_accuracy": 0.18830501139163972,
|
|
"num_tokens": 15198783.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.247761631011963,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.1913047045469284,
|
|
"num_tokens": 15214153.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.342239618301392,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.1817881390452385,
|
|
"num_tokens": 15229029.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.264386415481567,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.18658847063779832,
|
|
"num_tokens": 15244724.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.273080444335937,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.18482004404067992,
|
|
"num_tokens": 15258703.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.350534248352051,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.18285827338695526,
|
|
"num_tokens": 15272281.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.293913269042969,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.18722161501646042,
|
|
"num_tokens": 15286657.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.289205408096313,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.1903505340218544,
|
|
"num_tokens": 15300416.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.249413919448853,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.18952654153108597,
|
|
"num_tokens": 15313945.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.221739816665649,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.19326596558094025,
|
|
"num_tokens": 15328995.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.252273988723755,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.19307326376438141,
|
|
"num_tokens": 15342588.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.250972890853882,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.1962678462266922,
|
|
"num_tokens": 15357411.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.195329093933106,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.19176963716745377,
|
|
"num_tokens": 15371968.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.272292041778565,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.19267256557941437,
|
|
"num_tokens": 15387186.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.238138628005982,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.19592117220163346,
|
|
"num_tokens": 15398842.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.224260091781616,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.1924358233809471,
|
|
"num_tokens": 15411687.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.175791025161743,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.19553456753492354,
|
|
"num_tokens": 15425868.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.324447584152222,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17814426273107528,
|
|
"num_tokens": 15439489.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.328158569335938,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.19055284410715104,
|
|
"num_tokens": 15453067.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.209204244613647,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.1963087499141693,
|
|
"num_tokens": 15465357.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.22384786605835,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.18884702026844025,
|
|
"num_tokens": 15479657.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.459466791152954,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.17242255955934524,
|
|
"num_tokens": 15495245.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.3127727031707765,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.1900005280971527,
|
|
"num_tokens": 15507788.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.225294208526611,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.0923,
|
|
"mean_token_accuracy": 0.1860947862267494,
|
|
"num_tokens": 15521970.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.261061525344848,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.19425233453512192,
|
|
"num_tokens": 15534720.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.266478824615478,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.18198966681957246,
|
|
"num_tokens": 15549345.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.288567447662354,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.18770654499530792,
|
|
"num_tokens": 15562838.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.326519775390625,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.19171165823936462,
|
|
"num_tokens": 15575044.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.268227005004883,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.034,
|
|
"mean_token_accuracy": 0.19378841519355774,
|
|
"num_tokens": 15591912.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.315447473526001,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.18524022698402404,
|
|
"num_tokens": 15606903.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.232182836532592,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.1953340768814087,
|
|
"num_tokens": 15620885.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.343390560150146,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.18884147852659225,
|
|
"num_tokens": 15634927.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.2636474609375,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.1895744800567627,
|
|
"num_tokens": 15649369.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.270068407058716,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.18069495558738707,
|
|
"num_tokens": 15665288.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.296831655502319,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.19215119779109954,
|
|
"num_tokens": 15679117.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.2183443069458,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.1995480015873909,
|
|
"num_tokens": 15692177.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.2758708000183105,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.20209874361753463,
|
|
"num_tokens": 15706047.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.260066795349121,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.18586853444576262,
|
|
"num_tokens": 15721191.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.349901247024536,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.18478769063949585,
|
|
"num_tokens": 15735569.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.280852890014648,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.1951826587319374,
|
|
"num_tokens": 15749125.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.205649709701538,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.19599765986204148,
|
|
"num_tokens": 15765641.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.299585247039795,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.1844843327999115,
|
|
"num_tokens": 15780816.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.328836250305176,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.1795637398958206,
|
|
"num_tokens": 15795123.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.243233489990234,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.197913758456707,
|
|
"num_tokens": 15808428.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.30166482925415,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.1827080264687538,
|
|
"num_tokens": 15820618.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.2875278949737545,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.19748762100934983,
|
|
"num_tokens": 15833431.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.247407531738281,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.1989613026380539,
|
|
"num_tokens": 15845629.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.328744840621948,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.18075974136590958,
|
|
"num_tokens": 15859464.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.18330717086792,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.20337564945220948,
|
|
"num_tokens": 15873207.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.247575473785401,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.18798441886901857,
|
|
"num_tokens": 15888856.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.246871471405029,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.19902548491954802,
|
|
"num_tokens": 15901841.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.302401304244995,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.19169118404388427,
|
|
"num_tokens": 15914960.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.162592601776123,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.19473856687545776,
|
|
"num_tokens": 15929466.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.321282911300659,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18536283820867538,
|
|
"num_tokens": 15943934.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.270995187759399,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.1986171320080757,
|
|
"num_tokens": 15956214.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.285578203201294,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.187625452876091,
|
|
"num_tokens": 15970943.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.2747467994689945,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.18986504673957824,
|
|
"num_tokens": 15985539.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.24966950416565,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.20102044939994812,
|
|
"num_tokens": 15998622.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.28323278427124,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.194697830080986,
|
|
"num_tokens": 16013820.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.363418102264404,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.1819551855325699,
|
|
"num_tokens": 16026615.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.307887935638428,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.18798820674419403,
|
|
"num_tokens": 16039921.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.145106363296509,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.19763311594724656,
|
|
"num_tokens": 16054790.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.178565549850464,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.18603767454624176,
|
|
"num_tokens": 16069778.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.21142086982727,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.19405000805854797,
|
|
"num_tokens": 16086472.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.291449928283692,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.18848897218704225,
|
|
"num_tokens": 16100743.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.2107891082763675,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 4.9887,
|
|
"mean_token_accuracy": 0.19094934314489365,
|
|
"num_tokens": 16114894.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.2387885570526125,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.19607480615377426,
|
|
"num_tokens": 16129232.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.244196939468384,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.19929671436548232,
|
|
"num_tokens": 16142983.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.2671925067901615,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.19095949828624725,
|
|
"num_tokens": 16157195.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.230446243286133,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.18954994082450866,
|
|
"num_tokens": 16171240.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.352623462677002,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.18528846502304078,
|
|
"num_tokens": 16186313.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.271135902404785,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.18692163974046708,
|
|
"num_tokens": 16201394.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.194055080413818,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.19800458699464799,
|
|
"num_tokens": 16214917.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.270834112167359,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.19284452348947526,
|
|
"num_tokens": 16228700.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.209543514251709,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.2023202210664749,
|
|
"num_tokens": 16240262.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.180195093154907,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.19715639650821687,
|
|
"num_tokens": 16254830.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.200127077102661,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.20332298278808594,
|
|
"num_tokens": 16267547.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.222266101837159,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.1953933835029602,
|
|
"num_tokens": 16281223.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.3081449508667,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.1444,
|
|
"mean_token_accuracy": 0.18559690117835997,
|
|
"num_tokens": 16295366.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.317699718475342,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.19120134711265563,
|
|
"num_tokens": 16310081.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.31610426902771,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.18748878240585326,
|
|
"num_tokens": 16324544.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.346761417388916,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19018675535917282,
|
|
"num_tokens": 16339128.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.2298853397369385,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.19616030901670456,
|
|
"num_tokens": 16351997.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.1909592628479,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.19996345341205596,
|
|
"num_tokens": 16365075.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.191736507415771,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.2038533791899681,
|
|
"num_tokens": 16378635.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.250685310363769,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.20547545850276946,
|
|
"num_tokens": 16392224.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.200765657424927,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.1950543239712715,
|
|
"num_tokens": 16407830.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.163029909133911,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.19691397547721862,
|
|
"num_tokens": 16421576.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.323457479476929,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.19107279777526856,
|
|
"num_tokens": 16436548.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.290355110168457,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.192501936852932,
|
|
"num_tokens": 16451435.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.271506023406983,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.18329890817403793,
|
|
"num_tokens": 16465786.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.31269679069519,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.1890162318944931,
|
|
"num_tokens": 16479832.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.234739923477173,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.20115922540426254,
|
|
"num_tokens": 16491824.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.263653564453125,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.1893574208021164,
|
|
"num_tokens": 16507273.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.251615190505982,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.1916299819946289,
|
|
"num_tokens": 16521041.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.236955451965332,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 4.9959,
|
|
"mean_token_accuracy": 0.1968044713139534,
|
|
"num_tokens": 16534837.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.301002407073975,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.19276404976844788,
|
|
"num_tokens": 16549183.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.226874732971192,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 5.0268,
|
|
"mean_token_accuracy": 0.19167272746562958,
|
|
"num_tokens": 16562044.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.309398221969604,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.1873836487531662,
|
|
"num_tokens": 16577014.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.2666035175323485,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.20199701189994812,
|
|
"num_tokens": 16588289.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.229057741165161,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.19096744805574417,
|
|
"num_tokens": 16602433.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.350700569152832,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.18654951304197312,
|
|
"num_tokens": 16618178.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.3043416976928714,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19613948464393616,
|
|
"num_tokens": 16634090.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.212548780441284,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.20183636397123336,
|
|
"num_tokens": 16646713.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.23512601852417,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.19313346296548844,
|
|
"num_tokens": 16659172.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.263709688186646,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.19360265433788298,
|
|
"num_tokens": 16672592.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.292951822280884,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.1871548667550087,
|
|
"num_tokens": 16687026.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.224291753768921,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.20600415617227555,
|
|
"num_tokens": 16699489.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.217588567733765,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.19554176479578017,
|
|
"num_tokens": 16713821.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.306798267364502,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.19533285349607468,
|
|
"num_tokens": 16727271.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.288178586959839,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.19798011630773543,
|
|
"num_tokens": 16740387.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.191060638427734,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.1933645561337471,
|
|
"num_tokens": 16756131.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.212758207321167,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.19731339812278748,
|
|
"num_tokens": 16768781.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 5.033751152899572,
|
|
"eval_loss": 4.9821343421936035,
|
|
"eval_mean_token_accuracy": 0.20422642360146517,
|
|
"eval_num_tokens": 16768781.0,
|
|
"eval_runtime": 18.5538,
|
|
"eval_samples_per_second": 1375.081,
|
|
"eval_steps_per_second": 171.932,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"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": 4428498981519360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|