10145 lines
276 KiB
JSON
10145 lines
276 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 5.847953216374269,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 5000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 3.011503052711487,
|
||
|
|
"epoch": 0.005847953216374269,
|
||
|
|
"grad_norm": 35.75,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 14.1046,
|
||
|
|
"mean_token_accuracy": 0.035688506253063676,
|
||
|
|
"num_tokens": 13999.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 3.1570172786712645,
|
||
|
|
"epoch": 0.011695906432748537,
|
||
|
|
"grad_norm": 33.0,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 13.9181,
|
||
|
|
"mean_token_accuracy": 0.037344493344426154,
|
||
|
|
"num_tokens": 25888.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 3.506499719619751,
|
||
|
|
"epoch": 0.017543859649122806,
|
||
|
|
"grad_norm": 39.0,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 13.4816,
|
||
|
|
"mean_token_accuracy": 0.033669637702405456,
|
||
|
|
"num_tokens": 37699.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.382130026817322,
|
||
|
|
"epoch": 0.023391812865497075,
|
||
|
|
"grad_norm": 39.5,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 12.8513,
|
||
|
|
"mean_token_accuracy": 0.019791487697511913,
|
||
|
|
"num_tokens": 49648.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.491881942749023,
|
||
|
|
"epoch": 0.029239766081871343,
|
||
|
|
"grad_norm": 14.5625,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 11.2853,
|
||
|
|
"mean_token_accuracy": 0.019448780827224253,
|
||
|
|
"num_tokens": 62255.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.010943794250489,
|
||
|
|
"epoch": 0.03508771929824561,
|
||
|
|
"grad_norm": 4.84375,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.7751,
|
||
|
|
"mean_token_accuracy": 0.00878947232849896,
|
||
|
|
"num_tokens": 76003.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.62158660888672,
|
||
|
|
"epoch": 0.04093567251461988,
|
||
|
|
"grad_norm": 3.40625,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.5825,
|
||
|
|
"mean_token_accuracy": 0.009877379098907114,
|
||
|
|
"num_tokens": 87585.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.41454849243164,
|
||
|
|
"epoch": 0.04678362573099415,
|
||
|
|
"grad_norm": 4.59375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.1549,
|
||
|
|
"mean_token_accuracy": 0.019071799516677857,
|
||
|
|
"num_tokens": 100404.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.373588752746581,
|
||
|
|
"epoch": 0.05263157894736842,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.91,
|
||
|
|
"mean_token_accuracy": 0.0510077447630465,
|
||
|
|
"num_tokens": 113130.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.290110111236572,
|
||
|
|
"epoch": 0.05847953216374269,
|
||
|
|
"grad_norm": 2.65625,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.5708,
|
||
|
|
"mean_token_accuracy": 0.08142316564917565,
|
||
|
|
"num_tokens": 125430.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.002687644958495,
|
||
|
|
"epoch": 0.06432748538011696,
|
||
|
|
"grad_norm": 3.078125,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.5528,
|
||
|
|
"mean_token_accuracy": 0.0672168917953968,
|
||
|
|
"num_tokens": 137550.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.2318941116333,
|
||
|
|
"epoch": 0.07017543859649122,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.4611,
|
||
|
|
"mean_token_accuracy": 0.07226917184889317,
|
||
|
|
"num_tokens": 149530.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.194271087646484,
|
||
|
|
"epoch": 0.07602339181286549,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.4491,
|
||
|
|
"mean_token_accuracy": 0.07329789400100709,
|
||
|
|
"num_tokens": 161671.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.232907676696778,
|
||
|
|
"epoch": 0.08187134502923976,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.4074,
|
||
|
|
"mean_token_accuracy": 0.0754720564931631,
|
||
|
|
"num_tokens": 174160.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.223019981384278,
|
||
|
|
"epoch": 0.08771929824561403,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.357,
|
||
|
|
"mean_token_accuracy": 0.06809913516044616,
|
||
|
|
"num_tokens": 186969.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.965007305145264,
|
||
|
|
"epoch": 0.0935672514619883,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.2625,
|
||
|
|
"mean_token_accuracy": 0.0748597014695406,
|
||
|
|
"num_tokens": 199470.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.107829475402832,
|
||
|
|
"epoch": 0.09941520467836257,
|
||
|
|
"grad_norm": 1.8984375,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.1703,
|
||
|
|
"mean_token_accuracy": 0.07800811901688576,
|
||
|
|
"num_tokens": 211306.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.909124755859375,
|
||
|
|
"epoch": 0.10526315789473684,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.1713,
|
||
|
|
"mean_token_accuracy": 0.07304236702620984,
|
||
|
|
"num_tokens": 223323.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.078854656219482,
|
||
|
|
"epoch": 0.1111111111111111,
|
||
|
|
"grad_norm": 1.953125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.0578,
|
||
|
|
"mean_token_accuracy": 0.08289388790726662,
|
||
|
|
"num_tokens": 235896.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.830192375183106,
|
||
|
|
"epoch": 0.11695906432748537,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.021,
|
||
|
|
"mean_token_accuracy": 0.07751639671623707,
|
||
|
|
"num_tokens": 247879.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.94895429611206,
|
||
|
|
"epoch": 0.12280701754385964,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.9105,
|
||
|
|
"mean_token_accuracy": 0.07603972963988781,
|
||
|
|
"num_tokens": 259714.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.896305179595947,
|
||
|
|
"epoch": 0.1286549707602339,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.8763,
|
||
|
|
"mean_token_accuracy": 0.08195686042308807,
|
||
|
|
"num_tokens": 272429.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.760246086120606,
|
||
|
|
"epoch": 0.13450292397660818,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.8484,
|
||
|
|
"mean_token_accuracy": 0.07280035950243473,
|
||
|
|
"num_tokens": 285924.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.702124404907227,
|
||
|
|
"epoch": 0.14035087719298245,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.6942,
|
||
|
|
"mean_token_accuracy": 0.08684460520744323,
|
||
|
|
"num_tokens": 299453.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.505807209014893,
|
||
|
|
"epoch": 0.14619883040935672,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.6969,
|
||
|
|
"mean_token_accuracy": 0.0838764600455761,
|
||
|
|
"num_tokens": 312295.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.498956871032714,
|
||
|
|
"epoch": 0.15204678362573099,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.5488,
|
||
|
|
"mean_token_accuracy": 0.08384966105222702,
|
||
|
|
"num_tokens": 324730.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.271528625488282,
|
||
|
|
"epoch": 0.15789473684210525,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.4801,
|
||
|
|
"mean_token_accuracy": 0.08416559919714928,
|
||
|
|
"num_tokens": 336481.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.22463436126709,
|
||
|
|
"epoch": 0.16374269005847952,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.4865,
|
||
|
|
"mean_token_accuracy": 0.08492137640714645,
|
||
|
|
"num_tokens": 348987.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.034030055999756,
|
||
|
|
"epoch": 0.1695906432748538,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.3974,
|
||
|
|
"mean_token_accuracy": 0.08240444362163543,
|
||
|
|
"num_tokens": 360390.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.999344062805175,
|
||
|
|
"epoch": 0.17543859649122806,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.4036,
|
||
|
|
"mean_token_accuracy": 0.08263231143355369,
|
||
|
|
"num_tokens": 372456.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.908535861968994,
|
||
|
|
"epoch": 0.18128654970760233,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.3422,
|
||
|
|
"mean_token_accuracy": 0.07766095399856568,
|
||
|
|
"num_tokens": 384185.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.835869979858398,
|
||
|
|
"epoch": 0.1871345029239766,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.3227,
|
||
|
|
"mean_token_accuracy": 0.08606852069497109,
|
||
|
|
"num_tokens": 395399.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.697229862213135,
|
||
|
|
"epoch": 0.19298245614035087,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 8.337,
|
||
|
|
"mean_token_accuracy": 0.08855125159025193,
|
||
|
|
"num_tokens": 408676.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.610207080841064,
|
||
|
|
"epoch": 0.19883040935672514,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 8.3123,
|
||
|
|
"mean_token_accuracy": 0.08628950268030167,
|
||
|
|
"num_tokens": 421861.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.750581073760987,
|
||
|
|
"epoch": 0.2046783625730994,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 8.353,
|
||
|
|
"mean_token_accuracy": 0.09162932708859443,
|
||
|
|
"num_tokens": 434852.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.575475406646728,
|
||
|
|
"epoch": 0.21052631578947367,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 8.3025,
|
||
|
|
"mean_token_accuracy": 0.08264983892440796,
|
||
|
|
"num_tokens": 447313.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.66052532196045,
|
||
|
|
"epoch": 0.21637426900584794,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 8.242,
|
||
|
|
"mean_token_accuracy": 0.09072699844837188,
|
||
|
|
"num_tokens": 460271.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.458691787719726,
|
||
|
|
"epoch": 0.2222222222222222,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 8.2117,
|
||
|
|
"mean_token_accuracy": 0.0964887373149395,
|
||
|
|
"num_tokens": 473006.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.625473880767823,
|
||
|
|
"epoch": 0.22807017543859648,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 8.2416,
|
||
|
|
"mean_token_accuracy": 0.08616446778178215,
|
||
|
|
"num_tokens": 486100.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.410247135162354,
|
||
|
|
"epoch": 0.23391812865497075,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 8.1352,
|
||
|
|
"mean_token_accuracy": 0.09261524304747581,
|
||
|
|
"num_tokens": 499460.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.550405311584473,
|
||
|
|
"epoch": 0.23976608187134502,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 8.1476,
|
||
|
|
"mean_token_accuracy": 0.091904778778553,
|
||
|
|
"num_tokens": 511795.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.412632751464844,
|
||
|
|
"epoch": 0.24561403508771928,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 8.204,
|
||
|
|
"mean_token_accuracy": 0.09843768626451492,
|
||
|
|
"num_tokens": 524897.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.52775535583496,
|
||
|
|
"epoch": 0.25146198830409355,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 8.1374,
|
||
|
|
"mean_token_accuracy": 0.09786352440714836,
|
||
|
|
"num_tokens": 538325.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.386085700988769,
|
||
|
|
"epoch": 0.2573099415204678,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 8.1911,
|
||
|
|
"mean_token_accuracy": 0.09132648184895516,
|
||
|
|
"num_tokens": 550979.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.483522033691406,
|
||
|
|
"epoch": 0.2631578947368421,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 8.1602,
|
||
|
|
"mean_token_accuracy": 0.09506673067808151,
|
||
|
|
"num_tokens": 563001.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.336331844329834,
|
||
|
|
"epoch": 0.26900584795321636,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 8.0781,
|
||
|
|
"mean_token_accuracy": 0.09937207028269768,
|
||
|
|
"num_tokens": 573600.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.444112873077392,
|
||
|
|
"epoch": 0.27485380116959063,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 8.0893,
|
||
|
|
"mean_token_accuracy": 0.10078474283218383,
|
||
|
|
"num_tokens": 585287.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.33163080215454,
|
||
|
|
"epoch": 0.2807017543859649,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 8.1193,
|
||
|
|
"mean_token_accuracy": 0.09278298616409301,
|
||
|
|
"num_tokens": 597386.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.417845058441163,
|
||
|
|
"epoch": 0.28654970760233917,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 8.0979,
|
||
|
|
"mean_token_accuracy": 0.09884399548172951,
|
||
|
|
"num_tokens": 609256.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.383094787597656,
|
||
|
|
"epoch": 0.29239766081871343,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 8.0968,
|
||
|
|
"mean_token_accuracy": 0.10301539301872253,
|
||
|
|
"num_tokens": 621506.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.22484188079834,
|
||
|
|
"epoch": 0.2982456140350877,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 8.0108,
|
||
|
|
"mean_token_accuracy": 0.10739858150482177,
|
||
|
|
"num_tokens": 633512.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.35753002166748,
|
||
|
|
"epoch": 0.30409356725146197,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 8.1404,
|
||
|
|
"mean_token_accuracy": 0.09757127910852433,
|
||
|
|
"num_tokens": 647098.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.389013767242432,
|
||
|
|
"epoch": 0.30994152046783624,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 8.1411,
|
||
|
|
"mean_token_accuracy": 0.09518403038382531,
|
||
|
|
"num_tokens": 659559.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.338126182556152,
|
||
|
|
"epoch": 0.3157894736842105,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 8.0745,
|
||
|
|
"mean_token_accuracy": 0.09692913815379142,
|
||
|
|
"num_tokens": 672621.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.312376308441163,
|
||
|
|
"epoch": 0.3216374269005848,
|
||
|
|
"grad_norm": 2.828125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 8.0387,
|
||
|
|
"mean_token_accuracy": 0.10461566746234893,
|
||
|
|
"num_tokens": 685652.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.29957218170166,
|
||
|
|
"epoch": 0.32748538011695905,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 8.0998,
|
||
|
|
"mean_token_accuracy": 0.10161212980747222,
|
||
|
|
"num_tokens": 696910.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.248525142669678,
|
||
|
|
"epoch": 0.3333333333333333,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.9659,
|
||
|
|
"mean_token_accuracy": 0.10607651099562646,
|
||
|
|
"num_tokens": 709054.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.277126693725586,
|
||
|
|
"epoch": 0.3391812865497076,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.997,
|
||
|
|
"mean_token_accuracy": 0.1044411912560463,
|
||
|
|
"num_tokens": 720902.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.320906162261963,
|
||
|
|
"epoch": 0.34502923976608185,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 8.0586,
|
||
|
|
"mean_token_accuracy": 0.10378434732556344,
|
||
|
|
"num_tokens": 733319.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.274054527282715,
|
||
|
|
"epoch": 0.3508771929824561,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.9508,
|
||
|
|
"mean_token_accuracy": 0.10693862661719322,
|
||
|
|
"num_tokens": 744817.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.191329860687256,
|
||
|
|
"epoch": 0.3567251461988304,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 8.0044,
|
||
|
|
"mean_token_accuracy": 0.1035879172384739,
|
||
|
|
"num_tokens": 756582.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.263913822174072,
|
||
|
|
"epoch": 0.36257309941520466,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.9151,
|
||
|
|
"mean_token_accuracy": 0.1130017727613449,
|
||
|
|
"num_tokens": 769273.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.111418914794921,
|
||
|
|
"epoch": 0.3684210526315789,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.9862,
|
||
|
|
"mean_token_accuracy": 0.10989293605089187,
|
||
|
|
"num_tokens": 782001.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.221540355682373,
|
||
|
|
"epoch": 0.3742690058479532,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.9703,
|
||
|
|
"mean_token_accuracy": 0.112515377253294,
|
||
|
|
"num_tokens": 794575.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.238408851623536,
|
||
|
|
"epoch": 0.38011695906432746,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.9488,
|
||
|
|
"mean_token_accuracy": 0.10909051299095154,
|
||
|
|
"num_tokens": 805583.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.123234272003174,
|
||
|
|
"epoch": 0.38596491228070173,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.993,
|
||
|
|
"mean_token_accuracy": 0.10957283899188042,
|
||
|
|
"num_tokens": 817617.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.23239221572876,
|
||
|
|
"epoch": 0.391812865497076,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.8943,
|
||
|
|
"mean_token_accuracy": 0.11208963096141815,
|
||
|
|
"num_tokens": 830043.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.07594804763794,
|
||
|
|
"epoch": 0.39766081871345027,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.8714,
|
||
|
|
"mean_token_accuracy": 0.1205448180437088,
|
||
|
|
"num_tokens": 843200.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.210996723175048,
|
||
|
|
"epoch": 0.40350877192982454,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.918,
|
||
|
|
"mean_token_accuracy": 0.11632056310772895,
|
||
|
|
"num_tokens": 856031.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.029043245315552,
|
||
|
|
"epoch": 0.4093567251461988,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.8883,
|
||
|
|
"mean_token_accuracy": 0.11492086499929428,
|
||
|
|
"num_tokens": 869119.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.107694482803344,
|
||
|
|
"epoch": 0.4152046783625731,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.9053,
|
||
|
|
"mean_token_accuracy": 0.11929167732596398,
|
||
|
|
"num_tokens": 880802.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.145207405090332,
|
||
|
|
"epoch": 0.42105263157894735,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.8911,
|
||
|
|
"mean_token_accuracy": 0.1157754972577095,
|
||
|
|
"num_tokens": 894237.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.104444217681884,
|
||
|
|
"epoch": 0.4269005847953216,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.9097,
|
||
|
|
"mean_token_accuracy": 0.11690913587808609,
|
||
|
|
"num_tokens": 906695.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.126790809631348,
|
||
|
|
"epoch": 0.4327485380116959,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.8766,
|
||
|
|
"mean_token_accuracy": 0.11690322905778885,
|
||
|
|
"num_tokens": 918955.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.079369258880615,
|
||
|
|
"epoch": 0.43859649122807015,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.9117,
|
||
|
|
"mean_token_accuracy": 0.11631168648600579,
|
||
|
|
"num_tokens": 931812.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.124732828140258,
|
||
|
|
"epoch": 0.4444444444444444,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.9105,
|
||
|
|
"mean_token_accuracy": 0.10793866887688637,
|
||
|
|
"num_tokens": 945261.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.059471893310548,
|
||
|
|
"epoch": 0.4502923976608187,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.8211,
|
||
|
|
"mean_token_accuracy": 0.12420412302017211,
|
||
|
|
"num_tokens": 958376.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.045862627029418,
|
||
|
|
"epoch": 0.45614035087719296,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.8396,
|
||
|
|
"mean_token_accuracy": 0.12700849547982215,
|
||
|
|
"num_tokens": 971709.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.091754007339478,
|
||
|
|
"epoch": 0.4619883040935672,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.8096,
|
||
|
|
"mean_token_accuracy": 0.1235598661005497,
|
||
|
|
"num_tokens": 983847.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.116325187683106,
|
||
|
|
"epoch": 0.4678362573099415,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.8836,
|
||
|
|
"mean_token_accuracy": 0.11197860836982727,
|
||
|
|
"num_tokens": 997034.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.948489475250244,
|
||
|
|
"epoch": 0.47368421052631576,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.9183,
|
||
|
|
"mean_token_accuracy": 0.11601087674498559,
|
||
|
|
"num_tokens": 1010213.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.183907890319825,
|
||
|
|
"epoch": 0.47953216374269003,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.7917,
|
||
|
|
"mean_token_accuracy": 0.11840821728110314,
|
||
|
|
"num_tokens": 1021618.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.002576017379761,
|
||
|
|
"epoch": 0.4853801169590643,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.8151,
|
||
|
|
"mean_token_accuracy": 0.11744796931743622,
|
||
|
|
"num_tokens": 1033809.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.077327156066895,
|
||
|
|
"epoch": 0.49122807017543857,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.8025,
|
||
|
|
"mean_token_accuracy": 0.11957534328103066,
|
||
|
|
"num_tokens": 1045291.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.03057599067688,
|
||
|
|
"epoch": 0.49707602339181284,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.7792,
|
||
|
|
"mean_token_accuracy": 0.11945864260196686,
|
||
|
|
"num_tokens": 1057516.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.868794345855713,
|
||
|
|
"epoch": 0.5029239766081871,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.7351,
|
||
|
|
"mean_token_accuracy": 0.12831166237592698,
|
||
|
|
"num_tokens": 1070675.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.045708703994752,
|
||
|
|
"epoch": 0.5087719298245614,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.8167,
|
||
|
|
"mean_token_accuracy": 0.12775540575385094,
|
||
|
|
"num_tokens": 1082965.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.97526912689209,
|
||
|
|
"epoch": 0.5146198830409356,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.7974,
|
||
|
|
"mean_token_accuracy": 0.11712993755936622,
|
||
|
|
"num_tokens": 1095922.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9973499298095705,
|
||
|
|
"epoch": 0.52046783625731,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.7752,
|
||
|
|
"mean_token_accuracy": 0.12419187352061271,
|
||
|
|
"num_tokens": 1109002.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.025882577896118,
|
||
|
|
"epoch": 0.5263157894736842,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.7881,
|
||
|
|
"mean_token_accuracy": 0.11773632392287255,
|
||
|
|
"num_tokens": 1121199.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.909945821762085,
|
||
|
|
"epoch": 0.5321637426900585,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.7307,
|
||
|
|
"mean_token_accuracy": 0.12722171917557717,
|
||
|
|
"num_tokens": 1134721.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.956731367111206,
|
||
|
|
"epoch": 0.5380116959064327,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.7963,
|
||
|
|
"mean_token_accuracy": 0.12164180129766464,
|
||
|
|
"num_tokens": 1147954.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.956630373001099,
|
||
|
|
"epoch": 0.543859649122807,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.7275,
|
||
|
|
"mean_token_accuracy": 0.1270610734820366,
|
||
|
|
"num_tokens": 1161208.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.929465818405151,
|
||
|
|
"epoch": 0.5497076023391813,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.8257,
|
||
|
|
"mean_token_accuracy": 0.11997483149170876,
|
||
|
|
"num_tokens": 1173789.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.05664644241333,
|
||
|
|
"epoch": 0.5555555555555556,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.7272,
|
||
|
|
"mean_token_accuracy": 0.12666135057806968,
|
||
|
|
"num_tokens": 1185765.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.764935064315796,
|
||
|
|
"epoch": 0.5614035087719298,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.7499,
|
||
|
|
"mean_token_accuracy": 0.12476444989442825,
|
||
|
|
"num_tokens": 1197954.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.030300664901734,
|
||
|
|
"epoch": 0.5672514619883041,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.679,
|
||
|
|
"mean_token_accuracy": 0.12792463153600692,
|
||
|
|
"num_tokens": 1211285.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9220020294189455,
|
||
|
|
"epoch": 0.5730994152046783,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.7543,
|
||
|
|
"mean_token_accuracy": 0.11961747631430626,
|
||
|
|
"num_tokens": 1223197.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8508258819580075,
|
||
|
|
"epoch": 0.5789473684210527,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 7.68,
|
||
|
|
"mean_token_accuracy": 0.12632347792387008,
|
||
|
|
"num_tokens": 1234817.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9022626876831055,
|
||
|
|
"epoch": 0.5847953216374269,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.7281,
|
||
|
|
"mean_token_accuracy": 0.1318517729640007,
|
||
|
|
"num_tokens": 1249305.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5847953216374269,
|
||
|
|
"eval_entropy": 7.841686710143863,
|
||
|
|
"eval_loss": 7.758663654327393,
|
||
|
|
"eval_mean_token_accuracy": 0.1180623706160965,
|
||
|
|
"eval_num_tokens": 1249305.0,
|
||
|
|
"eval_runtime": 2.3012,
|
||
|
|
"eval_samples_per_second": 1176.366,
|
||
|
|
"eval_steps_per_second": 147.317,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.89346866607666,
|
||
|
|
"epoch": 0.5906432748538012,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.7086,
|
||
|
|
"mean_token_accuracy": 0.12867532819509506,
|
||
|
|
"num_tokens": 1262182.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.847484970092774,
|
||
|
|
"epoch": 0.5964912280701754,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.7312,
|
||
|
|
"mean_token_accuracy": 0.1298251412808895,
|
||
|
|
"num_tokens": 1274616.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.838339996337891,
|
||
|
|
"epoch": 0.6023391812865497,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.7403,
|
||
|
|
"mean_token_accuracy": 0.11953374072909355,
|
||
|
|
"num_tokens": 1287306.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.859510087966919,
|
||
|
|
"epoch": 0.6081871345029239,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.5908,
|
||
|
|
"mean_token_accuracy": 0.13276281207799911,
|
||
|
|
"num_tokens": 1299472.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7895465850830075,
|
||
|
|
"epoch": 0.6140350877192983,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 7.5534,
|
||
|
|
"mean_token_accuracy": 0.13485597670078278,
|
||
|
|
"num_tokens": 1312636.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6986805438995365,
|
||
|
|
"epoch": 0.6198830409356725,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.5875,
|
||
|
|
"mean_token_accuracy": 0.13942663818597795,
|
||
|
|
"num_tokens": 1324058.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.906114959716797,
|
||
|
|
"epoch": 0.6257309941520468,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.7124,
|
||
|
|
"mean_token_accuracy": 0.12152797058224678,
|
||
|
|
"num_tokens": 1337605.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.845144605636596,
|
||
|
|
"epoch": 0.631578947368421,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.7079,
|
||
|
|
"mean_token_accuracy": 0.12539200559258462,
|
||
|
|
"num_tokens": 1350658.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.842404890060425,
|
||
|
|
"epoch": 0.6374269005847953,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 7.6214,
|
||
|
|
"mean_token_accuracy": 0.13082724660634995,
|
||
|
|
"num_tokens": 1362091.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.808346605300903,
|
||
|
|
"epoch": 0.6432748538011696,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 7.6453,
|
||
|
|
"mean_token_accuracy": 0.12663563415408136,
|
||
|
|
"num_tokens": 1374055.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.67389407157898,
|
||
|
|
"epoch": 0.6491228070175439,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.5291,
|
||
|
|
"mean_token_accuracy": 0.1318692184984684,
|
||
|
|
"num_tokens": 1385269.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.744857835769653,
|
||
|
|
"epoch": 0.6549707602339181,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 7.6424,
|
||
|
|
"mean_token_accuracy": 0.1306732676923275,
|
||
|
|
"num_tokens": 1396559.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.729473543167114,
|
||
|
|
"epoch": 0.6608187134502924,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 7.6538,
|
||
|
|
"mean_token_accuracy": 0.13084901124238968,
|
||
|
|
"num_tokens": 1408838.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.766721534729004,
|
||
|
|
"epoch": 0.6666666666666666,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.5368,
|
||
|
|
"mean_token_accuracy": 0.13452390804886818,
|
||
|
|
"num_tokens": 1421023.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.697804594039917,
|
||
|
|
"epoch": 0.672514619883041,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 7.6167,
|
||
|
|
"mean_token_accuracy": 0.13060338124632836,
|
||
|
|
"num_tokens": 1433912.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.818636512756347,
|
||
|
|
"epoch": 0.6783625730994152,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 7.6231,
|
||
|
|
"mean_token_accuracy": 0.1270453654229641,
|
||
|
|
"num_tokens": 1445262.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.690509176254272,
|
||
|
|
"epoch": 0.6842105263157895,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 7.5815,
|
||
|
|
"mean_token_accuracy": 0.13163993805646895,
|
||
|
|
"num_tokens": 1457927.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.660882234573364,
|
||
|
|
"epoch": 0.6900584795321637,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 7.6489,
|
||
|
|
"mean_token_accuracy": 0.12540714517235757,
|
||
|
|
"num_tokens": 1470116.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.764140367507935,
|
||
|
|
"epoch": 0.695906432748538,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 7.5297,
|
||
|
|
"mean_token_accuracy": 0.13199650049209594,
|
||
|
|
"num_tokens": 1482067.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.73416576385498,
|
||
|
|
"epoch": 0.7017543859649122,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 7.6134,
|
||
|
|
"mean_token_accuracy": 0.1266568437218666,
|
||
|
|
"num_tokens": 1493902.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.750314617156983,
|
||
|
|
"epoch": 0.7076023391812866,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 7.5725,
|
||
|
|
"mean_token_accuracy": 0.12624214142560958,
|
||
|
|
"num_tokens": 1505689.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.611770343780518,
|
||
|
|
"epoch": 0.7134502923976608,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 7.5194,
|
||
|
|
"mean_token_accuracy": 0.14677974060177804,
|
||
|
|
"num_tokens": 1518002.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.710480356216431,
|
||
|
|
"epoch": 0.7192982456140351,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 7.5443,
|
||
|
|
"mean_token_accuracy": 0.13318197801709175,
|
||
|
|
"num_tokens": 1529307.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.769068670272827,
|
||
|
|
"epoch": 0.7251461988304093,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 7.6963,
|
||
|
|
"mean_token_accuracy": 0.11717625185847283,
|
||
|
|
"num_tokens": 1542351.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.606048679351806,
|
||
|
|
"epoch": 0.7309941520467836,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 7.5147,
|
||
|
|
"mean_token_accuracy": 0.135113126039505,
|
||
|
|
"num_tokens": 1556263.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.631821155548096,
|
||
|
|
"epoch": 0.7368421052631579,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 7.5509,
|
||
|
|
"mean_token_accuracy": 0.13068365454673767,
|
||
|
|
"num_tokens": 1568906.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.647361993789673,
|
||
|
|
"epoch": 0.7426900584795322,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 7.5375,
|
||
|
|
"mean_token_accuracy": 0.13785270750522613,
|
||
|
|
"num_tokens": 1580631.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.632867479324341,
|
||
|
|
"epoch": 0.7485380116959064,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 7.5521,
|
||
|
|
"mean_token_accuracy": 0.12791232094168664,
|
||
|
|
"num_tokens": 1592369.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.650920963287353,
|
||
|
|
"epoch": 0.7543859649122807,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 7.5862,
|
||
|
|
"mean_token_accuracy": 0.13423935249447821,
|
||
|
|
"num_tokens": 1604888.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6349873542785645,
|
||
|
|
"epoch": 0.7602339181286549,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 7.4819,
|
||
|
|
"mean_token_accuracy": 0.13629580438137054,
|
||
|
|
"num_tokens": 1617128.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.645885038375854,
|
||
|
|
"epoch": 0.7660818713450293,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 7.5341,
|
||
|
|
"mean_token_accuracy": 0.12496847957372666,
|
||
|
|
"num_tokens": 1629350.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.682138872146607,
|
||
|
|
"epoch": 0.7719298245614035,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 7.5573,
|
||
|
|
"mean_token_accuracy": 0.1278813175857067,
|
||
|
|
"num_tokens": 1643082.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.628981828689575,
|
||
|
|
"epoch": 0.7777777777777778,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 7.5434,
|
||
|
|
"mean_token_accuracy": 0.13124902471899985,
|
||
|
|
"num_tokens": 1654785.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.671693944931031,
|
||
|
|
"epoch": 0.783625730994152,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 7.5755,
|
||
|
|
"mean_token_accuracy": 0.12893529310822488,
|
||
|
|
"num_tokens": 1667704.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.678587818145752,
|
||
|
|
"epoch": 0.7894736842105263,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 7.5077,
|
||
|
|
"mean_token_accuracy": 0.1305314414203167,
|
||
|
|
"num_tokens": 1680459.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.557713508605957,
|
||
|
|
"epoch": 0.7953216374269005,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 7.4271,
|
||
|
|
"mean_token_accuracy": 0.13665740936994553,
|
||
|
|
"num_tokens": 1692912.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.614948320388794,
|
||
|
|
"epoch": 0.8011695906432749,
|
||
|
|
"grad_norm": 1.8359375,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 7.4574,
|
||
|
|
"mean_token_accuracy": 0.1333981230854988,
|
||
|
|
"num_tokens": 1705329.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.643642568588257,
|
||
|
|
"epoch": 0.8070175438596491,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 7.5618,
|
||
|
|
"mean_token_accuracy": 0.12579705193638802,
|
||
|
|
"num_tokens": 1717283.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.503328323364258,
|
||
|
|
"epoch": 0.8128654970760234,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 7.5046,
|
||
|
|
"mean_token_accuracy": 0.1324782818555832,
|
||
|
|
"num_tokens": 1730308.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.626899671554566,
|
||
|
|
"epoch": 0.8187134502923976,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 7.5432,
|
||
|
|
"mean_token_accuracy": 0.12995980978012084,
|
||
|
|
"num_tokens": 1742716.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.57134051322937,
|
||
|
|
"epoch": 0.8245614035087719,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 7.4896,
|
||
|
|
"mean_token_accuracy": 0.13513270914554595,
|
||
|
|
"num_tokens": 1754183.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.522201442718506,
|
||
|
|
"epoch": 0.8304093567251462,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 7.5076,
|
||
|
|
"mean_token_accuracy": 0.12541001066565513,
|
||
|
|
"num_tokens": 1766601.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.612595176696777,
|
||
|
|
"epoch": 0.8362573099415205,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 7.3986,
|
||
|
|
"mean_token_accuracy": 0.14329489395022393,
|
||
|
|
"num_tokens": 1778756.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3666143894195555,
|
||
|
|
"epoch": 0.8421052631578947,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 7.466,
|
||
|
|
"mean_token_accuracy": 0.13944232240319251,
|
||
|
|
"num_tokens": 1791485.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.58320369720459,
|
||
|
|
"epoch": 0.847953216374269,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 7.4825,
|
||
|
|
"mean_token_accuracy": 0.12936609014868736,
|
||
|
|
"num_tokens": 1803712.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.433703374862671,
|
||
|
|
"epoch": 0.8538011695906432,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 7.44,
|
||
|
|
"mean_token_accuracy": 0.1326867386698723,
|
||
|
|
"num_tokens": 1818387.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.604799032211304,
|
||
|
|
"epoch": 0.8596491228070176,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 7.4325,
|
||
|
|
"mean_token_accuracy": 0.13445507287979125,
|
||
|
|
"num_tokens": 1830113.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.533818340301513,
|
||
|
|
"epoch": 0.8654970760233918,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 7.5505,
|
||
|
|
"mean_token_accuracy": 0.13362800627946853,
|
||
|
|
"num_tokens": 1841789.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.506076908111572,
|
||
|
|
"epoch": 0.8713450292397661,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 7.3988,
|
||
|
|
"mean_token_accuracy": 0.13710973560810089,
|
||
|
|
"num_tokens": 1853669.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.449912071228027,
|
||
|
|
"epoch": 0.8771929824561403,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 7.469,
|
||
|
|
"mean_token_accuracy": 0.13512061759829522,
|
||
|
|
"num_tokens": 1865322.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.454483270645142,
|
||
|
|
"epoch": 0.8830409356725146,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 7.3563,
|
||
|
|
"mean_token_accuracy": 0.14202516600489618,
|
||
|
|
"num_tokens": 1879039.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.581981468200683,
|
||
|
|
"epoch": 0.8888888888888888,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 7.5329,
|
||
|
|
"mean_token_accuracy": 0.1277366228401661,
|
||
|
|
"num_tokens": 1893078.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.589095783233643,
|
||
|
|
"epoch": 0.8947368421052632,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 7.5463,
|
||
|
|
"mean_token_accuracy": 0.1306015282869339,
|
||
|
|
"num_tokens": 1907399.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.511038160324096,
|
||
|
|
"epoch": 0.9005847953216374,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 7.489,
|
||
|
|
"mean_token_accuracy": 0.12949865981936454,
|
||
|
|
"num_tokens": 1919290.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.527887201309204,
|
||
|
|
"epoch": 0.9064327485380117,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 7.4317,
|
||
|
|
"mean_token_accuracy": 0.13319515511393548,
|
||
|
|
"num_tokens": 1931658.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.557555913925171,
|
||
|
|
"epoch": 0.9122807017543859,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 7.4588,
|
||
|
|
"mean_token_accuracy": 0.12898892015218735,
|
||
|
|
"num_tokens": 1943881.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.488714742660522,
|
||
|
|
"epoch": 0.9181286549707602,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 7.3689,
|
||
|
|
"mean_token_accuracy": 0.1345718003809452,
|
||
|
|
"num_tokens": 1956288.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.382142972946167,
|
||
|
|
"epoch": 0.9239766081871345,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 7.2696,
|
||
|
|
"mean_token_accuracy": 0.1387133315205574,
|
||
|
|
"num_tokens": 1967265.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.400208759307861,
|
||
|
|
"epoch": 0.9298245614035088,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 7.4155,
|
||
|
|
"mean_token_accuracy": 0.13420891687273978,
|
||
|
|
"num_tokens": 1980039.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5092360496521,
|
||
|
|
"epoch": 0.935672514619883,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 7.3761,
|
||
|
|
"mean_token_accuracy": 0.13293110430240632,
|
||
|
|
"num_tokens": 1992735.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.502032279968262,
|
||
|
|
"epoch": 0.9415204678362573,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 7.4075,
|
||
|
|
"mean_token_accuracy": 0.13847337365150453,
|
||
|
|
"num_tokens": 2004545.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.40691909790039,
|
||
|
|
"epoch": 0.9473684210526315,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 7.3914,
|
||
|
|
"mean_token_accuracy": 0.13531816229224206,
|
||
|
|
"num_tokens": 2017100.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.43734827041626,
|
||
|
|
"epoch": 0.9532163742690059,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 7.3306,
|
||
|
|
"mean_token_accuracy": 0.14728882685303687,
|
||
|
|
"num_tokens": 2029868.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.466191053390503,
|
||
|
|
"epoch": 0.9590643274853801,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 7.4035,
|
||
|
|
"mean_token_accuracy": 0.13149953931570052,
|
||
|
|
"num_tokens": 2041334.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.460909032821656,
|
||
|
|
"epoch": 0.9649122807017544,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 7.4782,
|
||
|
|
"mean_token_accuracy": 0.13376137018203735,
|
||
|
|
"num_tokens": 2054797.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.42348313331604,
|
||
|
|
"epoch": 0.9707602339181286,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 7.3561,
|
||
|
|
"mean_token_accuracy": 0.1338147610425949,
|
||
|
|
"num_tokens": 2068337.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4611015796661375,
|
||
|
|
"epoch": 0.9766081871345029,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 7.3867,
|
||
|
|
"mean_token_accuracy": 0.13802094981074334,
|
||
|
|
"num_tokens": 2079984.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.447398233413696,
|
||
|
|
"epoch": 0.9824561403508771,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 7.4152,
|
||
|
|
"mean_token_accuracy": 0.13706867769360542,
|
||
|
|
"num_tokens": 2093069.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.325431823730469,
|
||
|
|
"epoch": 0.9883040935672515,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 7.3565,
|
||
|
|
"mean_token_accuracy": 0.1383918911218643,
|
||
|
|
"num_tokens": 2104753.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.395589447021484,
|
||
|
|
"epoch": 0.9941520467836257,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 7.3819,
|
||
|
|
"mean_token_accuracy": 0.13548673540353776,
|
||
|
|
"num_tokens": 2116576.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.470466804504395,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 7.3472,
|
||
|
|
"mean_token_accuracy": 0.13063811063766478,
|
||
|
|
"num_tokens": 2129484.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.311177539825439,
|
||
|
|
"epoch": 1.0058479532163742,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 7.1975,
|
||
|
|
"mean_token_accuracy": 0.14626543894410132,
|
||
|
|
"num_tokens": 2142000.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366611528396606,
|
||
|
|
"epoch": 1.0116959064327484,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 7.123,
|
||
|
|
"mean_token_accuracy": 0.1465772069990635,
|
||
|
|
"num_tokens": 2152965.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.341231441497802,
|
||
|
|
"epoch": 1.0175438596491229,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 7.2225,
|
||
|
|
"mean_token_accuracy": 0.1331010527908802,
|
||
|
|
"num_tokens": 2165078.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243547677993774,
|
||
|
|
"epoch": 1.023391812865497,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 7.151,
|
||
|
|
"mean_token_accuracy": 0.1457497827708721,
|
||
|
|
"num_tokens": 2176706.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.377624607086181,
|
||
|
|
"epoch": 1.0292397660818713,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 7.1943,
|
||
|
|
"mean_token_accuracy": 0.14025041311979294,
|
||
|
|
"num_tokens": 2190157.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366387224197387,
|
||
|
|
"epoch": 1.0350877192982457,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 7.1634,
|
||
|
|
"mean_token_accuracy": 0.14333848357200624,
|
||
|
|
"num_tokens": 2201821.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2149065971374515,
|
||
|
|
"epoch": 1.04093567251462,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 7.0878,
|
||
|
|
"mean_token_accuracy": 0.1505483314394951,
|
||
|
|
"num_tokens": 2214504.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.245018482208252,
|
||
|
|
"epoch": 1.0467836257309941,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 7.2145,
|
||
|
|
"mean_token_accuracy": 0.14023151621222496,
|
||
|
|
"num_tokens": 2226318.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.377814912796021,
|
||
|
|
"epoch": 1.0526315789473684,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 7.2412,
|
||
|
|
"mean_token_accuracy": 0.13482995182275773,
|
||
|
|
"num_tokens": 2237892.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.302912092208862,
|
||
|
|
"epoch": 1.0584795321637426,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 7.2105,
|
||
|
|
"mean_token_accuracy": 0.14221135154366493,
|
||
|
|
"num_tokens": 2250656.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.266082286834717,
|
||
|
|
"epoch": 1.064327485380117,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 7.2283,
|
||
|
|
"mean_token_accuracy": 0.13709186613559723,
|
||
|
|
"num_tokens": 2263685.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.261312961578369,
|
||
|
|
"epoch": 1.0701754385964912,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 7.1937,
|
||
|
|
"mean_token_accuracy": 0.13502099514007568,
|
||
|
|
"num_tokens": 2275413.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.305978202819825,
|
||
|
|
"epoch": 1.0760233918128654,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 7.1684,
|
||
|
|
"mean_token_accuracy": 0.1396795056760311,
|
||
|
|
"num_tokens": 2288165.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334664630889892,
|
||
|
|
"epoch": 1.0818713450292399,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 7.1615,
|
||
|
|
"mean_token_accuracy": 0.13400667384266854,
|
||
|
|
"num_tokens": 2300574.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.243153524398804,
|
||
|
|
"epoch": 1.087719298245614,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 7.1727,
|
||
|
|
"mean_token_accuracy": 0.13601783886551858,
|
||
|
|
"num_tokens": 2311631.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.27063479423523,
|
||
|
|
"epoch": 1.0935672514619883,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 7.1938,
|
||
|
|
"mean_token_accuracy": 0.13982510566711426,
|
||
|
|
"num_tokens": 2324312.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.349608087539673,
|
||
|
|
"epoch": 1.0994152046783625,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 7.2621,
|
||
|
|
"mean_token_accuracy": 0.133483674377203,
|
||
|
|
"num_tokens": 2337747.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.170055818557739,
|
||
|
|
"epoch": 1.1052631578947367,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 7.2157,
|
||
|
|
"mean_token_accuracy": 0.14102221578359603,
|
||
|
|
"num_tokens": 2349830.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.312947511672974,
|
||
|
|
"epoch": 1.1111111111111112,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 7.1527,
|
||
|
|
"mean_token_accuracy": 0.146473790705204,
|
||
|
|
"num_tokens": 2361825.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.233815908432007,
|
||
|
|
"epoch": 1.1169590643274854,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 7.084,
|
||
|
|
"mean_token_accuracy": 0.14439496994018555,
|
||
|
|
"num_tokens": 2373963.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.253248453140259,
|
||
|
|
"epoch": 1.1228070175438596,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 7.2355,
|
||
|
|
"mean_token_accuracy": 0.13487958535552025,
|
||
|
|
"num_tokens": 2386348.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.244376516342163,
|
||
|
|
"epoch": 1.128654970760234,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 7.1544,
|
||
|
|
"mean_token_accuracy": 0.13545818701386453,
|
||
|
|
"num_tokens": 2398338.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.206346225738526,
|
||
|
|
"epoch": 1.1345029239766082,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 7.1114,
|
||
|
|
"mean_token_accuracy": 0.14215215146541596,
|
||
|
|
"num_tokens": 2411855.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1879278182983395,
|
||
|
|
"epoch": 1.1403508771929824,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 7.19,
|
||
|
|
"mean_token_accuracy": 0.14433645009994506,
|
||
|
|
"num_tokens": 2424271.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.179539680480957,
|
||
|
|
"epoch": 1.1461988304093567,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 7.1922,
|
||
|
|
"mean_token_accuracy": 0.1384268395602703,
|
||
|
|
"num_tokens": 2436668.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.237603235244751,
|
||
|
|
"epoch": 1.1520467836257309,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 7.1159,
|
||
|
|
"mean_token_accuracy": 0.139103065431118,
|
||
|
|
"num_tokens": 2449451.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2184648513793945,
|
||
|
|
"epoch": 1.1578947368421053,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 7.2528,
|
||
|
|
"mean_token_accuracy": 0.1350694477558136,
|
||
|
|
"num_tokens": 2463107.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.333126020431519,
|
||
|
|
"epoch": 1.1637426900584795,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 7.1829,
|
||
|
|
"mean_token_accuracy": 0.1379982963204384,
|
||
|
|
"num_tokens": 2475443.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.138613986968994,
|
||
|
|
"epoch": 1.1695906432748537,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 7.101,
|
||
|
|
"mean_token_accuracy": 0.14087243527173995,
|
||
|
|
"num_tokens": 2486884.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1695906432748537,
|
||
|
|
"eval_entropy": 7.2734953070108865,
|
||
|
|
"eval_loss": 7.307929992675781,
|
||
|
|
"eval_mean_token_accuracy": 0.1282176822561298,
|
||
|
|
"eval_num_tokens": 2486884.0,
|
||
|
|
"eval_runtime": 2.2594,
|
||
|
|
"eval_samples_per_second": 1198.118,
|
||
|
|
"eval_steps_per_second": 150.041,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.200505685806275,
|
||
|
|
"epoch": 1.1754385964912282,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999996875147963,
|
||
|
|
"loss": 7.0712,
|
||
|
|
"mean_token_accuracy": 0.1509634733200073,
|
||
|
|
"num_tokens": 2499310.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.196539449691772,
|
||
|
|
"epoch": 1.1812865497076024,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999984180451436,
|
||
|
|
"loss": 7.1829,
|
||
|
|
"mean_token_accuracy": 0.1330198511481285,
|
||
|
|
"num_tokens": 2512230.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.228861284255982,
|
||
|
|
"epoch": 1.1871345029239766,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999961720662221,
|
||
|
|
"loss": 7.2334,
|
||
|
|
"mean_token_accuracy": 0.134628976136446,
|
||
|
|
"num_tokens": 2525255.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.139020681381226,
|
||
|
|
"epoch": 1.1929824561403508,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999929495877796,
|
||
|
|
"loss": 7.1263,
|
||
|
|
"mean_token_accuracy": 0.14136102497577668,
|
||
|
|
"num_tokens": 2537672.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.20037808418274,
|
||
|
|
"epoch": 1.198830409356725,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999887506238018,
|
||
|
|
"loss": 7.144,
|
||
|
|
"mean_token_accuracy": 0.13963264226913452,
|
||
|
|
"num_tokens": 2550371.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.154823732376099,
|
||
|
|
"epoch": 1.2046783625730995,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999835751925124,
|
||
|
|
"loss": 7.1484,
|
||
|
|
"mean_token_accuracy": 0.1348186582326889,
|
||
|
|
"num_tokens": 2563708.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.228437280654907,
|
||
|
|
"epoch": 1.2105263157894737,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999774233163734,
|
||
|
|
"loss": 7.1249,
|
||
|
|
"mean_token_accuracy": 0.13521802574396133,
|
||
|
|
"num_tokens": 2576529.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.180996465682983,
|
||
|
|
"epoch": 1.2163742690058479,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999702950220841,
|
||
|
|
"loss": 7.1407,
|
||
|
|
"mean_token_accuracy": 0.13425864800810813,
|
||
|
|
"num_tokens": 2588970.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.110421991348266,
|
||
|
|
"epoch": 1.2222222222222223,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999621903405819,
|
||
|
|
"loss": 7.0914,
|
||
|
|
"mean_token_accuracy": 0.1415217213332653,
|
||
|
|
"num_tokens": 2601134.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.224298429489136,
|
||
|
|
"epoch": 1.2280701754385965,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499953109307042,
|
||
|
|
"loss": 7.151,
|
||
|
|
"mean_token_accuracy": 0.1363483726978302,
|
||
|
|
"num_tokens": 2612670.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.112039279937744,
|
||
|
|
"epoch": 1.2339181286549707,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999430519608762,
|
||
|
|
"loss": 7.1142,
|
||
|
|
"mean_token_accuracy": 0.1467585191130638,
|
||
|
|
"num_tokens": 2625157.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.188581943511963,
|
||
|
|
"epoch": 1.239766081871345,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999320183457346,
|
||
|
|
"loss": 7.1156,
|
||
|
|
"mean_token_accuracy": 0.13688333332538605,
|
||
|
|
"num_tokens": 2638318.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.182509040832519,
|
||
|
|
"epoch": 1.2456140350877192,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999200085095035,
|
||
|
|
"loss": 7.0975,
|
||
|
|
"mean_token_accuracy": 0.14040600806474685,
|
||
|
|
"num_tokens": 2651024.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929991960525513,
|
||
|
|
"epoch": 1.2514619883040936,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999070225043068,
|
||
|
|
"loss": 7.0076,
|
||
|
|
"mean_token_accuracy": 0.1484173998236656,
|
||
|
|
"num_tokens": 2665568.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.320855331420899,
|
||
|
|
"epoch": 1.2573099415204678,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998930603865042,
|
||
|
|
"loss": 7.1486,
|
||
|
|
"mean_token_accuracy": 0.13886143118143082,
|
||
|
|
"num_tokens": 2678748.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.062246417999267,
|
||
|
|
"epoch": 1.263157894736842,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998781222166929,
|
||
|
|
"loss": 7.1028,
|
||
|
|
"mean_token_accuracy": 0.13795385062694548,
|
||
|
|
"num_tokens": 2690682.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.13513674736023,
|
||
|
|
"epoch": 1.2690058479532165,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998622080597052,
|
||
|
|
"loss": 7.1309,
|
||
|
|
"mean_token_accuracy": 0.13351953104138375,
|
||
|
|
"num_tokens": 2703077.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.121913051605224,
|
||
|
|
"epoch": 1.2748538011695907,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998453179846098,
|
||
|
|
"loss": 7.1073,
|
||
|
|
"mean_token_accuracy": 0.1391266979277134,
|
||
|
|
"num_tokens": 2714609.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.14010066986084,
|
||
|
|
"epoch": 1.280701754385965,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998274520647109,
|
||
|
|
"loss": 7.0566,
|
||
|
|
"mean_token_accuracy": 0.14392231404781342,
|
||
|
|
"num_tokens": 2726907.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.031551790237427,
|
||
|
|
"epoch": 1.286549707602339,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998086103775478,
|
||
|
|
"loss": 7.0621,
|
||
|
|
"mean_token_accuracy": 0.13830177783966063,
|
||
|
|
"num_tokens": 2739248.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.132552528381348,
|
||
|
|
"epoch": 1.2923976608187133,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997887930048947,
|
||
|
|
"loss": 7.014,
|
||
|
|
"mean_token_accuracy": 0.14461780115962028,
|
||
|
|
"num_tokens": 2753842.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9925319194793705,
|
||
|
|
"epoch": 1.2982456140350878,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997680000327607,
|
||
|
|
"loss": 7.1127,
|
||
|
|
"mean_token_accuracy": 0.13322388678789138,
|
||
|
|
"num_tokens": 2767249.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.155430698394776,
|
||
|
|
"epoch": 1.304093567251462,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004997462315513884,
|
||
|
|
"loss": 7.0855,
|
||
|
|
"mean_token_accuracy": 0.14028178676962852,
|
||
|
|
"num_tokens": 2779657.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046899271011353,
|
||
|
|
"epoch": 1.3099415204678362,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000499723487655255,
|
||
|
|
"loss": 6.9871,
|
||
|
|
"mean_token_accuracy": 0.14443906769156456,
|
||
|
|
"num_tokens": 2792760.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.05273756980896,
|
||
|
|
"epoch": 1.3157894736842106,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004996997684430703,
|
||
|
|
"loss": 7.0072,
|
||
|
|
"mean_token_accuracy": 0.14179261177778243,
|
||
|
|
"num_tokens": 2805277.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0507885932922365,
|
||
|
|
"epoch": 1.3216374269005848,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004996750740177775,
|
||
|
|
"loss": 7.1206,
|
||
|
|
"mean_token_accuracy": 0.13913794308900834,
|
||
|
|
"num_tokens": 2818341.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.174911212921143,
|
||
|
|
"epoch": 1.327485380116959,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996494044865521,
|
||
|
|
"loss": 7.0709,
|
||
|
|
"mean_token_accuracy": 0.14009531438350678,
|
||
|
|
"num_tokens": 2830199.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986618185043335,
|
||
|
|
"epoch": 1.3333333333333333,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004996227599608018,
|
||
|
|
"loss": 6.9673,
|
||
|
|
"mean_token_accuracy": 0.1467069461941719,
|
||
|
|
"num_tokens": 2842141.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.09279842376709,
|
||
|
|
"epoch": 1.3391812865497075,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995951405561658,
|
||
|
|
"loss": 7.0655,
|
||
|
|
"mean_token_accuracy": 0.13499290347099305,
|
||
|
|
"num_tokens": 2854929.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.056291580200195,
|
||
|
|
"epoch": 1.345029239766082,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995665463925142,
|
||
|
|
"loss": 7.0611,
|
||
|
|
"mean_token_accuracy": 0.14220297038555146,
|
||
|
|
"num_tokens": 2867034.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0605995655059814,
|
||
|
|
"epoch": 1.3508771929824561,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004995369775939478,
|
||
|
|
"loss": 6.9696,
|
||
|
|
"mean_token_accuracy": 0.14844031184911727,
|
||
|
|
"num_tokens": 2881254.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972619342803955,
|
||
|
|
"epoch": 1.3567251461988303,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004995064342887972,
|
||
|
|
"loss": 7.0747,
|
||
|
|
"mean_token_accuracy": 0.14061009883880615,
|
||
|
|
"num_tokens": 2894592.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0729388236999515,
|
||
|
|
"epoch": 1.3625730994152048,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004994749166096226,
|
||
|
|
"loss": 6.9918,
|
||
|
|
"mean_token_accuracy": 0.14350902065634727,
|
||
|
|
"num_tokens": 2907196.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046811580657959,
|
||
|
|
"epoch": 1.368421052631579,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004994424246932129,
|
||
|
|
"loss": 7.0659,
|
||
|
|
"mean_token_accuracy": 0.13506472632288932,
|
||
|
|
"num_tokens": 2920398.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.992996883392334,
|
||
|
|
"epoch": 1.3742690058479532,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004994089586805856,
|
||
|
|
"loss": 6.9787,
|
||
|
|
"mean_token_accuracy": 0.14449305981397628,
|
||
|
|
"num_tokens": 2932052.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.197365045547485,
|
||
|
|
"epoch": 1.3801169590643274,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004993745187169852,
|
||
|
|
"loss": 7.0659,
|
||
|
|
"mean_token_accuracy": 0.13700218349695206,
|
||
|
|
"num_tokens": 2943620.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.975704765319824,
|
||
|
|
"epoch": 1.3859649122807016,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499339104951884,
|
||
|
|
"loss": 7.0238,
|
||
|
|
"mean_token_accuracy": 0.15101929605007172,
|
||
|
|
"num_tokens": 2956159.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0983617305755615,
|
||
|
|
"epoch": 1.391812865497076,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00049930271753898,
|
||
|
|
"loss": 7.0003,
|
||
|
|
"mean_token_accuracy": 0.14037386998534201,
|
||
|
|
"num_tokens": 2967332.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.987351369857788,
|
||
|
|
"epoch": 1.3976608187134503,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004992653566361974,
|
||
|
|
"loss": 7.0158,
|
||
|
|
"mean_token_accuracy": 0.13745561614632607,
|
||
|
|
"num_tokens": 2980168.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.061203384399414,
|
||
|
|
"epoch": 1.4035087719298245,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004992270224056849,
|
||
|
|
"loss": 7.0847,
|
||
|
|
"mean_token_accuracy": 0.1388035885989666,
|
||
|
|
"num_tokens": 2993509.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.067679357528687,
|
||
|
|
"epoch": 1.409356725146199,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004991877150138162,
|
||
|
|
"loss": 7.0136,
|
||
|
|
"mean_token_accuracy": 0.13967382907867432,
|
||
|
|
"num_tokens": 3005827.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.979962635040283,
|
||
|
|
"epoch": 1.4152046783625731,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004991474346311879,
|
||
|
|
"loss": 6.985,
|
||
|
|
"mean_token_accuracy": 0.14625776931643486,
|
||
|
|
"num_tokens": 3018968.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0825128078460695,
|
||
|
|
"epoch": 1.4210526315789473,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004991061814326198,
|
||
|
|
"loss": 7.0176,
|
||
|
|
"mean_token_accuracy": 0.13643715381622315,
|
||
|
|
"num_tokens": 3031892.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.010417175292969,
|
||
|
|
"epoch": 1.4269005847953216,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0004990639555971539,
|
||
|
|
"loss": 6.9633,
|
||
|
|
"mean_token_accuracy": 0.14731772094964982,
|
||
|
|
"num_tokens": 3045994.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9524046897888185,
|
||
|
|
"epoch": 1.4327485380116958,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004990207573080533,
|
||
|
|
"loss": 6.9735,
|
||
|
|
"mean_token_accuracy": 0.14742070585489273,
|
||
|
|
"num_tokens": 3058304.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.96693868637085,
|
||
|
|
"epoch": 1.4385964912280702,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004989765867528014,
|
||
|
|
"loss": 6.9754,
|
||
|
|
"mean_token_accuracy": 0.1461901545524597,
|
||
|
|
"num_tokens": 3071102.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980545520782471,
|
||
|
|
"epoch": 1.4444444444444444,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004989314441231019,
|
||
|
|
"loss": 7.0051,
|
||
|
|
"mean_token_accuracy": 0.13849530145525932,
|
||
|
|
"num_tokens": 3084653.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.004353618621826,
|
||
|
|
"epoch": 1.4502923976608186,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000498885329614877,
|
||
|
|
"loss": 7.0107,
|
||
|
|
"mean_token_accuracy": 0.1477586805820465,
|
||
|
|
"num_tokens": 3097425.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01493558883667,
|
||
|
|
"epoch": 1.456140350877193,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004988382434282668,
|
||
|
|
"loss": 7.0225,
|
||
|
|
"mean_token_accuracy": 0.14672752395272254,
|
||
|
|
"num_tokens": 3111898.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046136426925659,
|
||
|
|
"epoch": 1.4619883040935673,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000498790185767629,
|
||
|
|
"loss": 6.9569,
|
||
|
|
"mean_token_accuracy": 0.14396907165646552,
|
||
|
|
"num_tokens": 3124271.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.026466512680054,
|
||
|
|
"epoch": 1.4678362573099415,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000498741156841537,
|
||
|
|
"loss": 7.06,
|
||
|
|
"mean_token_accuracy": 0.14034834802150725,
|
||
|
|
"num_tokens": 3136344.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.956720781326294,
|
||
|
|
"epoch": 1.4736842105263157,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00049869115686278,
|
||
|
|
"loss": 6.9586,
|
||
|
|
"mean_token_accuracy": 0.14445274844765663,
|
||
|
|
"num_tokens": 3148299.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0379047870635985,
|
||
|
|
"epoch": 1.47953216374269,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004986401860483615,
|
||
|
|
"loss": 7.0235,
|
||
|
|
"mean_token_accuracy": 0.13980134353041648,
|
||
|
|
"num_tokens": 3161537.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993751955032349,
|
||
|
|
"epoch": 1.4853801169590644,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004985882446194984,
|
||
|
|
"loss": 6.9608,
|
||
|
|
"mean_token_accuracy": 0.14578410163521766,
|
||
|
|
"num_tokens": 3173676.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.023461723327637,
|
||
|
|
"epoch": 1.4912280701754386,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 0.0004985353328016204,
|
||
|
|
"loss": 6.9302,
|
||
|
|
"mean_token_accuracy": 0.1545111432671547,
|
||
|
|
"num_tokens": 3186542.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9487221240997314,
|
||
|
|
"epoch": 1.4970760233918128,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004984814508243685,
|
||
|
|
"loss": 6.9651,
|
||
|
|
"mean_token_accuracy": 0.14461245387792587,
|
||
|
|
"num_tokens": 3197867.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.958335924148559,
|
||
|
|
"epoch": 1.5029239766081872,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004984265989215942,
|
||
|
|
"loss": 6.9275,
|
||
|
|
"mean_token_accuracy": 0.1436944842338562,
|
||
|
|
"num_tokens": 3209671.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9353508949279785,
|
||
|
|
"epoch": 1.5087719298245614,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004983707773313589,
|
||
|
|
"loss": 6.9134,
|
||
|
|
"mean_token_accuracy": 0.1483129307627678,
|
||
|
|
"num_tokens": 3220707.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889391088485718,
|
||
|
|
"epoch": 1.5146198830409356,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004983139862959322,
|
||
|
|
"loss": 6.8839,
|
||
|
|
"mean_token_accuracy": 0.15239101126790047,
|
||
|
|
"num_tokens": 3235122.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986405992507935,
|
||
|
|
"epoch": 1.52046783625731,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004982562260617912,
|
||
|
|
"loss": 6.8837,
|
||
|
|
"mean_token_accuracy": 0.14060088545083999,
|
||
|
|
"num_tokens": 3246833.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.970462274551392,
|
||
|
|
"epoch": 1.526315789473684,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004981974968796197,
|
||
|
|
"loss": 6.9859,
|
||
|
|
"mean_token_accuracy": 0.1401909612119198,
|
||
|
|
"num_tokens": 3260493.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918372440338135,
|
||
|
|
"epoch": 1.5321637426900585,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004981377990043064,
|
||
|
|
"loss": 6.9112,
|
||
|
|
"mean_token_accuracy": 0.14301369413733483,
|
||
|
|
"num_tokens": 3272445.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.954419040679932,
|
||
|
|
"epoch": 1.5380116959064327,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004980771326949442,
|
||
|
|
"loss": 6.9368,
|
||
|
|
"mean_token_accuracy": 0.1427830085158348,
|
||
|
|
"num_tokens": 3284360.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962142419815064,
|
||
|
|
"epoch": 1.543859649122807,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004980154982148296,
|
||
|
|
"loss": 6.9344,
|
||
|
|
"mean_token_accuracy": 0.1421595737338066,
|
||
|
|
"num_tokens": 3296841.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.923092269897461,
|
||
|
|
"epoch": 1.5497076023391814,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004979528958314604,
|
||
|
|
"loss": 6.9269,
|
||
|
|
"mean_token_accuracy": 0.14047582894563676,
|
||
|
|
"num_tokens": 3309393.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.016109418869019,
|
||
|
|
"epoch": 1.5555555555555556,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004978893258165354,
|
||
|
|
"loss": 7.0003,
|
||
|
|
"mean_token_accuracy": 0.14029522687196733,
|
||
|
|
"num_tokens": 3322094.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.91007022857666,
|
||
|
|
"epoch": 1.5614035087719298,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004978247884459532,
|
||
|
|
"loss": 6.9053,
|
||
|
|
"mean_token_accuracy": 0.14726511985063553,
|
||
|
|
"num_tokens": 3334468.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.969208383560181,
|
||
|
|
"epoch": 1.5672514619883042,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004977592839998105,
|
||
|
|
"loss": 6.895,
|
||
|
|
"mean_token_accuracy": 0.14278344213962554,
|
||
|
|
"num_tokens": 3346367.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.812116289138794,
|
||
|
|
"epoch": 1.5730994152046782,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004976928127624013,
|
||
|
|
"loss": 6.8944,
|
||
|
|
"mean_token_accuracy": 0.14796961098909378,
|
||
|
|
"num_tokens": 3357463.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.954991054534912,
|
||
|
|
"epoch": 1.5789473684210527,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004976253750222157,
|
||
|
|
"loss": 6.8847,
|
||
|
|
"mean_token_accuracy": 0.14616121351718903,
|
||
|
|
"num_tokens": 3369465.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.887133073806763,
|
||
|
|
"epoch": 1.5847953216374269,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004975569710719382,
|
||
|
|
"loss": 6.9901,
|
||
|
|
"mean_token_accuracy": 0.1367621600627899,
|
||
|
|
"num_tokens": 3382859.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.019903707504272,
|
||
|
|
"epoch": 1.590643274853801,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004974876012084468,
|
||
|
|
"loss": 6.9454,
|
||
|
|
"mean_token_accuracy": 0.14300204291939736,
|
||
|
|
"num_tokens": 3395431.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.903563165664673,
|
||
|
|
"epoch": 1.5964912280701755,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004974172657328116,
|
||
|
|
"loss": 6.8525,
|
||
|
|
"mean_token_accuracy": 0.14235405698418618,
|
||
|
|
"num_tokens": 3408388.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.882439708709716,
|
||
|
|
"epoch": 1.6023391812865497,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004973459649502939,
|
||
|
|
"loss": 6.8468,
|
||
|
|
"mean_token_accuracy": 0.14951836317777634,
|
||
|
|
"num_tokens": 3421275.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905644369125366,
|
||
|
|
"epoch": 1.608187134502924,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004972736991703439,
|
||
|
|
"loss": 6.9167,
|
||
|
|
"mean_token_accuracy": 0.14661416113376619,
|
||
|
|
"num_tokens": 3433537.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.914070510864258,
|
||
|
|
"epoch": 1.6140350877192984,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004972004687066005,
|
||
|
|
"loss": 6.8715,
|
||
|
|
"mean_token_accuracy": 0.14761748984456063,
|
||
|
|
"num_tokens": 3445167.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.824334239959716,
|
||
|
|
"epoch": 1.6198830409356724,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000497126273876889,
|
||
|
|
"loss": 6.8875,
|
||
|
|
"mean_token_accuracy": 0.15272206366062163,
|
||
|
|
"num_tokens": 3458529.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.895606422424317,
|
||
|
|
"epoch": 1.6257309941520468,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004970511150032205,
|
||
|
|
"loss": 6.8778,
|
||
|
|
"mean_token_accuracy": 0.1458844795823097,
|
||
|
|
"num_tokens": 3470315.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.840101718902588,
|
||
|
|
"epoch": 1.631578947368421,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004969749924117896,
|
||
|
|
"loss": 6.785,
|
||
|
|
"mean_token_accuracy": 0.14661094844341277,
|
||
|
|
"num_tokens": 3481899.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.906247091293335,
|
||
|
|
"epoch": 1.6374269005847952,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004968979064329741,
|
||
|
|
"loss": 6.925,
|
||
|
|
"mean_token_accuracy": 0.14958905652165413,
|
||
|
|
"num_tokens": 3494076.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980356884002686,
|
||
|
|
"epoch": 1.6432748538011697,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004968198574013323,
|
||
|
|
"loss": 6.9196,
|
||
|
|
"mean_token_accuracy": 0.1379689686000347,
|
||
|
|
"num_tokens": 3507670.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.925516939163208,
|
||
|
|
"epoch": 1.6491228070175439,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000496740845655603,
|
||
|
|
"loss": 6.8189,
|
||
|
|
"mean_token_accuracy": 0.14898837506771087,
|
||
|
|
"num_tokens": 3519704.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878632068634033,
|
||
|
|
"epoch": 1.654970760233918,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004966608715387029,
|
||
|
|
"loss": 6.8935,
|
||
|
|
"mean_token_accuracy": 0.14565708339214326,
|
||
|
|
"num_tokens": 3531665.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.823861360549927,
|
||
|
|
"epoch": 1.6608187134502925,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004965799353977248,
|
||
|
|
"loss": 6.9008,
|
||
|
|
"mean_token_accuracy": 0.15192211121320726,
|
||
|
|
"num_tokens": 3543876.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.818322944641113,
|
||
|
|
"epoch": 1.6666666666666665,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004964980375839379,
|
||
|
|
"loss": 6.8106,
|
||
|
|
"mean_token_accuracy": 0.1509052187204361,
|
||
|
|
"num_tokens": 3556517.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.901790475845337,
|
||
|
|
"epoch": 1.672514619883041,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004964151784527844,
|
||
|
|
"loss": 6.8247,
|
||
|
|
"mean_token_accuracy": 0.15195192098617555,
|
||
|
|
"num_tokens": 3569378.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8896238803863525,
|
||
|
|
"epoch": 1.6783625730994152,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000496331358363879,
|
||
|
|
"loss": 6.8214,
|
||
|
|
"mean_token_accuracy": 0.14606776535511018,
|
||
|
|
"num_tokens": 3581684.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813811302185059,
|
||
|
|
"epoch": 1.6842105263157894,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004962465776810066,
|
||
|
|
"loss": 6.7664,
|
||
|
|
"mean_token_accuracy": 0.16046139299869538,
|
||
|
|
"num_tokens": 3594961.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.862590074539185,
|
||
|
|
"epoch": 1.6900584795321638,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004961608367721217,
|
||
|
|
"loss": 6.8377,
|
||
|
|
"mean_token_accuracy": 0.14302278757095338,
|
||
|
|
"num_tokens": 3607197.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.810559988021851,
|
||
|
|
"epoch": 1.695906432748538,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004960741360093459,
|
||
|
|
"loss": 6.8444,
|
||
|
|
"mean_token_accuracy": 0.14837275072932243,
|
||
|
|
"num_tokens": 3618728.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915595960617066,
|
||
|
|
"epoch": 1.7017543859649122,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004959864757689669,
|
||
|
|
"loss": 6.959,
|
||
|
|
"mean_token_accuracy": 0.1320843756198883,
|
||
|
|
"num_tokens": 3630872.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.886625003814697,
|
||
|
|
"epoch": 1.7076023391812867,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004958978564314361,
|
||
|
|
"loss": 6.8478,
|
||
|
|
"mean_token_accuracy": 0.14627774357795714,
|
||
|
|
"num_tokens": 3642657.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878891372680664,
|
||
|
|
"epoch": 1.7134502923976607,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000495808278381368,
|
||
|
|
"loss": 6.8575,
|
||
|
|
"mean_token_accuracy": 0.14539648741483688,
|
||
|
|
"num_tokens": 3654505.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732045078277588,
|
||
|
|
"epoch": 1.719298245614035,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004957177420075377,
|
||
|
|
"loss": 6.7578,
|
||
|
|
"mean_token_accuracy": 0.15864465534687042,
|
||
|
|
"num_tokens": 3668554.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8867645263671875,
|
||
|
|
"epoch": 1.7251461988304093,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004956262477028797,
|
||
|
|
"loss": 6.9037,
|
||
|
|
"mean_token_accuracy": 0.14351411610841752,
|
||
|
|
"num_tokens": 3681448.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.818768930435181,
|
||
|
|
"epoch": 1.7309941520467835,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004955337958644857,
|
||
|
|
"loss": 6.8424,
|
||
|
|
"mean_token_accuracy": 0.1386769823729992,
|
||
|
|
"num_tokens": 3693677.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844368124008179,
|
||
|
|
"epoch": 1.736842105263158,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004954403868936032,
|
||
|
|
"loss": 6.8392,
|
||
|
|
"mean_token_accuracy": 0.15232345163822175,
|
||
|
|
"num_tokens": 3706204.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.894862413406372,
|
||
|
|
"epoch": 1.7426900584795322,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000495346021195634,
|
||
|
|
"loss": 6.8016,
|
||
|
|
"mean_token_accuracy": 0.15067129582166672,
|
||
|
|
"num_tokens": 3718255.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.843251037597656,
|
||
|
|
"epoch": 1.7485380116959064,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004952506991801319,
|
||
|
|
"loss": 6.8052,
|
||
|
|
"mean_token_accuracy": 0.15079464316368102,
|
||
|
|
"num_tokens": 3730623.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.819522666931152,
|
||
|
|
"epoch": 1.7543859649122808,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004951544212608015,
|
||
|
|
"loss": 6.8522,
|
||
|
|
"mean_token_accuracy": 0.14364330172538758,
|
||
|
|
"num_tokens": 3743636.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.7543859649122808,
|
||
|
|
"eval_entropy": 6.779693004304328,
|
||
|
|
"eval_loss": 6.981348991394043,
|
||
|
|
"eval_mean_token_accuracy": 0.1366379621155714,
|
||
|
|
"eval_num_tokens": 3743636.0,
|
||
|
|
"eval_runtime": 2.2598,
|
||
|
|
"eval_samples_per_second": 1197.882,
|
||
|
|
"eval_steps_per_second": 150.012,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8890303611755375,
|
||
|
|
"epoch": 1.7602339181286548,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004950571878554956,
|
||
|
|
"loss": 6.8984,
|
||
|
|
"mean_token_accuracy": 0.13721396028995514,
|
||
|
|
"num_tokens": 3755608.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.953851509094238,
|
||
|
|
"epoch": 1.7660818713450293,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004949589993862143,
|
||
|
|
"loss": 6.7887,
|
||
|
|
"mean_token_accuracy": 0.142920982837677,
|
||
|
|
"num_tokens": 3768208.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.759266138076782,
|
||
|
|
"epoch": 1.7719298245614035,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004948598562791025,
|
||
|
|
"loss": 6.8051,
|
||
|
|
"mean_token_accuracy": 0.14665916711091995,
|
||
|
|
"num_tokens": 3780550.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7835393905639645,
|
||
|
|
"epoch": 1.7777777777777777,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004947597589644484,
|
||
|
|
"loss": 6.8117,
|
||
|
|
"mean_token_accuracy": 0.14565980136394502,
|
||
|
|
"num_tokens": 3792417.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885556364059449,
|
||
|
|
"epoch": 1.7836257309941521,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004946587078766818,
|
||
|
|
"loss": 6.7896,
|
||
|
|
"mean_token_accuracy": 0.1500367507338524,
|
||
|
|
"num_tokens": 3803887.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8060931205749515,
|
||
|
|
"epoch": 1.7894736842105263,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004945567034543712,
|
||
|
|
"loss": 6.9281,
|
||
|
|
"mean_token_accuracy": 0.13749998882412912,
|
||
|
|
"num_tokens": 3816534.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.865039396286011,
|
||
|
|
"epoch": 1.7953216374269005,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004944537461402234,
|
||
|
|
"loss": 6.8765,
|
||
|
|
"mean_token_accuracy": 0.1459302008152008,
|
||
|
|
"num_tokens": 3827790.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.883976745605469,
|
||
|
|
"epoch": 1.801169590643275,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004943498363810807,
|
||
|
|
"loss": 6.8079,
|
||
|
|
"mean_token_accuracy": 0.15097410529851912,
|
||
|
|
"num_tokens": 3839800.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.63709602355957,
|
||
|
|
"epoch": 1.807017543859649,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004942449746279184,
|
||
|
|
"loss": 6.7519,
|
||
|
|
"mean_token_accuracy": 0.1563785195350647,
|
||
|
|
"num_tokens": 3852621.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.882471227645874,
|
||
|
|
"epoch": 1.8128654970760234,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004941391613358444,
|
||
|
|
"loss": 6.8109,
|
||
|
|
"mean_token_accuracy": 0.14244120046496392,
|
||
|
|
"num_tokens": 3864184.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8589356422424315,
|
||
|
|
"epoch": 1.8187134502923976,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000494032396964096,
|
||
|
|
"loss": 6.792,
|
||
|
|
"mean_token_accuracy": 0.14410900175571442,
|
||
|
|
"num_tokens": 3876750.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.847626399993897,
|
||
|
|
"epoch": 1.8245614035087718,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000493924681976038,
|
||
|
|
"loss": 6.8288,
|
||
|
|
"mean_token_accuracy": 0.15225238502025604,
|
||
|
|
"num_tokens": 3888788.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.72038631439209,
|
||
|
|
"epoch": 1.8304093567251463,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004938160168391614,
|
||
|
|
"loss": 6.8813,
|
||
|
|
"mean_token_accuracy": 0.14341572672128677,
|
||
|
|
"num_tokens": 3901816.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.849244832992554,
|
||
|
|
"epoch": 1.8362573099415205,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004937064020250804,
|
||
|
|
"loss": 6.778,
|
||
|
|
"mean_token_accuracy": 0.1504952922463417,
|
||
|
|
"num_tokens": 3913127.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784156847000122,
|
||
|
|
"epoch": 1.8421052631578947,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004935958380095316,
|
||
|
|
"loss": 6.7918,
|
||
|
|
"mean_token_accuracy": 0.14795291423797607,
|
||
|
|
"num_tokens": 3924878.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84570426940918,
|
||
|
|
"epoch": 1.8479532163742691,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004934843252723702,
|
||
|
|
"loss": 6.866,
|
||
|
|
"mean_token_accuracy": 0.1483178362250328,
|
||
|
|
"num_tokens": 3938334.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.788474178314209,
|
||
|
|
"epoch": 1.8538011695906431,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00049337186429757,
|
||
|
|
"loss": 6.831,
|
||
|
|
"mean_token_accuracy": 0.14488170817494392,
|
||
|
|
"num_tokens": 3949733.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938077831268311,
|
||
|
|
"epoch": 1.8596491228070176,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004932584555732192,
|
||
|
|
"loss": 6.8556,
|
||
|
|
"mean_token_accuracy": 0.14948586374521255,
|
||
|
|
"num_tokens": 3963109.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8389668464660645,
|
||
|
|
"epoch": 1.8654970760233918,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004931440995915203,
|
||
|
|
"loss": 6.8291,
|
||
|
|
"mean_token_accuracy": 0.14816600680351258,
|
||
|
|
"num_tokens": 3975477.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.767072439193726,
|
||
|
|
"epoch": 1.871345029239766,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000493028796848786,
|
||
|
|
"loss": 6.7911,
|
||
|
|
"mean_token_accuracy": 0.15247763097286224,
|
||
|
|
"num_tokens": 3987757.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83989143371582,
|
||
|
|
"epoch": 1.8771929824561404,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004929125478454389,
|
||
|
|
"loss": 6.6687,
|
||
|
|
"mean_token_accuracy": 0.1549072727560997,
|
||
|
|
"num_tokens": 3998807.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.672812414169312,
|
||
|
|
"epoch": 1.8830409356725146,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004927953530860077,
|
||
|
|
"loss": 6.7461,
|
||
|
|
"mean_token_accuracy": 0.14968679696321488,
|
||
|
|
"num_tokens": 4010320.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.898769187927246,
|
||
|
|
"epoch": 1.8888888888888888,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004926772130791261,
|
||
|
|
"loss": 6.8883,
|
||
|
|
"mean_token_accuracy": 0.13913559541106224,
|
||
|
|
"num_tokens": 4023432.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.751414585113525,
|
||
|
|
"epoch": 1.8947368421052633,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004925581283375303,
|
||
|
|
"loss": 6.8639,
|
||
|
|
"mean_token_accuracy": 0.1415519244968891,
|
||
|
|
"num_tokens": 4036282.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.809280681610107,
|
||
|
|
"epoch": 1.9005847953216373,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004924380993780566,
|
||
|
|
"loss": 6.7309,
|
||
|
|
"mean_token_accuracy": 0.15376169085502625,
|
||
|
|
"num_tokens": 4048164.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80910587310791,
|
||
|
|
"epoch": 1.9064327485380117,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004923171267216392,
|
||
|
|
"loss": 6.7784,
|
||
|
|
"mean_token_accuracy": 0.1471938133239746,
|
||
|
|
"num_tokens": 4059287.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755839729309082,
|
||
|
|
"epoch": 1.912280701754386,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004921952108933083,
|
||
|
|
"loss": 6.7682,
|
||
|
|
"mean_token_accuracy": 0.1458806127309799,
|
||
|
|
"num_tokens": 4071976.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.799160289764404,
|
||
|
|
"epoch": 1.9181286549707601,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004920723524221871,
|
||
|
|
"loss": 6.7869,
|
||
|
|
"mean_token_accuracy": 0.1511995568871498,
|
||
|
|
"num_tokens": 4085116.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.864682531356811,
|
||
|
|
"epoch": 1.9239766081871346,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004919485518414902,
|
||
|
|
"loss": 6.7874,
|
||
|
|
"mean_token_accuracy": 0.14133294969797133,
|
||
|
|
"num_tokens": 4096778.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6813818454742435,
|
||
|
|
"epoch": 1.9298245614035088,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004918238096885213,
|
||
|
|
"loss": 6.7158,
|
||
|
|
"mean_token_accuracy": 0.14623456373810767,
|
||
|
|
"num_tokens": 4109490.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.780474519729614,
|
||
|
|
"epoch": 1.935672514619883,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00049169812650467,
|
||
|
|
"loss": 6.7485,
|
||
|
|
"mean_token_accuracy": 0.14962287545204161,
|
||
|
|
"num_tokens": 4122832.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.894753551483154,
|
||
|
|
"epoch": 1.9415204678362574,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004915715028354102,
|
||
|
|
"loss": 6.7827,
|
||
|
|
"mean_token_accuracy": 0.1430698148906231,
|
||
|
|
"num_tokens": 4134585.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.750669002532959,
|
||
|
|
"epoch": 1.9473684210526314,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004914439392302981,
|
||
|
|
"loss": 6.719,
|
||
|
|
"mean_token_accuracy": 0.14639999717473984,
|
||
|
|
"num_tokens": 4145909.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.719008111953736,
|
||
|
|
"epoch": 1.9532163742690059,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004913154362429686,
|
||
|
|
"loss": 6.6346,
|
||
|
|
"mean_token_accuracy": 0.16258849799633027,
|
||
|
|
"num_tokens": 4157360.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7393451690673825,
|
||
|
|
"epoch": 1.95906432748538,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004911859944311341,
|
||
|
|
"loss": 6.8206,
|
||
|
|
"mean_token_accuracy": 0.1425321228802204,
|
||
|
|
"num_tokens": 4169789.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.851357126235962,
|
||
|
|
"epoch": 1.9649122807017543,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004910556143565812,
|
||
|
|
"loss": 6.8197,
|
||
|
|
"mean_token_accuracy": 0.1424817383289337,
|
||
|
|
"num_tokens": 4183131.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.74174394607544,
|
||
|
|
"epoch": 1.9707602339181287,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004909242965851688,
|
||
|
|
"loss": 6.7792,
|
||
|
|
"mean_token_accuracy": 0.14871800541877747,
|
||
|
|
"num_tokens": 4194865.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.816132688522339,
|
||
|
|
"epoch": 1.976608187134503,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004907920416868253,
|
||
|
|
"loss": 6.7806,
|
||
|
|
"mean_token_accuracy": 0.14722342789173126,
|
||
|
|
"num_tokens": 4207406.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.749181652069092,
|
||
|
|
"epoch": 1.9824561403508771,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0004906588502355467,
|
||
|
|
"loss": 6.7401,
|
||
|
|
"mean_token_accuracy": 0.150900137424469,
|
||
|
|
"num_tokens": 4221623.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.691790914535522,
|
||
|
|
"epoch": 1.9883040935672516,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004905247228093933,
|
||
|
|
"loss": 6.6811,
|
||
|
|
"mean_token_accuracy": 0.16417528837919235,
|
||
|
|
"num_tokens": 4233699.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.683874034881592,
|
||
|
|
"epoch": 1.9941520467836256,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004903896599904878,
|
||
|
|
"loss": 6.6816,
|
||
|
|
"mean_token_accuracy": 0.1530413195490837,
|
||
|
|
"num_tokens": 4247669.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.822535991668701,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004902536623650125,
|
||
|
|
"loss": 6.7422,
|
||
|
|
"mean_token_accuracy": 0.14640743434429168,
|
||
|
|
"num_tokens": 4258968.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7504712581634525,
|
||
|
|
"epoch": 2.0058479532163744,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004901167305232068,
|
||
|
|
"loss": 6.451,
|
||
|
|
"mean_token_accuracy": 0.15497071892023087,
|
||
|
|
"num_tokens": 4270684.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.666883039474487,
|
||
|
|
"epoch": 2.0116959064327484,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004899788650593648,
|
||
|
|
"loss": 6.3777,
|
||
|
|
"mean_token_accuracy": 0.16033632308244705,
|
||
|
|
"num_tokens": 4282567.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.681175184249878,
|
||
|
|
"epoch": 2.017543859649123,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004898400665718325,
|
||
|
|
"loss": 6.4128,
|
||
|
|
"mean_token_accuracy": 0.15490297377109527,
|
||
|
|
"num_tokens": 4294803.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649669218063354,
|
||
|
|
"epoch": 2.023391812865497,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004897003356630052,
|
||
|
|
"loss": 6.407,
|
||
|
|
"mean_token_accuracy": 0.15438900738954545,
|
||
|
|
"num_tokens": 4305898.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.627393817901611,
|
||
|
|
"epoch": 2.0292397660818713,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004895596729393252,
|
||
|
|
"loss": 6.3381,
|
||
|
|
"mean_token_accuracy": 0.16169263646006585,
|
||
|
|
"num_tokens": 4317985.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.55052924156189,
|
||
|
|
"epoch": 2.0350877192982457,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004894180790112787,
|
||
|
|
"loss": 6.4047,
|
||
|
|
"mean_token_accuracy": 0.15468447357416154,
|
||
|
|
"num_tokens": 4330482.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.670533227920532,
|
||
|
|
"epoch": 2.0409356725146197,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004892755544933934,
|
||
|
|
"loss": 6.4516,
|
||
|
|
"mean_token_accuracy": 0.1473391428589821,
|
||
|
|
"num_tokens": 4342782.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6448784351348875,
|
||
|
|
"epoch": 2.046783625730994,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004891321000042361,
|
||
|
|
"loss": 6.4742,
|
||
|
|
"mean_token_accuracy": 0.1497931510210037,
|
||
|
|
"num_tokens": 4356204.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5630717277526855,
|
||
|
|
"epoch": 2.0526315789473686,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004889877161664096,
|
||
|
|
"loss": 6.3678,
|
||
|
|
"mean_token_accuracy": 0.15779546350240709,
|
||
|
|
"num_tokens": 4370003.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.662812185287476,
|
||
|
|
"epoch": 2.0584795321637426,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00048884240360655,
|
||
|
|
"loss": 6.4325,
|
||
|
|
"mean_token_accuracy": 0.15411946624517442,
|
||
|
|
"num_tokens": 4381972.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.597726058959961,
|
||
|
|
"epoch": 2.064327485380117,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004886961629553242,
|
||
|
|
"loss": 6.3493,
|
||
|
|
"mean_token_accuracy": 0.16212794035673142,
|
||
|
|
"num_tokens": 4394033.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616933298110962,
|
||
|
|
"epoch": 2.0701754385964914,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004885489948474272,
|
||
|
|
"loss": 6.4448,
|
||
|
|
"mean_token_accuracy": 0.1546820417046547,
|
||
|
|
"num_tokens": 4406799.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.607996129989624,
|
||
|
|
"epoch": 2.0760233918128654,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004884008999215792,
|
||
|
|
"loss": 6.4547,
|
||
|
|
"mean_token_accuracy": 0.15387098342180253,
|
||
|
|
"num_tokens": 4420182.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.603867530822754,
|
||
|
|
"epoch": 2.08187134502924,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004882518788205225,
|
||
|
|
"loss": 6.409,
|
||
|
|
"mean_token_accuracy": 0.157459656894207,
|
||
|
|
"num_tokens": 4432014.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.684940528869629,
|
||
|
|
"epoch": 2.087719298245614,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004881019321910198,
|
||
|
|
"loss": 6.4221,
|
||
|
|
"mean_token_accuracy": 0.1587100252509117,
|
||
|
|
"num_tokens": 4444755.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580925369262696,
|
||
|
|
"epoch": 2.0935672514619883,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00048795106068384985,
|
||
|
|
"loss": 6.49,
|
||
|
|
"mean_token_accuracy": 0.15643275231122972,
|
||
|
|
"num_tokens": 4456390.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.632500457763672,
|
||
|
|
"epoch": 2.0994152046783627,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000487799264953806,
|
||
|
|
"loss": 6.3976,
|
||
|
|
"mean_token_accuracy": 0.15923093557357787,
|
||
|
|
"num_tokens": 4468567.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.583936357498169,
|
||
|
|
"epoch": 2.1052631578947367,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004876465456596926,
|
||
|
|
"loss": 6.3786,
|
||
|
|
"mean_token_accuracy": 0.1647219628095627,
|
||
|
|
"num_tokens": 4479553.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563723468780518,
|
||
|
|
"epoch": 2.111111111111111,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004874929034643223,
|
||
|
|
"loss": 6.3877,
|
||
|
|
"mean_token_accuracy": 0.16774867177009584,
|
||
|
|
"num_tokens": 4491505.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.60309476852417,
|
||
|
|
"epoch": 2.116959064327485,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004873383390345132,
|
||
|
|
"loss": 6.4582,
|
||
|
|
"mean_token_accuracy": 0.15345733910799025,
|
||
|
|
"num_tokens": 4504896.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.59870662689209,
|
||
|
|
"epoch": 2.1228070175438596,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00048718285304108613,
|
||
|
|
"loss": 6.4519,
|
||
|
|
"mean_token_accuracy": 0.15231310576200485,
|
||
|
|
"num_tokens": 4516319.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.596411275863647,
|
||
|
|
"epoch": 2.128654970760234,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00048702644615886137,
|
||
|
|
"loss": 6.4625,
|
||
|
|
"mean_token_accuracy": 0.15045736506581306,
|
||
|
|
"num_tokens": 4529132.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.60670485496521,
|
||
|
|
"epoch": 2.134502923976608,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00048686911906665597,
|
||
|
|
"loss": 6.4331,
|
||
|
|
"mean_token_accuracy": 0.15620148032903672,
|
||
|
|
"num_tokens": 4541080.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609990072250366,
|
||
|
|
"epoch": 2.1403508771929824,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00048671087244728093,
|
||
|
|
"loss": 6.4433,
|
||
|
|
"mean_token_accuracy": 0.15574345663189887,
|
||
|
|
"num_tokens": 4553442.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488572883605957,
|
||
|
|
"epoch": 2.146198830409357,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00048655170698753774,
|
||
|
|
"loss": 6.3716,
|
||
|
|
"mean_token_accuracy": 0.16827541142702102,
|
||
|
|
"num_tokens": 4565617.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653444433212281,
|
||
|
|
"epoch": 2.152046783625731,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000486391623378216,
|
||
|
|
"loss": 6.4612,
|
||
|
|
"mean_token_accuracy": 0.15232127755880356,
|
||
|
|
"num_tokens": 4577418.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565980768203735,
|
||
|
|
"epoch": 2.1578947368421053,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004862306223140901,
|
||
|
|
"loss": 6.3903,
|
||
|
|
"mean_token_accuracy": 0.1561780571937561,
|
||
|
|
"num_tokens": 4589763.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.636228275299072,
|
||
|
|
"epoch": 2.1637426900584797,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00048606870449391604,
|
||
|
|
"loss": 6.4788,
|
||
|
|
"mean_token_accuracy": 0.15752616673707961,
|
||
|
|
"num_tokens": 4602522.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.611583805084228,
|
||
|
|
"epoch": 2.1695906432748537,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00048590587062042907,
|
||
|
|
"loss": 6.4392,
|
||
|
|
"mean_token_accuracy": 0.1577591434121132,
|
||
|
|
"num_tokens": 4614680.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577220010757446,
|
||
|
|
"epoch": 2.175438596491228,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00048574212140033965,
|
||
|
|
"loss": 6.4673,
|
||
|
|
"mean_token_accuracy": 0.15203312337398528,
|
||
|
|
"num_tokens": 4628166.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.584661531448364,
|
||
|
|
"epoch": 2.181286549707602,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004855774575443311,
|
||
|
|
"loss": 6.4982,
|
||
|
|
"mean_token_accuracy": 0.15774697214365005,
|
||
|
|
"num_tokens": 4640200.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594009494781494,
|
||
|
|
"epoch": 2.1871345029239766,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00048541187976705645,
|
||
|
|
"loss": 6.4224,
|
||
|
|
"mean_token_accuracy": 0.15282342135906218,
|
||
|
|
"num_tokens": 4652968.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.572527456283569,
|
||
|
|
"epoch": 2.192982456140351,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00048524538878713517,
|
||
|
|
"loss": 6.4243,
|
||
|
|
"mean_token_accuracy": 0.15148500800132753,
|
||
|
|
"num_tokens": 4665741.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.576790428161621,
|
||
|
|
"epoch": 2.198830409356725,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00048507798532715005,
|
||
|
|
"loss": 6.4428,
|
||
|
|
"mean_token_accuracy": 0.15464532226324082,
|
||
|
|
"num_tokens": 4680074.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.599213886260986,
|
||
|
|
"epoch": 2.2046783625730995,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00048490967011364394,
|
||
|
|
"loss": 6.4596,
|
||
|
|
"mean_token_accuracy": 0.1567436784505844,
|
||
|
|
"num_tokens": 4692340.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552012872695923,
|
||
|
|
"epoch": 2.2105263157894735,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004847404438771172,
|
||
|
|
"loss": 6.4523,
|
||
|
|
"mean_token_accuracy": 0.15730515271425247,
|
||
|
|
"num_tokens": 4704470.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65509181022644,
|
||
|
|
"epoch": 2.216374269005848,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004845703073520236,
|
||
|
|
"loss": 6.4974,
|
||
|
|
"mean_token_accuracy": 0.14814944118261336,
|
||
|
|
"num_tokens": 4716253.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.687125492095947,
|
||
|
|
"epoch": 2.2222222222222223,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00048439926127676796,
|
||
|
|
"loss": 6.6045,
|
||
|
|
"mean_token_accuracy": 0.14494609385728835,
|
||
|
|
"num_tokens": 4730083.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.600670337677002,
|
||
|
|
"epoch": 2.2280701754385963,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00048422730639370256,
|
||
|
|
"loss": 6.3673,
|
||
|
|
"mean_token_accuracy": 0.16275593489408494,
|
||
|
|
"num_tokens": 4742770.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.529613828659057,
|
||
|
|
"epoch": 2.2339181286549707,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004840544434491238,
|
||
|
|
"loss": 6.4972,
|
||
|
|
"mean_token_accuracy": 0.15610447973012925,
|
||
|
|
"num_tokens": 4754299.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.591367197036743,
|
||
|
|
"epoch": 2.239766081871345,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00048388067319326937,
|
||
|
|
"loss": 6.4563,
|
||
|
|
"mean_token_accuracy": 0.15082078278064728,
|
||
|
|
"num_tokens": 4766964.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5736147403717045,
|
||
|
|
"epoch": 2.245614035087719,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00048370599638031464,
|
||
|
|
"loss": 6.4893,
|
||
|
|
"mean_token_accuracy": 0.152706515789032,
|
||
|
|
"num_tokens": 4779921.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.644272232055664,
|
||
|
|
"epoch": 2.2514619883040936,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00048353041376836937,
|
||
|
|
"loss": 6.4851,
|
||
|
|
"mean_token_accuracy": 0.150111523270607,
|
||
|
|
"num_tokens": 4792233.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5504697322845455,
|
||
|
|
"epoch": 2.257309941520468,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004833539261194749,
|
||
|
|
"loss": 6.4596,
|
||
|
|
"mean_token_accuracy": 0.16135370433330537,
|
||
|
|
"num_tokens": 4803348.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598280191421509,
|
||
|
|
"epoch": 2.263157894736842,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00048317653419960007,
|
||
|
|
"loss": 6.5297,
|
||
|
|
"mean_token_accuracy": 0.14848926216363906,
|
||
|
|
"num_tokens": 4816574.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.509727716445923,
|
||
|
|
"epoch": 2.2690058479532165,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00048299823877863857,
|
||
|
|
"loss": 6.4474,
|
||
|
|
"mean_token_accuracy": 0.1615246683359146,
|
||
|
|
"num_tokens": 4828008.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.667463397979736,
|
||
|
|
"epoch": 2.2748538011695905,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004828190406304054,
|
||
|
|
"loss": 6.5337,
|
||
|
|
"mean_token_accuracy": 0.15022147595882415,
|
||
|
|
"num_tokens": 4840621.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526378870010376,
|
||
|
|
"epoch": 2.280701754385965,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004826389405326334,
|
||
|
|
"loss": 6.4181,
|
||
|
|
"mean_token_accuracy": 0.155361807346344,
|
||
|
|
"num_tokens": 4853503.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.606720447540283,
|
||
|
|
"epoch": 2.2865497076023393,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004824579392669698,
|
||
|
|
"loss": 6.4384,
|
||
|
|
"mean_token_accuracy": 0.15409778654575348,
|
||
|
|
"num_tokens": 4865925.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5683465003967285,
|
||
|
|
"epoch": 2.2923976608187133,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00048227603761897316,
|
||
|
|
"loss": 6.5193,
|
||
|
|
"mean_token_accuracy": 0.15140500217676162,
|
||
|
|
"num_tokens": 4878704.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.612151765823365,
|
||
|
|
"epoch": 2.2982456140350878,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004820932363781096,
|
||
|
|
"loss": 6.4714,
|
||
|
|
"mean_token_accuracy": 0.15166847705841063,
|
||
|
|
"num_tokens": 4891750.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.575180625915527,
|
||
|
|
"epoch": 2.3040935672514617,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004819095363377496,
|
||
|
|
"loss": 6.4705,
|
||
|
|
"mean_token_accuracy": 0.15658862590789796,
|
||
|
|
"num_tokens": 4904539.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.452806282043457,
|
||
|
|
"epoch": 2.309941520467836,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00048172493829516465,
|
||
|
|
"loss": 6.3434,
|
||
|
|
"mean_token_accuracy": 0.16240692883729935,
|
||
|
|
"num_tokens": 4916210.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544571399688721,
|
||
|
|
"epoch": 2.3157894736842106,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004815394430515234,
|
||
|
|
"loss": 6.4152,
|
||
|
|
"mean_token_accuracy": 0.15815324783325196,
|
||
|
|
"num_tokens": 4929011.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.471958112716675,
|
||
|
|
"epoch": 2.3216374269005846,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004813530514118884,
|
||
|
|
"loss": 6.4003,
|
||
|
|
"mean_token_accuracy": 0.15740202665328978,
|
||
|
|
"num_tokens": 4942484.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535995006561279,
|
||
|
|
"epoch": 2.327485380116959,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004811657641852129,
|
||
|
|
"loss": 6.39,
|
||
|
|
"mean_token_accuracy": 0.1587621033191681,
|
||
|
|
"num_tokens": 4955395.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.499216175079345,
|
||
|
|
"epoch": 2.3333333333333335,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00048097758218433687,
|
||
|
|
"loss": 6.42,
|
||
|
|
"mean_token_accuracy": 0.1547679767012596,
|
||
|
|
"num_tokens": 4966853.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.421728944778442,
|
||
|
|
"epoch": 2.3391812865497075,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00048078850622598355,
|
||
|
|
"loss": 6.2927,
|
||
|
|
"mean_token_accuracy": 0.16700532883405686,
|
||
|
|
"num_tokens": 4978514.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.3391812865497075,
|
||
|
|
"eval_entropy": 6.455809226078269,
|
||
|
|
"eval_loss": 6.835439682006836,
|
||
|
|
"eval_mean_token_accuracy": 0.13983681909245463,
|
||
|
|
"eval_num_tokens": 4978514.0,
|
||
|
|
"eval_runtime": 2.2514,
|
||
|
|
"eval_samples_per_second": 1202.352,
|
||
|
|
"eval_steps_per_second": 150.572,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5295257568359375,
|
||
|
|
"epoch": 2.345029239766082,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.00048059853713075637,
|
||
|
|
"loss": 6.4416,
|
||
|
|
"mean_token_accuracy": 0.15362119674682617,
|
||
|
|
"num_tokens": 4991331.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546032667160034,
|
||
|
|
"epoch": 2.3508771929824563,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004804076757231347,
|
||
|
|
"loss": 6.4314,
|
||
|
|
"mean_token_accuracy": 0.15481286495923996,
|
||
|
|
"num_tokens": 5004652.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.545717191696167,
|
||
|
|
"epoch": 2.3567251461988303,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00048021592283147073,
|
||
|
|
"loss": 6.4361,
|
||
|
|
"mean_token_accuracy": 0.16364984959363937,
|
||
|
|
"num_tokens": 5017204.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.457218790054322,
|
||
|
|
"epoch": 2.3625730994152048,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004800232792879858,
|
||
|
|
"loss": 6.4503,
|
||
|
|
"mean_token_accuracy": 0.16370202898979186,
|
||
|
|
"num_tokens": 5029667.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.467345428466797,
|
||
|
|
"epoch": 2.3684210526315788,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00047982974592876665,
|
||
|
|
"loss": 6.2914,
|
||
|
|
"mean_token_accuracy": 0.16729763001203538,
|
||
|
|
"num_tokens": 5041490.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.501898097991943,
|
||
|
|
"epoch": 2.374269005847953,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000479635323593762,
|
||
|
|
"loss": 6.4582,
|
||
|
|
"mean_token_accuracy": 0.15127150043845178,
|
||
|
|
"num_tokens": 5054353.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.550432920455933,
|
||
|
|
"epoch": 2.3801169590643276,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00047944001312677867,
|
||
|
|
"loss": 6.4115,
|
||
|
|
"mean_token_accuracy": 0.15359611958265304,
|
||
|
|
"num_tokens": 5067322.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526231479644776,
|
||
|
|
"epoch": 2.3859649122807016,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004792438153754782,
|
||
|
|
"loss": 6.4649,
|
||
|
|
"mean_token_accuracy": 0.1627212718129158,
|
||
|
|
"num_tokens": 5079957.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503479528427124,
|
||
|
|
"epoch": 2.391812865497076,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004790467311913727,
|
||
|
|
"loss": 6.435,
|
||
|
|
"mean_token_accuracy": 0.1539318472146988,
|
||
|
|
"num_tokens": 5091975.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.572689867019653,
|
||
|
|
"epoch": 2.39766081871345,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004788487614298219,
|
||
|
|
"loss": 6.4626,
|
||
|
|
"mean_token_accuracy": 0.1516765758395195,
|
||
|
|
"num_tokens": 5103847.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519900369644165,
|
||
|
|
"epoch": 2.4035087719298245,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004786499069500286,
|
||
|
|
"loss": 6.3984,
|
||
|
|
"mean_token_accuracy": 0.16055867820978165,
|
||
|
|
"num_tokens": 5115153.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4418408393859865,
|
||
|
|
"epoch": 2.409356725146199,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00047845016861503556,
|
||
|
|
"loss": 6.3393,
|
||
|
|
"mean_token_accuracy": 0.16575780510902405,
|
||
|
|
"num_tokens": 5128008.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.393708181381226,
|
||
|
|
"epoch": 2.415204678362573,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00047824954729172136,
|
||
|
|
"loss": 6.3117,
|
||
|
|
"mean_token_accuracy": 0.16899289190769196,
|
||
|
|
"num_tokens": 5140023.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.466020154953003,
|
||
|
|
"epoch": 2.4210526315789473,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004780480438507972,
|
||
|
|
"loss": 6.3476,
|
||
|
|
"mean_token_accuracy": 0.16515520364046096,
|
||
|
|
"num_tokens": 5152660.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477208280563355,
|
||
|
|
"epoch": 2.426900584795322,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00047784565916680216,
|
||
|
|
"loss": 6.3768,
|
||
|
|
"mean_token_accuracy": 0.15766774863004684,
|
||
|
|
"num_tokens": 5164481.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568231534957886,
|
||
|
|
"epoch": 2.4327485380116958,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004776423941181005,
|
||
|
|
"loss": 6.4361,
|
||
|
|
"mean_token_accuracy": 0.16417670398950576,
|
||
|
|
"num_tokens": 5177178.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.501895427703857,
|
||
|
|
"epoch": 2.43859649122807,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00047743824958687694,
|
||
|
|
"loss": 6.3533,
|
||
|
|
"mean_token_accuracy": 0.16052256673574447,
|
||
|
|
"num_tokens": 5189385.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.484155321121216,
|
||
|
|
"epoch": 2.4444444444444446,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00047723322645913354,
|
||
|
|
"loss": 6.4157,
|
||
|
|
"mean_token_accuracy": 0.15802188068628312,
|
||
|
|
"num_tokens": 5201839.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497567558288575,
|
||
|
|
"epoch": 2.4502923976608186,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004770273256246853,
|
||
|
|
"loss": 6.4502,
|
||
|
|
"mean_token_accuracy": 0.15175531804561615,
|
||
|
|
"num_tokens": 5214565.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541861343383789,
|
||
|
|
"epoch": 2.456140350877193,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004768205479771566,
|
||
|
|
"loss": 6.417,
|
||
|
|
"mean_token_accuracy": 0.16060543060302734,
|
||
|
|
"num_tokens": 5227029.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.520119762420654,
|
||
|
|
"epoch": 2.461988304093567,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00047661289441397724,
|
||
|
|
"loss": 6.4521,
|
||
|
|
"mean_token_accuracy": 0.16085827499628066,
|
||
|
|
"num_tokens": 5239208.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.458652305603027,
|
||
|
|
"epoch": 2.4678362573099415,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00047640436583637865,
|
||
|
|
"loss": 6.4,
|
||
|
|
"mean_token_accuracy": 0.16391708254814147,
|
||
|
|
"num_tokens": 5252272.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589468860626221,
|
||
|
|
"epoch": 2.473684210526316,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00047619496314938977,
|
||
|
|
"loss": 6.5472,
|
||
|
|
"mean_token_accuracy": 0.14695970714092255,
|
||
|
|
"num_tokens": 5264387.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566831445693969,
|
||
|
|
"epoch": 2.47953216374269,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004759846872618332,
|
||
|
|
"loss": 6.4796,
|
||
|
|
"mean_token_accuracy": 0.1556633621454239,
|
||
|
|
"num_tokens": 5276662.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.467095232009887,
|
||
|
|
"epoch": 2.4853801169590644,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00047577353908632156,
|
||
|
|
"loss": 6.4223,
|
||
|
|
"mean_token_accuracy": 0.15920186787843704,
|
||
|
|
"num_tokens": 5290734.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4471629619598385,
|
||
|
|
"epoch": 2.4912280701754383,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00047556151953925287,
|
||
|
|
"loss": 6.296,
|
||
|
|
"mean_token_accuracy": 0.1659088522195816,
|
||
|
|
"num_tokens": 5302510.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.600066137313843,
|
||
|
|
"epoch": 2.497076023391813,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004753486295408073,
|
||
|
|
"loss": 6.3854,
|
||
|
|
"mean_token_accuracy": 0.16022948622703553,
|
||
|
|
"num_tokens": 5313243.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371742630004883,
|
||
|
|
"epoch": 2.502923976608187,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00047513487001494257,
|
||
|
|
"loss": 6.4781,
|
||
|
|
"mean_token_accuracy": 0.15527973771095277,
|
||
|
|
"num_tokens": 5325485.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.640823554992676,
|
||
|
|
"epoch": 2.5087719298245617,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00047492024188939056,
|
||
|
|
"loss": 6.5273,
|
||
|
|
"mean_token_accuracy": 0.150774721801281,
|
||
|
|
"num_tokens": 5339335.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519844007492066,
|
||
|
|
"epoch": 2.5146198830409356,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004747047460956525,
|
||
|
|
"loss": 6.4756,
|
||
|
|
"mean_token_accuracy": 0.15083398222923278,
|
||
|
|
"num_tokens": 5351195.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492697429656983,
|
||
|
|
"epoch": 2.52046783625731,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004744883835689958,
|
||
|
|
"loss": 6.4223,
|
||
|
|
"mean_token_accuracy": 0.15827751457691192,
|
||
|
|
"num_tokens": 5362884.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.447801780700684,
|
||
|
|
"epoch": 2.526315789473684,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004742711552484492,
|
||
|
|
"loss": 6.4486,
|
||
|
|
"mean_token_accuracy": 0.15634266585111617,
|
||
|
|
"num_tokens": 5375770.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.58181095123291,
|
||
|
|
"epoch": 2.5321637426900585,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00047405306207679926,
|
||
|
|
"loss": 6.4305,
|
||
|
|
"mean_token_accuracy": 0.15079367458820342,
|
||
|
|
"num_tokens": 5388673.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.294779443740845,
|
||
|
|
"epoch": 2.538011695906433,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004738341050005859,
|
||
|
|
"loss": 6.2744,
|
||
|
|
"mean_token_accuracy": 0.16661928594112396,
|
||
|
|
"num_tokens": 5400454.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526889801025391,
|
||
|
|
"epoch": 2.543859649122807,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004736142849700986,
|
||
|
|
"loss": 6.423,
|
||
|
|
"mean_token_accuracy": 0.16107723265886306,
|
||
|
|
"num_tokens": 5413740.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.504376840591431,
|
||
|
|
"epoch": 2.5497076023391814,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004733936029393721,
|
||
|
|
"loss": 6.4354,
|
||
|
|
"mean_token_accuracy": 0.15917587131261826,
|
||
|
|
"num_tokens": 5426089.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527545404434204,
|
||
|
|
"epoch": 2.5555555555555554,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004731720598661821,
|
||
|
|
"loss": 6.4706,
|
||
|
|
"mean_token_accuracy": 0.15158118084073066,
|
||
|
|
"num_tokens": 5438835.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416220617294312,
|
||
|
|
"epoch": 2.56140350877193,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004729496567120415,
|
||
|
|
"loss": 6.4385,
|
||
|
|
"mean_token_accuracy": 0.1590983361005783,
|
||
|
|
"num_tokens": 5452054.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.558721971511841,
|
||
|
|
"epoch": 2.5672514619883042,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000472726394442196,
|
||
|
|
"loss": 6.3738,
|
||
|
|
"mean_token_accuracy": 0.15141484290361404,
|
||
|
|
"num_tokens": 5466455.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430954647064209,
|
||
|
|
"epoch": 2.573099415204678,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00047250227402561976,
|
||
|
|
"loss": 6.3896,
|
||
|
|
"mean_token_accuracy": 0.1599864736199379,
|
||
|
|
"num_tokens": 5479990.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.579306507110596,
|
||
|
|
"epoch": 2.5789473684210527,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004722772964350115,
|
||
|
|
"loss": 6.4443,
|
||
|
|
"mean_token_accuracy": 0.1601562812924385,
|
||
|
|
"num_tokens": 5493035.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416007947921753,
|
||
|
|
"epoch": 2.5847953216374266,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00047205146264679015,
|
||
|
|
"loss": 6.4659,
|
||
|
|
"mean_token_accuracy": 0.1559721350669861,
|
||
|
|
"num_tokens": 5506093.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.499674892425537,
|
||
|
|
"epoch": 2.590643274853801,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00047182477364109045,
|
||
|
|
"loss": 6.4285,
|
||
|
|
"mean_token_accuracy": 0.16566468626260758,
|
||
|
|
"num_tokens": 5518552.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.50216064453125,
|
||
|
|
"epoch": 2.5964912280701755,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00047159723040175896,
|
||
|
|
"loss": 6.4415,
|
||
|
|
"mean_token_accuracy": 0.15585022121667863,
|
||
|
|
"num_tokens": 5530123.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.586924409866333,
|
||
|
|
"epoch": 2.60233918128655,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00047136883391634966,
|
||
|
|
"loss": 6.4638,
|
||
|
|
"mean_token_accuracy": 0.1510583743453026,
|
||
|
|
"num_tokens": 5542769.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3639349937438965,
|
||
|
|
"epoch": 2.608187134502924,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004711395851761198,
|
||
|
|
"loss": 6.2888,
|
||
|
|
"mean_token_accuracy": 0.1740984469652176,
|
||
|
|
"num_tokens": 5555975.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.433200883865356,
|
||
|
|
"epoch": 2.6140350877192984,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004709094851760251,
|
||
|
|
"loss": 6.3917,
|
||
|
|
"mean_token_accuracy": 0.15697622448205947,
|
||
|
|
"num_tokens": 5569059.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515594148635865,
|
||
|
|
"epoch": 2.6198830409356724,
|
||
|
|
"grad_norm": 1.75,
|
||
|
|
"learning_rate": 0.0004706785349147163,
|
||
|
|
"loss": 6.4369,
|
||
|
|
"mean_token_accuracy": 0.15214415192604064,
|
||
|
|
"num_tokens": 5581358.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.445247936248779,
|
||
|
|
"epoch": 2.625730994152047,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000470446735394534,
|
||
|
|
"loss": 6.3961,
|
||
|
|
"mean_token_accuracy": 0.15565400570631027,
|
||
|
|
"num_tokens": 5594256.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5402045249938965,
|
||
|
|
"epoch": 2.6315789473684212,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004702140876215047,
|
||
|
|
"loss": 6.4057,
|
||
|
|
"mean_token_accuracy": 0.15860477983951568,
|
||
|
|
"num_tokens": 5607236.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519019842147827,
|
||
|
|
"epoch": 2.6374269005847952,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004699805926053365,
|
||
|
|
"loss": 6.5057,
|
||
|
|
"mean_token_accuracy": 0.15038548409938812,
|
||
|
|
"num_tokens": 5619550.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.408275699615478,
|
||
|
|
"epoch": 2.6432748538011697,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.00046974625135941445,
|
||
|
|
"loss": 6.3623,
|
||
|
|
"mean_token_accuracy": 0.16836439967155456,
|
||
|
|
"num_tokens": 5632721.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430430221557617,
|
||
|
|
"epoch": 2.6491228070175437,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00046951106490079636,
|
||
|
|
"loss": 6.2229,
|
||
|
|
"mean_token_accuracy": 0.1644220918416977,
|
||
|
|
"num_tokens": 5643672.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.443275499343872,
|
||
|
|
"epoch": 2.654970760233918,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00046927503425020847,
|
||
|
|
"loss": 6.3705,
|
||
|
|
"mean_token_accuracy": 0.1590825006365776,
|
||
|
|
"num_tokens": 5656072.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492913722991943,
|
||
|
|
"epoch": 2.6608187134502925,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00046903816043204045,
|
||
|
|
"loss": 6.3833,
|
||
|
|
"mean_token_accuracy": 0.1627071052789688,
|
||
|
|
"num_tokens": 5668365.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3713613986969,
|
||
|
|
"epoch": 2.6666666666666665,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004688004444743419,
|
||
|
|
"loss": 6.3513,
|
||
|
|
"mean_token_accuracy": 0.16134851723909377,
|
||
|
|
"num_tokens": 5680013.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.421517705917358,
|
||
|
|
"epoch": 2.672514619883041,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000468561887408817,
|
||
|
|
"loss": 6.3684,
|
||
|
|
"mean_token_accuracy": 0.1644539475440979,
|
||
|
|
"num_tokens": 5691884.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.471812963485718,
|
||
|
|
"epoch": 2.678362573099415,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004683224902708206,
|
||
|
|
"loss": 6.4377,
|
||
|
|
"mean_token_accuracy": 0.15451103150844575,
|
||
|
|
"num_tokens": 5704340.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546636867523193,
|
||
|
|
"epoch": 2.6842105263157894,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004680822540993534,
|
||
|
|
"loss": 6.4923,
|
||
|
|
"mean_token_accuracy": 0.15456219315528869,
|
||
|
|
"num_tokens": 5717792.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.382723426818847,
|
||
|
|
"epoch": 2.690058479532164,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00046784117993705753,
|
||
|
|
"loss": 6.3559,
|
||
|
|
"mean_token_accuracy": 0.1601694941520691,
|
||
|
|
"num_tokens": 5730237.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.413783025741577,
|
||
|
|
"epoch": 2.6959064327485383,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00046759926883021234,
|
||
|
|
"loss": 6.3665,
|
||
|
|
"mean_token_accuracy": 0.16199508905410767,
|
||
|
|
"num_tokens": 5743953.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.393997526168823,
|
||
|
|
"epoch": 2.7017543859649122,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00046735652182872925,
|
||
|
|
"loss": 6.3394,
|
||
|
|
"mean_token_accuracy": 0.16054470017552375,
|
||
|
|
"num_tokens": 5756148.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47453727722168,
|
||
|
|
"epoch": 2.7076023391812867,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004671129399861476,
|
||
|
|
"loss": 6.3544,
|
||
|
|
"mean_token_accuracy": 0.16721498668193818,
|
||
|
|
"num_tokens": 5769163.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.467833232879639,
|
||
|
|
"epoch": 2.7134502923976607,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00046686852435963016,
|
||
|
|
"loss": 6.4051,
|
||
|
|
"mean_token_accuracy": 0.1565157249569893,
|
||
|
|
"num_tokens": 5781832.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.46702995300293,
|
||
|
|
"epoch": 2.719298245614035,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004666232760099583,
|
||
|
|
"loss": 6.3919,
|
||
|
|
"mean_token_accuracy": 0.15612493604421615,
|
||
|
|
"num_tokens": 5794803.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.413252496719361,
|
||
|
|
"epoch": 2.7251461988304095,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00046637719600152737,
|
||
|
|
"loss": 6.4092,
|
||
|
|
"mean_token_accuracy": 0.1549370437860489,
|
||
|
|
"num_tokens": 5806768.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.560105895996093,
|
||
|
|
"epoch": 2.7309941520467835,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00046613028540234226,
|
||
|
|
"loss": 6.4213,
|
||
|
|
"mean_token_accuracy": 0.1513759136199951,
|
||
|
|
"num_tokens": 5819113.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491551876068115,
|
||
|
|
"epoch": 2.736842105263158,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00046588254528401264,
|
||
|
|
"loss": 6.4003,
|
||
|
|
"mean_token_accuracy": 0.15968723744153976,
|
||
|
|
"num_tokens": 5830067.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.462792682647705,
|
||
|
|
"epoch": 2.742690058479532,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004656339767217485,
|
||
|
|
"loss": 6.4402,
|
||
|
|
"mean_token_accuracy": 0.15799568593502045,
|
||
|
|
"num_tokens": 5842882.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419540739059448,
|
||
|
|
"epoch": 2.7485380116959064,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00046538458079435516,
|
||
|
|
"loss": 6.3964,
|
||
|
|
"mean_token_accuracy": 0.159682597219944,
|
||
|
|
"num_tokens": 5854041.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488130855560303,
|
||
|
|
"epoch": 2.754385964912281,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004651343585842287,
|
||
|
|
"loss": 6.4189,
|
||
|
|
"mean_token_accuracy": 0.16038355678319932,
|
||
|
|
"num_tokens": 5866027.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.46736249923706,
|
||
|
|
"epoch": 2.760233918128655,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00046488331117735176,
|
||
|
|
"loss": 6.4514,
|
||
|
|
"mean_token_accuracy": 0.15868442356586457,
|
||
|
|
"num_tokens": 5877064.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497715282440185,
|
||
|
|
"epoch": 2.7660818713450293,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004646314396632878,
|
||
|
|
"loss": 6.4038,
|
||
|
|
"mean_token_accuracy": 0.1543351948261261,
|
||
|
|
"num_tokens": 5889190.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.457688665390014,
|
||
|
|
"epoch": 2.7719298245614032,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004643787451351774,
|
||
|
|
"loss": 6.3849,
|
||
|
|
"mean_token_accuracy": 0.16172885596752168,
|
||
|
|
"num_tokens": 5901615.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.429424476623535,
|
||
|
|
"epoch": 2.7777777777777777,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00046412522868973297,
|
||
|
|
"loss": 6.3838,
|
||
|
|
"mean_token_accuracy": 0.16126611828804016,
|
||
|
|
"num_tokens": 5913797.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.556289434432983,
|
||
|
|
"epoch": 2.783625730994152,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00046387089142723386,
|
||
|
|
"loss": 6.484,
|
||
|
|
"mean_token_accuracy": 0.15325869470834733,
|
||
|
|
"num_tokens": 5927607.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.326716327667237,
|
||
|
|
"epoch": 2.7894736842105265,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00046361573445152224,
|
||
|
|
"loss": 6.2802,
|
||
|
|
"mean_token_accuracy": 0.16957638710737227,
|
||
|
|
"num_tokens": 5940254.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.288288354873657,
|
||
|
|
"epoch": 2.7953216374269005,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00046335975886999754,
|
||
|
|
"loss": 6.1406,
|
||
|
|
"mean_token_accuracy": 0.17853645831346512,
|
||
|
|
"num_tokens": 5953341.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.288193035125732,
|
||
|
|
"epoch": 2.801169590643275,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00046310296579361225,
|
||
|
|
"loss": 6.1703,
|
||
|
|
"mean_token_accuracy": 0.17703435122966765,
|
||
|
|
"num_tokens": 5965148.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515323305130005,
|
||
|
|
"epoch": 2.807017543859649,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004628453563368666,
|
||
|
|
"loss": 6.4732,
|
||
|
|
"mean_token_accuracy": 0.15134917572140694,
|
||
|
|
"num_tokens": 5979143.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.466275310516357,
|
||
|
|
"epoch": 2.8128654970760234,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004625869316178043,
|
||
|
|
"loss": 6.4349,
|
||
|
|
"mean_token_accuracy": 0.15583141297101974,
|
||
|
|
"num_tokens": 5992735.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.504425954818726,
|
||
|
|
"epoch": 2.818713450292398,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000462327692758007,
|
||
|
|
"loss": 6.4949,
|
||
|
|
"mean_token_accuracy": 0.15118930339813233,
|
||
|
|
"num_tokens": 6005033.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.442822551727295,
|
||
|
|
"epoch": 2.824561403508772,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00046206764088259003,
|
||
|
|
"loss": 6.336,
|
||
|
|
"mean_token_accuracy": 0.15877799987792968,
|
||
|
|
"num_tokens": 6016746.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.365158128738403,
|
||
|
|
"epoch": 2.8304093567251463,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00046180677712019707,
|
||
|
|
"loss": 6.4506,
|
||
|
|
"mean_token_accuracy": 0.15918623954057692,
|
||
|
|
"num_tokens": 6029774.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5604291439056395,
|
||
|
|
"epoch": 2.8362573099415203,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004615451026029957,
|
||
|
|
"loss": 6.4661,
|
||
|
|
"mean_token_accuracy": 0.15172474086284637,
|
||
|
|
"num_tokens": 6043773.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.418456220626831,
|
||
|
|
"epoch": 2.8421052631578947,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000461282618466672,
|
||
|
|
"loss": 6.3809,
|
||
|
|
"mean_token_accuracy": 0.15369057804346084,
|
||
|
|
"num_tokens": 6055840.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.455171585083008,
|
||
|
|
"epoch": 2.847953216374269,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00046101932585042597,
|
||
|
|
"loss": 6.2946,
|
||
|
|
"mean_token_accuracy": 0.1648610144853592,
|
||
|
|
"num_tokens": 6069170.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.385668182373047,
|
||
|
|
"epoch": 2.853801169590643,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00046075522589696636,
|
||
|
|
"loss": 6.3633,
|
||
|
|
"mean_token_accuracy": 0.16001774966716767,
|
||
|
|
"num_tokens": 6080888.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.367319965362549,
|
||
|
|
"epoch": 2.8596491228070176,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000460490319752506,
|
||
|
|
"loss": 6.2952,
|
||
|
|
"mean_token_accuracy": 0.1636100247502327,
|
||
|
|
"num_tokens": 6093035.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446693038940429,
|
||
|
|
"epoch": 2.8654970760233915,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00046022460856675663,
|
||
|
|
"loss": 6.3669,
|
||
|
|
"mean_token_accuracy": 0.1542543351650238,
|
||
|
|
"num_tokens": 6105963.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.480491495132446,
|
||
|
|
"epoch": 2.871345029239766,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004599580934929237,
|
||
|
|
"loss": 6.4063,
|
||
|
|
"mean_token_accuracy": 0.15467619895935059,
|
||
|
|
"num_tokens": 6118541.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371702718734741,
|
||
|
|
"epoch": 2.8771929824561404,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004596907756877018,
|
||
|
|
"loss": 6.3163,
|
||
|
|
"mean_token_accuracy": 0.15824139714241028,
|
||
|
|
"num_tokens": 6131317.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.378661441802978,
|
||
|
|
"epoch": 2.883040935672515,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00045942265631126935,
|
||
|
|
"loss": 6.3798,
|
||
|
|
"mean_token_accuracy": 0.15825361758470535,
|
||
|
|
"num_tokens": 6143721.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.435754108428955,
|
||
|
|
"epoch": 2.888888888888889,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004591537365272837,
|
||
|
|
"loss": 6.3788,
|
||
|
|
"mean_token_accuracy": 0.15418335646390915,
|
||
|
|
"num_tokens": 6156497.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3720903396606445,
|
||
|
|
"epoch": 2.8947368421052633,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000458884017502876,
|
||
|
|
"loss": 6.3647,
|
||
|
|
"mean_token_accuracy": 0.1603195920586586,
|
||
|
|
"num_tokens": 6168140.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.490845584869385,
|
||
|
|
"epoch": 2.9005847953216373,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004586135004086461,
|
||
|
|
"loss": 6.3528,
|
||
|
|
"mean_token_accuracy": 0.15702196657657624,
|
||
|
|
"num_tokens": 6181067.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.412484741210937,
|
||
|
|
"epoch": 2.9064327485380117,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004583421864186577,
|
||
|
|
"loss": 6.3374,
|
||
|
|
"mean_token_accuracy": 0.15485871136188506,
|
||
|
|
"num_tokens": 6194072.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4414574146270756,
|
||
|
|
"epoch": 2.912280701754386,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004580700767104328,
|
||
|
|
"loss": 6.3978,
|
||
|
|
"mean_token_accuracy": 0.15681013315916062,
|
||
|
|
"num_tokens": 6206711.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.357868003845215,
|
||
|
|
"epoch": 2.91812865497076,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00045779717246494724,
|
||
|
|
"loss": 6.3193,
|
||
|
|
"mean_token_accuracy": 0.1601993829011917,
|
||
|
|
"num_tokens": 6219903.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.481598424911499,
|
||
|
|
"epoch": 2.9239766081871346,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004575234748666249,
|
||
|
|
"loss": 6.3694,
|
||
|
|
"mean_token_accuracy": 0.1591841161251068,
|
||
|
|
"num_tokens": 6232947.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.9239766081871346,
|
||
|
|
"eval_entropy": 6.330253553249843,
|
||
|
|
"eval_loss": 6.695201396942139,
|
||
|
|
"eval_mean_token_accuracy": 0.14393769834564235,
|
||
|
|
"eval_num_tokens": 6232947.0,
|
||
|
|
"eval_runtime": 2.4543,
|
||
|
|
"eval_samples_per_second": 1102.963,
|
||
|
|
"eval_steps_per_second": 138.125,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.419301176071167,
|
||
|
|
"epoch": 2.9298245614035086,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000457248985103333,
|
||
|
|
"loss": 6.3455,
|
||
|
|
"mean_token_accuracy": 0.16172951310873032,
|
||
|
|
"num_tokens": 6245597.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.338090705871582,
|
||
|
|
"epoch": 2.935672514619883,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004569737043663768,
|
||
|
|
"loss": 6.2748,
|
||
|
|
"mean_token_accuracy": 0.1580662027001381,
|
||
|
|
"num_tokens": 6257745.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403406953811645,
|
||
|
|
"epoch": 2.9415204678362574,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004566976338504945,
|
||
|
|
"loss": 6.3586,
|
||
|
|
"mean_token_accuracy": 0.16223775297403337,
|
||
|
|
"num_tokens": 6268871.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.380885744094849,
|
||
|
|
"epoch": 2.9473684210526314,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00045642077475385186,
|
||
|
|
"loss": 6.3282,
|
||
|
|
"mean_token_accuracy": 0.16251893788576127,
|
||
|
|
"num_tokens": 6281487.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.307056665420532,
|
||
|
|
"epoch": 2.953216374269006,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004561431282780372,
|
||
|
|
"loss": 6.309,
|
||
|
|
"mean_token_accuracy": 0.16125601381063462,
|
||
|
|
"num_tokens": 6292928.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416406774520874,
|
||
|
|
"epoch": 2.95906432748538,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00045586469562805624,
|
||
|
|
"loss": 6.3041,
|
||
|
|
"mean_token_accuracy": 0.1739753305912018,
|
||
|
|
"num_tokens": 6304340.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.361484575271606,
|
||
|
|
"epoch": 2.9649122807017543,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004555854780123265,
|
||
|
|
"loss": 6.3623,
|
||
|
|
"mean_token_accuracy": 0.15492762327194215,
|
||
|
|
"num_tokens": 6315972.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.436385250091552,
|
||
|
|
"epoch": 2.9707602339181287,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004553054766426725,
|
||
|
|
"loss": 6.3553,
|
||
|
|
"mean_token_accuracy": 0.161744923889637,
|
||
|
|
"num_tokens": 6327482.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.385243844985962,
|
||
|
|
"epoch": 2.976608187134503,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004550246927343203,
|
||
|
|
"loss": 6.3362,
|
||
|
|
"mean_token_accuracy": 0.16019928306341172,
|
||
|
|
"num_tokens": 6338932.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.383661460876465,
|
||
|
|
"epoch": 2.982456140350877,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00045474312750589226,
|
||
|
|
"loss": 6.3604,
|
||
|
|
"mean_token_accuracy": 0.16253289729356765,
|
||
|
|
"num_tokens": 6350770.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.433977651596069,
|
||
|
|
"epoch": 2.9883040935672516,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00045446078217940155,
|
||
|
|
"loss": 6.3869,
|
||
|
|
"mean_token_accuracy": 0.15729532539844512,
|
||
|
|
"num_tokens": 6363472.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.45090012550354,
|
||
|
|
"epoch": 2.9941520467836256,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00045417765798024716,
|
||
|
|
"loss": 6.3498,
|
||
|
|
"mean_token_accuracy": 0.15721661001443862,
|
||
|
|
"num_tokens": 6377174.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.356162595748901,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004538937561372086,
|
||
|
|
"loss": 6.3176,
|
||
|
|
"mean_token_accuracy": 0.15686715841293336,
|
||
|
|
"num_tokens": 6388452.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4929975986480715,
|
||
|
|
"epoch": 3.0058479532163744,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004536090778824398,
|
||
|
|
"loss": 5.9937,
|
||
|
|
"mean_token_accuracy": 0.16939886957406997,
|
||
|
|
"num_tokens": 6401740.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.272706079483032,
|
||
|
|
"epoch": 3.0116959064327484,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004533236244514652,
|
||
|
|
"loss": 5.961,
|
||
|
|
"mean_token_accuracy": 0.17892924547195435,
|
||
|
|
"num_tokens": 6414850.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.424148178100586,
|
||
|
|
"epoch": 3.017543859649123,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.00045303739708317303,
|
||
|
|
"loss": 6.1166,
|
||
|
|
"mean_token_accuracy": 0.1609419897198677,
|
||
|
|
"num_tokens": 6429250.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347711992263794,
|
||
|
|
"epoch": 3.023391812865497,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004527503970198105,
|
||
|
|
"loss": 5.9555,
|
||
|
|
"mean_token_accuracy": 0.17230001986026763,
|
||
|
|
"num_tokens": 6440583.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252596044540406,
|
||
|
|
"epoch": 3.0292397660818713,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004524626255069786,
|
||
|
|
"loss": 5.9666,
|
||
|
|
"mean_token_accuracy": 0.1721245363354683,
|
||
|
|
"num_tokens": 6452678.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.390771198272705,
|
||
|
|
"epoch": 3.0350877192982457,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00045217408379362635,
|
||
|
|
"loss": 6.0083,
|
||
|
|
"mean_token_accuracy": 0.1667831540107727,
|
||
|
|
"num_tokens": 6464751.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213038492202759,
|
||
|
|
"epoch": 3.0409356725146197,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00045188477313204536,
|
||
|
|
"loss": 5.9844,
|
||
|
|
"mean_token_accuracy": 0.16985960453748702,
|
||
|
|
"num_tokens": 6476017.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.456451368331909,
|
||
|
|
"epoch": 3.046783625730994,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00045159469477786457,
|
||
|
|
"loss": 5.9926,
|
||
|
|
"mean_token_accuracy": 0.16920494437217712,
|
||
|
|
"num_tokens": 6487404.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274428033828736,
|
||
|
|
"epoch": 3.0526315789473686,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004513038499900451,
|
||
|
|
"loss": 6.0573,
|
||
|
|
"mean_token_accuracy": 0.16484473049640655,
|
||
|
|
"num_tokens": 6500027.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.331849002838135,
|
||
|
|
"epoch": 3.0584795321637426,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000451012240030874,
|
||
|
|
"loss": 6.0417,
|
||
|
|
"mean_token_accuracy": 0.1605970486998558,
|
||
|
|
"num_tokens": 6513067.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28749303817749,
|
||
|
|
"epoch": 3.064327485380117,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00045071986616595946,
|
||
|
|
"loss": 5.9795,
|
||
|
|
"mean_token_accuracy": 0.16884554028511048,
|
||
|
|
"num_tokens": 6524932.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344663810729981,
|
||
|
|
"epoch": 3.0701754385964914,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00045042672966422506,
|
||
|
|
"loss": 6.0246,
|
||
|
|
"mean_token_accuracy": 0.16394265592098237,
|
||
|
|
"num_tokens": 6536843.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.389114332199097,
|
||
|
|
"epoch": 3.0760233918128654,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004501328317979041,
|
||
|
|
"loss": 5.9562,
|
||
|
|
"mean_token_accuracy": 0.1754080668091774,
|
||
|
|
"num_tokens": 6549414.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.240146160125732,
|
||
|
|
"epoch": 3.08187134502924,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004498381738425346,
|
||
|
|
"loss": 6.0245,
|
||
|
|
"mean_token_accuracy": 0.17039664834737778,
|
||
|
|
"num_tokens": 6561492.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266224479675293,
|
||
|
|
"epoch": 3.087719298245614,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00044954275707695304,
|
||
|
|
"loss": 5.9404,
|
||
|
|
"mean_token_accuracy": 0.17152028083801268,
|
||
|
|
"num_tokens": 6572873.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26595516204834,
|
||
|
|
"epoch": 3.0935672514619883,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004492465827832894,
|
||
|
|
"loss": 6.0728,
|
||
|
|
"mean_token_accuracy": 0.17039728611707688,
|
||
|
|
"num_tokens": 6584902.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.413704347610474,
|
||
|
|
"epoch": 3.0994152046783627,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00044894965224696144,
|
||
|
|
"loss": 6.1004,
|
||
|
|
"mean_token_accuracy": 0.1659897029399872,
|
||
|
|
"num_tokens": 6596792.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.301944208145142,
|
||
|
|
"epoch": 3.1052631578947367,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00044865196675666886,
|
||
|
|
"loss": 6.0163,
|
||
|
|
"mean_token_accuracy": 0.16773612350225447,
|
||
|
|
"num_tokens": 6608559.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303693532943726,
|
||
|
|
"epoch": 3.111111111111111,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004483535276043881,
|
||
|
|
"loss": 6.0736,
|
||
|
|
"mean_token_accuracy": 0.16600707471370696,
|
||
|
|
"num_tokens": 6619938.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.316706657409668,
|
||
|
|
"epoch": 3.116959064327485,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004480543360853665,
|
||
|
|
"loss": 6.0299,
|
||
|
|
"mean_token_accuracy": 0.16921459436416625,
|
||
|
|
"num_tokens": 6632850.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1754241466522215,
|
||
|
|
"epoch": 3.1228070175438596,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004477543934981167,
|
||
|
|
"loss": 5.9695,
|
||
|
|
"mean_token_accuracy": 0.17961825728416442,
|
||
|
|
"num_tokens": 6645761.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292502784729004,
|
||
|
|
"epoch": 3.128654970760234,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00044745370114441103,
|
||
|
|
"loss": 6.0366,
|
||
|
|
"mean_token_accuracy": 0.1701852262020111,
|
||
|
|
"num_tokens": 6657861.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.276504468917847,
|
||
|
|
"epoch": 3.134502923976608,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00044715226032927585,
|
||
|
|
"loss": 6.0006,
|
||
|
|
"mean_token_accuracy": 0.17872752547264098,
|
||
|
|
"num_tokens": 6670495.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1659952163696286,
|
||
|
|
"epoch": 3.1403508771929824,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004468500723609859,
|
||
|
|
"loss": 5.9432,
|
||
|
|
"mean_token_accuracy": 0.1738198384642601,
|
||
|
|
"num_tokens": 6683127.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334905481338501,
|
||
|
|
"epoch": 3.146198830409357,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00044654713855105864,
|
||
|
|
"loss": 6.0296,
|
||
|
|
"mean_token_accuracy": 0.15999045521020888,
|
||
|
|
"num_tokens": 6696159.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.220273876190186,
|
||
|
|
"epoch": 3.152046783625731,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004462434602142486,
|
||
|
|
"loss": 6.1062,
|
||
|
|
"mean_token_accuracy": 0.16007876843214036,
|
||
|
|
"num_tokens": 6708993.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.395969343185425,
|
||
|
|
"epoch": 3.1578947368421053,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004459390386685414,
|
||
|
|
"loss": 6.1123,
|
||
|
|
"mean_token_accuracy": 0.16330592781305314,
|
||
|
|
"num_tokens": 6722121.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2217127799987795,
|
||
|
|
"epoch": 3.1637426900584797,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00044563387523514854,
|
||
|
|
"loss": 5.9469,
|
||
|
|
"mean_token_accuracy": 0.1772634580731392,
|
||
|
|
"num_tokens": 6734167.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214418268203735,
|
||
|
|
"epoch": 3.1695906432748537,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004453279712385011,
|
||
|
|
"loss": 6.021,
|
||
|
|
"mean_token_accuracy": 0.16194382905960084,
|
||
|
|
"num_tokens": 6745720.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.237218379974365,
|
||
|
|
"epoch": 3.175438596491228,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004450213280062444,
|
||
|
|
"loss": 6.0187,
|
||
|
|
"mean_token_accuracy": 0.16889381408691406,
|
||
|
|
"num_tokens": 6757523.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3465491771698,
|
||
|
|
"epoch": 3.181286549707602,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00044471394686923206,
|
||
|
|
"loss": 6.0407,
|
||
|
|
"mean_token_accuracy": 0.1681484967470169,
|
||
|
|
"num_tokens": 6768775.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221315574645996,
|
||
|
|
"epoch": 3.1871345029239766,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004444058291615202,
|
||
|
|
"loss": 6.0266,
|
||
|
|
"mean_token_accuracy": 0.1673452228307724,
|
||
|
|
"num_tokens": 6781547.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.299113178253174,
|
||
|
|
"epoch": 3.192982456140351,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004440969762203618,
|
||
|
|
"loss": 6.078,
|
||
|
|
"mean_token_accuracy": 0.1614588350057602,
|
||
|
|
"num_tokens": 6794708.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23675856590271,
|
||
|
|
"epoch": 3.198830409356725,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004437873893862008,
|
||
|
|
"loss": 5.9975,
|
||
|
|
"mean_token_accuracy": 0.17490203380584718,
|
||
|
|
"num_tokens": 6807738.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.291070127487183,
|
||
|
|
"epoch": 3.2046783625730995,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00044347707000266627,
|
||
|
|
"loss": 6.0442,
|
||
|
|
"mean_token_accuracy": 0.1675952211022377,
|
||
|
|
"num_tokens": 6820851.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2867292881011965,
|
||
|
|
"epoch": 3.2105263157894735,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00044316601941656655,
|
||
|
|
"loss": 6.0184,
|
||
|
|
"mean_token_accuracy": 0.17706366404891014,
|
||
|
|
"num_tokens": 6833888.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255019903182983,
|
||
|
|
"epoch": 3.216374269005848,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004428542389778834,
|
||
|
|
"loss": 6.0274,
|
||
|
|
"mean_token_accuracy": 0.1700237587094307,
|
||
|
|
"num_tokens": 6846104.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2286630153656,
|
||
|
|
"epoch": 3.2222222222222223,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004425417300397665,
|
||
|
|
"loss": 6.037,
|
||
|
|
"mean_token_accuracy": 0.16896592527627946,
|
||
|
|
"num_tokens": 6857458.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.239684581756592,
|
||
|
|
"epoch": 3.2280701754385963,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00044222849395852683,
|
||
|
|
"loss": 5.9856,
|
||
|
|
"mean_token_accuracy": 0.1761329233646393,
|
||
|
|
"num_tokens": 6870455.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.306159734725952,
|
||
|
|
"epoch": 3.2339181286549707,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00044191453209363165,
|
||
|
|
"loss": 6.0668,
|
||
|
|
"mean_token_accuracy": 0.16515958905220032,
|
||
|
|
"num_tokens": 6883359.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227142190933227,
|
||
|
|
"epoch": 3.239766081871345,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004415998458076978,
|
||
|
|
"loss": 6.0007,
|
||
|
|
"mean_token_accuracy": 0.17450052350759507,
|
||
|
|
"num_tokens": 6894940.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2444319248199465,
|
||
|
|
"epoch": 3.245614035087719,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00044128443646648634,
|
||
|
|
"loss": 6.0544,
|
||
|
|
"mean_token_accuracy": 0.16498649269342422,
|
||
|
|
"num_tokens": 6905422.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267055034637451,
|
||
|
|
"epoch": 3.2514619883040936,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00044096830543889653,
|
||
|
|
"loss": 6.0624,
|
||
|
|
"mean_token_accuracy": 0.16859742850065232,
|
||
|
|
"num_tokens": 6918106.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.279865407943726,
|
||
|
|
"epoch": 3.257309941520468,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004406514540969596,
|
||
|
|
"loss": 6.0214,
|
||
|
|
"mean_token_accuracy": 0.1736454963684082,
|
||
|
|
"num_tokens": 6930975.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.294392347335815,
|
||
|
|
"epoch": 3.263157894736842,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00044033388381583324,
|
||
|
|
"loss": 6.1134,
|
||
|
|
"mean_token_accuracy": 0.16156723201274872,
|
||
|
|
"num_tokens": 6944436.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.283486270904541,
|
||
|
|
"epoch": 3.2690058479532165,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00044001559597379503,
|
||
|
|
"loss": 6.0695,
|
||
|
|
"mean_token_accuracy": 0.16336419731378554,
|
||
|
|
"num_tokens": 6957095.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25795955657959,
|
||
|
|
"epoch": 3.2748538011695905,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004396965919522373,
|
||
|
|
"loss": 6.0156,
|
||
|
|
"mean_token_accuracy": 0.17714956402778625,
|
||
|
|
"num_tokens": 6969792.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230940628051758,
|
||
|
|
"epoch": 3.280701754385965,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00043937687313565997,
|
||
|
|
"loss": 6.071,
|
||
|
|
"mean_token_accuracy": 0.16743203848600388,
|
||
|
|
"num_tokens": 6982054.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.288463973999024,
|
||
|
|
"epoch": 3.2865497076023393,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004390564409116661,
|
||
|
|
"loss": 6.0659,
|
||
|
|
"mean_token_accuracy": 0.1691078871488571,
|
||
|
|
"num_tokens": 6994057.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.253631114959717,
|
||
|
|
"epoch": 3.2923976608187133,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00043873529667095423,
|
||
|
|
"loss": 6.0641,
|
||
|
|
"mean_token_accuracy": 0.16721298396587372,
|
||
|
|
"num_tokens": 7006417.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.269735097885132,
|
||
|
|
"epoch": 3.2982456140350878,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00043841344180731346,
|
||
|
|
"loss": 6.0797,
|
||
|
|
"mean_token_accuracy": 0.1629992201924324,
|
||
|
|
"num_tokens": 7018331.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222368478775024,
|
||
|
|
"epoch": 3.3040935672514617,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000438090877717617,
|
||
|
|
"loss": 5.9721,
|
||
|
|
"mean_token_accuracy": 0.17398224472999574,
|
||
|
|
"num_tokens": 7031654.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366477680206299,
|
||
|
|
"epoch": 3.309941520467836,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004377676058018161,
|
||
|
|
"loss": 6.0526,
|
||
|
|
"mean_token_accuracy": 0.16913604736328125,
|
||
|
|
"num_tokens": 7044921.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193389797210694,
|
||
|
|
"epoch": 3.3157894736842106,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004374436274629341,
|
||
|
|
"loss": 6.0087,
|
||
|
|
"mean_token_accuracy": 0.16850136071443558,
|
||
|
|
"num_tokens": 7056700.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223044347763062,
|
||
|
|
"epoch": 3.3216374269005846,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004371189441070602,
|
||
|
|
"loss": 5.9538,
|
||
|
|
"mean_token_accuracy": 0.16803479343652725,
|
||
|
|
"num_tokens": 7069196.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1773065567016605,
|
||
|
|
"epoch": 3.327485380116959,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004367935571433433,
|
||
|
|
"loss": 5.9753,
|
||
|
|
"mean_token_accuracy": 0.1719022199511528,
|
||
|
|
"num_tokens": 7081528.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.324714183807373,
|
||
|
|
"epoch": 3.3333333333333335,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004364674679839864,
|
||
|
|
"loss": 6.0826,
|
||
|
|
"mean_token_accuracy": 0.16474541276693344,
|
||
|
|
"num_tokens": 7093474.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129945898056031,
|
||
|
|
"epoch": 3.3391812865497075,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004361406780442398,
|
||
|
|
"loss": 6.0099,
|
||
|
|
"mean_token_accuracy": 0.17193978726863862,
|
||
|
|
"num_tokens": 7105508.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215554857254029,
|
||
|
|
"epoch": 3.345029239766082,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00043581318874239504,
|
||
|
|
"loss": 6.0304,
|
||
|
|
"mean_token_accuracy": 0.17089419662952424,
|
||
|
|
"num_tokens": 7117952.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.258291435241699,
|
||
|
|
"epoch": 3.3508771929824563,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00043548500149977946,
|
||
|
|
"loss": 6.0095,
|
||
|
|
"mean_token_accuracy": 0.17439546287059784,
|
||
|
|
"num_tokens": 7130666.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.19056134223938,
|
||
|
|
"epoch": 3.3567251461988303,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004351561177407491,
|
||
|
|
"loss": 6.0386,
|
||
|
|
"mean_token_accuracy": 0.1704059824347496,
|
||
|
|
"num_tokens": 7142717.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332802963256836,
|
||
|
|
"epoch": 3.3625730994152048,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004348265388926831,
|
||
|
|
"loss": 6.0931,
|
||
|
|
"mean_token_accuracy": 0.17004126459360122,
|
||
|
|
"num_tokens": 7154794.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241904211044312,
|
||
|
|
"epoch": 3.3684210526315788,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004344962663859771,
|
||
|
|
"loss": 6.1317,
|
||
|
|
"mean_token_accuracy": 0.1645464852452278,
|
||
|
|
"num_tokens": 7168907.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176318168640137,
|
||
|
|
"epoch": 3.374269005847953,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00043416530165403777,
|
||
|
|
"loss": 5.9582,
|
||
|
|
"mean_token_accuracy": 0.18327067345380782,
|
||
|
|
"num_tokens": 7180828.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178667974472046,
|
||
|
|
"epoch": 3.3801169590643276,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004338336461332756,
|
||
|
|
"loss": 5.9757,
|
||
|
|
"mean_token_accuracy": 0.17354782670736313,
|
||
|
|
"num_tokens": 7193493.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248239278793335,
|
||
|
|
"epoch": 3.3859649122807016,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00043350130126309936,
|
||
|
|
"loss": 5.9901,
|
||
|
|
"mean_token_accuracy": 0.16796165108680725,
|
||
|
|
"num_tokens": 7206033.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2647926807403564,
|
||
|
|
"epoch": 3.391812865497076,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00043316826848590955,
|
||
|
|
"loss": 6.0306,
|
||
|
|
"mean_token_accuracy": 0.16667379140853883,
|
||
|
|
"num_tokens": 7218813.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211006784439087,
|
||
|
|
"epoch": 3.39766081871345,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004328345492470924,
|
||
|
|
"loss": 6.0334,
|
||
|
|
"mean_token_accuracy": 0.1743611142039299,
|
||
|
|
"num_tokens": 7230698.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228032875061035,
|
||
|
|
"epoch": 3.4035087719298245,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004325001449950134,
|
||
|
|
"loss": 6.0538,
|
||
|
|
"mean_token_accuracy": 0.16597449034452438,
|
||
|
|
"num_tokens": 7243354.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.166584300994873,
|
||
|
|
"epoch": 3.409356725146199,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004321650571810109,
|
||
|
|
"loss": 5.9793,
|
||
|
|
"mean_token_accuracy": 0.17830784916877745,
|
||
|
|
"num_tokens": 7255855.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192124128341675,
|
||
|
|
"epoch": 3.415204678362573,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004318292872593899,
|
||
|
|
"loss": 6.0771,
|
||
|
|
"mean_token_accuracy": 0.16802599728107454,
|
||
|
|
"num_tokens": 7268921.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322266912460327,
|
||
|
|
"epoch": 3.4210526315789473,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004314928366874162,
|
||
|
|
"loss": 6.0852,
|
||
|
|
"mean_token_accuracy": 0.16782018393278123,
|
||
|
|
"num_tokens": 7281467.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1737288475036625,
|
||
|
|
"epoch": 3.426900584795322,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004311557069253092,
|
||
|
|
"loss": 5.9958,
|
||
|
|
"mean_token_accuracy": 0.17513801902532578,
|
||
|
|
"num_tokens": 7294887.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26305046081543,
|
||
|
|
"epoch": 3.4327485380116958,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004308178994362364,
|
||
|
|
"loss": 6.1226,
|
||
|
|
"mean_token_accuracy": 0.16816052198410034,
|
||
|
|
"num_tokens": 7307009.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203187894821167,
|
||
|
|
"epoch": 3.43859649122807,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00043047941568630644,
|
||
|
|
"loss": 6.0258,
|
||
|
|
"mean_token_accuracy": 0.16697119027376175,
|
||
|
|
"num_tokens": 7319751.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.308957433700561,
|
||
|
|
"epoch": 3.4444444444444446,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00043014025714456305,
|
||
|
|
"loss": 6.159,
|
||
|
|
"mean_token_accuracy": 0.16409108489751817,
|
||
|
|
"num_tokens": 7333952.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.165237045288086,
|
||
|
|
"epoch": 3.4502923976608186,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004298004252829787,
|
||
|
|
"loss": 5.8983,
|
||
|
|
"mean_token_accuracy": 0.179711976647377,
|
||
|
|
"num_tokens": 7346834.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238269376754761,
|
||
|
|
"epoch": 3.456140350877193,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000429459921576448,
|
||
|
|
"loss": 6.0621,
|
||
|
|
"mean_token_accuracy": 0.16733657717704772,
|
||
|
|
"num_tokens": 7359165.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2978363037109375,
|
||
|
|
"epoch": 3.461988304093567,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00042911874750278133,
|
||
|
|
"loss": 6.1385,
|
||
|
|
"mean_token_accuracy": 0.1645335614681244,
|
||
|
|
"num_tokens": 7371585.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2088147640228275,
|
||
|
|
"epoch": 3.4678362573099415,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00042877690454269884,
|
||
|
|
"loss": 6.0273,
|
||
|
|
"mean_token_accuracy": 0.17075373977422714,
|
||
|
|
"num_tokens": 7383455.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189100456237793,
|
||
|
|
"epoch": 3.473684210526316,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00042843439417982344,
|
||
|
|
"loss": 6.0859,
|
||
|
|
"mean_token_accuracy": 0.16834579408168793,
|
||
|
|
"num_tokens": 7395918.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28304533958435,
|
||
|
|
"epoch": 3.47953216374269,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004280912179006746,
|
||
|
|
"loss": 6.0709,
|
||
|
|
"mean_token_accuracy": 0.17032156884670258,
|
||
|
|
"num_tokens": 7408053.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254499197006226,
|
||
|
|
"epoch": 3.4853801169590644,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000427747377194662,
|
||
|
|
"loss": 6.1103,
|
||
|
|
"mean_token_accuracy": 0.16387250721454621,
|
||
|
|
"num_tokens": 7419947.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178836011886597,
|
||
|
|
"epoch": 3.4912280701754383,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004274028735540789,
|
||
|
|
"loss": 5.9897,
|
||
|
|
"mean_token_accuracy": 0.16600441485643386,
|
||
|
|
"num_tokens": 7433022.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194962644577027,
|
||
|
|
"epoch": 3.497076023391813,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00042705770847409596,
|
||
|
|
"loss": 5.9971,
|
||
|
|
"mean_token_accuracy": 0.17548950910568237,
|
||
|
|
"num_tokens": 7445280.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.260204601287842,
|
||
|
|
"epoch": 3.502923976608187,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00042671188345275423,
|
||
|
|
"loss": 5.9881,
|
||
|
|
"mean_token_accuracy": 0.16856114268302919,
|
||
|
|
"num_tokens": 7457324.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204137372970581,
|
||
|
|
"epoch": 3.5087719298245617,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004263653999909593,
|
||
|
|
"loss": 6.029,
|
||
|
|
"mean_token_accuracy": 0.16895542293787003,
|
||
|
|
"num_tokens": 7469070.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.5087719298245617,
|
||
|
|
"eval_entropy": 6.128441359089539,
|
||
|
|
"eval_loss": 6.679920673370361,
|
||
|
|
"eval_mean_token_accuracy": 0.14558876126147477,
|
||
|
|
"eval_num_tokens": 7469070.0,
|
||
|
|
"eval_runtime": 2.2751,
|
||
|
|
"eval_samples_per_second": 1189.856,
|
||
|
|
"eval_steps_per_second": 149.007,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2145637512207035,
|
||
|
|
"epoch": 3.5146198830409356,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000426018259592474,
|
||
|
|
"loss": 6.1071,
|
||
|
|
"mean_token_accuracy": 0.1634528800845146,
|
||
|
|
"num_tokens": 7480988.0,
|
||
|
|
"step": 3005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211821174621582,
|
||
|
|
"epoch": 3.52046783625731,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004256704637639126,
|
||
|
|
"loss": 6.0321,
|
||
|
|
"mean_token_accuracy": 0.17610189467668533,
|
||
|
|
"num_tokens": 7493557.0,
|
||
|
|
"step": 3010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219289827346802,
|
||
|
|
"epoch": 3.526315789473684,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004253220140147341,
|
||
|
|
"loss": 6.0667,
|
||
|
|
"mean_token_accuracy": 0.16670928597450257,
|
||
|
|
"num_tokens": 7507446.0,
|
||
|
|
"step": 3015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223416662216186,
|
||
|
|
"epoch": 3.5321637426900585,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004249729118572352,
|
||
|
|
"loss": 5.9796,
|
||
|
|
"mean_token_accuracy": 0.16335187554359437,
|
||
|
|
"num_tokens": 7520054.0,
|
||
|
|
"step": 3020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134494256973267,
|
||
|
|
"epoch": 3.538011695906433,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004246231588065444,
|
||
|
|
"loss": 5.9011,
|
||
|
|
"mean_token_accuracy": 0.1799098491668701,
|
||
|
|
"num_tokens": 7533141.0,
|
||
|
|
"step": 3025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.218474960327148,
|
||
|
|
"epoch": 3.543859649122807,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000424272756380615,
|
||
|
|
"loss": 6.0845,
|
||
|
|
"mean_token_accuracy": 0.16653485000133514,
|
||
|
|
"num_tokens": 7545544.0,
|
||
|
|
"step": 3030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.219445610046387,
|
||
|
|
"epoch": 3.5497076023391814,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004239217061002188,
|
||
|
|
"loss": 6.049,
|
||
|
|
"mean_token_accuracy": 0.1735091909766197,
|
||
|
|
"num_tokens": 7558055.0,
|
||
|
|
"step": 3035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141424131393433,
|
||
|
|
"epoch": 3.5555555555555554,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00042357000948893894,
|
||
|
|
"loss": 5.968,
|
||
|
|
"mean_token_accuracy": 0.17887038886547088,
|
||
|
|
"num_tokens": 7569951.0,
|
||
|
|
"step": 3040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.251427221298218,
|
||
|
|
"epoch": 3.56140350877193,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00042321766807316405,
|
||
|
|
"loss": 6.1178,
|
||
|
|
"mean_token_accuracy": 0.160573510825634,
|
||
|
|
"num_tokens": 7581810.0,
|
||
|
|
"step": 3045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.284236001968384,
|
||
|
|
"epoch": 3.5672514619883042,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00042286468338208113,
|
||
|
|
"loss": 6.0595,
|
||
|
|
"mean_token_accuracy": 0.16903978437185288,
|
||
|
|
"num_tokens": 7594896.0,
|
||
|
|
"step": 3050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.211694717407227,
|
||
|
|
"epoch": 3.573099415204678,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004225110569476691,
|
||
|
|
"loss": 6.076,
|
||
|
|
"mean_token_accuracy": 0.17121948003768922,
|
||
|
|
"num_tokens": 7606620.0,
|
||
|
|
"step": 3055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.15580186843872,
|
||
|
|
"epoch": 3.5789473684210527,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000422156790304692,
|
||
|
|
"loss": 5.9498,
|
||
|
|
"mean_token_accuracy": 0.18231300860643387,
|
||
|
|
"num_tokens": 7619493.0,
|
||
|
|
"step": 3060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194050312042236,
|
||
|
|
"epoch": 3.5847953216374266,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00042180188499069246,
|
||
|
|
"loss": 5.9533,
|
||
|
|
"mean_token_accuracy": 0.1704913094639778,
|
||
|
|
"num_tokens": 7632711.0,
|
||
|
|
"step": 3065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184117841720581,
|
||
|
|
"epoch": 3.590643274853801,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000421446342545985,
|
||
|
|
"loss": 6.0073,
|
||
|
|
"mean_token_accuracy": 0.17123773247003554,
|
||
|
|
"num_tokens": 7645209.0,
|
||
|
|
"step": 3070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2523500442504885,
|
||
|
|
"epoch": 3.5964912280701755,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00042109016451364933,
|
||
|
|
"loss": 6.1221,
|
||
|
|
"mean_token_accuracy": 0.16324148774147035,
|
||
|
|
"num_tokens": 7657347.0,
|
||
|
|
"step": 3075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3153074264526365,
|
||
|
|
"epoch": 3.60233918128655,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00042073335243952354,
|
||
|
|
"loss": 6.0601,
|
||
|
|
"mean_token_accuracy": 0.16268718540668486,
|
||
|
|
"num_tokens": 7669593.0,
|
||
|
|
"step": 3080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202613353729248,
|
||
|
|
"epoch": 3.608187134502924,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004203759078721979,
|
||
|
|
"loss": 6.0781,
|
||
|
|
"mean_token_accuracy": 0.16427508741617203,
|
||
|
|
"num_tokens": 7682548.0,
|
||
|
|
"step": 3085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.246861743927002,
|
||
|
|
"epoch": 3.6140350877192984,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004200178323630072,
|
||
|
|
"loss": 6.0917,
|
||
|
|
"mean_token_accuracy": 0.16837276816368102,
|
||
|
|
"num_tokens": 7694554.0,
|
||
|
|
"step": 3090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.251531887054443,
|
||
|
|
"epoch": 3.6198830409356724,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00041965912746602495,
|
||
|
|
"loss": 6.1319,
|
||
|
|
"mean_token_accuracy": 0.16645267605781555,
|
||
|
|
"num_tokens": 7707747.0,
|
||
|
|
"step": 3095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.260301303863526,
|
||
|
|
"epoch": 3.625730994152047,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00041929979473805606,
|
||
|
|
"loss": 6.1083,
|
||
|
|
"mean_token_accuracy": 0.16741736829280854,
|
||
|
|
"num_tokens": 7719487.0,
|
||
|
|
"step": 3100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321317863464356,
|
||
|
|
"epoch": 3.6315789473684212,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00041893983573863044,
|
||
|
|
"loss": 6.1158,
|
||
|
|
"mean_token_accuracy": 0.16496975719928741,
|
||
|
|
"num_tokens": 7732531.0,
|
||
|
|
"step": 3105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.183379411697388,
|
||
|
|
"epoch": 3.6374269005847952,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00041857925202999586,
|
||
|
|
"loss": 6.0487,
|
||
|
|
"mean_token_accuracy": 0.17389170825481415,
|
||
|
|
"num_tokens": 7745034.0,
|
||
|
|
"step": 3110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238416576385498,
|
||
|
|
"epoch": 3.6432748538011697,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004182180451771115,
|
||
|
|
"loss": 6.0471,
|
||
|
|
"mean_token_accuracy": 0.17047393023967744,
|
||
|
|
"num_tokens": 7757442.0,
|
||
|
|
"step": 3115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203444528579712,
|
||
|
|
"epoch": 3.6491228070175437,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004178562167476409,
|
||
|
|
"loss": 6.059,
|
||
|
|
"mean_token_accuracy": 0.16772228926420213,
|
||
|
|
"num_tokens": 7770358.0,
|
||
|
|
"step": 3120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192870330810547,
|
||
|
|
"epoch": 3.654970760233918,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00041749376831194565,
|
||
|
|
"loss": 6.0368,
|
||
|
|
"mean_token_accuracy": 0.1692536473274231,
|
||
|
|
"num_tokens": 7783611.0,
|
||
|
|
"step": 3125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1335084438323975,
|
||
|
|
"epoch": 3.6608187134502925,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004171307014430777,
|
||
|
|
"loss": 6.0387,
|
||
|
|
"mean_token_accuracy": 0.16792730391025543,
|
||
|
|
"num_tokens": 7795522.0,
|
||
|
|
"step": 3130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.30687108039856,
|
||
|
|
"epoch": 3.6666666666666665,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00041676701771677343,
|
||
|
|
"loss": 6.0231,
|
||
|
|
"mean_token_accuracy": 0.17522512823343278,
|
||
|
|
"num_tokens": 7806801.0,
|
||
|
|
"step": 3135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.218495416641235,
|
||
|
|
"epoch": 3.672514619883041,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004164027187114463,
|
||
|
|
"loss": 6.1017,
|
||
|
|
"mean_token_accuracy": 0.16423556953668594,
|
||
|
|
"num_tokens": 7821084.0,
|
||
|
|
"step": 3140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064626693725586,
|
||
|
|
"epoch": 3.678362573099415,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00041603780600818,
|
||
|
|
"loss": 5.8612,
|
||
|
|
"mean_token_accuracy": 0.18930941075086594,
|
||
|
|
"num_tokens": 7834065.0,
|
||
|
|
"step": 3145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198625755310059,
|
||
|
|
"epoch": 3.6842105263157894,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004156722811907219,
|
||
|
|
"loss": 6.0545,
|
||
|
|
"mean_token_accuracy": 0.17617928832769394,
|
||
|
|
"num_tokens": 7846378.0,
|
||
|
|
"step": 3150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150203609466553,
|
||
|
|
"epoch": 3.690058479532164,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00041530614584547594,
|
||
|
|
"loss": 6.0576,
|
||
|
|
"mean_token_accuracy": 0.16719081699848176,
|
||
|
|
"num_tokens": 7858933.0,
|
||
|
|
"step": 3155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12995719909668,
|
||
|
|
"epoch": 3.6959064327485383,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00041493940156149577,
|
||
|
|
"loss": 5.8917,
|
||
|
|
"mean_token_accuracy": 0.17800081372261048,
|
||
|
|
"num_tokens": 7870408.0,
|
||
|
|
"step": 3160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26948504447937,
|
||
|
|
"epoch": 3.7017543859649122,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000414572049930478,
|
||
|
|
"loss": 6.0676,
|
||
|
|
"mean_token_accuracy": 0.16742925494909286,
|
||
|
|
"num_tokens": 7882778.0,
|
||
|
|
"step": 3165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120087480545044,
|
||
|
|
"epoch": 3.7076023391812867,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00041420409254675465,
|
||
|
|
"loss": 6.0476,
|
||
|
|
"mean_token_accuracy": 0.17076934576034547,
|
||
|
|
"num_tokens": 7895169.0,
|
||
|
|
"step": 3170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24736475944519,
|
||
|
|
"epoch": 3.7134502923976607,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004138355310072876,
|
||
|
|
"loss": 6.0927,
|
||
|
|
"mean_token_accuracy": 0.16883240789175033,
|
||
|
|
"num_tokens": 7908607.0,
|
||
|
|
"step": 3175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.208080291748047,
|
||
|
|
"epoch": 3.719298245614035,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00041346636691166015,
|
||
|
|
"loss": 6.0512,
|
||
|
|
"mean_token_accuracy": 0.16605579107999802,
|
||
|
|
"num_tokens": 7922269.0,
|
||
|
|
"step": 3180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169638681411743,
|
||
|
|
"epoch": 3.7251461988304095,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00041309660186207093,
|
||
|
|
"loss": 6.0064,
|
||
|
|
"mean_token_accuracy": 0.17252669036388396,
|
||
|
|
"num_tokens": 7935205.0,
|
||
|
|
"step": 3185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2019671440124515,
|
||
|
|
"epoch": 3.7309941520467835,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00041272623746332687,
|
||
|
|
"loss": 6.0503,
|
||
|
|
"mean_token_accuracy": 0.16953324526548386,
|
||
|
|
"num_tokens": 7947970.0,
|
||
|
|
"step": 3190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03260989189148,
|
||
|
|
"epoch": 3.736842105263158,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00041235527532283603,
|
||
|
|
"loss": 5.8989,
|
||
|
|
"mean_token_accuracy": 0.18294101357460021,
|
||
|
|
"num_tokens": 7961978.0,
|
||
|
|
"step": 3195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254106092453003,
|
||
|
|
"epoch": 3.742690058479532,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004119837170506005,
|
||
|
|
"loss": 6.0834,
|
||
|
|
"mean_token_accuracy": 0.16846547573804854,
|
||
|
|
"num_tokens": 7974708.0,
|
||
|
|
"step": 3200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181708240509034,
|
||
|
|
"epoch": 3.7485380116959064,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00041161156425921004,
|
||
|
|
"loss": 6.0482,
|
||
|
|
"mean_token_accuracy": 0.17681985050439836,
|
||
|
|
"num_tokens": 7986179.0,
|
||
|
|
"step": 3205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192408084869385,
|
||
|
|
"epoch": 3.754385964912281,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00041123881856383436,
|
||
|
|
"loss": 6.082,
|
||
|
|
"mean_token_accuracy": 0.1717871457338333,
|
||
|
|
"num_tokens": 7997816.0,
|
||
|
|
"step": 3210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.245402860641479,
|
||
|
|
"epoch": 3.760233918128655,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004108654815822165,
|
||
|
|
"loss": 6.0043,
|
||
|
|
"mean_token_accuracy": 0.17063761055469512,
|
||
|
|
"num_tokens": 8009407.0,
|
||
|
|
"step": 3215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148101043701172,
|
||
|
|
"epoch": 3.7660818713450293,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004104915549346658,
|
||
|
|
"loss": 6.0677,
|
||
|
|
"mean_token_accuracy": 0.16253868937492372,
|
||
|
|
"num_tokens": 8021446.0,
|
||
|
|
"step": 3220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234766340255737,
|
||
|
|
"epoch": 3.7719298245614032,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00041011704024405065,
|
||
|
|
"loss": 6.1113,
|
||
|
|
"mean_token_accuracy": 0.16665791124105453,
|
||
|
|
"num_tokens": 8035219.0,
|
||
|
|
"step": 3225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1720973491668705,
|
||
|
|
"epoch": 3.7777777777777777,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00040974193913579174,
|
||
|
|
"loss": 5.9081,
|
||
|
|
"mean_token_accuracy": 0.1849777117371559,
|
||
|
|
"num_tokens": 8047619.0,
|
||
|
|
"step": 3230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264918661117553,
|
||
|
|
"epoch": 3.783625730994152,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004093662532378547,
|
||
|
|
"loss": 6.1062,
|
||
|
|
"mean_token_accuracy": 0.168757888674736,
|
||
|
|
"num_tokens": 8059241.0,
|
||
|
|
"step": 3235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212861633300781,
|
||
|
|
"epoch": 3.7894736842105265,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004089899841807433,
|
||
|
|
"loss": 6.0373,
|
||
|
|
"mean_token_accuracy": 0.17117812037467955,
|
||
|
|
"num_tokens": 8071543.0,
|
||
|
|
"step": 3240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223536777496338,
|
||
|
|
"epoch": 3.7953216374269005,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00040861313359749217,
|
||
|
|
"loss": 6.0824,
|
||
|
|
"mean_token_accuracy": 0.1690210998058319,
|
||
|
|
"num_tokens": 8083515.0,
|
||
|
|
"step": 3245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0932951927185055,
|
||
|
|
"epoch": 3.801169590643275,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00040823570312366005,
|
||
|
|
"loss": 6.0213,
|
||
|
|
"mean_token_accuracy": 0.17479997277259826,
|
||
|
|
"num_tokens": 8095703.0,
|
||
|
|
"step": 3250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252005004882813,
|
||
|
|
"epoch": 3.807017543859649,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000407857694397322,
|
||
|
|
"loss": 6.1364,
|
||
|
|
"mean_token_accuracy": 0.1613328844308853,
|
||
|
|
"num_tokens": 8108285.0,
|
||
|
|
"step": 3255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.166118144989014,
|
||
|
|
"epoch": 3.8128654970760234,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004074791090590632,
|
||
|
|
"loss": 6.0569,
|
||
|
|
"mean_token_accuracy": 0.16914817690849304,
|
||
|
|
"num_tokens": 8120943.0,
|
||
|
|
"step": 3260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248325777053833,
|
||
|
|
"epoch": 3.818713450292398,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004070999487519711,
|
||
|
|
"loss": 6.0787,
|
||
|
|
"mean_token_accuracy": 0.1629582852125168,
|
||
|
|
"num_tokens": 8133086.0,
|
||
|
|
"step": 3265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.269057273864746,
|
||
|
|
"epoch": 3.824561403508772,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00040672021512162864,
|
||
|
|
"loss": 6.1203,
|
||
|
|
"mean_token_accuracy": 0.16393942683935164,
|
||
|
|
"num_tokens": 8147320.0,
|
||
|
|
"step": 3270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.225903034210205,
|
||
|
|
"epoch": 3.8304093567251463,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000406339909816107,
|
||
|
|
"loss": 6.0656,
|
||
|
|
"mean_token_accuracy": 0.1687285840511322,
|
||
|
|
"num_tokens": 8160796.0,
|
||
|
|
"step": 3275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24839186668396,
|
||
|
|
"epoch": 3.8362573099415203,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004059590344859584,
|
||
|
|
"loss": 6.0284,
|
||
|
|
"mean_token_accuracy": 0.17493421584367752,
|
||
|
|
"num_tokens": 8173087.0,
|
||
|
|
"step": 3280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.121807718276978,
|
||
|
|
"epoch": 3.8421052631578947,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004055775907842092,
|
||
|
|
"loss": 5.9823,
|
||
|
|
"mean_token_accuracy": 0.17113222181797028,
|
||
|
|
"num_tokens": 8185274.0,
|
||
|
|
"step": 3285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16531662940979,
|
||
|
|
"epoch": 3.847953216374269,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004051955803663523,
|
||
|
|
"loss": 6.0555,
|
||
|
|
"mean_token_accuracy": 0.17454719841480254,
|
||
|
|
"num_tokens": 8197753.0,
|
||
|
|
"step": 3290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154142713546753,
|
||
|
|
"epoch": 3.853801169590643,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004048130048903404,
|
||
|
|
"loss": 6.0371,
|
||
|
|
"mean_token_accuracy": 0.17322636097669603,
|
||
|
|
"num_tokens": 8211882.0,
|
||
|
|
"step": 3295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13438982963562,
|
||
|
|
"epoch": 3.8596491228070176,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004044298660165786,
|
||
|
|
"loss": 5.916,
|
||
|
|
"mean_token_accuracy": 0.18147685527801513,
|
||
|
|
"num_tokens": 8225089.0,
|
||
|
|
"step": 3300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150515222549439,
|
||
|
|
"epoch": 3.8654970760233915,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00040404616540791683,
|
||
|
|
"loss": 6.09,
|
||
|
|
"mean_token_accuracy": 0.1675315096974373,
|
||
|
|
"num_tokens": 8238808.0,
|
||
|
|
"step": 3305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181009578704834,
|
||
|
|
"epoch": 3.871345029239766,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004036619047296435,
|
||
|
|
"loss": 6.0156,
|
||
|
|
"mean_token_accuracy": 0.17612116634845734,
|
||
|
|
"num_tokens": 8252482.0,
|
||
|
|
"step": 3310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.134653234481812,
|
||
|
|
"epoch": 3.8771929824561404,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004032770856494772,
|
||
|
|
"loss": 6.0731,
|
||
|
|
"mean_token_accuracy": 0.168783563375473,
|
||
|
|
"num_tokens": 8264232.0,
|
||
|
|
"step": 3315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2494958400726315,
|
||
|
|
"epoch": 3.883040935672515,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00040289170983756075,
|
||
|
|
"loss": 6.044,
|
||
|
|
"mean_token_accuracy": 0.1671254426240921,
|
||
|
|
"num_tokens": 8276784.0,
|
||
|
|
"step": 3320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179021739959717,
|
||
|
|
"epoch": 3.888888888888889,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004025057789664524,
|
||
|
|
"loss": 5.9821,
|
||
|
|
"mean_token_accuracy": 0.1696772500872612,
|
||
|
|
"num_tokens": 8287887.0,
|
||
|
|
"step": 3325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056670808792115,
|
||
|
|
"epoch": 3.8947368421052633,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004021192947111201,
|
||
|
|
"loss": 5.8272,
|
||
|
|
"mean_token_accuracy": 0.18709901124238967,
|
||
|
|
"num_tokens": 8301258.0,
|
||
|
|
"step": 3330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.166034603118897,
|
||
|
|
"epoch": 3.9005847953216373,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00040173225874893305,
|
||
|
|
"loss": 6.0599,
|
||
|
|
"mean_token_accuracy": 0.16901754289865495,
|
||
|
|
"num_tokens": 8313520.0,
|
||
|
|
"step": 3335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3037145137786865,
|
||
|
|
"epoch": 3.9064327485380117,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00040134467275965515,
|
||
|
|
"loss": 6.1209,
|
||
|
|
"mean_token_accuracy": 0.1667875036597252,
|
||
|
|
"num_tokens": 8325597.0,
|
||
|
|
"step": 3340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.20469183921814,
|
||
|
|
"epoch": 3.912280701754386,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004009565384254374,
|
||
|
|
"loss": 6.1277,
|
||
|
|
"mean_token_accuracy": 0.1658939853310585,
|
||
|
|
"num_tokens": 8337449.0,
|
||
|
|
"step": 3345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221516418457031,
|
||
|
|
"epoch": 3.91812865497076,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00040056785743081065,
|
||
|
|
"loss": 6.0543,
|
||
|
|
"mean_token_accuracy": 0.16897163838148116,
|
||
|
|
"num_tokens": 8348802.0,
|
||
|
|
"step": 3350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154680442810059,
|
||
|
|
"epoch": 3.9239766081871346,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004001786314626783,
|
||
|
|
"loss": 6.0327,
|
||
|
|
"mean_token_accuracy": 0.16565302461385728,
|
||
|
|
"num_tokens": 8360284.0,
|
||
|
|
"step": 3355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238961315155029,
|
||
|
|
"epoch": 3.9298245614035086,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003997888622103088,
|
||
|
|
"loss": 6.0725,
|
||
|
|
"mean_token_accuracy": 0.16827183216810226,
|
||
|
|
"num_tokens": 8372080.0,
|
||
|
|
"step": 3360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209335374832153,
|
||
|
|
"epoch": 3.935672514619883,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003993985513653289,
|
||
|
|
"loss": 6.0348,
|
||
|
|
"mean_token_accuracy": 0.17299555987119675,
|
||
|
|
"num_tokens": 8385178.0,
|
||
|
|
"step": 3365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169796943664551,
|
||
|
|
"epoch": 3.9415204678362574,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003990077006217155,
|
||
|
|
"loss": 5.9952,
|
||
|
|
"mean_token_accuracy": 0.17895442843437195,
|
||
|
|
"num_tokens": 8397735.0,
|
||
|
|
"step": 3370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192292356491089,
|
||
|
|
"epoch": 3.9473684210526314,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000398616311675789,
|
||
|
|
"loss": 6.1014,
|
||
|
|
"mean_token_accuracy": 0.163040691614151,
|
||
|
|
"num_tokens": 8409916.0,
|
||
|
|
"step": 3375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.243372392654419,
|
||
|
|
"epoch": 3.953216374269006,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00039822438622620523,
|
||
|
|
"loss": 6.0961,
|
||
|
|
"mean_token_accuracy": 0.16576609313488005,
|
||
|
|
"num_tokens": 8421883.0,
|
||
|
|
"step": 3380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145286417007446,
|
||
|
|
"epoch": 3.95906432748538,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00039783192597394896,
|
||
|
|
"loss": 5.9557,
|
||
|
|
"mean_token_accuracy": 0.180135016143322,
|
||
|
|
"num_tokens": 8433610.0,
|
||
|
|
"step": 3385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142775154113769,
|
||
|
|
"epoch": 3.9649122807017543,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00039743893262232584,
|
||
|
|
"loss": 6.0337,
|
||
|
|
"mean_token_accuracy": 0.16999948471784593,
|
||
|
|
"num_tokens": 8446194.0,
|
||
|
|
"step": 3390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227932405471802,
|
||
|
|
"epoch": 3.9707602339181287,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0003970454078769551,
|
||
|
|
"loss": 5.9873,
|
||
|
|
"mean_token_accuracy": 0.1788391575217247,
|
||
|
|
"num_tokens": 8458846.0,
|
||
|
|
"step": 3395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146195125579834,
|
||
|
|
"epoch": 3.976608187134503,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003966513534457623,
|
||
|
|
"loss": 6.0188,
|
||
|
|
"mean_token_accuracy": 0.1675675630569458,
|
||
|
|
"num_tokens": 8470087.0,
|
||
|
|
"step": 3400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169763040542603,
|
||
|
|
"epoch": 3.982456140350877,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003962567710389721,
|
||
|
|
"loss": 6.0321,
|
||
|
|
"mean_token_accuracy": 0.16720447689294815,
|
||
|
|
"num_tokens": 8481293.0,
|
||
|
|
"step": 3405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.253786087036133,
|
||
|
|
"epoch": 3.9883040935672516,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00039586166236910033,
|
||
|
|
"loss": 6.0778,
|
||
|
|
"mean_token_accuracy": 0.17446618378162385,
|
||
|
|
"num_tokens": 8493376.0,
|
||
|
|
"step": 3410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084576177597046,
|
||
|
|
"epoch": 3.9941520467836256,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003954660291509469,
|
||
|
|
"loss": 5.9455,
|
||
|
|
"mean_token_accuracy": 0.17232361286878586,
|
||
|
|
"num_tokens": 8506132.0,
|
||
|
|
"step": 3415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.168551397323609,
|
||
|
|
"epoch": 4.0,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00039506987310158854,
|
||
|
|
"loss": 6.0267,
|
||
|
|
"mean_token_accuracy": 0.1724356308579445,
|
||
|
|
"num_tokens": 8517936.0,
|
||
|
|
"step": 3420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230937385559082,
|
||
|
|
"epoch": 4.005847953216374,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00039467319594037076,
|
||
|
|
"loss": 5.6847,
|
||
|
|
"mean_token_accuracy": 0.17525452226400376,
|
||
|
|
"num_tokens": 8529863.0,
|
||
|
|
"step": 3425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085280418395996,
|
||
|
|
"epoch": 4.011695906432749,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0003942759993889009,
|
||
|
|
"loss": 5.6709,
|
||
|
|
"mean_token_accuracy": 0.1806148812174797,
|
||
|
|
"num_tokens": 8543621.0,
|
||
|
|
"step": 3430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150941228866577,
|
||
|
|
"epoch": 4.017543859649122,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00039387828517104044,
|
||
|
|
"loss": 5.6565,
|
||
|
|
"mean_token_accuracy": 0.18862948268651963,
|
||
|
|
"num_tokens": 8557865.0,
|
||
|
|
"step": 3435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003830862045288,
|
||
|
|
"epoch": 4.023391812865497,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00039348005501289775,
|
||
|
|
"loss": 5.5749,
|
||
|
|
"mean_token_accuracy": 0.1865679696202278,
|
||
|
|
"num_tokens": 8570203.0,
|
||
|
|
"step": 3440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034450674057007,
|
||
|
|
"epoch": 4.029239766081871,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00039308131064282016,
|
||
|
|
"loss": 5.6702,
|
||
|
|
"mean_token_accuracy": 0.1920771211385727,
|
||
|
|
"num_tokens": 8582638.0,
|
||
|
|
"step": 3445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160071849822998,
|
||
|
|
"epoch": 4.035087719298246,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0003926820537913868,
|
||
|
|
"loss": 5.7602,
|
||
|
|
"mean_token_accuracy": 0.1819230929017067,
|
||
|
|
"num_tokens": 8594973.0,
|
||
|
|
"step": 3450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104519033432007,
|
||
|
|
"epoch": 4.04093567251462,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003922822861914012,
|
||
|
|
"loss": 5.6108,
|
||
|
|
"mean_token_accuracy": 0.1898810312151909,
|
||
|
|
"num_tokens": 8607216.0,
|
||
|
|
"step": 3455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171421670913697,
|
||
|
|
"epoch": 4.046783625730994,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003918820095778832,
|
||
|
|
"loss": 5.837,
|
||
|
|
"mean_token_accuracy": 0.1758796513080597,
|
||
|
|
"num_tokens": 8620833.0,
|
||
|
|
"step": 3460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.086927223205566,
|
||
|
|
"epoch": 4.052631578947368,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00039148122568806215,
|
||
|
|
"loss": 5.6604,
|
||
|
|
"mean_token_accuracy": 0.19358818978071213,
|
||
|
|
"num_tokens": 8632931.0,
|
||
|
|
"step": 3465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072336101531983,
|
||
|
|
"epoch": 4.058479532163743,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003910799362613688,
|
||
|
|
"loss": 5.7241,
|
||
|
|
"mean_token_accuracy": 0.18470965772867204,
|
||
|
|
"num_tokens": 8644226.0,
|
||
|
|
"step": 3470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0288084030151365,
|
||
|
|
"epoch": 4.064327485380117,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00039067814303942806,
|
||
|
|
"loss": 5.5455,
|
||
|
|
"mean_token_accuracy": 0.2006165862083435,
|
||
|
|
"num_tokens": 8656569.0,
|
||
|
|
"step": 3475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935900688171387,
|
||
|
|
"epoch": 4.0701754385964914,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00039027584776605136,
|
||
|
|
"loss": 5.5805,
|
||
|
|
"mean_token_accuracy": 0.19241596907377242,
|
||
|
|
"num_tokens": 8668077.0,
|
||
|
|
"step": 3480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.110996341705322,
|
||
|
|
"epoch": 4.076023391812866,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00038987305218722904,
|
||
|
|
"loss": 5.6474,
|
||
|
|
"mean_token_accuracy": 0.18419574946165085,
|
||
|
|
"num_tokens": 8680227.0,
|
||
|
|
"step": 3485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142756986618042,
|
||
|
|
"epoch": 4.081871345029239,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003894697580511226,
|
||
|
|
"loss": 5.7381,
|
||
|
|
"mean_token_accuracy": 0.18420160561800003,
|
||
|
|
"num_tokens": 8692354.0,
|
||
|
|
"step": 3490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0983741760253904,
|
||
|
|
"epoch": 4.087719298245614,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003890659671080579,
|
||
|
|
"loss": 5.6895,
|
||
|
|
"mean_token_accuracy": 0.17424611002206802,
|
||
|
|
"num_tokens": 8704634.0,
|
||
|
|
"step": 3495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1060715675354,
|
||
|
|
"epoch": 4.093567251461988,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003886616811105162,
|
||
|
|
"loss": 5.745,
|
||
|
|
"mean_token_accuracy": 0.17576200813055037,
|
||
|
|
"num_tokens": 8717253.0,
|
||
|
|
"step": 3500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 4.093567251461988,
|
||
|
|
"eval_entropy": 6.073108372083456,
|
||
|
|
"eval_loss": 6.639997482299805,
|
||
|
|
"eval_mean_token_accuracy": 0.14698238965332683,
|
||
|
|
"eval_num_tokens": 8717253.0,
|
||
|
|
"eval_runtime": 2.2586,
|
||
|
|
"eval_samples_per_second": 1198.518,
|
||
|
|
"eval_steps_per_second": 150.091,
|
||
|
|
"step": 3500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143516969680786,
|
||
|
|
"epoch": 4.099415204678363,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00038825690181312793,
|
||
|
|
"loss": 5.7202,
|
||
|
|
"mean_token_accuracy": 0.18116975128650664,
|
||
|
|
"num_tokens": 8729840.0,
|
||
|
|
"step": 3505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049521732330322,
|
||
|
|
"epoch": 4.105263157894737,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00038785163097266424,
|
||
|
|
"loss": 5.5938,
|
||
|
|
"mean_token_accuracy": 0.19613462686538696,
|
||
|
|
"num_tokens": 8742065.0,
|
||
|
|
"step": 3510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133887815475464,
|
||
|
|
"epoch": 4.111111111111111,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003874458703480296,
|
||
|
|
"loss": 5.7423,
|
||
|
|
"mean_token_accuracy": 0.1807527393102646,
|
||
|
|
"num_tokens": 8754113.0,
|
||
|
|
"step": 3515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154109621047974,
|
||
|
|
"epoch": 4.116959064327485,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003870396217002542,
|
||
|
|
"loss": 5.8046,
|
||
|
|
"mean_token_accuracy": 0.1692167639732361,
|
||
|
|
"num_tokens": 8767255.0,
|
||
|
|
"step": 3520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071951532363892,
|
||
|
|
"epoch": 4.12280701754386,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0003866328867924864,
|
||
|
|
"loss": 5.7148,
|
||
|
|
"mean_token_accuracy": 0.1758098065853119,
|
||
|
|
"num_tokens": 8781010.0,
|
||
|
|
"step": 3525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154963207244873,
|
||
|
|
"epoch": 4.128654970760234,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003862256673899848,
|
||
|
|
"loss": 5.7342,
|
||
|
|
"mean_token_accuracy": 0.17801330834627152,
|
||
|
|
"num_tokens": 8794393.0,
|
||
|
|
"step": 3530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118505430221558,
|
||
|
|
"epoch": 4.1345029239766085,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0003858179652601108,
|
||
|
|
"loss": 5.8133,
|
||
|
|
"mean_token_accuracy": 0.16940056830644606,
|
||
|
|
"num_tokens": 8806496.0,
|
||
|
|
"step": 3535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076881074905396,
|
||
|
|
"epoch": 4.140350877192983,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00038540978217232086,
|
||
|
|
"loss": 5.6173,
|
||
|
|
"mean_token_accuracy": 0.18687908500432968,
|
||
|
|
"num_tokens": 8818411.0,
|
||
|
|
"step": 3540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091665840148925,
|
||
|
|
"epoch": 4.146198830409356,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00038500111989815894,
|
||
|
|
"loss": 5.7137,
|
||
|
|
"mean_token_accuracy": 0.18006578981876373,
|
||
|
|
"num_tokens": 8829714.0,
|
||
|
|
"step": 3545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047852277755737,
|
||
|
|
"epoch": 4.152046783625731,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00038459198021124853,
|
||
|
|
"loss": 5.6807,
|
||
|
|
"mean_token_accuracy": 0.182119782269001,
|
||
|
|
"num_tokens": 8842393.0,
|
||
|
|
"step": 3550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123600721359253,
|
||
|
|
"epoch": 4.157894736842105,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003841823648872852,
|
||
|
|
"loss": 5.7051,
|
||
|
|
"mean_token_accuracy": 0.18013963401317595,
|
||
|
|
"num_tokens": 8855263.0,
|
||
|
|
"step": 3555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101170301437378,
|
||
|
|
"epoch": 4.16374269005848,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003837722757040289,
|
||
|
|
"loss": 5.7581,
|
||
|
|
"mean_token_accuracy": 0.17724370807409287,
|
||
|
|
"num_tokens": 8868220.0,
|
||
|
|
"step": 3560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090213441848755,
|
||
|
|
"epoch": 4.169590643274854,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003833617144412961,
|
||
|
|
"loss": 5.7053,
|
||
|
|
"mean_token_accuracy": 0.18455604910850526,
|
||
|
|
"num_tokens": 8879106.0,
|
||
|
|
"step": 3565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087253141403198,
|
||
|
|
"epoch": 4.175438596491228,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0003829506828809521,
|
||
|
|
"loss": 5.776,
|
||
|
|
"mean_token_accuracy": 0.18370483666658402,
|
||
|
|
"num_tokens": 8891358.0,
|
||
|
|
"step": 3570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.154461765289307,
|
||
|
|
"epoch": 4.181286549707602,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003825391828069032,
|
||
|
|
"loss": 5.7036,
|
||
|
|
"mean_token_accuracy": 0.18057027608156204,
|
||
|
|
"num_tokens": 8904327.0,
|
||
|
|
"step": 3575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056489086151123,
|
||
|
|
"epoch": 4.187134502923977,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003821272160050894,
|
||
|
|
"loss": 5.6609,
|
||
|
|
"mean_token_accuracy": 0.1817365527153015,
|
||
|
|
"num_tokens": 8916515.0,
|
||
|
|
"step": 3580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060200548171997,
|
||
|
|
"epoch": 4.192982456140351,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003817147842634762,
|
||
|
|
"loss": 5.7409,
|
||
|
|
"mean_token_accuracy": 0.17737309783697128,
|
||
|
|
"num_tokens": 8929482.0,
|
||
|
|
"step": 3585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192071437835693,
|
||
|
|
"epoch": 4.1988304093567255,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003813018893720468,
|
||
|
|
"loss": 5.7947,
|
||
|
|
"mean_token_accuracy": 0.17069124579429626,
|
||
|
|
"num_tokens": 8942328.0,
|
||
|
|
"step": 3590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0926515579223635,
|
||
|
|
"epoch": 4.204678362573099,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00038088853312279473,
|
||
|
|
"loss": 5.7099,
|
||
|
|
"mean_token_accuracy": 0.1848149061203003,
|
||
|
|
"num_tokens": 8955116.0,
|
||
|
|
"step": 3595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098628997802734,
|
||
|
|
"epoch": 4.2105263157894735,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003804747173097157,
|
||
|
|
"loss": 5.7856,
|
||
|
|
"mean_token_accuracy": 0.17035460472106934,
|
||
|
|
"num_tokens": 8967459.0,
|
||
|
|
"step": 3600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093827104568481,
|
||
|
|
"epoch": 4.216374269005848,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00038006044372880006,
|
||
|
|
"loss": 5.7075,
|
||
|
|
"mean_token_accuracy": 0.1807893306016922,
|
||
|
|
"num_tokens": 8980079.0,
|
||
|
|
"step": 3605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103314018249511,
|
||
|
|
"epoch": 4.222222222222222,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00037964571417802473,
|
||
|
|
"loss": 5.7428,
|
||
|
|
"mean_token_accuracy": 0.18536509275436402,
|
||
|
|
"num_tokens": 8992764.0,
|
||
|
|
"step": 3610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993658971786499,
|
||
|
|
"epoch": 4.228070175438597,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00037923053045734595,
|
||
|
|
"loss": 5.628,
|
||
|
|
"mean_token_accuracy": 0.17806357592344285,
|
||
|
|
"num_tokens": 9004904.0,
|
||
|
|
"step": 3615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.235083770751953,
|
||
|
|
"epoch": 4.23391812865497,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00037881489436869054,
|
||
|
|
"loss": 5.8381,
|
||
|
|
"mean_token_accuracy": 0.17020698338747026,
|
||
|
|
"num_tokens": 9018411.0,
|
||
|
|
"step": 3620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049836683273315,
|
||
|
|
"epoch": 4.239766081871345,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003783988077159491,
|
||
|
|
"loss": 5.6706,
|
||
|
|
"mean_token_accuracy": 0.18683329671621324,
|
||
|
|
"num_tokens": 9030593.0,
|
||
|
|
"step": 3625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9810981273651125,
|
||
|
|
"epoch": 4.245614035087719,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00037798227230496754,
|
||
|
|
"loss": 5.675,
|
||
|
|
"mean_token_accuracy": 0.1914150223135948,
|
||
|
|
"num_tokens": 9043715.0,
|
||
|
|
"step": 3630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002139616012573,
|
||
|
|
"epoch": 4.251461988304094,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00037756528994353945,
|
||
|
|
"loss": 5.6241,
|
||
|
|
"mean_token_accuracy": 0.19150300174951554,
|
||
|
|
"num_tokens": 9056384.0,
|
||
|
|
"step": 3635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.056487655639648,
|
||
|
|
"epoch": 4.257309941520468,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000377147862441398,
|
||
|
|
"loss": 5.7443,
|
||
|
|
"mean_token_accuracy": 0.178622330725193,
|
||
|
|
"num_tokens": 9069444.0,
|
||
|
|
"step": 3640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0783336639404295,
|
||
|
|
"epoch": 4.2631578947368425,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00037672999161020873,
|
||
|
|
"loss": 5.6648,
|
||
|
|
"mean_token_accuracy": 0.1798129513859749,
|
||
|
|
"num_tokens": 9080933.0,
|
||
|
|
"step": 3645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063358354568481,
|
||
|
|
"epoch": 4.269005847953216,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00037631167926356087,
|
||
|
|
"loss": 5.7345,
|
||
|
|
"mean_token_accuracy": 0.18442935198545457,
|
||
|
|
"num_tokens": 9093405.0,
|
||
|
|
"step": 3650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016696119308472,
|
||
|
|
"epoch": 4.2748538011695905,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003758929272169599,
|
||
|
|
"loss": 5.7042,
|
||
|
|
"mean_token_accuracy": 0.18871267586946489,
|
||
|
|
"num_tokens": 9105707.0,
|
||
|
|
"step": 3655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.106068468093872,
|
||
|
|
"epoch": 4.280701754385965,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00037547373728781996,
|
||
|
|
"loss": 5.6618,
|
||
|
|
"mean_token_accuracy": 0.18460064232349396,
|
||
|
|
"num_tokens": 9119476.0,
|
||
|
|
"step": 3660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026667213439941,
|
||
|
|
"epoch": 4.286549707602339,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003750541112954552,
|
||
|
|
"loss": 5.6361,
|
||
|
|
"mean_token_accuracy": 0.1868304803967476,
|
||
|
|
"num_tokens": 9131788.0,
|
||
|
|
"step": 3665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083682632446289,
|
||
|
|
"epoch": 4.292397660818714,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003746340510610727,
|
||
|
|
"loss": 5.7431,
|
||
|
|
"mean_token_accuracy": 0.1785563573241234,
|
||
|
|
"num_tokens": 9144340.0,
|
||
|
|
"step": 3670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090314817428589,
|
||
|
|
"epoch": 4.298245614035087,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00037421355840776396,
|
||
|
|
"loss": 5.7128,
|
||
|
|
"mean_token_accuracy": 0.18332460671663284,
|
||
|
|
"num_tokens": 9156757.0,
|
||
|
|
"step": 3675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972487115859986,
|
||
|
|
"epoch": 4.304093567251462,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003737926351604971,
|
||
|
|
"loss": 5.696,
|
||
|
|
"mean_token_accuracy": 0.18716051131486894,
|
||
|
|
"num_tokens": 9169975.0,
|
||
|
|
"step": 3680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.123587608337402,
|
||
|
|
"epoch": 4.309941520467836,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00037337128314610926,
|
||
|
|
"loss": 5.72,
|
||
|
|
"mean_token_accuracy": 0.18307694643735886,
|
||
|
|
"num_tokens": 9181891.0,
|
||
|
|
"step": 3685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049408960342407,
|
||
|
|
"epoch": 4.315789473684211,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003729495041932984,
|
||
|
|
"loss": 5.7558,
|
||
|
|
"mean_token_accuracy": 0.173971788585186,
|
||
|
|
"num_tokens": 9194068.0,
|
||
|
|
"step": 3690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039019346237183,
|
||
|
|
"epoch": 4.321637426900585,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003725273001326155,
|
||
|
|
"loss": 5.7778,
|
||
|
|
"mean_token_accuracy": 0.17577221840620041,
|
||
|
|
"num_tokens": 9205530.0,
|
||
|
|
"step": 3695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049701690673828,
|
||
|
|
"epoch": 4.3274853801169595,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0003721046727964565,
|
||
|
|
"loss": 5.6716,
|
||
|
|
"mean_token_accuracy": 0.1905227407813072,
|
||
|
|
"num_tokens": 9218444.0,
|
||
|
|
"step": 3700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060033798217773,
|
||
|
|
"epoch": 4.333333333333333,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00037168162401905416,
|
||
|
|
"loss": 5.7869,
|
||
|
|
"mean_token_accuracy": 0.18076651394367219,
|
||
|
|
"num_tokens": 9229507.0,
|
||
|
|
"step": 3705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142893886566162,
|
||
|
|
"epoch": 4.3391812865497075,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00037125815563647063,
|
||
|
|
"loss": 5.8128,
|
||
|
|
"mean_token_accuracy": 0.1772017925977707,
|
||
|
|
"num_tokens": 9242128.0,
|
||
|
|
"step": 3710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089156723022461,
|
||
|
|
"epoch": 4.345029239766082,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00037083426948658903,
|
||
|
|
"loss": 5.7688,
|
||
|
|
"mean_token_accuracy": 0.17735524624586105,
|
||
|
|
"num_tokens": 9255598.0,
|
||
|
|
"step": 3715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064697980880737,
|
||
|
|
"epoch": 4.350877192982456,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00037040996740910566,
|
||
|
|
"loss": 5.7137,
|
||
|
|
"mean_token_accuracy": 0.18292889446020127,
|
||
|
|
"num_tokens": 9267568.0,
|
||
|
|
"step": 3720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0719091415405275,
|
||
|
|
"epoch": 4.356725146198831,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000369985251245522,
|
||
|
|
"loss": 5.7446,
|
||
|
|
"mean_token_accuracy": 0.18237178772687912,
|
||
|
|
"num_tokens": 9280223.0,
|
||
|
|
"step": 3725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087396144866943,
|
||
|
|
"epoch": 4.362573099415204,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00036956012283913655,
|
||
|
|
"loss": 5.8103,
|
||
|
|
"mean_token_accuracy": 0.1788751408457756,
|
||
|
|
"num_tokens": 9292933.0,
|
||
|
|
"step": 3730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036611795425415,
|
||
|
|
"epoch": 4.368421052631579,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00036913458403503715,
|
||
|
|
"loss": 5.7492,
|
||
|
|
"mean_token_accuracy": 0.18761264979839326,
|
||
|
|
"num_tokens": 9306739.0,
|
||
|
|
"step": 3735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101815032958984,
|
||
|
|
"epoch": 4.374269005847953,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003687086366800927,
|
||
|
|
"loss": 5.7122,
|
||
|
|
"mean_token_accuracy": 0.18057099282741546,
|
||
|
|
"num_tokens": 9319151.0,
|
||
|
|
"step": 3740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0984121799469,
|
||
|
|
"epoch": 4.380116959064328,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003682822826229453,
|
||
|
|
"loss": 5.7666,
|
||
|
|
"mean_token_accuracy": 0.17586230039596557,
|
||
|
|
"num_tokens": 9332035.0,
|
||
|
|
"step": 3745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113546228408813,
|
||
|
|
"epoch": 4.385964912280702,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00036785552371400206,
|
||
|
|
"loss": 5.8164,
|
||
|
|
"mean_token_accuracy": 0.17480721026659013,
|
||
|
|
"num_tokens": 9345248.0,
|
||
|
|
"step": 3750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087632560729981,
|
||
|
|
"epoch": 4.391812865497076,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003674283618054273,
|
||
|
|
"loss": 5.7698,
|
||
|
|
"mean_token_accuracy": 0.18116946816444396,
|
||
|
|
"num_tokens": 9357514.0,
|
||
|
|
"step": 3755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074438810348511,
|
||
|
|
"epoch": 4.39766081871345,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003670007987511344,
|
||
|
|
"loss": 5.7951,
|
||
|
|
"mean_token_accuracy": 0.1722947984933853,
|
||
|
|
"num_tokens": 9368627.0,
|
||
|
|
"step": 3760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005817794799805,
|
||
|
|
"epoch": 4.4035087719298245,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0003665728364067776,
|
||
|
|
"loss": 5.724,
|
||
|
|
"mean_token_accuracy": 0.18333328515291214,
|
||
|
|
"num_tokens": 9380591.0,
|
||
|
|
"step": 3765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05264630317688,
|
||
|
|
"epoch": 4.409356725146199,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00036614447662974413,
|
||
|
|
"loss": 5.697,
|
||
|
|
"mean_token_accuracy": 0.18376569002866744,
|
||
|
|
"num_tokens": 9392873.0,
|
||
|
|
"step": 3770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.125674533843994,
|
||
|
|
"epoch": 4.415204678362573,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003657157212791462,
|
||
|
|
"loss": 5.8262,
|
||
|
|
"mean_token_accuracy": 0.1721200466156006,
|
||
|
|
"num_tokens": 9404252.0,
|
||
|
|
"step": 3775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.023804616928101,
|
||
|
|
"epoch": 4.421052631578947,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003652865722158128,
|
||
|
|
"loss": 5.7525,
|
||
|
|
"mean_token_accuracy": 0.18338014036417008,
|
||
|
|
"num_tokens": 9416091.0,
|
||
|
|
"step": 3780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0366161346435545,
|
||
|
|
"epoch": 4.426900584795321,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00036485703130228147,
|
||
|
|
"loss": 5.6988,
|
||
|
|
"mean_token_accuracy": 0.1907563716173172,
|
||
|
|
"num_tokens": 9429913.0,
|
||
|
|
"step": 3785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096364116668701,
|
||
|
|
"epoch": 4.432748538011696,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00036442710040279086,
|
||
|
|
"loss": 5.6961,
|
||
|
|
"mean_token_accuracy": 0.189450640976429,
|
||
|
|
"num_tokens": 9442413.0,
|
||
|
|
"step": 3790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.841395616531372,
|
||
|
|
"epoch": 4.43859649122807,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003639967813832717,
|
||
|
|
"loss": 5.6044,
|
||
|
|
"mean_token_accuracy": 0.19091520458459854,
|
||
|
|
"num_tokens": 9453636.0,
|
||
|
|
"step": 3795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054208612442016,
|
||
|
|
"epoch": 4.444444444444445,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003635660761113394,
|
||
|
|
"loss": 5.7031,
|
||
|
|
"mean_token_accuracy": 0.18323550075292588,
|
||
|
|
"num_tokens": 9466577.0,
|
||
|
|
"step": 3800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035559225082397,
|
||
|
|
"epoch": 4.450292397660819,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003631349864562857,
|
||
|
|
"loss": 5.7024,
|
||
|
|
"mean_token_accuracy": 0.17979553788900376,
|
||
|
|
"num_tokens": 9479852.0,
|
||
|
|
"step": 3805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05486102104187,
|
||
|
|
"epoch": 4.456140350877193,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003627035142890708,
|
||
|
|
"loss": 5.6514,
|
||
|
|
"mean_token_accuracy": 0.18412256687879563,
|
||
|
|
"num_tokens": 9493373.0,
|
||
|
|
"step": 3810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0225457668304445,
|
||
|
|
"epoch": 4.461988304093567,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003622716614823147,
|
||
|
|
"loss": 5.7651,
|
||
|
|
"mean_token_accuracy": 0.18874280899763107,
|
||
|
|
"num_tokens": 9505793.0,
|
||
|
|
"step": 3815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0164961338043215,
|
||
|
|
"epoch": 4.4678362573099415,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003618394299102896,
|
||
|
|
"loss": 5.7854,
|
||
|
|
"mean_token_accuracy": 0.17374557256698608,
|
||
|
|
"num_tokens": 9517810.0,
|
||
|
|
"step": 3820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096640968322754,
|
||
|
|
"epoch": 4.473684210526316,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00036140682144891143,
|
||
|
|
"loss": 5.7694,
|
||
|
|
"mean_token_accuracy": 0.1758706510066986,
|
||
|
|
"num_tokens": 9529430.0,
|
||
|
|
"step": 3825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.07417402267456,
|
||
|
|
"epoch": 4.47953216374269,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00036097383797573205,
|
||
|
|
"loss": 5.7478,
|
||
|
|
"mean_token_accuracy": 0.18484017252922058,
|
||
|
|
"num_tokens": 9542385.0,
|
||
|
|
"step": 3830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0596723556518555,
|
||
|
|
"epoch": 4.485380116959064,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00036054048136993075,
|
||
|
|
"loss": 5.7161,
|
||
|
|
"mean_token_accuracy": 0.182282692193985,
|
||
|
|
"num_tokens": 9553955.0,
|
||
|
|
"step": 3835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115431213378907,
|
||
|
|
"epoch": 4.491228070175438,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00036010675351230616,
|
||
|
|
"loss": 5.7638,
|
||
|
|
"mean_token_accuracy": 0.17440795451402663,
|
||
|
|
"num_tokens": 9566494.0,
|
||
|
|
"step": 3840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00538272857666,
|
||
|
|
"epoch": 4.497076023391813,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003596726562852684,
|
||
|
|
"loss": 5.6812,
|
||
|
|
"mean_token_accuracy": 0.19397484362125397,
|
||
|
|
"num_tokens": 9579122.0,
|
||
|
|
"step": 3845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000626850128174,
|
||
|
|
"epoch": 4.502923976608187,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00035923819157283074,
|
||
|
|
"loss": 5.7201,
|
||
|
|
"mean_token_accuracy": 0.18014489114284515,
|
||
|
|
"num_tokens": 9592144.0,
|
||
|
|
"step": 3850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.94548225402832,
|
||
|
|
"epoch": 4.508771929824562,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00035880336126060074,
|
||
|
|
"loss": 5.6009,
|
||
|
|
"mean_token_accuracy": 0.18524586111307145,
|
||
|
|
"num_tokens": 9604533.0,
|
||
|
|
"step": 3855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044953060150147,
|
||
|
|
"epoch": 4.514619883040936,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00035836816723577354,
|
||
|
|
"loss": 5.781,
|
||
|
|
"mean_token_accuracy": 0.1815061315894127,
|
||
|
|
"num_tokens": 9617349.0,
|
||
|
|
"step": 3860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070717859268188,
|
||
|
|
"epoch": 4.52046783625731,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003579326113871222,
|
||
|
|
"loss": 5.7527,
|
||
|
|
"mean_token_accuracy": 0.18412501811981202,
|
||
|
|
"num_tokens": 9629599.0,
|
||
|
|
"step": 3865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.022063779830932,
|
||
|
|
"epoch": 4.526315789473684,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003574966956049904,
|
||
|
|
"loss": 5.7303,
|
||
|
|
"mean_token_accuracy": 0.18435552418231965,
|
||
|
|
"num_tokens": 9642041.0,
|
||
|
|
"step": 3870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.015185308456421,
|
||
|
|
"epoch": 4.5321637426900585,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00035706042178128397,
|
||
|
|
"loss": 5.7564,
|
||
|
|
"mean_token_accuracy": 0.18077756762504577,
|
||
|
|
"num_tokens": 9654796.0,
|
||
|
|
"step": 3875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0529402732849125,
|
||
|
|
"epoch": 4.538011695906433,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003566237918094625,
|
||
|
|
"loss": 5.7665,
|
||
|
|
"mean_token_accuracy": 0.18183130472898484,
|
||
|
|
"num_tokens": 9667211.0,
|
||
|
|
"step": 3880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0243847370147705,
|
||
|
|
"epoch": 4.543859649122807,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003561868075845313,
|
||
|
|
"loss": 5.7176,
|
||
|
|
"mean_token_accuracy": 0.18677378445863724,
|
||
|
|
"num_tokens": 9679526.0,
|
||
|
|
"step": 3885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.109017276763916,
|
||
|
|
"epoch": 4.549707602339181,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00035574947100303327,
|
||
|
|
"loss": 5.8851,
|
||
|
|
"mean_token_accuracy": 0.1711428940296173,
|
||
|
|
"num_tokens": 9691760.0,
|
||
|
|
"step": 3890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0831221580505375,
|
||
|
|
"epoch": 4.555555555555555,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00035531178396304083,
|
||
|
|
"loss": 5.7893,
|
||
|
|
"mean_token_accuracy": 0.182478691637516,
|
||
|
|
"num_tokens": 9704154.0,
|
||
|
|
"step": 3895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9242438793182375,
|
||
|
|
"epoch": 4.56140350877193,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00035487374836414676,
|
||
|
|
"loss": 5.5796,
|
||
|
|
"mean_token_accuracy": 0.1925991803407669,
|
||
|
|
"num_tokens": 9715850.0,
|
||
|
|
"step": 3900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04068398475647,
|
||
|
|
"epoch": 4.567251461988304,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00035443536610745707,
|
||
|
|
"loss": 5.7583,
|
||
|
|
"mean_token_accuracy": 0.18043858408927918,
|
||
|
|
"num_tokens": 9728202.0,
|
||
|
|
"step": 3905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148542165756226,
|
||
|
|
"epoch": 4.573099415204679,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00035399663909558226,
|
||
|
|
"loss": 5.7593,
|
||
|
|
"mean_token_accuracy": 0.1764737144112587,
|
||
|
|
"num_tokens": 9741363.0,
|
||
|
|
"step": 3910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010446453094483,
|
||
|
|
"epoch": 4.578947368421053,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00035355756923262897,
|
||
|
|
"loss": 5.7549,
|
||
|
|
"mean_token_accuracy": 0.17936043292284012,
|
||
|
|
"num_tokens": 9755231.0,
|
||
|
|
"step": 3915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974240493774414,
|
||
|
|
"epoch": 4.584795321637427,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003531181584241919,
|
||
|
|
"loss": 5.5769,
|
||
|
|
"mean_token_accuracy": 0.19668386578559877,
|
||
|
|
"num_tokens": 9768972.0,
|
||
|
|
"step": 3920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105667781829834,
|
||
|
|
"epoch": 4.590643274853801,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003526784085773455,
|
||
|
|
"loss": 5.7977,
|
||
|
|
"mean_token_accuracy": 0.1753503203392029,
|
||
|
|
"num_tokens": 9781356.0,
|
||
|
|
"step": 3925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995253419876098,
|
||
|
|
"epoch": 4.5964912280701755,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003522383216006356,
|
||
|
|
"loss": 5.7313,
|
||
|
|
"mean_token_accuracy": 0.17796422988176347,
|
||
|
|
"num_tokens": 9793227.0,
|
||
|
|
"step": 3930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05514702796936,
|
||
|
|
"epoch": 4.60233918128655,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003517978994040713,
|
||
|
|
"loss": 5.732,
|
||
|
|
"mean_token_accuracy": 0.1808537572622299,
|
||
|
|
"num_tokens": 9805968.0,
|
||
|
|
"step": 3935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043203687667846,
|
||
|
|
"epoch": 4.6081871345029235,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00035135714389911637,
|
||
|
|
"loss": 5.7266,
|
||
|
|
"mean_token_accuracy": 0.18140557706356047,
|
||
|
|
"num_tokens": 9817864.0,
|
||
|
|
"step": 3940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039916896820069,
|
||
|
|
"epoch": 4.614035087719298,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003509160569986814,
|
||
|
|
"loss": 5.7195,
|
||
|
|
"mean_token_accuracy": 0.18547867387533187,
|
||
|
|
"num_tokens": 9831192.0,
|
||
|
|
"step": 3945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024516248703003,
|
||
|
|
"epoch": 4.619883040935672,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00035047464061711527,
|
||
|
|
"loss": 5.7243,
|
||
|
|
"mean_token_accuracy": 0.17629852294921874,
|
||
|
|
"num_tokens": 9842813.0,
|
||
|
|
"step": 3950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071889019012451,
|
||
|
|
"epoch": 4.625730994152047,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00035003289667019655,
|
||
|
|
"loss": 5.7509,
|
||
|
|
"mean_token_accuracy": 0.1803283393383026,
|
||
|
|
"num_tokens": 9854500.0,
|
||
|
|
"step": 3955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037901878356934,
|
||
|
|
"epoch": 4.631578947368421,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003495908270751257,
|
||
|
|
"loss": 5.7404,
|
||
|
|
"mean_token_accuracy": 0.18182432353496553,
|
||
|
|
"num_tokens": 9865729.0,
|
||
|
|
"step": 3960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1051630020141605,
|
||
|
|
"epoch": 4.637426900584796,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003491484337505166,
|
||
|
|
"loss": 5.7699,
|
||
|
|
"mean_token_accuracy": 0.1800166755914688,
|
||
|
|
"num_tokens": 9878306.0,
|
||
|
|
"step": 3965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005567932128907,
|
||
|
|
"epoch": 4.643274853801169,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00034870571861638785,
|
||
|
|
"loss": 5.8004,
|
||
|
|
"mean_token_accuracy": 0.1816330999135971,
|
||
|
|
"num_tokens": 9890384.0,
|
||
|
|
"step": 3970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.040593576431275,
|
||
|
|
"epoch": 4.649122807017544,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00034826268359415487,
|
||
|
|
"loss": 5.7443,
|
||
|
|
"mean_token_accuracy": 0.18089356720447541,
|
||
|
|
"num_tokens": 9902960.0,
|
||
|
|
"step": 3975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.041272497177124,
|
||
|
|
"epoch": 4.654970760233918,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003478193306066215,
|
||
|
|
"loss": 5.712,
|
||
|
|
"mean_token_accuracy": 0.18326338976621628,
|
||
|
|
"num_tokens": 9915143.0,
|
||
|
|
"step": 3980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038553190231323,
|
||
|
|
"epoch": 4.6608187134502925,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00034737566157797147,
|
||
|
|
"loss": 5.8233,
|
||
|
|
"mean_token_accuracy": 0.1754396840929985,
|
||
|
|
"num_tokens": 9928440.0,
|
||
|
|
"step": 3985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.109258699417114,
|
||
|
|
"epoch": 4.666666666666667,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00034693167843376016,
|
||
|
|
"loss": 5.828,
|
||
|
|
"mean_token_accuracy": 0.17697842717170714,
|
||
|
|
"num_tokens": 9940973.0,
|
||
|
|
"step": 3990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02032732963562,
|
||
|
|
"epoch": 4.6725146198830405,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00034648738310090634,
|
||
|
|
"loss": 5.7203,
|
||
|
|
"mean_token_accuracy": 0.18732102066278458,
|
||
|
|
"num_tokens": 9953433.0,
|
||
|
|
"step": 3995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93368010520935,
|
||
|
|
"epoch": 4.678362573099415,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003460427775076835,
|
||
|
|
"loss": 5.6445,
|
||
|
|
"mean_token_accuracy": 0.18906634598970412,
|
||
|
|
"num_tokens": 9964641.0,
|
||
|
|
"step": 4000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 4.678362573099415,
|
||
|
|
"eval_entropy": 5.961484056658449,
|
||
|
|
"eval_loss": 6.598062992095947,
|
||
|
|
"eval_mean_token_accuracy": 0.1488603737018453,
|
||
|
|
"eval_num_tokens": 9964641.0,
|
||
|
|
"eval_runtime": 2.2422,
|
||
|
|
"eval_samples_per_second": 1207.296,
|
||
|
|
"eval_steps_per_second": 151.191,
|
||
|
|
"step": 4000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100713062286377,
|
||
|
|
"epoch": 4.684210526315789,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00034559786358371187,
|
||
|
|
"loss": 5.8346,
|
||
|
|
"mean_token_accuracy": 0.17341675162315368,
|
||
|
|
"num_tokens": 9978625.0,
|
||
|
|
"step": 4005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046002626419067,
|
||
|
|
"epoch": 4.690058479532164,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00034515264325994975,
|
||
|
|
"loss": 5.6908,
|
||
|
|
"mean_token_accuracy": 0.18274984359741211,
|
||
|
|
"num_tokens": 9991758.0,
|
||
|
|
"step": 4010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.125883913040161,
|
||
|
|
"epoch": 4.695906432748538,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00034470711846868525,
|
||
|
|
"loss": 5.7918,
|
||
|
|
"mean_token_accuracy": 0.17529552280902863,
|
||
|
|
"num_tokens": 10005496.0,
|
||
|
|
"step": 4015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036362028121948,
|
||
|
|
"epoch": 4.701754385964913,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00034426129114352807,
|
||
|
|
"loss": 5.8335,
|
||
|
|
"mean_token_accuracy": 0.1784819021821022,
|
||
|
|
"num_tokens": 10019025.0,
|
||
|
|
"step": 4020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011404514312744,
|
||
|
|
"epoch": 4.707602339181286,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003438151632194006,
|
||
|
|
"loss": 5.6821,
|
||
|
|
"mean_token_accuracy": 0.18766568303108216,
|
||
|
|
"num_tokens": 10030741.0,
|
||
|
|
"step": 4025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048987293243409,
|
||
|
|
"epoch": 4.713450292397661,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00034336873663252997,
|
||
|
|
"loss": 5.7908,
|
||
|
|
"mean_token_accuracy": 0.18190405070781707,
|
||
|
|
"num_tokens": 10043138.0,
|
||
|
|
"step": 4030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9766051292419435,
|
||
|
|
"epoch": 4.719298245614035,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00034292201332043976,
|
||
|
|
"loss": 5.747,
|
||
|
|
"mean_token_accuracy": 0.17837461829185486,
|
||
|
|
"num_tokens": 10055927.0,
|
||
|
|
"step": 4035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05901083946228,
|
||
|
|
"epoch": 4.7251461988304095,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003424749952219411,
|
||
|
|
"loss": 5.676,
|
||
|
|
"mean_token_accuracy": 0.18671796470880508,
|
||
|
|
"num_tokens": 10067392.0,
|
||
|
|
"step": 4040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0083160400390625,
|
||
|
|
"epoch": 4.730994152046784,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00034202768427712456,
|
||
|
|
"loss": 5.7325,
|
||
|
|
"mean_token_accuracy": 0.18567821234464646,
|
||
|
|
"num_tokens": 10079245.0,
|
||
|
|
"step": 4045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985035610198975,
|
||
|
|
"epoch": 4.7368421052631575,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003415800824273518,
|
||
|
|
"loss": 5.6213,
|
||
|
|
"mean_token_accuracy": 0.19095280915498733,
|
||
|
|
"num_tokens": 10091923.0,
|
||
|
|
"step": 4050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989601135253906,
|
||
|
|
"epoch": 4.742690058479532,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003411321916152469,
|
||
|
|
"loss": 5.7121,
|
||
|
|
"mean_token_accuracy": 0.18403569161891936,
|
||
|
|
"num_tokens": 10105121.0,
|
||
|
|
"step": 4055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019980573654175,
|
||
|
|
"epoch": 4.748538011695906,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003406840137846881,
|
||
|
|
"loss": 5.7849,
|
||
|
|
"mean_token_accuracy": 0.18171993345022203,
|
||
|
|
"num_tokens": 10117005.0,
|
||
|
|
"step": 4060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977855110168457,
|
||
|
|
"epoch": 4.754385964912281,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00034023555088079924,
|
||
|
|
"loss": 5.6837,
|
||
|
|
"mean_token_accuracy": 0.18971304446458817,
|
||
|
|
"num_tokens": 10129958.0,
|
||
|
|
"step": 4065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028247976303101,
|
||
|
|
"epoch": 4.760233918128655,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003397868048499416,
|
||
|
|
"loss": 5.746,
|
||
|
|
"mean_token_accuracy": 0.18107693493366242,
|
||
|
|
"num_tokens": 10141537.0,
|
||
|
|
"step": 4070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032972621917724,
|
||
|
|
"epoch": 4.76608187134503,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00033933777763970506,
|
||
|
|
"loss": 5.764,
|
||
|
|
"mean_token_accuracy": 0.18917388319969178,
|
||
|
|
"num_tokens": 10153882.0,
|
||
|
|
"step": 4075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026349687576294,
|
||
|
|
"epoch": 4.771929824561403,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003388884711989,
|
||
|
|
"loss": 5.7606,
|
||
|
|
"mean_token_accuracy": 0.17605427503585816,
|
||
|
|
"num_tokens": 10165147.0,
|
||
|
|
"step": 4080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.087088632583618,
|
||
|
|
"epoch": 4.777777777777778,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003384388874775486,
|
||
|
|
"loss": 5.7931,
|
||
|
|
"mean_token_accuracy": 0.17155395746231078,
|
||
|
|
"num_tokens": 10177926.0,
|
||
|
|
"step": 4085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001613426208496,
|
||
|
|
"epoch": 4.783625730994152,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00033798902842687627,
|
||
|
|
"loss": 5.7373,
|
||
|
|
"mean_token_accuracy": 0.1835317373275757,
|
||
|
|
"num_tokens": 10190343.0,
|
||
|
|
"step": 4090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102108383178711,
|
||
|
|
"epoch": 4.7894736842105265,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003375388959993037,
|
||
|
|
"loss": 5.8375,
|
||
|
|
"mean_token_accuracy": 0.1743247389793396,
|
||
|
|
"num_tokens": 10201363.0,
|
||
|
|
"step": 4095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951845264434814,
|
||
|
|
"epoch": 4.7953216374269,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003370884921484379,
|
||
|
|
"loss": 5.6746,
|
||
|
|
"mean_token_accuracy": 0.1877143830060959,
|
||
|
|
"num_tokens": 10213976.0,
|
||
|
|
"step": 4100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988868141174317,
|
||
|
|
"epoch": 4.8011695906432745,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003366378188290638,
|
||
|
|
"loss": 5.7226,
|
||
|
|
"mean_token_accuracy": 0.18624048233032225,
|
||
|
|
"num_tokens": 10225645.0,
|
||
|
|
"step": 4105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112516832351685,
|
||
|
|
"epoch": 4.807017543859649,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003361868779971361,
|
||
|
|
"loss": 5.7301,
|
||
|
|
"mean_token_accuracy": 0.18756964951753616,
|
||
|
|
"num_tokens": 10237144.0,
|
||
|
|
"step": 4110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.106003665924073,
|
||
|
|
"epoch": 4.812865497076023,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00033573567160977017,
|
||
|
|
"loss": 5.9088,
|
||
|
|
"mean_token_accuracy": 0.17325395047664643,
|
||
|
|
"num_tokens": 10249215.0,
|
||
|
|
"step": 4115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974528551101685,
|
||
|
|
"epoch": 4.818713450292398,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000335284201625234,
|
||
|
|
"loss": 5.7218,
|
||
|
|
"mean_token_accuracy": 0.18335625827312468,
|
||
|
|
"num_tokens": 10262428.0,
|
||
|
|
"step": 4120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00980281829834,
|
||
|
|
"epoch": 4.824561403508772,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00033483247000294,
|
||
|
|
"loss": 5.74,
|
||
|
|
"mean_token_accuracy": 0.18660111725330353,
|
||
|
|
"num_tokens": 10275370.0,
|
||
|
|
"step": 4125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057599258422852,
|
||
|
|
"epoch": 4.830409356725146,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0003343804787034357,
|
||
|
|
"loss": 5.7555,
|
||
|
|
"mean_token_accuracy": 0.1862301006913185,
|
||
|
|
"num_tokens": 10287378.0,
|
||
|
|
"step": 4130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0287903308868405,
|
||
|
|
"epoch": 4.83625730994152,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003339282296883956,
|
||
|
|
"loss": 5.7361,
|
||
|
|
"mean_token_accuracy": 0.17569071799516678,
|
||
|
|
"num_tokens": 10300063.0,
|
||
|
|
"step": 4135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0668891906738285,
|
||
|
|
"epoch": 4.842105263157895,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000333475724920613,
|
||
|
|
"loss": 5.7326,
|
||
|
|
"mean_token_accuracy": 0.18561510294675826,
|
||
|
|
"num_tokens": 10312095.0,
|
||
|
|
"step": 4140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956810092926025,
|
||
|
|
"epoch": 4.847953216374269,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003330229663639909,
|
||
|
|
"loss": 5.7746,
|
||
|
|
"mean_token_accuracy": 0.18179905265569687,
|
||
|
|
"num_tokens": 10324903.0,
|
||
|
|
"step": 4145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.119417905807495,
|
||
|
|
"epoch": 4.853801169590644,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000332569955983534,
|
||
|
|
"loss": 5.7776,
|
||
|
|
"mean_token_accuracy": 0.18115380257368088,
|
||
|
|
"num_tokens": 10339253.0,
|
||
|
|
"step": 4150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059303951263428,
|
||
|
|
"epoch": 4.859649122807017,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003321166957453398,
|
||
|
|
"loss": 5.7979,
|
||
|
|
"mean_token_accuracy": 0.17429704666137696,
|
||
|
|
"num_tokens": 10350845.0,
|
||
|
|
"step": 4155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0442798137664795,
|
||
|
|
"epoch": 4.8654970760233915,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003316631876165904,
|
||
|
|
"loss": 5.7278,
|
||
|
|
"mean_token_accuracy": 0.18378590494394303,
|
||
|
|
"num_tokens": 10363357.0,
|
||
|
|
"step": 4160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942074823379516,
|
||
|
|
"epoch": 4.871345029239766,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00033120943356554334,
|
||
|
|
"loss": 5.6538,
|
||
|
|
"mean_token_accuracy": 0.18856242895126343,
|
||
|
|
"num_tokens": 10375664.0,
|
||
|
|
"step": 4165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.02304892539978,
|
||
|
|
"epoch": 4.87719298245614,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000330755435561524,
|
||
|
|
"loss": 5.7076,
|
||
|
|
"mean_token_accuracy": 0.1843791276216507,
|
||
|
|
"num_tokens": 10387412.0,
|
||
|
|
"step": 4170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004294490814209,
|
||
|
|
"epoch": 4.883040935672515,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00033030119557491604,
|
||
|
|
"loss": 5.758,
|
||
|
|
"mean_token_accuracy": 0.18571807742118834,
|
||
|
|
"num_tokens": 10399083.0,
|
||
|
|
"step": 4175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.117018842697144,
|
||
|
|
"epoch": 4.888888888888889,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003298467155771537,
|
||
|
|
"loss": 5.8083,
|
||
|
|
"mean_token_accuracy": 0.1694980412721634,
|
||
|
|
"num_tokens": 10412713.0,
|
||
|
|
"step": 4180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947074460983276,
|
||
|
|
"epoch": 4.894736842105263,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00032939199754071274,
|
||
|
|
"loss": 5.6643,
|
||
|
|
"mean_token_accuracy": 0.1835461750626564,
|
||
|
|
"num_tokens": 10426836.0,
|
||
|
|
"step": 4185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975785255432129,
|
||
|
|
"epoch": 4.900584795321637,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000328937043439102,
|
||
|
|
"loss": 5.7619,
|
||
|
|
"mean_token_accuracy": 0.18162133991718293,
|
||
|
|
"num_tokens": 10439817.0,
|
||
|
|
"step": 4190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061240148544312,
|
||
|
|
"epoch": 4.906432748538012,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00032848185524685504,
|
||
|
|
"loss": 5.7405,
|
||
|
|
"mean_token_accuracy": 0.17897771745920182,
|
||
|
|
"num_tokens": 10452509.0,
|
||
|
|
"step": 4195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.069028043746949,
|
||
|
|
"epoch": 4.912280701754386,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00032802643493952106,
|
||
|
|
"loss": 5.7725,
|
||
|
|
"mean_token_accuracy": 0.17496760189533234,
|
||
|
|
"num_tokens": 10464593.0,
|
||
|
|
"step": 4200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.040318870544434,
|
||
|
|
"epoch": 4.918128654970761,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000327570784493657,
|
||
|
|
"loss": 5.7959,
|
||
|
|
"mean_token_accuracy": 0.17725964337587358,
|
||
|
|
"num_tokens": 10476868.0,
|
||
|
|
"step": 4205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000529861450195,
|
||
|
|
"epoch": 4.923976608187134,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00032711490588681845,
|
||
|
|
"loss": 5.6337,
|
||
|
|
"mean_token_accuracy": 0.18518804758787155,
|
||
|
|
"num_tokens": 10489510.0,
|
||
|
|
"step": 4210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054291534423828,
|
||
|
|
"epoch": 4.9298245614035086,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003266588010975512,
|
||
|
|
"loss": 5.7939,
|
||
|
|
"mean_token_accuracy": 0.17776275277137757,
|
||
|
|
"num_tokens": 10501901.0,
|
||
|
|
"step": 4215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9743047714233395,
|
||
|
|
"epoch": 4.935672514619883,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003262024721053827,
|
||
|
|
"loss": 5.6973,
|
||
|
|
"mean_token_accuracy": 0.18604688346385956,
|
||
|
|
"num_tokens": 10513604.0,
|
||
|
|
"step": 4220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.99264669418335,
|
||
|
|
"epoch": 4.941520467836257,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00032574592089081375,
|
||
|
|
"loss": 5.7246,
|
||
|
|
"mean_token_accuracy": 0.19234126210212707,
|
||
|
|
"num_tokens": 10527882.0,
|
||
|
|
"step": 4225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0635645389556885,
|
||
|
|
"epoch": 4.947368421052632,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00032528914943530905,
|
||
|
|
"loss": 5.6811,
|
||
|
|
"mean_token_accuracy": 0.19177028983831407,
|
||
|
|
"num_tokens": 10539514.0,
|
||
|
|
"step": 4230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024539136886597,
|
||
|
|
"epoch": 4.953216374269006,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003248321597212896,
|
||
|
|
"loss": 5.7335,
|
||
|
|
"mean_token_accuracy": 0.18102981001138688,
|
||
|
|
"num_tokens": 10551984.0,
|
||
|
|
"step": 4235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129781723022461,
|
||
|
|
"epoch": 4.95906432748538,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003243749537321236,
|
||
|
|
"loss": 5.8234,
|
||
|
|
"mean_token_accuracy": 0.1759945884346962,
|
||
|
|
"num_tokens": 10564915.0,
|
||
|
|
"step": 4240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008909416198731,
|
||
|
|
"epoch": 4.964912280701754,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00032391753345211767,
|
||
|
|
"loss": 5.7746,
|
||
|
|
"mean_token_accuracy": 0.18243280202150344,
|
||
|
|
"num_tokens": 10576614.0,
|
||
|
|
"step": 4245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.00213475227356,
|
||
|
|
"epoch": 4.970760233918129,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003234599008665088,
|
||
|
|
"loss": 5.7496,
|
||
|
|
"mean_token_accuracy": 0.18730467408895493,
|
||
|
|
"num_tokens": 10588746.0,
|
||
|
|
"step": 4250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021085405349732,
|
||
|
|
"epoch": 4.976608187134503,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003230020579614551,
|
||
|
|
"loss": 5.7699,
|
||
|
|
"mean_token_accuracy": 0.18032314032316207,
|
||
|
|
"num_tokens": 10600101.0,
|
||
|
|
"step": 4255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032131481170654,
|
||
|
|
"epoch": 4.982456140350877,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003225440067240276,
|
||
|
|
"loss": 5.7237,
|
||
|
|
"mean_token_accuracy": 0.18516920655965804,
|
||
|
|
"num_tokens": 10611879.0,
|
||
|
|
"step": 4260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032303190231323,
|
||
|
|
"epoch": 4.988304093567251,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00032208574914220167,
|
||
|
|
"loss": 5.7874,
|
||
|
|
"mean_token_accuracy": 0.18113457262516022,
|
||
|
|
"num_tokens": 10624201.0,
|
||
|
|
"step": 4265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0659300804138185,
|
||
|
|
"epoch": 4.994152046783626,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003216272872048479,
|
||
|
|
"loss": 5.7322,
|
||
|
|
"mean_token_accuracy": 0.17785232961177827,
|
||
|
|
"num_tokens": 10636612.0,
|
||
|
|
"step": 4270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988249969482422,
|
||
|
|
"epoch": 5.0,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0003211686229017241,
|
||
|
|
"loss": 5.7318,
|
||
|
|
"mean_token_accuracy": 0.1846519336104393,
|
||
|
|
"num_tokens": 10647420.0,
|
||
|
|
"step": 4275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024672126770019,
|
||
|
|
"epoch": 5.005847953216374,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003207097582234662,
|
||
|
|
"loss": 5.5173,
|
||
|
|
"mean_token_accuracy": 0.18643636554479598,
|
||
|
|
"num_tokens": 10660096.0,
|
||
|
|
"step": 4280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976779317855835,
|
||
|
|
"epoch": 5.011695906432749,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003202506951615798,
|
||
|
|
"loss": 5.445,
|
||
|
|
"mean_token_accuracy": 0.1972539559006691,
|
||
|
|
"num_tokens": 10672364.0,
|
||
|
|
"step": 4285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0123389720916744,
|
||
|
|
"epoch": 5.017543859649122,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00031979143570843145,
|
||
|
|
"loss": 5.4204,
|
||
|
|
"mean_token_accuracy": 0.19713484942913057,
|
||
|
|
"num_tokens": 10685230.0,
|
||
|
|
"step": 4290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074600505828857,
|
||
|
|
"epoch": 5.023391812865497,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00031933198185724016,
|
||
|
|
"loss": 5.5452,
|
||
|
|
"mean_token_accuracy": 0.1875850036740303,
|
||
|
|
"num_tokens": 10697837.0,
|
||
|
|
"step": 4295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976657342910767,
|
||
|
|
"epoch": 5.029239766081871,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00031887233560206864,
|
||
|
|
"loss": 5.3516,
|
||
|
|
"mean_token_accuracy": 0.20017823278903962,
|
||
|
|
"num_tokens": 10711549.0,
|
||
|
|
"step": 4300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.096521472930908,
|
||
|
|
"epoch": 5.035087719298246,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00031841249893781447,
|
||
|
|
"loss": 5.5338,
|
||
|
|
"mean_token_accuracy": 0.19166284501552583,
|
||
|
|
"num_tokens": 10724897.0,
|
||
|
|
"step": 4305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994932985305786,
|
||
|
|
"epoch": 5.04093567251462,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003179524738602019,
|
||
|
|
"loss": 5.4581,
|
||
|
|
"mean_token_accuracy": 0.19029559046030045,
|
||
|
|
"num_tokens": 10735808.0,
|
||
|
|
"step": 4310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95796947479248,
|
||
|
|
"epoch": 5.046783625730994,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00031749226236577277,
|
||
|
|
"loss": 5.3982,
|
||
|
|
"mean_token_accuracy": 0.20198494493961333,
|
||
|
|
"num_tokens": 10749083.0,
|
||
|
|
"step": 4315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000226783752441,
|
||
|
|
"epoch": 5.052631578947368,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00031703186645187776,
|
||
|
|
"loss": 5.4394,
|
||
|
|
"mean_token_accuracy": 0.1959536299109459,
|
||
|
|
"num_tokens": 10761215.0,
|
||
|
|
"step": 4320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.915547657012939,
|
||
|
|
"epoch": 5.058479532163743,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00031657128811666836,
|
||
|
|
"loss": 5.3567,
|
||
|
|
"mean_token_accuracy": 0.21385197937488556,
|
||
|
|
"num_tokens": 10772505.0,
|
||
|
|
"step": 4325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0455069065094,
|
||
|
|
"epoch": 5.064327485380117,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00031611052935908736,
|
||
|
|
"loss": 5.5643,
|
||
|
|
"mean_token_accuracy": 0.18447889238595963,
|
||
|
|
"num_tokens": 10785205.0,
|
||
|
|
"step": 4330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988374090194702,
|
||
|
|
"epoch": 5.0701754385964914,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000315649592178861,
|
||
|
|
"loss": 5.3905,
|
||
|
|
"mean_token_accuracy": 0.19894834309816362,
|
||
|
|
"num_tokens": 10796632.0,
|
||
|
|
"step": 4335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039369535446167,
|
||
|
|
"epoch": 5.076023391812866,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003151884785764897,
|
||
|
|
"loss": 5.4453,
|
||
|
|
"mean_token_accuracy": 0.19376769363880159,
|
||
|
|
"num_tokens": 10809466.0,
|
||
|
|
"step": 4340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01085467338562,
|
||
|
|
"epoch": 5.081871345029239,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003147271905532394,
|
||
|
|
"loss": 5.4998,
|
||
|
|
"mean_token_accuracy": 0.19298903197050093,
|
||
|
|
"num_tokens": 10821894.0,
|
||
|
|
"step": 4345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920192861557007,
|
||
|
|
"epoch": 5.087719298245614,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003142657301111333,
|
||
|
|
"loss": 5.4351,
|
||
|
|
"mean_token_accuracy": 0.19298215359449386,
|
||
|
|
"num_tokens": 10833612.0,
|
||
|
|
"step": 4350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017073917388916,
|
||
|
|
"epoch": 5.093567251461988,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003138040992529428,
|
||
|
|
"loss": 5.4847,
|
||
|
|
"mean_token_accuracy": 0.18651023954153062,
|
||
|
|
"num_tokens": 10845146.0,
|
||
|
|
"step": 4355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95059905052185,
|
||
|
|
"epoch": 5.099415204678363,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000313342299982179,
|
||
|
|
"loss": 5.4893,
|
||
|
|
"mean_token_accuracy": 0.193601655960083,
|
||
|
|
"num_tokens": 10857376.0,
|
||
|
|
"step": 4360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008613967895508,
|
||
|
|
"epoch": 5.105263157894737,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003128803343030836,
|
||
|
|
"loss": 5.4808,
|
||
|
|
"mean_token_accuracy": 0.19172981828451158,
|
||
|
|
"num_tokens": 10868778.0,
|
||
|
|
"step": 4365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010405158996582,
|
||
|
|
"epoch": 5.111111111111111,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00031241820422062117,
|
||
|
|
"loss": 5.5197,
|
||
|
|
"mean_token_accuracy": 0.18894066661596298,
|
||
|
|
"num_tokens": 10881050.0,
|
||
|
|
"step": 4370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991783952713012,
|
||
|
|
"epoch": 5.116959064327485,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00031195591174046914,
|
||
|
|
"loss": 5.5199,
|
||
|
|
"mean_token_accuracy": 0.18959715515375136,
|
||
|
|
"num_tokens": 10894468.0,
|
||
|
|
"step": 4375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968203783035278,
|
||
|
|
"epoch": 5.12280701754386,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00031149345886901,
|
||
|
|
"loss": 5.4447,
|
||
|
|
"mean_token_accuracy": 0.20225874483585357,
|
||
|
|
"num_tokens": 10907039.0,
|
||
|
|
"step": 4380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967371845245362,
|
||
|
|
"epoch": 5.128654970760234,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003110308476133225,
|
||
|
|
"loss": 5.4612,
|
||
|
|
"mean_token_accuracy": 0.19480236917734145,
|
||
|
|
"num_tokens": 10918772.0,
|
||
|
|
"step": 4385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918122720718384,
|
||
|
|
"epoch": 5.1345029239766085,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00031056807998117256,
|
||
|
|
"loss": 5.3717,
|
||
|
|
"mean_token_accuracy": 0.20253790020942689,
|
||
|
|
"num_tokens": 10931397.0,
|
||
|
|
"step": 4390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033661413192749,
|
||
|
|
"epoch": 5.140350877192983,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000310105157981005,
|
||
|
|
"loss": 5.4917,
|
||
|
|
"mean_token_accuracy": 0.1909372627735138,
|
||
|
|
"num_tokens": 10942728.0,
|
||
|
|
"step": 4395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.925847482681275,
|
||
|
|
"epoch": 5.146198830409356,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00030964208362193436,
|
||
|
|
"loss": 5.4219,
|
||
|
|
"mean_token_accuracy": 0.19562945067882537,
|
||
|
|
"num_tokens": 10954277.0,
|
||
|
|
"step": 4400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955894517898559,
|
||
|
|
"epoch": 5.152046783625731,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00030917885891373664,
|
||
|
|
"loss": 5.4597,
|
||
|
|
"mean_token_accuracy": 0.19100184887647628,
|
||
|
|
"num_tokens": 10966894.0,
|
||
|
|
"step": 4405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.988796091079712,
|
||
|
|
"epoch": 5.157894736842105,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0003087154858668404,
|
||
|
|
"loss": 5.4545,
|
||
|
|
"mean_token_accuracy": 0.19253304600715637,
|
||
|
|
"num_tokens": 10979229.0,
|
||
|
|
"step": 4410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.948918962478638,
|
||
|
|
"epoch": 5.16374269005848,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003082519664923177,
|
||
|
|
"loss": 5.5192,
|
||
|
|
"mean_token_accuracy": 0.1919144108891487,
|
||
|
|
"num_tokens": 10991999.0,
|
||
|
|
"step": 4415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.045034122467041,
|
||
|
|
"epoch": 5.169590643274854,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000307788302801876,
|
||
|
|
"loss": 5.4655,
|
||
|
|
"mean_token_accuracy": 0.19015197157859803,
|
||
|
|
"num_tokens": 11004408.0,
|
||
|
|
"step": 4420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.919661521911621,
|
||
|
|
"epoch": 5.175438596491228,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00030732449680784886,
|
||
|
|
"loss": 5.5709,
|
||
|
|
"mean_token_accuracy": 0.18848305195569992,
|
||
|
|
"num_tokens": 11016322.0,
|
||
|
|
"step": 4425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.022153902053833,
|
||
|
|
"epoch": 5.181286549707602,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0003068605505231877,
|
||
|
|
"loss": 5.5255,
|
||
|
|
"mean_token_accuracy": 0.18656002432107927,
|
||
|
|
"num_tokens": 11028798.0,
|
||
|
|
"step": 4430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887226486206055,
|
||
|
|
"epoch": 5.187134502923977,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00030639646596145243,
|
||
|
|
"loss": 5.3705,
|
||
|
|
"mean_token_accuracy": 0.20132058560848237,
|
||
|
|
"num_tokens": 11039837.0,
|
||
|
|
"step": 4435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970758390426636,
|
||
|
|
"epoch": 5.192982456140351,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00030593224513680357,
|
||
|
|
"loss": 5.4075,
|
||
|
|
"mean_token_accuracy": 0.19955101609230042,
|
||
|
|
"num_tokens": 11052943.0,
|
||
|
|
"step": 4440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.042226362228393,
|
||
|
|
"epoch": 5.1988304093567255,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003054678900639927,
|
||
|
|
"loss": 5.4845,
|
||
|
|
"mean_token_accuracy": 0.18954504430294036,
|
||
|
|
"num_tokens": 11065483.0,
|
||
|
|
"step": 4445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935854768753051,
|
||
|
|
"epoch": 5.204678362573099,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00030500340275835405,
|
||
|
|
"loss": 5.4532,
|
||
|
|
"mean_token_accuracy": 0.19841210693120956,
|
||
|
|
"num_tokens": 11077743.0,
|
||
|
|
"step": 4450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953109359741211,
|
||
|
|
"epoch": 5.2105263157894735,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00030453878523579596,
|
||
|
|
"loss": 5.4794,
|
||
|
|
"mean_token_accuracy": 0.19056453108787536,
|
||
|
|
"num_tokens": 11089692.0,
|
||
|
|
"step": 4455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878514957427979,
|
||
|
|
"epoch": 5.216374269005848,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00030407403951279174,
|
||
|
|
"loss": 5.3032,
|
||
|
|
"mean_token_accuracy": 0.21644137501716615,
|
||
|
|
"num_tokens": 11104220.0,
|
||
|
|
"step": 4460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942462205886841,
|
||
|
|
"epoch": 5.222222222222222,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003036091676063711,
|
||
|
|
"loss": 5.4513,
|
||
|
|
"mean_token_accuracy": 0.1942198395729065,
|
||
|
|
"num_tokens": 11115599.0,
|
||
|
|
"step": 4465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938215494155884,
|
||
|
|
"epoch": 5.228070175438597,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0003031441715341115,
|
||
|
|
"loss": 5.4298,
|
||
|
|
"mean_token_accuracy": 0.19609365016222,
|
||
|
|
"num_tokens": 11128125.0,
|
||
|
|
"step": 4470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936326265335083,
|
||
|
|
"epoch": 5.23391812865497,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003026790533141293,
|
||
|
|
"loss": 5.4208,
|
||
|
|
"mean_token_accuracy": 0.202788282930851,
|
||
|
|
"num_tokens": 11140105.0,
|
||
|
|
"step": 4475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.883962631225586,
|
||
|
|
"epoch": 5.239766081871345,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0003022138149650708,
|
||
|
|
"loss": 5.4244,
|
||
|
|
"mean_token_accuracy": 0.20240918546915054,
|
||
|
|
"num_tokens": 11152291.0,
|
||
|
|
"step": 4480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9096128940582275,
|
||
|
|
"epoch": 5.245614035087719,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003017484585061039,
|
||
|
|
"loss": 5.4587,
|
||
|
|
"mean_token_accuracy": 0.2016108438372612,
|
||
|
|
"num_tokens": 11166330.0,
|
||
|
|
"step": 4485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997616815567016,
|
||
|
|
"epoch": 5.251461988304094,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00030128298595690905,
|
||
|
|
"loss": 5.4329,
|
||
|
|
"mean_token_accuracy": 0.19642306566238404,
|
||
|
|
"num_tokens": 11178737.0,
|
||
|
|
"step": 4490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979503440856933,
|
||
|
|
"epoch": 5.257309941520468,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00030081739933767034,
|
||
|
|
"loss": 5.488,
|
||
|
|
"mean_token_accuracy": 0.19103857427835463,
|
||
|
|
"num_tokens": 11191179.0,
|
||
|
|
"step": 4495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933886528015137,
|
||
|
|
"epoch": 5.2631578947368425,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003003517006690672,
|
||
|
|
"loss": 5.4287,
|
||
|
|
"mean_token_accuracy": 0.19391554445028306,
|
||
|
|
"num_tokens": 11203890.0,
|
||
|
|
"step": 4500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 5.2631578947368425,
|
||
|
|
"eval_entropy": 5.912843805498781,
|
||
|
|
"eval_loss": 6.584635257720947,
|
||
|
|
"eval_mean_token_accuracy": 0.1491837761966528,
|
||
|
|
"eval_num_tokens": 11203890.0,
|
||
|
|
"eval_runtime": 2.2601,
|
||
|
|
"eval_samples_per_second": 1197.739,
|
||
|
|
"eval_steps_per_second": 149.994,
|
||
|
|
"step": 4500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9200362205505375,
|
||
|
|
"epoch": 5.269005847953216,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00029988589197226515,
|
||
|
|
"loss": 5.4469,
|
||
|
|
"mean_token_accuracy": 0.1923572301864624,
|
||
|
|
"num_tokens": 11216556.0,
|
||
|
|
"step": 4505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96320333480835,
|
||
|
|
"epoch": 5.2748538011695905,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00029941997526890745,
|
||
|
|
"loss": 5.4581,
|
||
|
|
"mean_token_accuracy": 0.19888003915548325,
|
||
|
|
"num_tokens": 11228352.0,
|
||
|
|
"step": 4510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9294623851776125,
|
||
|
|
"epoch": 5.280701754385965,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000298953952581106,
|
||
|
|
"loss": 5.4571,
|
||
|
|
"mean_token_accuracy": 0.19423750191926956,
|
||
|
|
"num_tokens": 11239423.0,
|
||
|
|
"step": 4515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937313842773437,
|
||
|
|
"epoch": 5.286549707602339,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00029848782593143246,
|
||
|
|
"loss": 5.4229,
|
||
|
|
"mean_token_accuracy": 0.19343676865100862,
|
||
|
|
"num_tokens": 11251117.0,
|
||
|
|
"step": 4520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9353701114654545,
|
||
|
|
"epoch": 5.292397660818714,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00029802159734291015,
|
||
|
|
"loss": 5.4721,
|
||
|
|
"mean_token_accuracy": 0.19762906432151794,
|
||
|
|
"num_tokens": 11264459.0,
|
||
|
|
"step": 4525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.861942863464355,
|
||
|
|
"epoch": 5.298245614035087,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002975552688390045,
|
||
|
|
"loss": 5.3824,
|
||
|
|
"mean_token_accuracy": 0.20630926191806792,
|
||
|
|
"num_tokens": 11276020.0,
|
||
|
|
"step": 4530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969491052627563,
|
||
|
|
"epoch": 5.304093567251462,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00029708884244361474,
|
||
|
|
"loss": 5.4476,
|
||
|
|
"mean_token_accuracy": 0.19427042752504348,
|
||
|
|
"num_tokens": 11287412.0,
|
||
|
|
"step": 4535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954285669326782,
|
||
|
|
"epoch": 5.309941520467836,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00029662232018106473,
|
||
|
|
"loss": 5.5205,
|
||
|
|
"mean_token_accuracy": 0.19134369492530823,
|
||
|
|
"num_tokens": 11298607.0,
|
||
|
|
"step": 4540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0158768653869625,
|
||
|
|
"epoch": 5.315789473684211,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00029615570407609467,
|
||
|
|
"loss": 5.5726,
|
||
|
|
"mean_token_accuracy": 0.19140319973230363,
|
||
|
|
"num_tokens": 11310943.0,
|
||
|
|
"step": 4545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89475531578064,
|
||
|
|
"epoch": 5.321637426900585,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00029568899615385174,
|
||
|
|
"loss": 5.4197,
|
||
|
|
"mean_token_accuracy": 0.19673997908830643,
|
||
|
|
"num_tokens": 11323684.0,
|
||
|
|
"step": 4550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8167280673980715,
|
||
|
|
"epoch": 5.3274853801169595,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000295222198439882,
|
||
|
|
"loss": 5.4022,
|
||
|
|
"mean_token_accuracy": 0.19947143346071244,
|
||
|
|
"num_tokens": 11336817.0,
|
||
|
|
"step": 4555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037799978256226,
|
||
|
|
"epoch": 5.333333333333333,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002947553129601209,
|
||
|
|
"loss": 5.5724,
|
||
|
|
"mean_token_accuracy": 0.18857804536819459,
|
||
|
|
"num_tokens": 11349246.0,
|
||
|
|
"step": 4560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965430164337159,
|
||
|
|
"epoch": 5.3391812865497075,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002942883417408849,
|
||
|
|
"loss": 5.4565,
|
||
|
|
"mean_token_accuracy": 0.19550773054361342,
|
||
|
|
"num_tokens": 11360995.0,
|
||
|
|
"step": 4565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.858381986618042,
|
||
|
|
"epoch": 5.345029239766082,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002938212868088626,
|
||
|
|
"loss": 5.3966,
|
||
|
|
"mean_token_accuracy": 0.20248076170682908,
|
||
|
|
"num_tokens": 11373713.0,
|
||
|
|
"step": 4570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.942375898361206,
|
||
|
|
"epoch": 5.350877192982456,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00029335415019110593,
|
||
|
|
"loss": 5.4613,
|
||
|
|
"mean_token_accuracy": 0.19696496278047562,
|
||
|
|
"num_tokens": 11386532.0,
|
||
|
|
"step": 4575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8755193710327145,
|
||
|
|
"epoch": 5.356725146198831,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002928869339150212,
|
||
|
|
"loss": 5.3721,
|
||
|
|
"mean_token_accuracy": 0.20515065640211105,
|
||
|
|
"num_tokens": 11400535.0,
|
||
|
|
"step": 4580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894622564315796,
|
||
|
|
"epoch": 5.362573099415204,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0002924196400083607,
|
||
|
|
"loss": 5.4497,
|
||
|
|
"mean_token_accuracy": 0.19950962513685228,
|
||
|
|
"num_tokens": 11412577.0,
|
||
|
|
"step": 4585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9192116260528564,
|
||
|
|
"epoch": 5.368421052631579,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00029195227049921336,
|
||
|
|
"loss": 5.4484,
|
||
|
|
"mean_token_accuracy": 0.19551462382078172,
|
||
|
|
"num_tokens": 11427142.0,
|
||
|
|
"step": 4590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959398984909058,
|
||
|
|
"epoch": 5.374269005847953,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00029148482741599634,
|
||
|
|
"loss": 5.5074,
|
||
|
|
"mean_token_accuracy": 0.19466634839773178,
|
||
|
|
"num_tokens": 11441319.0,
|
||
|
|
"step": 4595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933380174636841,
|
||
|
|
"epoch": 5.380116959064328,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00029101731278744636,
|
||
|
|
"loss": 5.4295,
|
||
|
|
"mean_token_accuracy": 0.19273726493120194,
|
||
|
|
"num_tokens": 11453947.0,
|
||
|
|
"step": 4600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963898324966431,
|
||
|
|
"epoch": 5.385964912280702,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002905497286426102,
|
||
|
|
"loss": 5.4527,
|
||
|
|
"mean_token_accuracy": 0.19423352628946305,
|
||
|
|
"num_tokens": 11465463.0,
|
||
|
|
"step": 4605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967693328857422,
|
||
|
|
"epoch": 5.391812865497076,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00029008207701083677,
|
||
|
|
"loss": 5.4762,
|
||
|
|
"mean_token_accuracy": 0.19695046097040175,
|
||
|
|
"num_tokens": 11477249.0,
|
||
|
|
"step": 4610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96759786605835,
|
||
|
|
"epoch": 5.39766081871345,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002896143599217674,
|
||
|
|
"loss": 5.5253,
|
||
|
|
"mean_token_accuracy": 0.19219062775373458,
|
||
|
|
"num_tokens": 11490184.0,
|
||
|
|
"step": 4615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.904387044906616,
|
||
|
|
"epoch": 5.4035087719298245,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0002891465794053282,
|
||
|
|
"loss": 5.5503,
|
||
|
|
"mean_token_accuracy": 0.1932561919093132,
|
||
|
|
"num_tokens": 11502935.0,
|
||
|
|
"step": 4620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980705881118775,
|
||
|
|
"epoch": 5.409356725146199,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002886787374917198,
|
||
|
|
"loss": 5.5018,
|
||
|
|
"mean_token_accuracy": 0.1991418942809105,
|
||
|
|
"num_tokens": 11515385.0,
|
||
|
|
"step": 4625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012708044052124,
|
||
|
|
"epoch": 5.415204678362573,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00028821083621140986,
|
||
|
|
"loss": 5.5587,
|
||
|
|
"mean_token_accuracy": 0.18672311156988144,
|
||
|
|
"num_tokens": 11528786.0,
|
||
|
|
"step": 4630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920512437820435,
|
||
|
|
"epoch": 5.421052631578947,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0002877428775951234,
|
||
|
|
"loss": 5.5432,
|
||
|
|
"mean_token_accuracy": 0.18925438225269317,
|
||
|
|
"num_tokens": 11540401.0,
|
||
|
|
"step": 4635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936688995361328,
|
||
|
|
"epoch": 5.426900584795321,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0002872748636738344,
|
||
|
|
"loss": 5.5023,
|
||
|
|
"mean_token_accuracy": 0.1907402604818344,
|
||
|
|
"num_tokens": 11552920.0,
|
||
|
|
"step": 4640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990766143798828,
|
||
|
|
"epoch": 5.432748538011696,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002868067964787568,
|
||
|
|
"loss": 5.5707,
|
||
|
|
"mean_token_accuracy": 0.18776880502700805,
|
||
|
|
"num_tokens": 11566237.0,
|
||
|
|
"step": 4645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.933041620254516,
|
||
|
|
"epoch": 5.43859649122807,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00028633867804133583,
|
||
|
|
"loss": 5.4763,
|
||
|
|
"mean_token_accuracy": 0.18934521079063416,
|
||
|
|
"num_tokens": 11577380.0,
|
||
|
|
"step": 4650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954767799377441,
|
||
|
|
"epoch": 5.444444444444445,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002858705103932391,
|
||
|
|
"loss": 5.4863,
|
||
|
|
"mean_token_accuracy": 0.18684083670377732,
|
||
|
|
"num_tokens": 11590708.0,
|
||
|
|
"step": 4655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024817752838135,
|
||
|
|
"epoch": 5.450292397660819,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00028540229556634785,
|
||
|
|
"loss": 5.5449,
|
||
|
|
"mean_token_accuracy": 0.1924133315682411,
|
||
|
|
"num_tokens": 11603351.0,
|
||
|
|
"step": 4660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874948263168335,
|
||
|
|
"epoch": 5.456140350877193,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002849340355927477,
|
||
|
|
"loss": 5.4716,
|
||
|
|
"mean_token_accuracy": 0.19483616799116135,
|
||
|
|
"num_tokens": 11615675.0,
|
||
|
|
"step": 4665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97089319229126,
|
||
|
|
"epoch": 5.461988304093567,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002844657325047208,
|
||
|
|
"loss": 5.4821,
|
||
|
|
"mean_token_accuracy": 0.19129352122545243,
|
||
|
|
"num_tokens": 11628184.0,
|
||
|
|
"step": 4670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939920234680176,
|
||
|
|
"epoch": 5.4678362573099415,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002839973883347361,
|
||
|
|
"loss": 5.5104,
|
||
|
|
"mean_token_accuracy": 0.1911798298358917,
|
||
|
|
"num_tokens": 11641058.0,
|
||
|
|
"step": 4675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.795039892196655,
|
||
|
|
"epoch": 5.473684210526316,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00028352900511544076,
|
||
|
|
"loss": 5.4214,
|
||
|
|
"mean_token_accuracy": 0.20322235971689223,
|
||
|
|
"num_tokens": 11653959.0,
|
||
|
|
"step": 4680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970742321014404,
|
||
|
|
"epoch": 5.47953216374269,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00028306058487965156,
|
||
|
|
"loss": 5.5072,
|
||
|
|
"mean_token_accuracy": 0.18967682421207427,
|
||
|
|
"num_tokens": 11665241.0,
|
||
|
|
"step": 4685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0189086437225345,
|
||
|
|
"epoch": 5.485380116959064,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002825921296603461,
|
||
|
|
"loss": 5.5283,
|
||
|
|
"mean_token_accuracy": 0.19461022168397904,
|
||
|
|
"num_tokens": 11678670.0,
|
||
|
|
"step": 4690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905443143844605,
|
||
|
|
"epoch": 5.491228070175438,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00028212364149065347,
|
||
|
|
"loss": 5.4445,
|
||
|
|
"mean_token_accuracy": 0.19465976655483247,
|
||
|
|
"num_tokens": 11689964.0,
|
||
|
|
"step": 4695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945306205749512,
|
||
|
|
"epoch": 5.497076023391813,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002816551224038458,
|
||
|
|
"loss": 5.5111,
|
||
|
|
"mean_token_accuracy": 0.19405128359794616,
|
||
|
|
"num_tokens": 11701895.0,
|
||
|
|
"step": 4700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947712802886963,
|
||
|
|
"epoch": 5.502923976608187,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00028118657443332984,
|
||
|
|
"loss": 5.4713,
|
||
|
|
"mean_token_accuracy": 0.19427902698516847,
|
||
|
|
"num_tokens": 11714335.0,
|
||
|
|
"step": 4705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9421563148498535,
|
||
|
|
"epoch": 5.508771929824562,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002807179996126371,
|
||
|
|
"loss": 5.4503,
|
||
|
|
"mean_token_accuracy": 0.19544649124145508,
|
||
|
|
"num_tokens": 11726828.0,
|
||
|
|
"step": 4710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880207920074463,
|
||
|
|
"epoch": 5.514619883040936,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00028024939997541606,
|
||
|
|
"loss": 5.4048,
|
||
|
|
"mean_token_accuracy": 0.20408879965543747,
|
||
|
|
"num_tokens": 11740729.0,
|
||
|
|
"step": 4715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967812204360962,
|
||
|
|
"epoch": 5.52046783625731,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00027978077755542264,
|
||
|
|
"loss": 5.5255,
|
||
|
|
"mean_token_accuracy": 0.18523763567209245,
|
||
|
|
"num_tokens": 11753017.0,
|
||
|
|
"step": 4720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989854621887207,
|
||
|
|
"epoch": 5.526315789473684,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002793121343865119,
|
||
|
|
"loss": 5.414,
|
||
|
|
"mean_token_accuracy": 0.19923020303249359,
|
||
|
|
"num_tokens": 11766139.0,
|
||
|
|
"step": 4725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7327488422393795,
|
||
|
|
"epoch": 5.5321637426900585,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0002788434725026286,
|
||
|
|
"loss": 5.3153,
|
||
|
|
"mean_token_accuracy": 0.2106275588274002,
|
||
|
|
"num_tokens": 11780315.0,
|
||
|
|
"step": 4730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9214788436889645,
|
||
|
|
"epoch": 5.538011695906433,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000278374793937799,
|
||
|
|
"loss": 5.4408,
|
||
|
|
"mean_token_accuracy": 0.19870334714651108,
|
||
|
|
"num_tokens": 11792342.0,
|
||
|
|
"step": 4735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.895834493637085,
|
||
|
|
"epoch": 5.543859649122807,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00027790610072612174,
|
||
|
|
"loss": 5.4638,
|
||
|
|
"mean_token_accuracy": 0.1970258519053459,
|
||
|
|
"num_tokens": 11804587.0,
|
||
|
|
"step": 4740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943404817581177,
|
||
|
|
"epoch": 5.549707602339181,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00027743739490175903,
|
||
|
|
"loss": 5.5057,
|
||
|
|
"mean_token_accuracy": 0.19159785211086272,
|
||
|
|
"num_tokens": 11815884.0,
|
||
|
|
"step": 4745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989337921142578,
|
||
|
|
"epoch": 5.555555555555555,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002769686784989276,
|
||
|
|
"loss": 5.5353,
|
||
|
|
"mean_token_accuracy": 0.18934809267520905,
|
||
|
|
"num_tokens": 11827279.0,
|
||
|
|
"step": 4750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943430709838867,
|
||
|
|
"epoch": 5.56140350877193,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00027649995355189026,
|
||
|
|
"loss": 5.4593,
|
||
|
|
"mean_token_accuracy": 0.19424251914024354,
|
||
|
|
"num_tokens": 11838646.0,
|
||
|
|
"step": 4755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031342363357544,
|
||
|
|
"epoch": 5.567251461988304,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000276031222094947,
|
||
|
|
"loss": 5.5093,
|
||
|
|
"mean_token_accuracy": 0.19725333005189896,
|
||
|
|
"num_tokens": 11850565.0,
|
||
|
|
"step": 4760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.727534341812134,
|
||
|
|
"epoch": 5.573099415204679,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002755624861624259,
|
||
|
|
"loss": 5.3448,
|
||
|
|
"mean_token_accuracy": 0.21594859510660172,
|
||
|
|
"num_tokens": 11863244.0,
|
||
|
|
"step": 4765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.84840202331543,
|
||
|
|
"epoch": 5.578947368421053,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0002750937477886745,
|
||
|
|
"loss": 5.4198,
|
||
|
|
"mean_token_accuracy": 0.2015600770711899,
|
||
|
|
"num_tokens": 11876884.0,
|
||
|
|
"step": 4770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918019437789917,
|
||
|
|
"epoch": 5.584795321637427,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000274625009008051,
|
||
|
|
"loss": 5.4455,
|
||
|
|
"mean_token_accuracy": 0.20234338492155074,
|
||
|
|
"num_tokens": 11889624.0,
|
||
|
|
"step": 4775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924061965942383,
|
||
|
|
"epoch": 5.590643274853801,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0002741562718549152,
|
||
|
|
"loss": 5.4891,
|
||
|
|
"mean_token_accuracy": 0.19300525039434432,
|
||
|
|
"num_tokens": 11901304.0,
|
||
|
|
"step": 4780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.783681058883667,
|
||
|
|
"epoch": 5.5964912280701755,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00027368753836362023,
|
||
|
|
"loss": 5.2982,
|
||
|
|
"mean_token_accuracy": 0.2075055405497551,
|
||
|
|
"num_tokens": 11913188.0,
|
||
|
|
"step": 4785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001254463195801,
|
||
|
|
"epoch": 5.60233918128655,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002732188105685027,
|
||
|
|
"loss": 5.5302,
|
||
|
|
"mean_token_accuracy": 0.1915764570236206,
|
||
|
|
"num_tokens": 11926771.0,
|
||
|
|
"step": 4790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912238216400146,
|
||
|
|
"epoch": 5.6081871345029235,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002727500905038752,
|
||
|
|
"loss": 5.5162,
|
||
|
|
"mean_token_accuracy": 0.19161727726459504,
|
||
|
|
"num_tokens": 11939162.0,
|
||
|
|
"step": 4795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995923137664795,
|
||
|
|
"epoch": 5.614035087719298,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002722813802040161,
|
||
|
|
"loss": 5.552,
|
||
|
|
"mean_token_accuracy": 0.1830344557762146,
|
||
|
|
"num_tokens": 11952376.0,
|
||
|
|
"step": 4800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924818611145019,
|
||
|
|
"epoch": 5.619883040935672,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00027181268170316193,
|
||
|
|
"loss": 5.3778,
|
||
|
|
"mean_token_accuracy": 0.20272146612405778,
|
||
|
|
"num_tokens": 11965154.0,
|
||
|
|
"step": 4805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.842271947860718,
|
||
|
|
"epoch": 5.625730994152047,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0002713439970354978,
|
||
|
|
"loss": 5.4231,
|
||
|
|
"mean_token_accuracy": 0.20478268712759018,
|
||
|
|
"num_tokens": 11978492.0,
|
||
|
|
"step": 4810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.949887466430664,
|
||
|
|
"epoch": 5.631578947368421,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002708753282351486,
|
||
|
|
"loss": 5.5073,
|
||
|
|
"mean_token_accuracy": 0.19294035136699678,
|
||
|
|
"num_tokens": 11990603.0,
|
||
|
|
"step": 4815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961982774734497,
|
||
|
|
"epoch": 5.637426900584796,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002704066773361706,
|
||
|
|
"loss": 5.5525,
|
||
|
|
"mean_token_accuracy": 0.18886120170354842,
|
||
|
|
"num_tokens": 12002608.0,
|
||
|
|
"step": 4820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941114187240601,
|
||
|
|
"epoch": 5.643274853801169,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002699380463725425,
|
||
|
|
"loss": 5.5459,
|
||
|
|
"mean_token_accuracy": 0.1918204516172409,
|
||
|
|
"num_tokens": 12016112.0,
|
||
|
|
"step": 4825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998517417907715,
|
||
|
|
"epoch": 5.649122807017544,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000269469437378156,
|
||
|
|
"loss": 5.5539,
|
||
|
|
"mean_token_accuracy": 0.18836696147918702,
|
||
|
|
"num_tokens": 12027685.0,
|
||
|
|
"step": 4830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874228286743164,
|
||
|
|
"epoch": 5.654970760233918,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00026900085238680787,
|
||
|
|
"loss": 5.3968,
|
||
|
|
"mean_token_accuracy": 0.20431167632341385,
|
||
|
|
"num_tokens": 12040524.0,
|
||
|
|
"step": 4835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878893280029297,
|
||
|
|
"epoch": 5.6608187134502925,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002685322934321907,
|
||
|
|
"loss": 5.4596,
|
||
|
|
"mean_token_accuracy": 0.19717695116996764,
|
||
|
|
"num_tokens": 12052841.0,
|
||
|
|
"step": 4840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9935300827026365,
|
||
|
|
"epoch": 5.666666666666667,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002680637625478837,
|
||
|
|
"loss": 5.5029,
|
||
|
|
"mean_token_accuracy": 0.194629667699337,
|
||
|
|
"num_tokens": 12065375.0,
|
||
|
|
"step": 4845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016139984130859,
|
||
|
|
"epoch": 5.6725146198830405,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0002675952617673446,
|
||
|
|
"loss": 5.5241,
|
||
|
|
"mean_token_accuracy": 0.19547293782234193,
|
||
|
|
"num_tokens": 12078034.0,
|
||
|
|
"step": 4850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932389593124389,
|
||
|
|
"epoch": 5.678362573099415,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002671267931239006,
|
||
|
|
"loss": 5.5552,
|
||
|
|
"mean_token_accuracy": 0.19167326539754867,
|
||
|
|
"num_tokens": 12090218.0,
|
||
|
|
"step": 4855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.958886003494262,
|
||
|
|
"epoch": 5.684210526315789,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00026665835865073896,
|
||
|
|
"loss": 5.48,
|
||
|
|
"mean_token_accuracy": 0.1946641191840172,
|
||
|
|
"num_tokens": 12101927.0,
|
||
|
|
"step": 4860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01270899772644,
|
||
|
|
"epoch": 5.690058479532164,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0002661899603808989,
|
||
|
|
"loss": 5.5248,
|
||
|
|
"mean_token_accuracy": 0.18494480550289155,
|
||
|
|
"num_tokens": 12114887.0,
|
||
|
|
"step": 4865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961265659332275,
|
||
|
|
"epoch": 5.695906432748538,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002657216003472626,
|
||
|
|
"loss": 5.5254,
|
||
|
|
"mean_token_accuracy": 0.191181218624115,
|
||
|
|
"num_tokens": 12127151.0,
|
||
|
|
"step": 4870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.967305612564087,
|
||
|
|
"epoch": 5.701754385964913,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00026525328058254604,
|
||
|
|
"loss": 5.5258,
|
||
|
|
"mean_token_accuracy": 0.19985068887472152,
|
||
|
|
"num_tokens": 12141987.0,
|
||
|
|
"step": 4875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897636651992798,
|
||
|
|
"epoch": 5.707602339181286,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00026478500311929076,
|
||
|
|
"loss": 5.4138,
|
||
|
|
"mean_token_accuracy": 0.19909739941358567,
|
||
|
|
"num_tokens": 12154525.0,
|
||
|
|
"step": 4880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7962370872497555,
|
||
|
|
"epoch": 5.713450292397661,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00026431676998985444,
|
||
|
|
"loss": 5.337,
|
||
|
|
"mean_token_accuracy": 0.2098366767168045,
|
||
|
|
"num_tokens": 12166599.0,
|
||
|
|
"step": 4885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935725736618042,
|
||
|
|
"epoch": 5.719298245614035,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002638485832264024,
|
||
|
|
"loss": 5.5699,
|
||
|
|
"mean_token_accuracy": 0.19258134067058563,
|
||
|
|
"num_tokens": 12178658.0,
|
||
|
|
"step": 4890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920307397842407,
|
||
|
|
"epoch": 5.7251461988304095,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00026338044486089895,
|
||
|
|
"loss": 5.4132,
|
||
|
|
"mean_token_accuracy": 0.19877748489379882,
|
||
|
|
"num_tokens": 12190311.0,
|
||
|
|
"step": 4895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947762203216553,
|
||
|
|
"epoch": 5.730994152046784,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00026291235692509795,
|
||
|
|
"loss": 5.5306,
|
||
|
|
"mean_token_accuracy": 0.1878758192062378,
|
||
|
|
"num_tokens": 12202443.0,
|
||
|
|
"step": 4900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.950115489959717,
|
||
|
|
"epoch": 5.7368421052631575,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00026244432145053467,
|
||
|
|
"loss": 5.5596,
|
||
|
|
"mean_token_accuracy": 0.1880561739206314,
|
||
|
|
"num_tokens": 12214245.0,
|
||
|
|
"step": 4905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911825370788574,
|
||
|
|
"epoch": 5.742690058479532,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002619763404685167,
|
||
|
|
"loss": 5.4685,
|
||
|
|
"mean_token_accuracy": 0.2016769155859947,
|
||
|
|
"num_tokens": 12226752.0,
|
||
|
|
"step": 4910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951898145675659,
|
||
|
|
"epoch": 5.748538011695906,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00026150841601011495,
|
||
|
|
"loss": 5.5351,
|
||
|
|
"mean_token_accuracy": 0.18928302675485612,
|
||
|
|
"num_tokens": 12239043.0,
|
||
|
|
"step": 4915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.909374666213989,
|
||
|
|
"epoch": 5.754385964912281,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002610405501061552,
|
||
|
|
"loss": 5.5178,
|
||
|
|
"mean_token_accuracy": 0.19401704221963884,
|
||
|
|
"num_tokens": 12250799.0,
|
||
|
|
"step": 4920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995615434646607,
|
||
|
|
"epoch": 5.760233918128655,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002605727447872091,
|
||
|
|
"loss": 5.6411,
|
||
|
|
"mean_token_accuracy": 0.1770036429166794,
|
||
|
|
"num_tokens": 12264503.0,
|
||
|
|
"step": 4925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.995881843566894,
|
||
|
|
"epoch": 5.76608187134503,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002601050020835851,
|
||
|
|
"loss": 5.5241,
|
||
|
|
"mean_token_accuracy": 0.19251661747694016,
|
||
|
|
"num_tokens": 12276106.0,
|
||
|
|
"step": 4930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.886055850982666,
|
||
|
|
"epoch": 5.771929824561403,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00025963732402532026,
|
||
|
|
"loss": 5.4433,
|
||
|
|
"mean_token_accuracy": 0.19460997134447097,
|
||
|
|
"num_tokens": 12288322.0,
|
||
|
|
"step": 4935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.937154722213745,
|
||
|
|
"epoch": 5.777777777777778,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0002591697126421707,
|
||
|
|
"loss": 5.4804,
|
||
|
|
"mean_token_accuracy": 0.19665079563856125,
|
||
|
|
"num_tokens": 12301059.0,
|
||
|
|
"step": 4940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977020740509033,
|
||
|
|
"epoch": 5.783625730994152,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002587021699636035,
|
||
|
|
"loss": 5.5162,
|
||
|
|
"mean_token_accuracy": 0.1935534283518791,
|
||
|
|
"num_tokens": 12313206.0,
|
||
|
|
"step": 4945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9122649192810055,
|
||
|
|
"epoch": 5.7894736842105265,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00025823469801878734,
|
||
|
|
"loss": 5.4481,
|
||
|
|
"mean_token_accuracy": 0.2032322183251381,
|
||
|
|
"num_tokens": 12325426.0,
|
||
|
|
"step": 4950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.877651357650757,
|
||
|
|
"epoch": 5.7953216374269,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00025776729883658406,
|
||
|
|
"loss": 5.5181,
|
||
|
|
"mean_token_accuracy": 0.19333651661872864,
|
||
|
|
"num_tokens": 12338683.0,
|
||
|
|
"step": 4955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945428705215454,
|
||
|
|
"epoch": 5.8011695906432745,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002572999744455395,
|
||
|
|
"loss": 5.4876,
|
||
|
|
"mean_token_accuracy": 0.20007674396038055,
|
||
|
|
"num_tokens": 12351139.0,
|
||
|
|
"step": 4960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.886772394180298,
|
||
|
|
"epoch": 5.807017543859649,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00025683272687387513,
|
||
|
|
"loss": 5.4098,
|
||
|
|
"mean_token_accuracy": 0.1998754158616066,
|
||
|
|
"num_tokens": 12362804.0,
|
||
|
|
"step": 4965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003363037109375,
|
||
|
|
"epoch": 5.812865497076023,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0002563655581494789,
|
||
|
|
"loss": 5.6011,
|
||
|
|
"mean_token_accuracy": 0.18788198679685592,
|
||
|
|
"num_tokens": 12375069.0,
|
||
|
|
"step": 4970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973224782943726,
|
||
|
|
"epoch": 5.818713450292398,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00025589847029989653,
|
||
|
|
"loss": 5.476,
|
||
|
|
"mean_token_accuracy": 0.19356760531663894,
|
||
|
|
"num_tokens": 12387434.0,
|
||
|
|
"step": 4975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92840085029602,
|
||
|
|
"epoch": 5.824561403508772,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00025543146535232295,
|
||
|
|
"loss": 5.5266,
|
||
|
|
"mean_token_accuracy": 0.1936199903488159,
|
||
|
|
"num_tokens": 12400141.0,
|
||
|
|
"step": 4980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.886835241317749,
|
||
|
|
"epoch": 5.830409356725146,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00025496454533359284,
|
||
|
|
"loss": 5.4757,
|
||
|
|
"mean_token_accuracy": 0.19721769541502,
|
||
|
|
"num_tokens": 12412619.0,
|
||
|
|
"step": 4985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932554721832275,
|
||
|
|
"epoch": 5.83625730994152,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00025449771227017265,
|
||
|
|
"loss": 5.4577,
|
||
|
|
"mean_token_accuracy": 0.193479260802269,
|
||
|
|
"num_tokens": 12425312.0,
|
||
|
|
"step": 4990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960072135925293,
|
||
|
|
"epoch": 5.842105263157895,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0002540309681881516,
|
||
|
|
"loss": 5.4997,
|
||
|
|
"mean_token_accuracy": 0.19472804963588713,
|
||
|
|
"num_tokens": 12436972.0,
|
||
|
|
"step": 4995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0214738845825195,
|
||
|
|
"epoch": 5.847953216374269,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0002535643151132321,
|
||
|
|
"loss": 5.5417,
|
||
|
|
"mean_token_accuracy": 0.18650467693805695,
|
||
|
|
"num_tokens": 12448543.0,
|
||
|
|
"step": 5000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 5.847953216374269,
|
||
|
|
"eval_entropy": 5.971811319874451,
|
||
|
|
"eval_loss": 6.5513224601745605,
|
||
|
|
"eval_mean_token_accuracy": 0.15066081152509095,
|
||
|
|
"eval_num_tokens": 12448543.0,
|
||
|
|
"eval_runtime": 2.2607,
|
||
|
|
"eval_samples_per_second": 1197.407,
|
||
|
|
"eval_steps_per_second": 149.952,
|
||
|
|
"step": 5000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 8540,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.8018758746368e+16,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|