6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.29655990510083036,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.69198923110962,
|
||
|
|
"epoch": 0.0004942665085013839,
|
||
|
|
"grad_norm": 13.625,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.8511,
|
||
|
|
"mean_token_accuracy": 9.813542710617185e-05,
|
||
|
|
"num_tokens": 11289.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.69196434020996,
|
||
|
|
"epoch": 0.0009885330170027679,
|
||
|
|
"grad_norm": 13.0,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7685,
|
||
|
|
"mean_token_accuracy": 9.980039903894067e-05,
|
||
|
|
"num_tokens": 21541.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691250991821288,
|
||
|
|
"epoch": 0.0014827995255041518,
|
||
|
|
"grad_norm": 9.875,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.5143,
|
||
|
|
"mean_token_accuracy": 0.02034043968305923,
|
||
|
|
"num_tokens": 32257.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.681182479858398,
|
||
|
|
"epoch": 0.0019770660340055358,
|
||
|
|
"grad_norm": 5.9375,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.1975,
|
||
|
|
"mean_token_accuracy": 0.04461864829063415,
|
||
|
|
"num_tokens": 44176.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.627556705474854,
|
||
|
|
"epoch": 0.0024713325425069197,
|
||
|
|
"grad_norm": 3.9375,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 9.9357,
|
||
|
|
"mean_token_accuracy": 0.039965702407062056,
|
||
|
|
"num_tokens": 56115.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.602597999572755,
|
||
|
|
"epoch": 0.0029655990510083037,
|
||
|
|
"grad_norm": 3.265625,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.8069,
|
||
|
|
"mean_token_accuracy": 0.04259452596306801,
|
||
|
|
"num_tokens": 68828.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.593318939208984,
|
||
|
|
"epoch": 0.0034598655595096876,
|
||
|
|
"grad_norm": 2.96875,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.6975,
|
||
|
|
"mean_token_accuracy": 0.041454059071838856,
|
||
|
|
"num_tokens": 80097.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.583466339111329,
|
||
|
|
"epoch": 0.0039541320680110716,
|
||
|
|
"grad_norm": 2.5625,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.6252,
|
||
|
|
"mean_token_accuracy": 0.041735239885747434,
|
||
|
|
"num_tokens": 91510.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.582863330841064,
|
||
|
|
"epoch": 0.004448398576512456,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.5757,
|
||
|
|
"mean_token_accuracy": 0.04492984525859356,
|
||
|
|
"num_tokens": 103443.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.559914302825927,
|
||
|
|
"epoch": 0.0049426650850138395,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.5717,
|
||
|
|
"mean_token_accuracy": 0.04110746793448925,
|
||
|
|
"num_tokens": 114629.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.571237468719483,
|
||
|
|
"epoch": 0.005436931593515224,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.5118,
|
||
|
|
"mean_token_accuracy": 0.04097981490194798,
|
||
|
|
"num_tokens": 125012.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.549415683746338,
|
||
|
|
"epoch": 0.005931198102016607,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.4131,
|
||
|
|
"mean_token_accuracy": 0.05204631946980953,
|
||
|
|
"num_tokens": 135834.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.44157009124756,
|
||
|
|
"epoch": 0.006425464610517992,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.3321,
|
||
|
|
"mean_token_accuracy": 0.0504114169627428,
|
||
|
|
"num_tokens": 147413.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.382845687866212,
|
||
|
|
"epoch": 0.006919731119019375,
|
||
|
|
"grad_norm": 2.328125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.2904,
|
||
|
|
"mean_token_accuracy": 0.05800989344716072,
|
||
|
|
"num_tokens": 158046.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.461502265930175,
|
||
|
|
"epoch": 0.00741399762752076,
|
||
|
|
"grad_norm": 2.390625,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.1643,
|
||
|
|
"mean_token_accuracy": 0.056254255771636966,
|
||
|
|
"num_tokens": 168564.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.425090026855468,
|
||
|
|
"epoch": 0.007908264136022143,
|
||
|
|
"grad_norm": 2.28125,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.1411,
|
||
|
|
"mean_token_accuracy": 0.056681671738624574,
|
||
|
|
"num_tokens": 181168.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.372301387786866,
|
||
|
|
"epoch": 0.008402530644523527,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.0212,
|
||
|
|
"mean_token_accuracy": 0.056995033472776416,
|
||
|
|
"num_tokens": 192666.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.375147438049316,
|
||
|
|
"epoch": 0.008896797153024912,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 8.9484,
|
||
|
|
"mean_token_accuracy": 0.06448689587414265,
|
||
|
|
"num_tokens": 203688.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.224098777770996,
|
||
|
|
"epoch": 0.009391063661526295,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.8003,
|
||
|
|
"mean_token_accuracy": 0.06981704570353031,
|
||
|
|
"num_tokens": 214399.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.271527671813965,
|
||
|
|
"epoch": 0.009885330170027679,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.7944,
|
||
|
|
"mean_token_accuracy": 0.06457024440169334,
|
||
|
|
"num_tokens": 227549.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.180687618255615,
|
||
|
|
"epoch": 0.010379596678529062,
|
||
|
|
"grad_norm": 2.203125,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.5903,
|
||
|
|
"mean_token_accuracy": 0.07823638059198856,
|
||
|
|
"num_tokens": 239612.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.10289478302002,
|
||
|
|
"epoch": 0.010873863187030448,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.5791,
|
||
|
|
"mean_token_accuracy": 0.07145100198686123,
|
||
|
|
"num_tokens": 251163.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.903892230987548,
|
||
|
|
"epoch": 0.011368129695531831,
|
||
|
|
"grad_norm": 1.9375,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.3843,
|
||
|
|
"mean_token_accuracy": 0.0816077221184969,
|
||
|
|
"num_tokens": 263995.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.960233402252197,
|
||
|
|
"epoch": 0.011862396204033215,
|
||
|
|
"grad_norm": 1.8125,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.425,
|
||
|
|
"mean_token_accuracy": 0.06415067501366138,
|
||
|
|
"num_tokens": 275103.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.838393878936767,
|
||
|
|
"epoch": 0.012356662712534598,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.2674,
|
||
|
|
"mean_token_accuracy": 0.06674193441867829,
|
||
|
|
"num_tokens": 286838.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.746806716918945,
|
||
|
|
"epoch": 0.012850929221035983,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.1767,
|
||
|
|
"mean_token_accuracy": 0.06822415627539158,
|
||
|
|
"num_tokens": 298750.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.384112930297851,
|
||
|
|
"epoch": 0.013345195729537367,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 7.9711,
|
||
|
|
"mean_token_accuracy": 0.08611446619033813,
|
||
|
|
"num_tokens": 310451.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.315298366546632,
|
||
|
|
"epoch": 0.01383946223803875,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.9683,
|
||
|
|
"mean_token_accuracy": 0.0793497048318386,
|
||
|
|
"num_tokens": 321232.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.070902252197266,
|
||
|
|
"epoch": 0.014333728746540134,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.8467,
|
||
|
|
"mean_token_accuracy": 0.08167413920164109,
|
||
|
|
"num_tokens": 332531.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.893198204040527,
|
||
|
|
"epoch": 0.01482799525504152,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.7824,
|
||
|
|
"mean_token_accuracy": 0.08233431465923786,
|
||
|
|
"num_tokens": 346002.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.604196453094483,
|
||
|
|
"epoch": 0.015322261763542903,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.6918,
|
||
|
|
"mean_token_accuracy": 0.08017267808318138,
|
||
|
|
"num_tokens": 356691.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.595713043212891,
|
||
|
|
"epoch": 0.015816528272044286,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.6619,
|
||
|
|
"mean_token_accuracy": 0.08665368482470512,
|
||
|
|
"num_tokens": 368749.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.324952697753906,
|
||
|
|
"epoch": 0.01631079478054567,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.5719,
|
||
|
|
"mean_token_accuracy": 0.09090175405144692,
|
||
|
|
"num_tokens": 379484.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.320633029937744,
|
||
|
|
"epoch": 0.016805061289047053,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.5789,
|
||
|
|
"mean_token_accuracy": 0.07478476092219352,
|
||
|
|
"num_tokens": 389751.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.1990966796875,
|
||
|
|
"epoch": 0.017299327797548437,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.5788,
|
||
|
|
"mean_token_accuracy": 0.08275405988097191,
|
||
|
|
"num_tokens": 400771.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.125025653839112,
|
||
|
|
"epoch": 0.017793594306049824,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.5601,
|
||
|
|
"mean_token_accuracy": 0.0846537172794342,
|
||
|
|
"num_tokens": 413575.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.066452836990356,
|
||
|
|
"epoch": 0.018287860814551207,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.4998,
|
||
|
|
"mean_token_accuracy": 0.08586764261126519,
|
||
|
|
"num_tokens": 424825.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.964886236190796,
|
||
|
|
"epoch": 0.01878212732305259,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.5346,
|
||
|
|
"mean_token_accuracy": 0.09030681177973747,
|
||
|
|
"num_tokens": 435610.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.015780639648437,
|
||
|
|
"epoch": 0.019276393831553974,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.5224,
|
||
|
|
"mean_token_accuracy": 0.08522208034992218,
|
||
|
|
"num_tokens": 445855.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.982599878311158,
|
||
|
|
"epoch": 0.019770660340055358,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.4161,
|
||
|
|
"mean_token_accuracy": 0.0847946710884571,
|
||
|
|
"num_tokens": 456895.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.934762954711914,
|
||
|
|
"epoch": 0.02026492684855674,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.5294,
|
||
|
|
"mean_token_accuracy": 0.08614946454763413,
|
||
|
|
"num_tokens": 467446.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.875687599182129,
|
||
|
|
"epoch": 0.020759193357058125,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.4513,
|
||
|
|
"mean_token_accuracy": 0.08521210327744484,
|
||
|
|
"num_tokens": 478988.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.806298780441284,
|
||
|
|
"epoch": 0.02125345986555951,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.4466,
|
||
|
|
"mean_token_accuracy": 0.09093363285064697,
|
||
|
|
"num_tokens": 491053.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.944227981567383,
|
||
|
|
"epoch": 0.021747726374060895,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.5179,
|
||
|
|
"mean_token_accuracy": 0.07997574843466282,
|
||
|
|
"num_tokens": 502279.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.813448143005371,
|
||
|
|
"epoch": 0.02224199288256228,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.3679,
|
||
|
|
"mean_token_accuracy": 0.09318176656961441,
|
||
|
|
"num_tokens": 513470.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8025350093841555,
|
||
|
|
"epoch": 0.022736259391063662,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.4257,
|
||
|
|
"mean_token_accuracy": 0.08424223065376282,
|
||
|
|
"num_tokens": 524380.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.810437917709351,
|
||
|
|
"epoch": 0.023230525899565046,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.4437,
|
||
|
|
"mean_token_accuracy": 0.09268885552883148,
|
||
|
|
"num_tokens": 535798.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.708868885040284,
|
||
|
|
"epoch": 0.02372479240806643,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.36,
|
||
|
|
"mean_token_accuracy": 0.093184432387352,
|
||
|
|
"num_tokens": 545720.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.793004894256592,
|
||
|
|
"epoch": 0.024219058916567813,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.3897,
|
||
|
|
"mean_token_accuracy": 0.08860904648900032,
|
||
|
|
"num_tokens": 557110.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.733625698089599,
|
||
|
|
"epoch": 0.024713325425069196,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.3565,
|
||
|
|
"mean_token_accuracy": 0.09297666698694229,
|
||
|
|
"num_tokens": 568966.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.760022974014282,
|
||
|
|
"epoch": 0.02520759193357058,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3633,
|
||
|
|
"mean_token_accuracy": 0.09142611697316169,
|
||
|
|
"num_tokens": 580441.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.757736253738403,
|
||
|
|
"epoch": 0.025701858442071967,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.3716,
|
||
|
|
"mean_token_accuracy": 0.08710438385605812,
|
||
|
|
"num_tokens": 592698.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.643496417999268,
|
||
|
|
"epoch": 0.02619612495057335,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.3212,
|
||
|
|
"mean_token_accuracy": 0.09259616583585739,
|
||
|
|
"num_tokens": 604787.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6857993602752686,
|
||
|
|
"epoch": 0.026690391459074734,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.3171,
|
||
|
|
"mean_token_accuracy": 0.09055408537387848,
|
||
|
|
"num_tokens": 616445.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7413246631622314,
|
||
|
|
"epoch": 0.027184657967576117,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.3593,
|
||
|
|
"mean_token_accuracy": 0.0906876116991043,
|
||
|
|
"num_tokens": 627723.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.73683533668518,
|
||
|
|
"epoch": 0.0276789244760775,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.3984,
|
||
|
|
"mean_token_accuracy": 0.09326281249523163,
|
||
|
|
"num_tokens": 638987.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6382591247558596,
|
||
|
|
"epoch": 0.028173190984578884,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.2142,
|
||
|
|
"mean_token_accuracy": 0.09618987664580345,
|
||
|
|
"num_tokens": 650626.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5611570358276365,
|
||
|
|
"epoch": 0.028667457493080268,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.2345,
|
||
|
|
"mean_token_accuracy": 0.1005303256213665,
|
||
|
|
"num_tokens": 661911.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.647679138183594,
|
||
|
|
"epoch": 0.02916172400158165,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.2825,
|
||
|
|
"mean_token_accuracy": 0.09565488621592522,
|
||
|
|
"num_tokens": 674298.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6432453155517575,
|
||
|
|
"epoch": 0.02965599051008304,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.2078,
|
||
|
|
"mean_token_accuracy": 0.10528751984238624,
|
||
|
|
"num_tokens": 686000.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.544150352478027,
|
||
|
|
"epoch": 0.030150257018584422,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.2392,
|
||
|
|
"mean_token_accuracy": 0.09542082250118256,
|
||
|
|
"num_tokens": 698464.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.56985502243042,
|
||
|
|
"epoch": 0.030644523527085805,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.2536,
|
||
|
|
"mean_token_accuracy": 0.09196790009737014,
|
||
|
|
"num_tokens": 709702.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.720779943466186,
|
||
|
|
"epoch": 0.03113879003558719,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.346,
|
||
|
|
"mean_token_accuracy": 0.09406937882304192,
|
||
|
|
"num_tokens": 722234.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.581376028060913,
|
||
|
|
"epoch": 0.03163305654408857,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.2839,
|
||
|
|
"mean_token_accuracy": 0.09505393728613853,
|
||
|
|
"num_tokens": 733001.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.49077296257019,
|
||
|
|
"epoch": 0.03212732305258996,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.2599,
|
||
|
|
"mean_token_accuracy": 0.0962059386074543,
|
||
|
|
"num_tokens": 743315.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.528533220291138,
|
||
|
|
"epoch": 0.03262158956109134,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.2062,
|
||
|
|
"mean_token_accuracy": 0.0949233591556549,
|
||
|
|
"num_tokens": 754386.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.633228158950805,
|
||
|
|
"epoch": 0.033115856069592726,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.295,
|
||
|
|
"mean_token_accuracy": 0.09804042801260948,
|
||
|
|
"num_tokens": 766504.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.388225507736206,
|
||
|
|
"epoch": 0.033610122578094107,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.1353,
|
||
|
|
"mean_token_accuracy": 0.10608720779418945,
|
||
|
|
"num_tokens": 777039.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5571861743927,
|
||
|
|
"epoch": 0.034104389086595494,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.213,
|
||
|
|
"mean_token_accuracy": 0.0967411994934082,
|
||
|
|
"num_tokens": 787890.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.585029363632202,
|
||
|
|
"epoch": 0.034598655595096874,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.1904,
|
||
|
|
"mean_token_accuracy": 0.09388899356126786,
|
||
|
|
"num_tokens": 800129.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.519090270996093,
|
||
|
|
"epoch": 0.03509292210359826,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.2753,
|
||
|
|
"mean_token_accuracy": 0.08706354051828384,
|
||
|
|
"num_tokens": 812517.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.475762224197387,
|
||
|
|
"epoch": 0.03558718861209965,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.1867,
|
||
|
|
"mean_token_accuracy": 0.09729651510715484,
|
||
|
|
"num_tokens": 824570.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.495535516738892,
|
||
|
|
"epoch": 0.03608145512060103,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.1807,
|
||
|
|
"mean_token_accuracy": 0.09826134368777276,
|
||
|
|
"num_tokens": 836506.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.534515857696533,
|
||
|
|
"epoch": 0.036575721629102415,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.1878,
|
||
|
|
"mean_token_accuracy": 0.10016850084066391,
|
||
|
|
"num_tokens": 846841.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.50739107131958,
|
||
|
|
"epoch": 0.037069988137603795,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.2228,
|
||
|
|
"mean_token_accuracy": 0.0973518904298544,
|
||
|
|
"num_tokens": 858770.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4406991481781,
|
||
|
|
"epoch": 0.03756425464610518,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.0723,
|
||
|
|
"mean_token_accuracy": 0.10061725601553917,
|
||
|
|
"num_tokens": 870184.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.402413034439087,
|
||
|
|
"epoch": 0.03805852115460656,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.1224,
|
||
|
|
"mean_token_accuracy": 0.10140243172645569,
|
||
|
|
"num_tokens": 881843.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.528499603271484,
|
||
|
|
"epoch": 0.03855278766310795,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.151,
|
||
|
|
"mean_token_accuracy": 0.09550150707364083,
|
||
|
|
"num_tokens": 893453.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4038654327392575,
|
||
|
|
"epoch": 0.03904705417160933,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.188,
|
||
|
|
"mean_token_accuracy": 0.08902871310710907,
|
||
|
|
"num_tokens": 904417.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.467393684387207,
|
||
|
|
"epoch": 0.039541320680110716,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.127,
|
||
|
|
"mean_token_accuracy": 0.09610793069005012,
|
||
|
|
"num_tokens": 915134.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.380018091201782,
|
||
|
|
"epoch": 0.0400355871886121,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.1373,
|
||
|
|
"mean_token_accuracy": 0.09769618287682533,
|
||
|
|
"num_tokens": 926361.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.329358005523682,
|
||
|
|
"epoch": 0.04052985369711348,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.0624,
|
||
|
|
"mean_token_accuracy": 0.09888514652848243,
|
||
|
|
"num_tokens": 937474.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.479707336425781,
|
||
|
|
"epoch": 0.04102412020561487,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.1264,
|
||
|
|
"mean_token_accuracy": 0.09987385869026184,
|
||
|
|
"num_tokens": 948897.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.383866643905639,
|
||
|
|
"epoch": 0.04151838671411625,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.1417,
|
||
|
|
"mean_token_accuracy": 0.095736575871706,
|
||
|
|
"num_tokens": 960669.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.281150865554809,
|
||
|
|
"epoch": 0.04201265322261764,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.003,
|
||
|
|
"mean_token_accuracy": 0.09964865893125534,
|
||
|
|
"num_tokens": 973001.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.312557888031006,
|
||
|
|
"epoch": 0.04250691973111902,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.0689,
|
||
|
|
"mean_token_accuracy": 0.09953263103961944,
|
||
|
|
"num_tokens": 986214.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.278632974624633,
|
||
|
|
"epoch": 0.043001186239620404,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.0668,
|
||
|
|
"mean_token_accuracy": 0.09420256316661835,
|
||
|
|
"num_tokens": 997363.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3221252918243405,
|
||
|
|
"epoch": 0.04349545274812179,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.9879,
|
||
|
|
"mean_token_accuracy": 0.1078550562262535,
|
||
|
|
"num_tokens": 1009543.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.354555606842041,
|
||
|
|
"epoch": 0.04398971925662317,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.0839,
|
||
|
|
"mean_token_accuracy": 0.09625534787774086,
|
||
|
|
"num_tokens": 1020561.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.316053104400635,
|
||
|
|
"epoch": 0.04448398576512456,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.0278,
|
||
|
|
"mean_token_accuracy": 0.09594150930643082,
|
||
|
|
"num_tokens": 1032587.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.357148027420044,
|
||
|
|
"epoch": 0.04497825227362594,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.0405,
|
||
|
|
"mean_token_accuracy": 0.09594763442873955,
|
||
|
|
"num_tokens": 1044249.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.250429964065551,
|
||
|
|
"epoch": 0.045472518782127325,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.0862,
|
||
|
|
"mean_token_accuracy": 0.09893084913492203,
|
||
|
|
"num_tokens": 1055415.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3101239681243895,
|
||
|
|
"epoch": 0.045966785290628705,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.0427,
|
||
|
|
"mean_token_accuracy": 0.09975223317742347,
|
||
|
|
"num_tokens": 1066593.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.332342672348022,
|
||
|
|
"epoch": 0.04646105179913009,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.0494,
|
||
|
|
"mean_token_accuracy": 0.10509061589837074,
|
||
|
|
"num_tokens": 1076966.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.271913814544678,
|
||
|
|
"epoch": 0.04695531830763147,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.0986,
|
||
|
|
"mean_token_accuracy": 0.0981233686208725,
|
||
|
|
"num_tokens": 1089927.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.272168922424316,
|
||
|
|
"epoch": 0.04744958481613286,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.0256,
|
||
|
|
"mean_token_accuracy": 0.10296122953295708,
|
||
|
|
"num_tokens": 1101920.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.331663513183594,
|
||
|
|
"epoch": 0.047943851324634246,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.0921,
|
||
|
|
"mean_token_accuracy": 0.1024775855243206,
|
||
|
|
"num_tokens": 1115078.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.29973840713501,
|
||
|
|
"epoch": 0.048438117833135626,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.1811,
|
||
|
|
"mean_token_accuracy": 0.09624339342117309,
|
||
|
|
"num_tokens": 1127138.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.282535600662231,
|
||
|
|
"epoch": 0.04893238434163701,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.973,
|
||
|
|
"mean_token_accuracy": 0.09775002524256707,
|
||
|
|
"num_tokens": 1138390.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.132982683181763,
|
||
|
|
"epoch": 0.04942665085013839,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.9148,
|
||
|
|
"mean_token_accuracy": 0.10242879241704941,
|
||
|
|
"num_tokens": 1149124.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.269606828689575,
|
||
|
|
"epoch": 0.04992091735863978,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.9985,
|
||
|
|
"mean_token_accuracy": 0.10452278256416321,
|
||
|
|
"num_tokens": 1161091.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.252136373519898,
|
||
|
|
"epoch": 0.05041518386714116,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.9829,
|
||
|
|
"mean_token_accuracy": 0.1010063998401165,
|
||
|
|
"num_tokens": 1171919.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.214443826675415,
|
||
|
|
"epoch": 0.05090945037564255,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.0023,
|
||
|
|
"mean_token_accuracy": 0.10076434314250945,
|
||
|
|
"num_tokens": 1183688.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1838603019714355,
|
||
|
|
"epoch": 0.051403716884143934,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.9263,
|
||
|
|
"mean_token_accuracy": 0.09976266697049141,
|
||
|
|
"num_tokens": 1195323.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2711670875549315,
|
||
|
|
"epoch": 0.051897983392645314,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 7.0389,
|
||
|
|
"mean_token_accuracy": 0.09715224653482438,
|
||
|
|
"num_tokens": 1206782.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.073988342285157,
|
||
|
|
"epoch": 0.0523922499011467,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.9372,
|
||
|
|
"mean_token_accuracy": 0.10476875677704811,
|
||
|
|
"num_tokens": 1218102.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.177066278457642,
|
||
|
|
"epoch": 0.05288651640964808,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.8961,
|
||
|
|
"mean_token_accuracy": 0.10652716383337975,
|
||
|
|
"num_tokens": 1230199.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.199627637863159,
|
||
|
|
"epoch": 0.05338078291814947,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.0331,
|
||
|
|
"mean_token_accuracy": 0.0983577199280262,
|
||
|
|
"num_tokens": 1242127.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.208913135528564,
|
||
|
|
"epoch": 0.05387504942665085,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.884,
|
||
|
|
"mean_token_accuracy": 0.10501328334212304,
|
||
|
|
"num_tokens": 1252329.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.939323949813843,
|
||
|
|
"epoch": 0.054369315935152235,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.8934,
|
||
|
|
"mean_token_accuracy": 0.10581276491284371,
|
||
|
|
"num_tokens": 1264832.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.205942392349243,
|
||
|
|
"epoch": 0.054863582443653615,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.9616,
|
||
|
|
"mean_token_accuracy": 0.10314971879124642,
|
||
|
|
"num_tokens": 1276708.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.153828191757202,
|
||
|
|
"epoch": 0.055357848952155,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.8726,
|
||
|
|
"mean_token_accuracy": 0.11329025998711587,
|
||
|
|
"num_tokens": 1288089.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.161610555648804,
|
||
|
|
"epoch": 0.05585211546065639,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 7.0273,
|
||
|
|
"mean_token_accuracy": 0.09660614281892776,
|
||
|
|
"num_tokens": 1299411.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.163782167434692,
|
||
|
|
"epoch": 0.05634638196915777,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.0025,
|
||
|
|
"mean_token_accuracy": 0.09989360198378563,
|
||
|
|
"num_tokens": 1311368.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.174857044219971,
|
||
|
|
"epoch": 0.056840648477659156,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.9089,
|
||
|
|
"mean_token_accuracy": 0.10894362777471542,
|
||
|
|
"num_tokens": 1321962.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.071204948425293,
|
||
|
|
"epoch": 0.057334914986160536,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.902,
|
||
|
|
"mean_token_accuracy": 0.10397432371973991,
|
||
|
|
"num_tokens": 1335150.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1267462253570555,
|
||
|
|
"epoch": 0.05782918149466192,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.9269,
|
||
|
|
"mean_token_accuracy": 0.1051826611161232,
|
||
|
|
"num_tokens": 1346986.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.112785482406617,
|
||
|
|
"epoch": 0.0583234480031633,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.8656,
|
||
|
|
"mean_token_accuracy": 0.10970147848129272,
|
||
|
|
"num_tokens": 1357820.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.047489166259766,
|
||
|
|
"epoch": 0.05881771451166469,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.8507,
|
||
|
|
"mean_token_accuracy": 0.10967678129673004,
|
||
|
|
"num_tokens": 1368269.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029166984558105,
|
||
|
|
"epoch": 0.05931198102016608,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.8756,
|
||
|
|
"mean_token_accuracy": 0.10604512766003608,
|
||
|
|
"num_tokens": 1380364.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.090877056121826,
|
||
|
|
"epoch": 0.05980624752866746,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.8434,
|
||
|
|
"mean_token_accuracy": 0.11243339478969575,
|
||
|
|
"num_tokens": 1390667.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.975702571868896,
|
||
|
|
"epoch": 0.060300514037168844,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.7862,
|
||
|
|
"mean_token_accuracy": 0.10896089002490043,
|
||
|
|
"num_tokens": 1401452.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.058058023452759,
|
||
|
|
"epoch": 0.060794780545670224,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.8048,
|
||
|
|
"mean_token_accuracy": 0.10580957233905793,
|
||
|
|
"num_tokens": 1412947.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0039595603942875,
|
||
|
|
"epoch": 0.06128904705417161,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.8539,
|
||
|
|
"mean_token_accuracy": 0.10166370421648026,
|
||
|
|
"num_tokens": 1425123.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.994016408920288,
|
||
|
|
"epoch": 0.06178331356267299,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.8209,
|
||
|
|
"mean_token_accuracy": 0.10429305657744407,
|
||
|
|
"num_tokens": 1436538.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.999717473983765,
|
||
|
|
"epoch": 0.06227758007117438,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.8751,
|
||
|
|
"mean_token_accuracy": 0.10226834043860436,
|
||
|
|
"num_tokens": 1448269.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.064650678634644,
|
||
|
|
"epoch": 0.06277184657967576,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.8399,
|
||
|
|
"mean_token_accuracy": 0.10944770202040673,
|
||
|
|
"num_tokens": 1459729.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0405889511108395,
|
||
|
|
"epoch": 0.06326611308817714,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.861,
|
||
|
|
"mean_token_accuracy": 0.10923529267311097,
|
||
|
|
"num_tokens": 1470684.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.989497947692871,
|
||
|
|
"epoch": 0.06376037959667853,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.8231,
|
||
|
|
"mean_token_accuracy": 0.1039299450814724,
|
||
|
|
"num_tokens": 1483571.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.946833992004395,
|
||
|
|
"epoch": 0.06425464610517992,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.7837,
|
||
|
|
"mean_token_accuracy": 0.11393694505095482,
|
||
|
|
"num_tokens": 1494671.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.05028281211853,
|
||
|
|
"epoch": 0.06474891261368129,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.815,
|
||
|
|
"mean_token_accuracy": 0.10791449770331382,
|
||
|
|
"num_tokens": 1505435.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01549129486084,
|
||
|
|
"epoch": 0.06524317912218268,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.905,
|
||
|
|
"mean_token_accuracy": 0.10271791145205497,
|
||
|
|
"num_tokens": 1518510.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.01969428062439,
|
||
|
|
"epoch": 0.06573744563068407,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.8145,
|
||
|
|
"mean_token_accuracy": 0.11035969778895378,
|
||
|
|
"num_tokens": 1530218.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.99644832611084,
|
||
|
|
"epoch": 0.06623171213918545,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.8628,
|
||
|
|
"mean_token_accuracy": 0.10982906743884087,
|
||
|
|
"num_tokens": 1542486.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9659065246582035,
|
||
|
|
"epoch": 0.06672597864768683,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.8508,
|
||
|
|
"mean_token_accuracy": 0.11023544520139694,
|
||
|
|
"num_tokens": 1553873.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.024175119400025,
|
||
|
|
"epoch": 0.06722024515618821,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.8118,
|
||
|
|
"mean_token_accuracy": 0.10845338329672813,
|
||
|
|
"num_tokens": 1565343.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.998782205581665,
|
||
|
|
"epoch": 0.0677145116646896,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.8542,
|
||
|
|
"mean_token_accuracy": 0.10380253493785858,
|
||
|
|
"num_tokens": 1577061.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9577474117279055,
|
||
|
|
"epoch": 0.06820877817319099,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.8329,
|
||
|
|
"mean_token_accuracy": 0.11085338145494461,
|
||
|
|
"num_tokens": 1588083.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986978530883789,
|
||
|
|
"epoch": 0.06870304468169237,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.8007,
|
||
|
|
"mean_token_accuracy": 0.10315440371632575,
|
||
|
|
"num_tokens": 1599796.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.972596454620361,
|
||
|
|
"epoch": 0.06919731119019375,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.8572,
|
||
|
|
"mean_token_accuracy": 0.10334469750523567,
|
||
|
|
"num_tokens": 1611994.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8772365093231205,
|
||
|
|
"epoch": 0.06969157769869513,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.7898,
|
||
|
|
"mean_token_accuracy": 0.1049453303217888,
|
||
|
|
"num_tokens": 1623280.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.965932464599609,
|
||
|
|
"epoch": 0.07018584420719652,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.8494,
|
||
|
|
"mean_token_accuracy": 0.10564259961247444,
|
||
|
|
"num_tokens": 1634989.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.067782068252564,
|
||
|
|
"epoch": 0.07068011071569791,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.8849,
|
||
|
|
"mean_token_accuracy": 0.10287278667092323,
|
||
|
|
"num_tokens": 1647042.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.912572956085205,
|
||
|
|
"epoch": 0.0711743772241993,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.7651,
|
||
|
|
"mean_token_accuracy": 0.11166846603155137,
|
||
|
|
"num_tokens": 1659245.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80322904586792,
|
||
|
|
"epoch": 0.07166864373270067,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.7586,
|
||
|
|
"mean_token_accuracy": 0.10756073594093322,
|
||
|
|
"num_tokens": 1670271.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.940843629837036,
|
||
|
|
"epoch": 0.07216291024120206,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.8203,
|
||
|
|
"mean_token_accuracy": 0.1087859407067299,
|
||
|
|
"num_tokens": 1682648.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938844823837281,
|
||
|
|
"epoch": 0.07265717674970344,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.8388,
|
||
|
|
"mean_token_accuracy": 0.10283323600888253,
|
||
|
|
"num_tokens": 1694542.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.940903759002685,
|
||
|
|
"epoch": 0.07315144325820483,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.7228,
|
||
|
|
"mean_token_accuracy": 0.10595641434192657,
|
||
|
|
"num_tokens": 1705737.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8896369457244875,
|
||
|
|
"epoch": 0.0736457097667062,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.7982,
|
||
|
|
"mean_token_accuracy": 0.10578844174742699,
|
||
|
|
"num_tokens": 1718474.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.86991171836853,
|
||
|
|
"epoch": 0.07413997627520759,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.7712,
|
||
|
|
"mean_token_accuracy": 0.10600817650556564,
|
||
|
|
"num_tokens": 1729360.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.886312341690063,
|
||
|
|
"epoch": 0.07463424278370898,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.7704,
|
||
|
|
"mean_token_accuracy": 0.10894044563174247,
|
||
|
|
"num_tokens": 1739654.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.932852458953858,
|
||
|
|
"epoch": 0.07512850929221036,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.7739,
|
||
|
|
"mean_token_accuracy": 0.11049990877509117,
|
||
|
|
"num_tokens": 1752158.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.89213080406189,
|
||
|
|
"epoch": 0.07562277580071175,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.77,
|
||
|
|
"mean_token_accuracy": 0.1128721371293068,
|
||
|
|
"num_tokens": 1764545.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857365846633911,
|
||
|
|
"epoch": 0.07611704230921312,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.7586,
|
||
|
|
"mean_token_accuracy": 0.11279137954115867,
|
||
|
|
"num_tokens": 1775422.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.88516058921814,
|
||
|
|
"epoch": 0.07661130881771451,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.7939,
|
||
|
|
"mean_token_accuracy": 0.10151734873652458,
|
||
|
|
"num_tokens": 1787833.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.859038400650024,
|
||
|
|
"epoch": 0.0771055753262159,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.6418,
|
||
|
|
"mean_token_accuracy": 0.11993765309453011,
|
||
|
|
"num_tokens": 1798508.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.737257575988769,
|
||
|
|
"epoch": 0.07759984183471728,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.7112,
|
||
|
|
"mean_token_accuracy": 0.11113684475421906,
|
||
|
|
"num_tokens": 1809873.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879690313339234,
|
||
|
|
"epoch": 0.07809410834321866,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.7876,
|
||
|
|
"mean_token_accuracy": 0.11018007099628449,
|
||
|
|
"num_tokens": 1820876.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.838776350021362,
|
||
|
|
"epoch": 0.07858837485172004,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.7566,
|
||
|
|
"mean_token_accuracy": 0.10615676119923592,
|
||
|
|
"num_tokens": 1833233.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918010139465332,
|
||
|
|
"epoch": 0.07908264136022143,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.8284,
|
||
|
|
"mean_token_accuracy": 0.10389258489012718,
|
||
|
|
"num_tokens": 1844520.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.786227464675903,
|
||
|
|
"epoch": 0.07957690786872282,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.7034,
|
||
|
|
"mean_token_accuracy": 0.11290365755558014,
|
||
|
|
"num_tokens": 1856814.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813175868988037,
|
||
|
|
"epoch": 0.0800711743772242,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.6919,
|
||
|
|
"mean_token_accuracy": 0.11492616683244705,
|
||
|
|
"num_tokens": 1867581.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.917808771133423,
|
||
|
|
"epoch": 0.08056544088572558,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.7668,
|
||
|
|
"mean_token_accuracy": 0.1026224099099636,
|
||
|
|
"num_tokens": 1879302.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807746696472168,
|
||
|
|
"epoch": 0.08105970739422697,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.7233,
|
||
|
|
"mean_token_accuracy": 0.10366639867424965,
|
||
|
|
"num_tokens": 1891697.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7796924114227295,
|
||
|
|
"epoch": 0.08155397390272835,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.6648,
|
||
|
|
"mean_token_accuracy": 0.1127976194024086,
|
||
|
|
"num_tokens": 1903544.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879214906692505,
|
||
|
|
"epoch": 0.08204824041122974,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.7223,
|
||
|
|
"mean_token_accuracy": 0.10973726511001587,
|
||
|
|
"num_tokens": 1915286.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.705264568328857,
|
||
|
|
"epoch": 0.08254250691973111,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.5961,
|
||
|
|
"mean_token_accuracy": 0.11404297724366189,
|
||
|
|
"num_tokens": 1926361.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.816687965393067,
|
||
|
|
"epoch": 0.0830367734282325,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.7031,
|
||
|
|
"mean_token_accuracy": 0.10863827988505363,
|
||
|
|
"num_tokens": 1938540.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.804880666732788,
|
||
|
|
"epoch": 0.08353103993673389,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.7195,
|
||
|
|
"mean_token_accuracy": 0.10949295833706855,
|
||
|
|
"num_tokens": 1950532.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.845176124572754,
|
||
|
|
"epoch": 0.08402530644523527,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.7359,
|
||
|
|
"mean_token_accuracy": 0.11156460493803025,
|
||
|
|
"num_tokens": 1960899.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755578899383545,
|
||
|
|
"epoch": 0.08451957295373666,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.7042,
|
||
|
|
"mean_token_accuracy": 0.11670901104807854,
|
||
|
|
"num_tokens": 1972278.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.716426515579224,
|
||
|
|
"epoch": 0.08501383946223803,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.7255,
|
||
|
|
"mean_token_accuracy": 0.10719798132777214,
|
||
|
|
"num_tokens": 1985079.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.739371871948242,
|
||
|
|
"epoch": 0.08550810597073942,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.767,
|
||
|
|
"mean_token_accuracy": 0.10439837947487832,
|
||
|
|
"num_tokens": 1996467.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.765180349349976,
|
||
|
|
"epoch": 0.08600237247924081,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.6488,
|
||
|
|
"mean_token_accuracy": 0.1103054165840149,
|
||
|
|
"num_tokens": 2007339.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.78636326789856,
|
||
|
|
"epoch": 0.0864966389877422,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.6542,
|
||
|
|
"mean_token_accuracy": 0.117033851146698,
|
||
|
|
"num_tokens": 2019962.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8178417682647705,
|
||
|
|
"epoch": 0.08699090549624358,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.6517,
|
||
|
|
"mean_token_accuracy": 0.11530169770121575,
|
||
|
|
"num_tokens": 2031251.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5937264919281,
|
||
|
|
"epoch": 0.08748517200474495,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.673,
|
||
|
|
"mean_token_accuracy": 0.11114488393068314,
|
||
|
|
"num_tokens": 2042412.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730161142349243,
|
||
|
|
"epoch": 0.08797943851324634,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.6888,
|
||
|
|
"mean_token_accuracy": 0.11397303268313408,
|
||
|
|
"num_tokens": 2054423.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.722592115402222,
|
||
|
|
"epoch": 0.08847370502174773,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.6594,
|
||
|
|
"mean_token_accuracy": 0.10811133831739425,
|
||
|
|
"num_tokens": 2065657.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.763195466995239,
|
||
|
|
"epoch": 0.08896797153024912,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.6425,
|
||
|
|
"mean_token_accuracy": 0.11057304218411446,
|
||
|
|
"num_tokens": 2076305.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7415228366851805,
|
||
|
|
"epoch": 0.08946223803875049,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.6284,
|
||
|
|
"mean_token_accuracy": 0.11273603141307831,
|
||
|
|
"num_tokens": 2087734.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.641074132919312,
|
||
|
|
"epoch": 0.08995650454725188,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.5485,
|
||
|
|
"mean_token_accuracy": 0.11758684813976288,
|
||
|
|
"num_tokens": 2098016.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.690926361083984,
|
||
|
|
"epoch": 0.09045077105575326,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.7327,
|
||
|
|
"mean_token_accuracy": 0.1100957915186882,
|
||
|
|
"num_tokens": 2110293.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.703506088256836,
|
||
|
|
"epoch": 0.09094503756425465,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.5204,
|
||
|
|
"mean_token_accuracy": 0.11451509669423103,
|
||
|
|
"num_tokens": 2120441.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566627359390258,
|
||
|
|
"epoch": 0.09143930407275604,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.6277,
|
||
|
|
"mean_token_accuracy": 0.11738944351673126,
|
||
|
|
"num_tokens": 2131520.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.713652467727661,
|
||
|
|
"epoch": 0.09193357058125741,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.6465,
|
||
|
|
"mean_token_accuracy": 0.11316604092717171,
|
||
|
|
"num_tokens": 2145005.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623152732849121,
|
||
|
|
"epoch": 0.0924278370897588,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.5846,
|
||
|
|
"mean_token_accuracy": 0.12091677188873291,
|
||
|
|
"num_tokens": 2156608.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651329898834229,
|
||
|
|
"epoch": 0.09292210359826018,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.5796,
|
||
|
|
"mean_token_accuracy": 0.12188688293099403,
|
||
|
|
"num_tokens": 2168341.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.642852067947388,
|
||
|
|
"epoch": 0.09341637010676157,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.5904,
|
||
|
|
"mean_token_accuracy": 0.1089819423854351,
|
||
|
|
"num_tokens": 2178704.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754391765594482,
|
||
|
|
"epoch": 0.09391063661526294,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.7635,
|
||
|
|
"mean_token_accuracy": 0.10869134515523911,
|
||
|
|
"num_tokens": 2190884.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.752915477752685,
|
||
|
|
"epoch": 0.09440490312376433,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.6492,
|
||
|
|
"mean_token_accuracy": 0.11656087636947632,
|
||
|
|
"num_tokens": 2201822.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6327839374542235,
|
||
|
|
"epoch": 0.09489916963226572,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.6499,
|
||
|
|
"mean_token_accuracy": 0.10982675924897194,
|
||
|
|
"num_tokens": 2213362.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.745302629470825,
|
||
|
|
"epoch": 0.0953934361407671,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.6611,
|
||
|
|
"mean_token_accuracy": 0.11452150940895081,
|
||
|
|
"num_tokens": 2224366.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526859760284424,
|
||
|
|
"epoch": 0.09588770264926849,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.5073,
|
||
|
|
"mean_token_accuracy": 0.11500997394323349,
|
||
|
|
"num_tokens": 2234645.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.658684253692627,
|
||
|
|
"epoch": 0.09638196915776986,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.5956,
|
||
|
|
"mean_token_accuracy": 0.12246652096509933,
|
||
|
|
"num_tokens": 2245904.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546703433990478,
|
||
|
|
"epoch": 0.09687623566627125,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.538,
|
||
|
|
"mean_token_accuracy": 0.11811117008328438,
|
||
|
|
"num_tokens": 2257753.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526799488067627,
|
||
|
|
"epoch": 0.09737050217477264,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.5511,
|
||
|
|
"mean_token_accuracy": 0.12520263567566872,
|
||
|
|
"num_tokens": 2269009.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.717652273178101,
|
||
|
|
"epoch": 0.09786476868327403,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.6017,
|
||
|
|
"mean_token_accuracy": 0.11403435990214347,
|
||
|
|
"num_tokens": 2279840.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616256618499756,
|
||
|
|
"epoch": 0.0983590351917754,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.5677,
|
||
|
|
"mean_token_accuracy": 0.1170521154999733,
|
||
|
|
"num_tokens": 2290577.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.553269243240356,
|
||
|
|
"epoch": 0.09885330170027679,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.5847,
|
||
|
|
"mean_token_accuracy": 0.1192831926047802,
|
||
|
|
"num_tokens": 2301341.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5955955505371096,
|
||
|
|
"epoch": 0.09934756820877817,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999999982287888,
|
||
|
|
"loss": 6.6316,
|
||
|
|
"mean_token_accuracy": 0.11239909082651138,
|
||
|
|
"num_tokens": 2312505.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.756361579895019,
|
||
|
|
"epoch": 0.09984183471727956,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999999910332434,
|
||
|
|
"loss": 6.5702,
|
||
|
|
"mean_token_accuracy": 0.11360275968909264,
|
||
|
|
"num_tokens": 2323443.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5370465278625485,
|
||
|
|
"epoch": 0.10033610122578095,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999999783026635,
|
||
|
|
"loss": 6.6113,
|
||
|
|
"mean_token_accuracy": 0.11296669542789459,
|
||
|
|
"num_tokens": 2335686.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4977209091186525,
|
||
|
|
"epoch": 0.10083036773428232,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999999600370491,
|
||
|
|
"loss": 6.5754,
|
||
|
|
"mean_token_accuracy": 0.1125928744673729,
|
||
|
|
"num_tokens": 2347273.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.599768400192261,
|
||
|
|
"epoch": 0.1013246342427837,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999999362364008,
|
||
|
|
"loss": 6.4974,
|
||
|
|
"mean_token_accuracy": 0.12364283204078674,
|
||
|
|
"num_tokens": 2358011.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.547587585449219,
|
||
|
|
"epoch": 0.1018189007512851,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999999069007191,
|
||
|
|
"loss": 6.6375,
|
||
|
|
"mean_token_accuracy": 0.11347849667072296,
|
||
|
|
"num_tokens": 2371390.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620147085189819,
|
||
|
|
"epoch": 0.10231316725978648,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999998720300048,
|
||
|
|
"loss": 6.574,
|
||
|
|
"mean_token_accuracy": 0.11589496359229087,
|
||
|
|
"num_tokens": 2381887.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623451662063599,
|
||
|
|
"epoch": 0.10280743376828787,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999998316242589,
|
||
|
|
"loss": 6.5181,
|
||
|
|
"mean_token_accuracy": 0.1186449609696865,
|
||
|
|
"num_tokens": 2393632.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565800905227661,
|
||
|
|
"epoch": 0.10330170027678924,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999997856834821,
|
||
|
|
"loss": 6.5429,
|
||
|
|
"mean_token_accuracy": 0.11829646304249763,
|
||
|
|
"num_tokens": 2405686.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.476983976364136,
|
||
|
|
"epoch": 0.10379596678529063,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999997342076757,
|
||
|
|
"loss": 6.5049,
|
||
|
|
"mean_token_accuracy": 0.11723731234669685,
|
||
|
|
"num_tokens": 2417459.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.62911171913147,
|
||
|
|
"epoch": 0.10429023329379201,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999996771968408,
|
||
|
|
"loss": 6.549,
|
||
|
|
"mean_token_accuracy": 0.11742187961935997,
|
||
|
|
"num_tokens": 2428689.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541408109664917,
|
||
|
|
"epoch": 0.1047844998022934,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999996146509791,
|
||
|
|
"loss": 6.5844,
|
||
|
|
"mean_token_accuracy": 0.11144702807068825,
|
||
|
|
"num_tokens": 2439437.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.611022901535034,
|
||
|
|
"epoch": 0.10527876631079477,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999995465700919,
|
||
|
|
"loss": 6.5624,
|
||
|
|
"mean_token_accuracy": 0.11505987718701363,
|
||
|
|
"num_tokens": 2450576.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620437097549439,
|
||
|
|
"epoch": 0.10577303281929616,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999994729541809,
|
||
|
|
"loss": 6.6951,
|
||
|
|
"mean_token_accuracy": 0.1110321931540966,
|
||
|
|
"num_tokens": 2462684.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609294176101685,
|
||
|
|
"epoch": 0.10626729932779755,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999993938032481,
|
||
|
|
"loss": 6.5761,
|
||
|
|
"mean_token_accuracy": 0.12244995087385177,
|
||
|
|
"num_tokens": 2474193.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4717964172363285,
|
||
|
|
"epoch": 0.10676156583629894,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999993091172952,
|
||
|
|
"loss": 6.5088,
|
||
|
|
"mean_token_accuracy": 0.11520365998148918,
|
||
|
|
"num_tokens": 2486264.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566349363327026,
|
||
|
|
"epoch": 0.10725583234480032,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999992188963245,
|
||
|
|
"loss": 6.5056,
|
||
|
|
"mean_token_accuracy": 0.12804400250315667,
|
||
|
|
"num_tokens": 2497668.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491508913040161,
|
||
|
|
"epoch": 0.1077500988533017,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000499999123140338,
|
||
|
|
"loss": 6.5584,
|
||
|
|
"mean_token_accuracy": 0.11530945152044296,
|
||
|
|
"num_tokens": 2509635.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6176024913787845,
|
||
|
|
"epoch": 0.10824436536180308,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999990218493382,
|
||
|
|
"loss": 6.5544,
|
||
|
|
"mean_token_accuracy": 0.1210338070988655,
|
||
|
|
"num_tokens": 2521980.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.490401124954223,
|
||
|
|
"epoch": 0.10873863187030447,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999989150233276,
|
||
|
|
"loss": 6.5117,
|
||
|
|
"mean_token_accuracy": 0.11823379397392272,
|
||
|
|
"num_tokens": 2533750.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.604971313476563,
|
||
|
|
"epoch": 0.10923289837880586,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999988026623088,
|
||
|
|
"loss": 6.6152,
|
||
|
|
"mean_token_accuracy": 0.11355350241065025,
|
||
|
|
"num_tokens": 2545620.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.490075254440308,
|
||
|
|
"epoch": 0.10972716488730723,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999986847662843,
|
||
|
|
"loss": 6.3791,
|
||
|
|
"mean_token_accuracy": 0.13139019086956977,
|
||
|
|
"num_tokens": 2556463.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.510465478897094,
|
||
|
|
"epoch": 0.11022143139580862,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999985613352576,
|
||
|
|
"loss": 6.5856,
|
||
|
|
"mean_token_accuracy": 0.11922621130943298,
|
||
|
|
"num_tokens": 2567396.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568830108642578,
|
||
|
|
"epoch": 0.11071569790431,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999984323692311,
|
||
|
|
"loss": 6.5299,
|
||
|
|
"mean_token_accuracy": 0.12173295393586159,
|
||
|
|
"num_tokens": 2579208.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.483700370788574,
|
||
|
|
"epoch": 0.11120996441281139,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999982978682085,
|
||
|
|
"loss": 6.4691,
|
||
|
|
"mean_token_accuracy": 0.1236620731651783,
|
||
|
|
"num_tokens": 2590940.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544557523727417,
|
||
|
|
"epoch": 0.11170423092131278,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999981578321927,
|
||
|
|
"loss": 6.5492,
|
||
|
|
"mean_token_accuracy": 0.1240879513323307,
|
||
|
|
"num_tokens": 2602491.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.44443998336792,
|
||
|
|
"epoch": 0.11219849742981415,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004999980122611874,
|
||
|
|
"loss": 6.3772,
|
||
|
|
"mean_token_accuracy": 0.12767384871840476,
|
||
|
|
"num_tokens": 2612139.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491549348831176,
|
||
|
|
"epoch": 0.11269276393831554,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499997861155196,
|
||
|
|
"loss": 6.5488,
|
||
|
|
"mean_token_accuracy": 0.12024773359298706,
|
||
|
|
"num_tokens": 2624906.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.480259275436401,
|
||
|
|
"epoch": 0.11318703044681692,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999977045142223,
|
||
|
|
"loss": 6.4643,
|
||
|
|
"mean_token_accuracy": 0.11957029402256011,
|
||
|
|
"num_tokens": 2636046.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.550483131408692,
|
||
|
|
"epoch": 0.11368129695531831,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999975423382703,
|
||
|
|
"loss": 6.4622,
|
||
|
|
"mean_token_accuracy": 0.13179895728826524,
|
||
|
|
"num_tokens": 2645617.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.524023389816284,
|
||
|
|
"epoch": 0.11417556346381968,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999973746273438,
|
||
|
|
"loss": 6.4976,
|
||
|
|
"mean_token_accuracy": 0.1235875591635704,
|
||
|
|
"num_tokens": 2656780.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.455898904800415,
|
||
|
|
"epoch": 0.11466982997232107,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499997201381447,
|
||
|
|
"loss": 6.4932,
|
||
|
|
"mean_token_accuracy": 0.1219210870563984,
|
||
|
|
"num_tokens": 2668078.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51015043258667,
|
||
|
|
"epoch": 0.11516409648082246,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999970226005841,
|
||
|
|
"loss": 6.56,
|
||
|
|
"mean_token_accuracy": 0.11763008236885071,
|
||
|
|
"num_tokens": 2679049.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.621534633636474,
|
||
|
|
"epoch": 0.11565836298932385,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999968382847595,
|
||
|
|
"loss": 6.506,
|
||
|
|
"mean_token_accuracy": 0.12311880514025689,
|
||
|
|
"num_tokens": 2690165.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.472107076644898,
|
||
|
|
"epoch": 0.11615262949782523,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999966484339778,
|
||
|
|
"loss": 6.5458,
|
||
|
|
"mean_token_accuracy": 0.1172202080488205,
|
||
|
|
"num_tokens": 2701965.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446794605255127,
|
||
|
|
"epoch": 0.1166468960063266,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999964530482437,
|
||
|
|
"loss": 6.4599,
|
||
|
|
"mean_token_accuracy": 0.12496482133865357,
|
||
|
|
"num_tokens": 2713479.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503753185272217,
|
||
|
|
"epoch": 0.11714116251482799,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999962521275619,
|
||
|
|
"loss": 6.4715,
|
||
|
|
"mean_token_accuracy": 0.11783510446548462,
|
||
|
|
"num_tokens": 2725629.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.276622581481933,
|
||
|
|
"epoch": 0.11763542902332938,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999960456719374,
|
||
|
|
"loss": 6.3834,
|
||
|
|
"mean_token_accuracy": 0.124742291867733,
|
||
|
|
"num_tokens": 2736620.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4470867156982425,
|
||
|
|
"epoch": 0.11812969553183077,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999958336813753,
|
||
|
|
"loss": 6.3636,
|
||
|
|
"mean_token_accuracy": 0.13019711673259735,
|
||
|
|
"num_tokens": 2747118.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.444910097122192,
|
||
|
|
"epoch": 0.11862396204033215,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999956161558807,
|
||
|
|
"loss": 6.4204,
|
||
|
|
"mean_token_accuracy": 0.12328561544418334,
|
||
|
|
"num_tokens": 2758371.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344172763824463,
|
||
|
|
"epoch": 0.11911822854883353,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999953930954591,
|
||
|
|
"loss": 6.4241,
|
||
|
|
"mean_token_accuracy": 0.12501891031861306,
|
||
|
|
"num_tokens": 2770575.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.501115942001343,
|
||
|
|
"epoch": 0.11961249505733491,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999951645001159,
|
||
|
|
"loss": 6.3853,
|
||
|
|
"mean_token_accuracy": 0.12834980860352516,
|
||
|
|
"num_tokens": 2783103.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386120176315307,
|
||
|
|
"epoch": 0.1201067615658363,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004999949303698568,
|
||
|
|
"loss": 6.5101,
|
||
|
|
"mean_token_accuracy": 0.1248599722981453,
|
||
|
|
"num_tokens": 2796636.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4623698711395265,
|
||
|
|
"epoch": 0.12060102807433769,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999946907046875,
|
||
|
|
"loss": 6.3609,
|
||
|
|
"mean_token_accuracy": 0.12875436767935752,
|
||
|
|
"num_tokens": 2807798.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.34276967048645,
|
||
|
|
"epoch": 0.12109529458283906,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999944455046139,
|
||
|
|
"loss": 6.4789,
|
||
|
|
"mean_token_accuracy": 0.12591336220502852,
|
||
|
|
"num_tokens": 2819255.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.498102235794067,
|
||
|
|
"epoch": 0.12158956109134045,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499994194769642,
|
||
|
|
"loss": 6.4391,
|
||
|
|
"mean_token_accuracy": 0.12560312896966935,
|
||
|
|
"num_tokens": 2829952.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546961975097656,
|
||
|
|
"epoch": 0.12208382759984183,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499993938499778,
|
||
|
|
"loss": 6.5145,
|
||
|
|
"mean_token_accuracy": 0.13051729574799537,
|
||
|
|
"num_tokens": 2841056.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.36198673248291,
|
||
|
|
"epoch": 0.12257809410834322,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999936766950283,
|
||
|
|
"loss": 6.3615,
|
||
|
|
"mean_token_accuracy": 0.1320299357175827,
|
||
|
|
"num_tokens": 2852045.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4954948902130125,
|
||
|
|
"epoch": 0.12307236061684461,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999934093553992,
|
||
|
|
"loss": 6.4512,
|
||
|
|
"mean_token_accuracy": 0.12794553861021996,
|
||
|
|
"num_tokens": 2863440.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.454316186904907,
|
||
|
|
"epoch": 0.12356662712534598,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999931364808972,
|
||
|
|
"loss": 6.4622,
|
||
|
|
"mean_token_accuracy": 0.12663676366209983,
|
||
|
|
"num_tokens": 2874017.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41609001159668,
|
||
|
|
"epoch": 0.12406089363384737,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999928580715293,
|
||
|
|
"loss": 6.4036,
|
||
|
|
"mean_token_accuracy": 0.12331892997026443,
|
||
|
|
"num_tokens": 2885677.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.424873685836792,
|
||
|
|
"epoch": 0.12455516014234876,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499992574127302,
|
||
|
|
"loss": 6.5093,
|
||
|
|
"mean_token_accuracy": 0.1242648720741272,
|
||
|
|
"num_tokens": 2897825.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.551000785827637,
|
||
|
|
"epoch": 0.12504942665085014,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999922846482226,
|
||
|
|
"loss": 6.5696,
|
||
|
|
"mean_token_accuracy": 0.11755598485469818,
|
||
|
|
"num_tokens": 2909304.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.434643840789795,
|
||
|
|
"epoch": 0.12554369315935152,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999919896342981,
|
||
|
|
"loss": 6.493,
|
||
|
|
"mean_token_accuracy": 0.11869716048240661,
|
||
|
|
"num_tokens": 2920918.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5160829544067385,
|
||
|
|
"epoch": 0.12603795966785292,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999916890855358,
|
||
|
|
"loss": 6.4375,
|
||
|
|
"mean_token_accuracy": 0.12541168332099914,
|
||
|
|
"num_tokens": 2932294.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.365032720565796,
|
||
|
|
"epoch": 0.1265322261763543,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999913830019431,
|
||
|
|
"loss": 6.3555,
|
||
|
|
"mean_token_accuracy": 0.13344720974564553,
|
||
|
|
"num_tokens": 2943372.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3610412120819095,
|
||
|
|
"epoch": 0.12702649268485566,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999910713835272,
|
||
|
|
"loss": 6.328,
|
||
|
|
"mean_token_accuracy": 0.12761889919638633,
|
||
|
|
"num_tokens": 2953807.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.343585634231568,
|
||
|
|
"epoch": 0.12752075919335706,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999907542302962,
|
||
|
|
"loss": 6.2728,
|
||
|
|
"mean_token_accuracy": 0.13296097964048387,
|
||
|
|
"num_tokens": 2964372.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386247301101685,
|
||
|
|
"epoch": 0.12801502570185844,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999904315422577,
|
||
|
|
"loss": 6.3717,
|
||
|
|
"mean_token_accuracy": 0.12678787335753441,
|
||
|
|
"num_tokens": 2975537.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332472610473633,
|
||
|
|
"epoch": 0.12850929221035984,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999901033194198,
|
||
|
|
"loss": 6.3473,
|
||
|
|
"mean_token_accuracy": 0.125575702637434,
|
||
|
|
"num_tokens": 2986094.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.430452728271485,
|
||
|
|
"epoch": 0.1290035587188612,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999897695617904,
|
||
|
|
"loss": 6.4639,
|
||
|
|
"mean_token_accuracy": 0.1235688142478466,
|
||
|
|
"num_tokens": 2996023.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.478709506988525,
|
||
|
|
"epoch": 0.12949782522736258,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999894302693778,
|
||
|
|
"loss": 6.4605,
|
||
|
|
"mean_token_accuracy": 0.11822991967201232,
|
||
|
|
"num_tokens": 3007584.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.49374566078186,
|
||
|
|
"epoch": 0.12999209173586398,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999890854421902,
|
||
|
|
"loss": 6.5016,
|
||
|
|
"mean_token_accuracy": 0.11945728063583375,
|
||
|
|
"num_tokens": 3018995.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.282643270492554,
|
||
|
|
"epoch": 0.13048635824436536,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999887350802362,
|
||
|
|
"loss": 6.2924,
|
||
|
|
"mean_token_accuracy": 0.13177173137664794,
|
||
|
|
"num_tokens": 3030576.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.345934104919434,
|
||
|
|
"epoch": 0.13098062475286676,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999883791835246,
|
||
|
|
"loss": 6.3514,
|
||
|
|
"mean_token_accuracy": 0.12681909948587416,
|
||
|
|
"num_tokens": 3040765.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.423272371292114,
|
||
|
|
"epoch": 0.13147489126136813,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999880177520637,
|
||
|
|
"loss": 6.409,
|
||
|
|
"mean_token_accuracy": 0.12248991131782531,
|
||
|
|
"num_tokens": 3053912.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311845588684082,
|
||
|
|
"epoch": 0.1319691577698695,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999876507858628,
|
||
|
|
"loss": 6.3965,
|
||
|
|
"mean_token_accuracy": 0.1286996364593506,
|
||
|
|
"num_tokens": 3065921.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4796422004699705,
|
||
|
|
"epoch": 0.1324634242783709,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999872782849308,
|
||
|
|
"loss": 6.4359,
|
||
|
|
"mean_token_accuracy": 0.12490473389625549,
|
||
|
|
"num_tokens": 3078643.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.327112102508545,
|
||
|
|
"epoch": 0.13295769078687228,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999869002492768,
|
||
|
|
"loss": 6.3472,
|
||
|
|
"mean_token_accuracy": 0.12497142925858498,
|
||
|
|
"num_tokens": 3090300.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.305787992477417,
|
||
|
|
"epoch": 0.13345195729537365,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999865166789102,
|
||
|
|
"loss": 6.2728,
|
||
|
|
"mean_token_accuracy": 0.1346057914197445,
|
||
|
|
"num_tokens": 3102307.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4519752025604244,
|
||
|
|
"epoch": 0.13394622380387505,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999861275738404,
|
||
|
|
"loss": 6.4322,
|
||
|
|
"mean_token_accuracy": 0.1196314588189125,
|
||
|
|
"num_tokens": 3113817.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347658109664917,
|
||
|
|
"epoch": 0.13444049031237643,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999857329340769,
|
||
|
|
"loss": 6.2713,
|
||
|
|
"mean_token_accuracy": 0.13168584033846856,
|
||
|
|
"num_tokens": 3124719.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256230401992798,
|
||
|
|
"epoch": 0.13493475682087783,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999853327596295,
|
||
|
|
"loss": 6.3081,
|
||
|
|
"mean_token_accuracy": 0.12787580043077468,
|
||
|
|
"num_tokens": 3136136.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.380978584289551,
|
||
|
|
"epoch": 0.1354290233293792,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499984927050508,
|
||
|
|
"loss": 6.3239,
|
||
|
|
"mean_token_accuracy": 0.12932682633399964,
|
||
|
|
"num_tokens": 3148977.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.404514932632447,
|
||
|
|
"epoch": 0.13592328983788057,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999845158067223,
|
||
|
|
"loss": 6.3858,
|
||
|
|
"mean_token_accuracy": 0.12331946268677711,
|
||
|
|
"num_tokens": 3160520.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.340874814987183,
|
||
|
|
"epoch": 0.13641755634638197,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999840990282828,
|
||
|
|
"loss": 6.3682,
|
||
|
|
"mean_token_accuracy": 0.12766008079051971,
|
||
|
|
"num_tokens": 3172895.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.378203678131103,
|
||
|
|
"epoch": 0.13691182285488335,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999836767151994,
|
||
|
|
"loss": 6.3759,
|
||
|
|
"mean_token_accuracy": 0.12594013586640357,
|
||
|
|
"num_tokens": 3183960.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.33987774848938,
|
||
|
|
"epoch": 0.13740608936338475,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999832488674827,
|
||
|
|
"loss": 6.4062,
|
||
|
|
"mean_token_accuracy": 0.12821368426084517,
|
||
|
|
"num_tokens": 3194276.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.364788675308228,
|
||
|
|
"epoch": 0.13790035587188612,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999828154851432,
|
||
|
|
"loss": 6.2715,
|
||
|
|
"mean_token_accuracy": 0.12825500443577767,
|
||
|
|
"num_tokens": 3206084.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311763143539428,
|
||
|
|
"epoch": 0.1383946223803875,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999823765681915,
|
||
|
|
"loss": 6.315,
|
||
|
|
"mean_token_accuracy": 0.13517030254006385,
|
||
|
|
"num_tokens": 3217941.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372605180740356,
|
||
|
|
"epoch": 0.1388888888888889,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999819321166385,
|
||
|
|
"loss": 6.2937,
|
||
|
|
"mean_token_accuracy": 0.13194846287369727,
|
||
|
|
"num_tokens": 3229088.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.226320409774781,
|
||
|
|
"epoch": 0.13938315539739027,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499981482130495,
|
||
|
|
"loss": 6.2465,
|
||
|
|
"mean_token_accuracy": 0.13179270252585412,
|
||
|
|
"num_tokens": 3240708.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346386909484863,
|
||
|
|
"epoch": 0.13987742190589167,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999810266097721,
|
||
|
|
"loss": 6.3626,
|
||
|
|
"mean_token_accuracy": 0.12732164114713668,
|
||
|
|
"num_tokens": 3251040.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.329486846923828,
|
||
|
|
"epoch": 0.14037168841439304,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999805655544811,
|
||
|
|
"loss": 6.3098,
|
||
|
|
"mean_token_accuracy": 0.13264497891068458,
|
||
|
|
"num_tokens": 3262655.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212118196487427,
|
||
|
|
"epoch": 0.14086595492289442,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999800989646333,
|
||
|
|
"loss": 6.2491,
|
||
|
|
"mean_token_accuracy": 0.13740817755460738,
|
||
|
|
"num_tokens": 3273160.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.370003509521484,
|
||
|
|
"epoch": 0.14136022143139582,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999796268402401,
|
||
|
|
"loss": 6.2927,
|
||
|
|
"mean_token_accuracy": 0.12932768389582633,
|
||
|
|
"num_tokens": 3285932.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204702472686767,
|
||
|
|
"epoch": 0.1418544879398972,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999791491813132,
|
||
|
|
"loss": 6.3249,
|
||
|
|
"mean_token_accuracy": 0.12708639204502106,
|
||
|
|
"num_tokens": 3298834.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446914958953857,
|
||
|
|
"epoch": 0.1423487544483986,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999786659878643,
|
||
|
|
"loss": 6.306,
|
||
|
|
"mean_token_accuracy": 0.12587132155895234,
|
||
|
|
"num_tokens": 3310473.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21795768737793,
|
||
|
|
"epoch": 0.14284302095689996,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999781772599055,
|
||
|
|
"loss": 6.2681,
|
||
|
|
"mean_token_accuracy": 0.13160885125398636,
|
||
|
|
"num_tokens": 3322662.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.403645086288452,
|
||
|
|
"epoch": 0.14333728746540134,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999776829974484,
|
||
|
|
"loss": 6.3586,
|
||
|
|
"mean_token_accuracy": 0.13399278223514557,
|
||
|
|
"num_tokens": 3334321.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.237197971343994,
|
||
|
|
"epoch": 0.14383155397390274,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999771832005055,
|
||
|
|
"loss": 6.2566,
|
||
|
|
"mean_token_accuracy": 0.13325597643852233,
|
||
|
|
"num_tokens": 3345130.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300555944442749,
|
||
|
|
"epoch": 0.1443258204824041,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499976677869089,
|
||
|
|
"loss": 6.2482,
|
||
|
|
"mean_token_accuracy": 0.13124737069010733,
|
||
|
|
"num_tokens": 3355601.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.177254724502563,
|
||
|
|
"epoch": 0.14482008699090548,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999761670032115,
|
||
|
|
"loss": 6.2445,
|
||
|
|
"mean_token_accuracy": 0.13512926325201988,
|
||
|
|
"num_tokens": 3367075.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346540451049805,
|
||
|
|
"epoch": 0.14531435349940688,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999756506028851,
|
||
|
|
"loss": 6.2138,
|
||
|
|
"mean_token_accuracy": 0.1346349760890007,
|
||
|
|
"num_tokens": 3378888.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257204246520996,
|
||
|
|
"epoch": 0.14580862000790826,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999751286681229,
|
||
|
|
"loss": 6.2592,
|
||
|
|
"mean_token_accuracy": 0.12868553325533866,
|
||
|
|
"num_tokens": 3390705.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.271823263168335,
|
||
|
|
"epoch": 0.14630288651640966,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999746011989376,
|
||
|
|
"loss": 6.2786,
|
||
|
|
"mean_token_accuracy": 0.1390862375497818,
|
||
|
|
"num_tokens": 3401710.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3559166431427006,
|
||
|
|
"epoch": 0.14679715302491103,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999740681953422,
|
||
|
|
"loss": 6.4007,
|
||
|
|
"mean_token_accuracy": 0.1307731091976166,
|
||
|
|
"num_tokens": 3413467.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.352506494522094,
|
||
|
|
"epoch": 0.1472914195334124,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999735296573499,
|
||
|
|
"loss": 6.3169,
|
||
|
|
"mean_token_accuracy": 0.1303673006594181,
|
||
|
|
"num_tokens": 3425885.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319741106033325,
|
||
|
|
"epoch": 0.1477856860419138,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999729855849738,
|
||
|
|
"loss": 6.3423,
|
||
|
|
"mean_token_accuracy": 0.12189344838261604,
|
||
|
|
"num_tokens": 3437952.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297153282165527,
|
||
|
|
"epoch": 0.14827995255041518,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999724359782274,
|
||
|
|
"loss": 6.2108,
|
||
|
|
"mean_token_accuracy": 0.146717868745327,
|
||
|
|
"num_tokens": 3449680.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.320958423614502,
|
||
|
|
"epoch": 0.14877421905891658,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999718808371241,
|
||
|
|
"loss": 6.3669,
|
||
|
|
"mean_token_accuracy": 0.12667585760354996,
|
||
|
|
"num_tokens": 3460699.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.33337435722351,
|
||
|
|
"epoch": 0.14926848556741795,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999713201616776,
|
||
|
|
"loss": 6.2453,
|
||
|
|
"mean_token_accuracy": 0.13252191320061685,
|
||
|
|
"num_tokens": 3471919.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197843170166015,
|
||
|
|
"epoch": 0.14976275207591933,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499970753951902,
|
||
|
|
"loss": 6.34,
|
||
|
|
"mean_token_accuracy": 0.1314842201769352,
|
||
|
|
"num_tokens": 3484110.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.376157331466675,
|
||
|
|
"epoch": 0.15025701858442073,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999701822078107,
|
||
|
|
"loss": 6.267,
|
||
|
|
"mean_token_accuracy": 0.12918772250413896,
|
||
|
|
"num_tokens": 3496103.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2873046875,
|
||
|
|
"epoch": 0.1507512850929221,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499969604929418,
|
||
|
|
"loss": 6.3306,
|
||
|
|
"mean_token_accuracy": 0.1289186179637909,
|
||
|
|
"num_tokens": 3507291.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.321810102462768,
|
||
|
|
"epoch": 0.1512455516014235,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999690221167382,
|
||
|
|
"loss": 6.3375,
|
||
|
|
"mean_token_accuracy": 0.12606015801429749,
|
||
|
|
"num_tokens": 3519564.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227030229568482,
|
||
|
|
"epoch": 0.15173981810992487,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999684337697855,
|
||
|
|
"loss": 6.1794,
|
||
|
|
"mean_token_accuracy": 0.13856639936566353,
|
||
|
|
"num_tokens": 3530679.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.286623477935791,
|
||
|
|
"epoch": 0.15223408461842625,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999678398885746,
|
||
|
|
"loss": 6.2568,
|
||
|
|
"mean_token_accuracy": 0.13309661373496057,
|
||
|
|
"num_tokens": 3542662.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.339551496505737,
|
||
|
|
"epoch": 0.15272835112692765,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999672404731197,
|
||
|
|
"loss": 6.3693,
|
||
|
|
"mean_token_accuracy": 0.1256125934422016,
|
||
|
|
"num_tokens": 3554760.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2353137016296385,
|
||
|
|
"epoch": 0.15322261763542902,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499966635523436,
|
||
|
|
"loss": 6.177,
|
||
|
|
"mean_token_accuracy": 0.14254598543047906,
|
||
|
|
"num_tokens": 3565604.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.287824535369873,
|
||
|
|
"epoch": 0.1537168841439304,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999660250395381,
|
||
|
|
"loss": 6.3409,
|
||
|
|
"mean_token_accuracy": 0.12926940694451333,
|
||
|
|
"num_tokens": 3577535.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.315780210494995,
|
||
|
|
"epoch": 0.1542111506524318,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499965409021441,
|
||
|
|
"loss": 6.3456,
|
||
|
|
"mean_token_accuracy": 0.12645572200417518,
|
||
|
|
"num_tokens": 3590458.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346096706390381,
|
||
|
|
"epoch": 0.15470541716093317,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00049996478746916,
|
||
|
|
"loss": 6.2968,
|
||
|
|
"mean_token_accuracy": 0.1334037959575653,
|
||
|
|
"num_tokens": 3600916.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.283687400817871,
|
||
|
|
"epoch": 0.15519968366943457,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999641603827104,
|
||
|
|
"loss": 6.3154,
|
||
|
|
"mean_token_accuracy": 0.12896228358149528,
|
||
|
|
"num_tokens": 3612794.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.242175149917602,
|
||
|
|
"epoch": 0.15569395017793594,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999635277621073,
|
||
|
|
"loss": 6.2266,
|
||
|
|
"mean_token_accuracy": 0.1417408972978592,
|
||
|
|
"num_tokens": 3624186.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214152431488037,
|
||
|
|
"epoch": 0.15618821668643731,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999628896073668,
|
||
|
|
"loss": 6.2588,
|
||
|
|
"mean_token_accuracy": 0.13209749460220338,
|
||
|
|
"num_tokens": 3636041.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.344410371780396,
|
||
|
|
"epoch": 0.15668248319493872,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999622459185042,
|
||
|
|
"loss": 6.3133,
|
||
|
|
"mean_token_accuracy": 0.12568183317780496,
|
||
|
|
"num_tokens": 3646859.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202246046066284,
|
||
|
|
"epoch": 0.1571767497034401,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999615966955354,
|
||
|
|
"loss": 6.1356,
|
||
|
|
"mean_token_accuracy": 0.14240555465221405,
|
||
|
|
"num_tokens": 3657853.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3169105052948,
|
||
|
|
"epoch": 0.1576710162119415,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999609419384764,
|
||
|
|
"loss": 6.2357,
|
||
|
|
"mean_token_accuracy": 0.13412488624453545,
|
||
|
|
"num_tokens": 3668341.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222606992721557,
|
||
|
|
"epoch": 0.15816528272044286,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999602816473434,
|
||
|
|
"loss": 6.2746,
|
||
|
|
"mean_token_accuracy": 0.13777462095022203,
|
||
|
|
"num_tokens": 3679020.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204525804519653,
|
||
|
|
"epoch": 0.15865954922894424,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999596158221526,
|
||
|
|
"loss": 6.1868,
|
||
|
|
"mean_token_accuracy": 0.13501218110322952,
|
||
|
|
"num_tokens": 3691121.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281662178039551,
|
||
|
|
"epoch": 0.15915381573744564,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999589444629203,
|
||
|
|
"loss": 6.2345,
|
||
|
|
"mean_token_accuracy": 0.13559392616152763,
|
||
|
|
"num_tokens": 3702584.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1406842231750485,
|
||
|
|
"epoch": 0.159648082245947,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999582675696631,
|
||
|
|
"loss": 6.1953,
|
||
|
|
"mean_token_accuracy": 0.13631167709827424,
|
||
|
|
"num_tokens": 3713085.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366911602020264,
|
||
|
|
"epoch": 0.1601423487544484,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999575851423976,
|
||
|
|
"loss": 6.3011,
|
||
|
|
"mean_token_accuracy": 0.12538277432322503,
|
||
|
|
"num_tokens": 3724318.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267498779296875,
|
||
|
|
"epoch": 0.16063661526294978,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999568971811407,
|
||
|
|
"loss": 6.2124,
|
||
|
|
"mean_token_accuracy": 0.13635317981243134,
|
||
|
|
"num_tokens": 3734288.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2429688453674315,
|
||
|
|
"epoch": 0.16113088177145116,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499956203685909,
|
||
|
|
"loss": 6.213,
|
||
|
|
"mean_token_accuracy": 0.13301184847950936,
|
||
|
|
"num_tokens": 3744645.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.262392187118531,
|
||
|
|
"epoch": 0.16162514827995256,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00049995550465672,
|
||
|
|
"loss": 6.2066,
|
||
|
|
"mean_token_accuracy": 0.13891988545656203,
|
||
|
|
"num_tokens": 3755660.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186764144897461,
|
||
|
|
"epoch": 0.16211941478845393,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999548000935906,
|
||
|
|
"loss": 6.1703,
|
||
|
|
"mean_token_accuracy": 0.14325928688049316,
|
||
|
|
"num_tokens": 3767614.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2171549797058105,
|
||
|
|
"epoch": 0.16261368129695533,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999540899965383,
|
||
|
|
"loss": 6.3215,
|
||
|
|
"mean_token_accuracy": 0.13531928211450578,
|
||
|
|
"num_tokens": 3780750.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270230484008789,
|
||
|
|
"epoch": 0.1631079478054567,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999533743655803,
|
||
|
|
"loss": 6.3177,
|
||
|
|
"mean_token_accuracy": 0.12921538352966308,
|
||
|
|
"num_tokens": 3793195.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2332807064056395,
|
||
|
|
"epoch": 0.16360221431395808,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999526532007346,
|
||
|
|
"loss": 6.2687,
|
||
|
|
"mean_token_accuracy": 0.13402236700057985,
|
||
|
|
"num_tokens": 3804256.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.268304014205933,
|
||
|
|
"epoch": 0.16409648082245948,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999519265020187,
|
||
|
|
"loss": 6.241,
|
||
|
|
"mean_token_accuracy": 0.13152503371238708,
|
||
|
|
"num_tokens": 3815403.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141922092437744,
|
||
|
|
"epoch": 0.16459074733096085,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999511942694504,
|
||
|
|
"loss": 6.145,
|
||
|
|
"mean_token_accuracy": 0.14074706807732582,
|
||
|
|
"num_tokens": 3826682.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.183226728439331,
|
||
|
|
"epoch": 0.16508501383946222,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999504565030479,
|
||
|
|
"loss": 6.1477,
|
||
|
|
"mean_token_accuracy": 0.13699368238449097,
|
||
|
|
"num_tokens": 3837780.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.232640504837036,
|
||
|
|
"epoch": 0.16557928034796363,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999497132028293,
|
||
|
|
"loss": 6.2122,
|
||
|
|
"mean_token_accuracy": 0.13325633332133294,
|
||
|
|
"num_tokens": 3848782.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2934805393219,
|
||
|
|
"epoch": 0.166073546856465,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999489643688127,
|
||
|
|
"loss": 6.1686,
|
||
|
|
"mean_token_accuracy": 0.14154083654284477,
|
||
|
|
"num_tokens": 3859220.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090300416946411,
|
||
|
|
"epoch": 0.1665678133649664,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999482100010169,
|
||
|
|
"loss": 6.0887,
|
||
|
|
"mean_token_accuracy": 0.13925182297825814,
|
||
|
|
"num_tokens": 3869794.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.150887966156006,
|
||
|
|
"epoch": 0.16706207987346777,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999474500994601,
|
||
|
|
"loss": 6.2364,
|
||
|
|
"mean_token_accuracy": 0.13384735137224196,
|
||
|
|
"num_tokens": 3881133.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21327486038208,
|
||
|
|
"epoch": 0.16755634638196915,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999466846641611,
|
||
|
|
"loss": 6.1703,
|
||
|
|
"mean_token_accuracy": 0.13535154461860657,
|
||
|
|
"num_tokens": 3891600.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223018407821655,
|
||
|
|
"epoch": 0.16805061289047055,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999459136951389,
|
||
|
|
"loss": 6.2544,
|
||
|
|
"mean_token_accuracy": 0.12869785651564597,
|
||
|
|
"num_tokens": 3903287.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270557594299317,
|
||
|
|
"epoch": 0.16854487939897192,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999451371924123,
|
||
|
|
"loss": 6.1722,
|
||
|
|
"mean_token_accuracy": 0.1409811407327652,
|
||
|
|
"num_tokens": 3914497.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.178465557098389,
|
||
|
|
"epoch": 0.16903914590747332,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999443551560003,
|
||
|
|
"loss": 6.2012,
|
||
|
|
"mean_token_accuracy": 0.13772032260894776,
|
||
|
|
"num_tokens": 3925536.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.187081527709961,
|
||
|
|
"epoch": 0.1695334124159747,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999435675859224,
|
||
|
|
"loss": 6.1614,
|
||
|
|
"mean_token_accuracy": 0.14096814393997192,
|
||
|
|
"num_tokens": 3936705.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180002164840698,
|
||
|
|
"epoch": 0.17002767892447607,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999427744821977,
|
||
|
|
"loss": 6.0466,
|
||
|
|
"mean_token_accuracy": 0.14241904616355897,
|
||
|
|
"num_tokens": 3948422.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131735038757324,
|
||
|
|
"epoch": 0.17052194543297747,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499941975844846,
|
||
|
|
"loss": 6.1164,
|
||
|
|
"mean_token_accuracy": 0.14995900243520738,
|
||
|
|
"num_tokens": 3958697.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118026256561279,
|
||
|
|
"epoch": 0.17101621194147884,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999411716738866,
|
||
|
|
"loss": 6.1331,
|
||
|
|
"mean_token_accuracy": 0.13519771322607993,
|
||
|
|
"num_tokens": 3970255.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195291328430176,
|
||
|
|
"epoch": 0.17151047844998024,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999403619693397,
|
||
|
|
"loss": 6.2176,
|
||
|
|
"mean_token_accuracy": 0.1338466487824917,
|
||
|
|
"num_tokens": 3980892.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100106287002563,
|
||
|
|
"epoch": 0.17200474495848161,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999395467312249,
|
||
|
|
"loss": 6.1802,
|
||
|
|
"mean_token_accuracy": 0.13538480401039124,
|
||
|
|
"num_tokens": 3991375.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2856316566467285,
|
||
|
|
"epoch": 0.172499011466983,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999387259595623,
|
||
|
|
"loss": 6.3027,
|
||
|
|
"mean_token_accuracy": 0.12879397645592688,
|
||
|
|
"num_tokens": 4003352.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174993705749512,
|
||
|
|
"epoch": 0.1729932779754844,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999378996543723,
|
||
|
|
"loss": 6.17,
|
||
|
|
"mean_token_accuracy": 0.1376201942563057,
|
||
|
|
"num_tokens": 4014429.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198324298858642,
|
||
|
|
"epoch": 0.17348754448398576,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999370678156749,
|
||
|
|
"loss": 6.1103,
|
||
|
|
"mean_token_accuracy": 0.1439209058880806,
|
||
|
|
"num_tokens": 4025213.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090781736373901,
|
||
|
|
"epoch": 0.17398181099248716,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999362304434909,
|
||
|
|
"loss": 6.0962,
|
||
|
|
"mean_token_accuracy": 0.13730676025152205,
|
||
|
|
"num_tokens": 4036244.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.233505058288574,
|
||
|
|
"epoch": 0.17447607750098854,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999353875378406,
|
||
|
|
"loss": 6.1452,
|
||
|
|
"mean_token_accuracy": 0.14138466492295265,
|
||
|
|
"num_tokens": 4047944.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11910719871521,
|
||
|
|
"epoch": 0.1749703440094899,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000499934539098745,
|
||
|
|
"loss": 6.1252,
|
||
|
|
"mean_token_accuracy": 0.1402312107384205,
|
||
|
|
"num_tokens": 4058865.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147714710235595,
|
||
|
|
"epoch": 0.1754646105179913,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999336851262247,
|
||
|
|
"loss": 6.1812,
|
||
|
|
"mean_token_accuracy": 0.1386764883995056,
|
||
|
|
"num_tokens": 4070627.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.254544258117676,
|
||
|
|
"epoch": 0.17595887702649268,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999328256203009,
|
||
|
|
"loss": 6.2109,
|
||
|
|
"mean_token_accuracy": 0.13585594072937965,
|
||
|
|
"num_tokens": 4081406.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.233277177810669,
|
||
|
|
"epoch": 0.17645314353499406,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999319605809947,
|
||
|
|
"loss": 6.1741,
|
||
|
|
"mean_token_accuracy": 0.1320988729596138,
|
||
|
|
"num_tokens": 4092957.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197539043426514,
|
||
|
|
"epoch": 0.17694741004349546,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999310900083274,
|
||
|
|
"loss": 6.232,
|
||
|
|
"mean_token_accuracy": 0.1367380939424038,
|
||
|
|
"num_tokens": 4104381.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197038173675537,
|
||
|
|
"epoch": 0.17744167655199683,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999302139023204,
|
||
|
|
"loss": 6.1557,
|
||
|
|
"mean_token_accuracy": 0.1400916777551174,
|
||
|
|
"num_tokens": 4117190.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102609157562256,
|
||
|
|
"epoch": 0.17793594306049823,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999293322629951,
|
||
|
|
"loss": 6.079,
|
||
|
|
"mean_token_accuracy": 0.14549081772565842,
|
||
|
|
"num_tokens": 4127870.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.129020547866821,
|
||
|
|
"epoch": 0.1784302095689996,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999284450903736,
|
||
|
|
"loss": 6.138,
|
||
|
|
"mean_token_accuracy": 0.13854647651314736,
|
||
|
|
"num_tokens": 4139240.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215698909759522,
|
||
|
|
"epoch": 0.17892447607750098,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999275523844772,
|
||
|
|
"loss": 6.1085,
|
||
|
|
"mean_token_accuracy": 0.14032288491725922,
|
||
|
|
"num_tokens": 4149885.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214642906188965,
|
||
|
|
"epoch": 0.17941874258600238,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999266541453283,
|
||
|
|
"loss": 6.2802,
|
||
|
|
"mean_token_accuracy": 0.1323930524289608,
|
||
|
|
"num_tokens": 4161824.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.177837657928467,
|
||
|
|
"epoch": 0.17991300909450375,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999257503729487,
|
||
|
|
"loss": 6.2496,
|
||
|
|
"mean_token_accuracy": 0.13705600500106813,
|
||
|
|
"num_tokens": 4173581.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221150159835815,
|
||
|
|
"epoch": 0.18040727560300515,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999248410673607,
|
||
|
|
"loss": 6.1126,
|
||
|
|
"mean_token_accuracy": 0.143480521440506,
|
||
|
|
"num_tokens": 4184843.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179816675186157,
|
||
|
|
"epoch": 0.18090154211150652,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999239262285869,
|
||
|
|
"loss": 6.2056,
|
||
|
|
"mean_token_accuracy": 0.1283841423690319,
|
||
|
|
"num_tokens": 4195016.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203648567199707,
|
||
|
|
"epoch": 0.1813958086200079,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999230058566495,
|
||
|
|
"loss": 6.1525,
|
||
|
|
"mean_token_accuracy": 0.14047808349132537,
|
||
|
|
"num_tokens": 4206798.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.165553855895996,
|
||
|
|
"epoch": 0.1818900751285093,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999220799515713,
|
||
|
|
"loss": 6.1249,
|
||
|
|
"mean_token_accuracy": 0.13490928784012796,
|
||
|
|
"num_tokens": 4218784.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162996768951416,
|
||
|
|
"epoch": 0.18238434163701067,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000499921148513375,
|
||
|
|
"loss": 6.1574,
|
||
|
|
"mean_token_accuracy": 0.13539374321699144,
|
||
|
|
"num_tokens": 4229875.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105266094207764,
|
||
|
|
"epoch": 0.18287860814551207,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999202115420836,
|
||
|
|
"loss": 6.1374,
|
||
|
|
"mean_token_accuracy": 0.13884504958987237,
|
||
|
|
"num_tokens": 4241801.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1361840724945065,
|
||
|
|
"epoch": 0.18337287465401345,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999192690377201,
|
||
|
|
"loss": 6.1217,
|
||
|
|
"mean_token_accuracy": 0.13783150538802147,
|
||
|
|
"num_tokens": 4253168.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.160350656509399,
|
||
|
|
"epoch": 0.18386714116251482,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999183210003076,
|
||
|
|
"loss": 6.1528,
|
||
|
|
"mean_token_accuracy": 0.13963853120803832,
|
||
|
|
"num_tokens": 4264791.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135101652145385,
|
||
|
|
"epoch": 0.18436140767101622,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999173674298696,
|
||
|
|
"loss": 6.0804,
|
||
|
|
"mean_token_accuracy": 0.14632727056741715,
|
||
|
|
"num_tokens": 4275816.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215121698379517,
|
||
|
|
"epoch": 0.1848556741795176,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999164083264294,
|
||
|
|
"loss": 6.1752,
|
||
|
|
"mean_token_accuracy": 0.13552125170826912,
|
||
|
|
"num_tokens": 4287806.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.176086950302124,
|
||
|
|
"epoch": 0.185349940688019,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999154436900108,
|
||
|
|
"loss": 6.1989,
|
||
|
|
"mean_token_accuracy": 0.13699856549501419,
|
||
|
|
"num_tokens": 4300319.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.225120544433594,
|
||
|
|
"epoch": 0.18584420719652037,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999144735206373,
|
||
|
|
"loss": 6.2186,
|
||
|
|
"mean_token_accuracy": 0.13408265337347985,
|
||
|
|
"num_tokens": 4310987.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.155704164505005,
|
||
|
|
"epoch": 0.18633847370502174,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999134978183328,
|
||
|
|
"loss": 6.1547,
|
||
|
|
"mean_token_accuracy": 0.14136892259120942,
|
||
|
|
"num_tokens": 4322438.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222135353088379,
|
||
|
|
"epoch": 0.18683274021352314,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999125165831215,
|
||
|
|
"loss": 6.1992,
|
||
|
|
"mean_token_accuracy": 0.14112223237752913,
|
||
|
|
"num_tokens": 4333242.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.118614387512207,
|
||
|
|
"epoch": 0.1873270067220245,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999115298150273,
|
||
|
|
"loss": 6.0501,
|
||
|
|
"mean_token_accuracy": 0.14115071669220924,
|
||
|
|
"num_tokens": 4343660.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148045778274536,
|
||
|
|
"epoch": 0.1878212732305259,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999105375140746,
|
||
|
|
"loss": 6.14,
|
||
|
|
"mean_token_accuracy": 0.14061596095561982,
|
||
|
|
"num_tokens": 4353382.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116020345687867,
|
||
|
|
"epoch": 0.1883155397390273,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999095396802878,
|
||
|
|
"loss": 6.1107,
|
||
|
|
"mean_token_accuracy": 0.13059590086340905,
|
||
|
|
"num_tokens": 4364614.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234473514556885,
|
||
|
|
"epoch": 0.18880980624752866,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999085363136913,
|
||
|
|
"loss": 6.1821,
|
||
|
|
"mean_token_accuracy": 0.1370852842926979,
|
||
|
|
"num_tokens": 4376001.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1575816631317135,
|
||
|
|
"epoch": 0.18930407275603006,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00049990752741431,
|
||
|
|
"loss": 6.1881,
|
||
|
|
"mean_token_accuracy": 0.13424815014004707,
|
||
|
|
"num_tokens": 4387083.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139787340164185,
|
||
|
|
"epoch": 0.18979833926453143,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999065129821687,
|
||
|
|
"loss": 6.137,
|
||
|
|
"mean_token_accuracy": 0.1406305432319641,
|
||
|
|
"num_tokens": 4399977.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068781757354737,
|
||
|
|
"epoch": 0.1902926057730328,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999054930172923,
|
||
|
|
"loss": 6.0596,
|
||
|
|
"mean_token_accuracy": 0.14291156306862832,
|
||
|
|
"num_tokens": 4411609.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212024402618408,
|
||
|
|
"epoch": 0.1907868722815342,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999044675197058,
|
||
|
|
"loss": 6.1796,
|
||
|
|
"mean_token_accuracy": 0.14021965712308884,
|
||
|
|
"num_tokens": 4423567.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122093629837036,
|
||
|
|
"epoch": 0.19128113879003558,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999034364894345,
|
||
|
|
"loss": 6.1471,
|
||
|
|
"mean_token_accuracy": 0.14296084716916085,
|
||
|
|
"num_tokens": 4435410.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227278757095337,
|
||
|
|
"epoch": 0.19177540529853698,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999023999265039,
|
||
|
|
"loss": 6.1687,
|
||
|
|
"mean_token_accuracy": 0.13742463737726213,
|
||
|
|
"num_tokens": 4445279.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052986907958984,
|
||
|
|
"epoch": 0.19226967180703836,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999013578309392,
|
||
|
|
"loss": 6.0426,
|
||
|
|
"mean_token_accuracy": 0.14442079216241838,
|
||
|
|
"num_tokens": 4456017.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.164314031600952,
|
||
|
|
"epoch": 0.19276393831553973,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999003102027663,
|
||
|
|
"loss": 6.0397,
|
||
|
|
"mean_token_accuracy": 0.14643031507730483,
|
||
|
|
"num_tokens": 4466759.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049403285980224,
|
||
|
|
"epoch": 0.19325820482404113,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499899257042011,
|
||
|
|
"loss": 6.1095,
|
||
|
|
"mean_token_accuracy": 0.13636567667126656,
|
||
|
|
"num_tokens": 4478316.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.268176746368408,
|
||
|
|
"epoch": 0.1937524713325425,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998981983486988,
|
||
|
|
"loss": 6.1857,
|
||
|
|
"mean_token_accuracy": 0.13160716071724893,
|
||
|
|
"num_tokens": 4490775.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01789960861206,
|
||
|
|
"epoch": 0.1942467378410439,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998971341228563,
|
||
|
|
"loss": 6.0397,
|
||
|
|
"mean_token_accuracy": 0.14438610523939133,
|
||
|
|
"num_tokens": 4501622.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192607975006103,
|
||
|
|
"epoch": 0.19474100434954528,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998960643645093,
|
||
|
|
"loss": 6.1417,
|
||
|
|
"mean_token_accuracy": 0.13959416076540948,
|
||
|
|
"num_tokens": 4512279.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141578912734985,
|
||
|
|
"epoch": 0.19523527085804665,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998949890736841,
|
||
|
|
"loss": 6.1366,
|
||
|
|
"mean_token_accuracy": 0.14056662544608117,
|
||
|
|
"num_tokens": 4524087.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163547372817993,
|
||
|
|
"epoch": 0.19572953736654805,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998939082504075,
|
||
|
|
"loss": 6.1107,
|
||
|
|
"mean_token_accuracy": 0.13843527510762216,
|
||
|
|
"num_tokens": 4534816.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093228673934936,
|
||
|
|
"epoch": 0.19622380387504942,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998928218947057,
|
||
|
|
"loss": 6.0846,
|
||
|
|
"mean_token_accuracy": 0.14316740408539771,
|
||
|
|
"num_tokens": 4545725.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.200720977783203,
|
||
|
|
"epoch": 0.1967180703835508,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998917300066056,
|
||
|
|
"loss": 6.1917,
|
||
|
|
"mean_token_accuracy": 0.13488160222768783,
|
||
|
|
"num_tokens": 4557003.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116532039642334,
|
||
|
|
"epoch": 0.1972123368920522,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998906325861342,
|
||
|
|
"loss": 6.1186,
|
||
|
|
"mean_token_accuracy": 0.13448214009404183,
|
||
|
|
"num_tokens": 4568768.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061165761947632,
|
||
|
|
"epoch": 0.19770660340055357,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998895296333183,
|
||
|
|
"loss": 6.075,
|
||
|
|
"mean_token_accuracy": 0.14456838592886925,
|
||
|
|
"num_tokens": 4581116.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159106636047364,
|
||
|
|
"epoch": 0.19820086990905497,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499888421148185,
|
||
|
|
"loss": 6.1472,
|
||
|
|
"mean_token_accuracy": 0.13944101855158805,
|
||
|
|
"num_tokens": 4592660.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1140529155731205,
|
||
|
|
"epoch": 0.19869513641755635,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998873071307617,
|
||
|
|
"loss": 6.1306,
|
||
|
|
"mean_token_accuracy": 0.14218790084123611,
|
||
|
|
"num_tokens": 4603057.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099922132492066,
|
||
|
|
"epoch": 0.19918940292605772,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998861875810758,
|
||
|
|
"loss": 6.0173,
|
||
|
|
"mean_token_accuracy": 0.1523900419473648,
|
||
|
|
"num_tokens": 4613546.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.114162826538086,
|
||
|
|
"epoch": 0.19968366943455912,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998850624991548,
|
||
|
|
"loss": 6.1026,
|
||
|
|
"mean_token_accuracy": 0.13796947225928308,
|
||
|
|
"num_tokens": 4624613.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.098139095306396,
|
||
|
|
"epoch": 0.2001779359430605,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998839318850263,
|
||
|
|
"loss": 6.0514,
|
||
|
|
"mean_token_accuracy": 0.14360944032669068,
|
||
|
|
"num_tokens": 4636004.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120128488540649,
|
||
|
|
"epoch": 0.2006722024515619,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998827957387182,
|
||
|
|
"loss": 6.1129,
|
||
|
|
"mean_token_accuracy": 0.14691153317689895,
|
||
|
|
"num_tokens": 4646450.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081124877929687,
|
||
|
|
"epoch": 0.20116646896006327,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998816540602584,
|
||
|
|
"loss": 6.1041,
|
||
|
|
"mean_token_accuracy": 0.14503619000315665,
|
||
|
|
"num_tokens": 4658928.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133530998229981,
|
||
|
|
"epoch": 0.20166073546856464,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998805068496752,
|
||
|
|
"loss": 6.1183,
|
||
|
|
"mean_token_accuracy": 0.1382000871002674,
|
||
|
|
"num_tokens": 4670392.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.139105319976807,
|
||
|
|
"epoch": 0.20215500197706604,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998793541069964,
|
||
|
|
"loss": 6.1037,
|
||
|
|
"mean_token_accuracy": 0.14044443294405937,
|
||
|
|
"num_tokens": 4680605.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105360126495361,
|
||
|
|
"epoch": 0.2026492684855674,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998781958322507,
|
||
|
|
"loss": 6.0178,
|
||
|
|
"mean_token_accuracy": 0.148818439245224,
|
||
|
|
"num_tokens": 4694250.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0853666305542,
|
||
|
|
"epoch": 0.20314353499406881,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998770320254666,
|
||
|
|
"loss": 6.1773,
|
||
|
|
"mean_token_accuracy": 0.14307564869523048,
|
||
|
|
"num_tokens": 4705754.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17984561920166,
|
||
|
|
"epoch": 0.2036378015025702,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998758626866725,
|
||
|
|
"loss": 6.0514,
|
||
|
|
"mean_token_accuracy": 0.14124418497085572,
|
||
|
|
"num_tokens": 4716393.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0255289554595945,
|
||
|
|
"epoch": 0.20413206801107156,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998746878158973,
|
||
|
|
"loss": 6.0695,
|
||
|
|
"mean_token_accuracy": 0.1441777989268303,
|
||
|
|
"num_tokens": 4726894.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100637626647949,
|
||
|
|
"epoch": 0.20462633451957296,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998735074131699,
|
||
|
|
"loss": 6.0719,
|
||
|
|
"mean_token_accuracy": 0.14012258723378182,
|
||
|
|
"num_tokens": 4737488.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.15246262550354,
|
||
|
|
"epoch": 0.20512060102807433,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998723214785194,
|
||
|
|
"loss": 6.1491,
|
||
|
|
"mean_token_accuracy": 0.13380857929587364,
|
||
|
|
"num_tokens": 4749131.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111332082748413,
|
||
|
|
"epoch": 0.20561486753657574,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998711300119749,
|
||
|
|
"loss": 6.0323,
|
||
|
|
"mean_token_accuracy": 0.14320058673620223,
|
||
|
|
"num_tokens": 4760503.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.136212539672852,
|
||
|
|
"epoch": 0.2061091340450771,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998699330135656,
|
||
|
|
"loss": 6.1539,
|
||
|
|
"mean_token_accuracy": 0.13834208101034165,
|
||
|
|
"num_tokens": 4771965.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138793087005615,
|
||
|
|
"epoch": 0.20660340055357848,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998687304833212,
|
||
|
|
"loss": 6.1213,
|
||
|
|
"mean_token_accuracy": 0.1382380060851574,
|
||
|
|
"num_tokens": 4784215.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092998313903808,
|
||
|
|
"epoch": 0.20709766706207988,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000499867522421271,
|
||
|
|
"loss": 6.0456,
|
||
|
|
"mean_token_accuracy": 0.1476783685386181,
|
||
|
|
"num_tokens": 4796410.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064586448669433,
|
||
|
|
"epoch": 0.20759193357058126,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499866308827445,
|
||
|
|
"loss": 6.0507,
|
||
|
|
"mean_token_accuracy": 0.14678769260644914,
|
||
|
|
"num_tokens": 4806990.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122417736053467,
|
||
|
|
"epoch": 0.20808620007908263,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998650897018729,
|
||
|
|
"loss": 6.0925,
|
||
|
|
"mean_token_accuracy": 0.1402530699968338,
|
||
|
|
"num_tokens": 4818903.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067685079574585,
|
||
|
|
"epoch": 0.20858046658758403,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004998638650445847,
|
||
|
|
"loss": 6.0168,
|
||
|
|
"mean_token_accuracy": 0.14625680148601533,
|
||
|
|
"num_tokens": 4829130.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103088474273681,
|
||
|
|
"epoch": 0.2090747330960854,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998626348556105,
|
||
|
|
"loss": 6.0418,
|
||
|
|
"mean_token_accuracy": 0.15239209532737732,
|
||
|
|
"num_tokens": 4840424.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071985864639283,
|
||
|
|
"epoch": 0.2095689996045868,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998613991349807,
|
||
|
|
"loss": 6.032,
|
||
|
|
"mean_token_accuracy": 0.14296659007668494,
|
||
|
|
"num_tokens": 4851674.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971784257888794,
|
||
|
|
"epoch": 0.21006326611308818,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998601578827255,
|
||
|
|
"loss": 5.984,
|
||
|
|
"mean_token_accuracy": 0.15040734261274338,
|
||
|
|
"num_tokens": 4863884.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005367851257324,
|
||
|
|
"epoch": 0.21055753262158955,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998589110988755,
|
||
|
|
"loss": 6.0507,
|
||
|
|
"mean_token_accuracy": 0.14619937613606454,
|
||
|
|
"num_tokens": 4875582.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.183507490158081,
|
||
|
|
"epoch": 0.21105179913009095,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998576587834614,
|
||
|
|
"loss": 6.0823,
|
||
|
|
"mean_token_accuracy": 0.13843935653567313,
|
||
|
|
"num_tokens": 4888325.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027950668334961,
|
||
|
|
"epoch": 0.21154606563859232,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499856400936514,
|
||
|
|
"loss": 6.0577,
|
||
|
|
"mean_token_accuracy": 0.14149413332343103,
|
||
|
|
"num_tokens": 4899631.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.089634227752685,
|
||
|
|
"epoch": 0.21204033214709372,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998551375580643,
|
||
|
|
"loss": 6.0628,
|
||
|
|
"mean_token_accuracy": 0.1428640715777874,
|
||
|
|
"num_tokens": 4910954.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083458280563354,
|
||
|
|
"epoch": 0.2125345986555951,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998538686481435,
|
||
|
|
"loss": 6.0633,
|
||
|
|
"mean_token_accuracy": 0.14101619869470597,
|
||
|
|
"num_tokens": 4921952.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0476446628570555,
|
||
|
|
"epoch": 0.21302886516409647,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004998525942067824,
|
||
|
|
"loss": 6.02,
|
||
|
|
"mean_token_accuracy": 0.14522978365421296,
|
||
|
|
"num_tokens": 4933984.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145360994338989,
|
||
|
|
"epoch": 0.21352313167259787,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998513142340128,
|
||
|
|
"loss": 6.1588,
|
||
|
|
"mean_token_accuracy": 0.14218130186200142,
|
||
|
|
"num_tokens": 4945926.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046855878829956,
|
||
|
|
"epoch": 0.21401739818109924,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998500287298657,
|
||
|
|
"loss": 6.077,
|
||
|
|
"mean_token_accuracy": 0.15306318998336793,
|
||
|
|
"num_tokens": 4958123.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17364239692688,
|
||
|
|
"epoch": 0.21451166468960065,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998487376943733,
|
||
|
|
"loss": 6.1514,
|
||
|
|
"mean_token_accuracy": 0.13683199137449265,
|
||
|
|
"num_tokens": 4970409.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111607265472412,
|
||
|
|
"epoch": 0.21500593119810202,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499847441127567,
|
||
|
|
"loss": 6.047,
|
||
|
|
"mean_token_accuracy": 0.13707778006792068,
|
||
|
|
"num_tokens": 4980429.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080226469039917,
|
||
|
|
"epoch": 0.2155001977066034,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004998461390294787,
|
||
|
|
"loss": 6.0593,
|
||
|
|
"mean_token_accuracy": 0.14490607976913453,
|
||
|
|
"num_tokens": 4991790.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080314683914184,
|
||
|
|
"epoch": 0.2159944642151048,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998448314001405,
|
||
|
|
"loss": 6.0923,
|
||
|
|
"mean_token_accuracy": 0.14397517889738082,
|
||
|
|
"num_tokens": 5003611.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.201275777816773,
|
||
|
|
"epoch": 0.21648873072360617,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998435182395845,
|
||
|
|
"loss": 6.1295,
|
||
|
|
"mean_token_accuracy": 0.13416502475738526,
|
||
|
|
"num_tokens": 5014824.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.138464641571045,
|
||
|
|
"epoch": 0.21698299723210757,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998421995478432,
|
||
|
|
"loss": 6.0771,
|
||
|
|
"mean_token_accuracy": 0.14302236288785936,
|
||
|
|
"num_tokens": 5026937.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1277509212493895,
|
||
|
|
"epoch": 0.21747726374060894,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998408753249489,
|
||
|
|
"loss": 6.1044,
|
||
|
|
"mean_token_accuracy": 0.13709214180707932,
|
||
|
|
"num_tokens": 5037996.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113880014419555,
|
||
|
|
"epoch": 0.2179715302491103,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998395455709342,
|
||
|
|
"loss": 6.0501,
|
||
|
|
"mean_token_accuracy": 0.1471073068678379,
|
||
|
|
"num_tokens": 5050944.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091850614547729,
|
||
|
|
"epoch": 0.2184657967576117,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998382102858317,
|
||
|
|
"loss": 6.0858,
|
||
|
|
"mean_token_accuracy": 0.14265154898166657,
|
||
|
|
"num_tokens": 5062129.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.112558794021607,
|
||
|
|
"epoch": 0.2189600632661131,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998368694696743,
|
||
|
|
"loss": 6.0979,
|
||
|
|
"mean_token_accuracy": 0.14317942932248115,
|
||
|
|
"num_tokens": 5073318.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054451847076416,
|
||
|
|
"epoch": 0.21945432977461446,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998355231224952,
|
||
|
|
"loss": 6.1274,
|
||
|
|
"mean_token_accuracy": 0.13541247174143792,
|
||
|
|
"num_tokens": 5084607.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143736171722412,
|
||
|
|
"epoch": 0.21994859628311586,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998341712443273,
|
||
|
|
"loss": 6.0116,
|
||
|
|
"mean_token_accuracy": 0.14480162858963014,
|
||
|
|
"num_tokens": 5096004.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0386497497558596,
|
||
|
|
"epoch": 0.22044286279161723,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499832813835204,
|
||
|
|
"loss": 6.0258,
|
||
|
|
"mean_token_accuracy": 0.14188448041677476,
|
||
|
|
"num_tokens": 5107171.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038194227218628,
|
||
|
|
"epoch": 0.22093712930011863,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998314508951584,
|
||
|
|
"loss": 5.9714,
|
||
|
|
"mean_token_accuracy": 0.14874040186405182,
|
||
|
|
"num_tokens": 5119249.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014321422576904,
|
||
|
|
"epoch": 0.22143139580862,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998300824242244,
|
||
|
|
"loss": 5.9818,
|
||
|
|
"mean_token_accuracy": 0.14201819226145745,
|
||
|
|
"num_tokens": 5130798.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.15811128616333,
|
||
|
|
"epoch": 0.22192566231712138,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004998287084224353,
|
||
|
|
"loss": 6.1526,
|
||
|
|
"mean_token_accuracy": 0.12994178161025047,
|
||
|
|
"num_tokens": 5141376.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973361825942993,
|
||
|
|
"epoch": 0.22241992882562278,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004998273288898252,
|
||
|
|
"loss": 5.9432,
|
||
|
|
"mean_token_accuracy": 0.14647954925894738,
|
||
|
|
"num_tokens": 5152888.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027700901031494,
|
||
|
|
"epoch": 0.22291419533412415,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499825943826428,
|
||
|
|
"loss": 6.0566,
|
||
|
|
"mean_token_accuracy": 0.1389557845890522,
|
||
|
|
"num_tokens": 5165720.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031054973602295,
|
||
|
|
"epoch": 0.22340846184262556,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998245532322776,
|
||
|
|
"loss": 5.9101,
|
||
|
|
"mean_token_accuracy": 0.15394312962889672,
|
||
|
|
"num_tokens": 5177345.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.022589492797851,
|
||
|
|
"epoch": 0.22390272835112693,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004998231571074083,
|
||
|
|
"loss": 5.9495,
|
||
|
|
"mean_token_accuracy": 0.14755924567580223,
|
||
|
|
"num_tokens": 5187385.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068315124511718,
|
||
|
|
"epoch": 0.2243969948596283,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998217554518545,
|
||
|
|
"loss": 6.0572,
|
||
|
|
"mean_token_accuracy": 0.1392125703394413,
|
||
|
|
"num_tokens": 5199552.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0350470542907715,
|
||
|
|
"epoch": 0.2248912613681297,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998203482656507,
|
||
|
|
"loss": 6.0283,
|
||
|
|
"mean_token_accuracy": 0.14803602397441865,
|
||
|
|
"num_tokens": 5210316.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048583602905273,
|
||
|
|
"epoch": 0.22538552787663108,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998189355488314,
|
||
|
|
"loss": 6.0954,
|
||
|
|
"mean_token_accuracy": 0.14758584052324294,
|
||
|
|
"num_tokens": 5221595.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120372581481933,
|
||
|
|
"epoch": 0.22587979438513248,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998175173014313,
|
||
|
|
"loss": 6.0551,
|
||
|
|
"mean_token_accuracy": 0.14053108245134355,
|
||
|
|
"num_tokens": 5232882.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.132087659835816,
|
||
|
|
"epoch": 0.22637406089363385,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998160935234857,
|
||
|
|
"loss": 6.152,
|
||
|
|
"mean_token_accuracy": 0.13917720541357995,
|
||
|
|
"num_tokens": 5244841.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063738393783569,
|
||
|
|
"epoch": 0.22686832740213522,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499814664215029,
|
||
|
|
"loss": 5.9704,
|
||
|
|
"mean_token_accuracy": 0.1481175698339939,
|
||
|
|
"num_tokens": 5256162.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983815002441406,
|
||
|
|
"epoch": 0.22736259391063662,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004998132293760968,
|
||
|
|
"loss": 5.898,
|
||
|
|
"mean_token_accuracy": 0.1525217816233635,
|
||
|
|
"num_tokens": 5267130.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939467334747315,
|
||
|
|
"epoch": 0.227856860419138,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998117890067243,
|
||
|
|
"loss": 6.0079,
|
||
|
|
"mean_token_accuracy": 0.14762039110064507,
|
||
|
|
"num_tokens": 5279394.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.013275957107544,
|
||
|
|
"epoch": 0.22835112692763937,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998103431069469,
|
||
|
|
"loss": 5.9937,
|
||
|
|
"mean_token_accuracy": 0.15029912441968918,
|
||
|
|
"num_tokens": 5291068.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.081356239318848,
|
||
|
|
"epoch": 0.22884539343614077,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998088916768002,
|
||
|
|
"loss": 5.9548,
|
||
|
|
"mean_token_accuracy": 0.15199253410100938,
|
||
|
|
"num_tokens": 5300924.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993150043487549,
|
||
|
|
"epoch": 0.22933965994464214,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998074347163199,
|
||
|
|
"loss": 5.9399,
|
||
|
|
"mean_token_accuracy": 0.1527443841099739,
|
||
|
|
"num_tokens": 5311998.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032688617706299,
|
||
|
|
"epoch": 0.22983392645314354,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998059722255418,
|
||
|
|
"loss": 5.9924,
|
||
|
|
"mean_token_accuracy": 0.14725389033555986,
|
||
|
|
"num_tokens": 5322163.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007277011871338,
|
||
|
|
"epoch": 0.23032819296164492,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998045042045019,
|
||
|
|
"loss": 5.9906,
|
||
|
|
"mean_token_accuracy": 0.1542594239115715,
|
||
|
|
"num_tokens": 5331638.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072580623626709,
|
||
|
|
"epoch": 0.2308224594701463,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998030306532363,
|
||
|
|
"loss": 5.986,
|
||
|
|
"mean_token_accuracy": 0.1526090383529663,
|
||
|
|
"num_tokens": 5342399.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.028491258621216,
|
||
|
|
"epoch": 0.2313167259786477,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998015515717813,
|
||
|
|
"loss": 6.0566,
|
||
|
|
"mean_token_accuracy": 0.14529409930109977,
|
||
|
|
"num_tokens": 5353481.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0241279125213625,
|
||
|
|
"epoch": 0.23181099248714906,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998000669601733,
|
||
|
|
"loss": 5.9732,
|
||
|
|
"mean_token_accuracy": 0.14455975815653802,
|
||
|
|
"num_tokens": 5365167.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98075385093689,
|
||
|
|
"epoch": 0.23230525899565047,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004997985768184488,
|
||
|
|
"loss": 5.9851,
|
||
|
|
"mean_token_accuracy": 0.1466409333050251,
|
||
|
|
"num_tokens": 5375809.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963445615768433,
|
||
|
|
"epoch": 0.23279952550415184,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004997970811466443,
|
||
|
|
"loss": 5.906,
|
||
|
|
"mean_token_accuracy": 0.1537403479218483,
|
||
|
|
"num_tokens": 5387372.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1771141529083256,
|
||
|
|
"epoch": 0.2332937920126532,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997955799447969,
|
||
|
|
"loss": 6.0804,
|
||
|
|
"mean_token_accuracy": 0.1352565936744213,
|
||
|
|
"num_tokens": 5399210.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.964342451095581,
|
||
|
|
"epoch": 0.2337880585211546,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997940732129432,
|
||
|
|
"loss": 6.0112,
|
||
|
|
"mean_token_accuracy": 0.14232615232467652,
|
||
|
|
"num_tokens": 5410969.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003983497619629,
|
||
|
|
"epoch": 0.23428232502965599,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997925609511205,
|
||
|
|
"loss": 5.9666,
|
||
|
|
"mean_token_accuracy": 0.15019387900829315,
|
||
|
|
"num_tokens": 5422569.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0198101043701175,
|
||
|
|
"epoch": 0.2347765915381574,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997910431593659,
|
||
|
|
"loss": 5.9505,
|
||
|
|
"mean_token_accuracy": 0.15176005214452742,
|
||
|
|
"num_tokens": 5434592.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0387218475341795,
|
||
|
|
"epoch": 0.23527085804665876,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997895198377168,
|
||
|
|
"loss": 6.0366,
|
||
|
|
"mean_token_accuracy": 0.14615647867321968,
|
||
|
|
"num_tokens": 5446525.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019752073287964,
|
||
|
|
"epoch": 0.23576512455516013,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997879909862105,
|
||
|
|
"loss": 6.0301,
|
||
|
|
"mean_token_accuracy": 0.14742079228162766,
|
||
|
|
"num_tokens": 5457327.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120648956298828,
|
||
|
|
"epoch": 0.23625939106366153,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499786456604885,
|
||
|
|
"loss": 6.0541,
|
||
|
|
"mean_token_accuracy": 0.1368759371340275,
|
||
|
|
"num_tokens": 5468533.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95186448097229,
|
||
|
|
"epoch": 0.2367536575721629,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997849166937776,
|
||
|
|
"loss": 5.9333,
|
||
|
|
"mean_token_accuracy": 0.14826373681426047,
|
||
|
|
"num_tokens": 5480652.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061347103118896,
|
||
|
|
"epoch": 0.2372479240806643,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997833712529265,
|
||
|
|
"loss": 5.9805,
|
||
|
|
"mean_token_accuracy": 0.14440520107746124,
|
||
|
|
"num_tokens": 5491446.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924786996841431,
|
||
|
|
"epoch": 0.23774219058916568,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997818202823695,
|
||
|
|
"loss": 5.9826,
|
||
|
|
"mean_token_accuracy": 0.15192526578903198,
|
||
|
|
"num_tokens": 5502886.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090293073654175,
|
||
|
|
"epoch": 0.23823645709766705,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997802637821449,
|
||
|
|
"loss": 6.0118,
|
||
|
|
"mean_token_accuracy": 0.14142660200595855,
|
||
|
|
"num_tokens": 5514305.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993340682983399,
|
||
|
|
"epoch": 0.23873072360616845,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997787017522909,
|
||
|
|
"loss": 5.9357,
|
||
|
|
"mean_token_accuracy": 0.1537352740764618,
|
||
|
|
"num_tokens": 5525913.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.851289081573486,
|
||
|
|
"epoch": 0.23922499011466983,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997771341928459,
|
||
|
|
"loss": 5.927,
|
||
|
|
"mean_token_accuracy": 0.155362518876791,
|
||
|
|
"num_tokens": 5537069.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976904964447021,
|
||
|
|
"epoch": 0.2397192566231712,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997755611038487,
|
||
|
|
"loss": 6.0364,
|
||
|
|
"mean_token_accuracy": 0.14183334335684777,
|
||
|
|
"num_tokens": 5547988.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.145206165313721,
|
||
|
|
"epoch": 0.2402135231316726,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997739824853378,
|
||
|
|
"loss": 6.1045,
|
||
|
|
"mean_token_accuracy": 0.1407170847058296,
|
||
|
|
"num_tokens": 5560400.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976816606521607,
|
||
|
|
"epoch": 0.24070778964017397,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997723983373519,
|
||
|
|
"loss": 5.955,
|
||
|
|
"mean_token_accuracy": 0.1523662328720093,
|
||
|
|
"num_tokens": 5572291.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068643808364868,
|
||
|
|
"epoch": 0.24120205614867538,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997708086599303,
|
||
|
|
"loss": 5.9698,
|
||
|
|
"mean_token_accuracy": 0.14599963128566742,
|
||
|
|
"num_tokens": 5583583.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1259246349334715,
|
||
|
|
"epoch": 0.24169632265717675,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997692134531119,
|
||
|
|
"loss": 6.0095,
|
||
|
|
"mean_token_accuracy": 0.14188680574297904,
|
||
|
|
"num_tokens": 5595499.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951526737213134,
|
||
|
|
"epoch": 0.24219058916567812,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499767612716936,
|
||
|
|
"loss": 5.9391,
|
||
|
|
"mean_token_accuracy": 0.1545530304312706,
|
||
|
|
"num_tokens": 5606745.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952944898605347,
|
||
|
|
"epoch": 0.24268485567417952,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004997660064514419,
|
||
|
|
"loss": 6.0191,
|
||
|
|
"mean_token_accuracy": 0.14769974946975709,
|
||
|
|
"num_tokens": 5618226.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157197761535644,
|
||
|
|
"epoch": 0.2431791221826809,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997643946566691,
|
||
|
|
"loss": 6.0315,
|
||
|
|
"mean_token_accuracy": 0.1460500955581665,
|
||
|
|
"num_tokens": 5628941.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916741037368775,
|
||
|
|
"epoch": 0.2436733886911823,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997627773326574,
|
||
|
|
"loss": 5.8343,
|
||
|
|
"mean_token_accuracy": 0.1558911144733429,
|
||
|
|
"num_tokens": 5641077.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01477689743042,
|
||
|
|
"epoch": 0.24416765519968367,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004997611544794465,
|
||
|
|
"loss": 6.1393,
|
||
|
|
"mean_token_accuracy": 0.13928801268339158,
|
||
|
|
"num_tokens": 5652156.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163790941238403,
|
||
|
|
"epoch": 0.24466192170818504,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997595260970764,
|
||
|
|
"loss": 6.0775,
|
||
|
|
"mean_token_accuracy": 0.14202985018491746,
|
||
|
|
"num_tokens": 5663988.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9817280769348145,
|
||
|
|
"epoch": 0.24515618821668644,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.000499757892185587,
|
||
|
|
"loss": 5.9921,
|
||
|
|
"mean_token_accuracy": 0.14620494544506074,
|
||
|
|
"num_tokens": 5676302.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.063017749786377,
|
||
|
|
"epoch": 0.24565045472518782,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997562527450187,
|
||
|
|
"loss": 6.033,
|
||
|
|
"mean_token_accuracy": 0.14422825276851653,
|
||
|
|
"num_tokens": 5686686.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991397285461426,
|
||
|
|
"epoch": 0.24614472123368922,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997546077754116,
|
||
|
|
"loss": 5.9403,
|
||
|
|
"mean_token_accuracy": 0.16051050424575805,
|
||
|
|
"num_tokens": 5698379.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992690753936768,
|
||
|
|
"epoch": 0.2466389877421906,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997529572768063,
|
||
|
|
"loss": 5.9391,
|
||
|
|
"mean_token_accuracy": 0.14876208752393721,
|
||
|
|
"num_tokens": 5708891.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952452564239502,
|
||
|
|
"epoch": 0.24713325425069196,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004997513012492434,
|
||
|
|
"loss": 5.9863,
|
||
|
|
"mean_token_accuracy": 0.1444184496998787,
|
||
|
|
"num_tokens": 5720326.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.040128898620606,
|
||
|
|
"epoch": 0.24762752075919336,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997496396927636,
|
||
|
|
"loss": 5.9179,
|
||
|
|
"mean_token_accuracy": 0.15258342027664185,
|
||
|
|
"num_tokens": 5731121.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.035462713241577,
|
||
|
|
"epoch": 0.24812178726769474,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997479726074077,
|
||
|
|
"loss": 5.9641,
|
||
|
|
"mean_token_accuracy": 0.14694138541817664,
|
||
|
|
"num_tokens": 5741637.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0350688934326175,
|
||
|
|
"epoch": 0.24861605377619614,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499746299993217,
|
||
|
|
"loss": 6.0015,
|
||
|
|
"mean_token_accuracy": 0.14862585216760635,
|
||
|
|
"num_tokens": 5752659.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005650043487549,
|
||
|
|
"epoch": 0.2491103202846975,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004997446218502324,
|
||
|
|
"loss": 5.9734,
|
||
|
|
"mean_token_accuracy": 0.14695398658514022,
|
||
|
|
"num_tokens": 5763829.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100779962539673,
|
||
|
|
"epoch": 0.24960458679319888,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997429381784952,
|
||
|
|
"loss": 6.0532,
|
||
|
|
"mean_token_accuracy": 0.14432904571294786,
|
||
|
|
"num_tokens": 5775848.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9548462390899655,
|
||
|
|
"epoch": 0.2500988533017003,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004997412489780469,
|
||
|
|
"loss": 5.9821,
|
||
|
|
"mean_token_accuracy": 0.15172261595726014,
|
||
|
|
"num_tokens": 5786595.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969020795822144,
|
||
|
|
"epoch": 0.25059311981020166,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499739554248929,
|
||
|
|
"loss": 5.8878,
|
||
|
|
"mean_token_accuracy": 0.1573539599776268,
|
||
|
|
"num_tokens": 5797841.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932478904724121,
|
||
|
|
"epoch": 0.25108738631870303,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997378539911832,
|
||
|
|
"loss": 5.9079,
|
||
|
|
"mean_token_accuracy": 0.1543175220489502,
|
||
|
|
"num_tokens": 5809106.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974126529693604,
|
||
|
|
"epoch": 0.2515816528272044,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004997361482048513,
|
||
|
|
"loss": 5.9168,
|
||
|
|
"mean_token_accuracy": 0.15173292234539987,
|
||
|
|
"num_tokens": 5820316.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.029713773727417,
|
||
|
|
"epoch": 0.25207591933570583,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997344368899753,
|
||
|
|
"loss": 6.0299,
|
||
|
|
"mean_token_accuracy": 0.14046320617198943,
|
||
|
|
"num_tokens": 5833137.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.029439783096313,
|
||
|
|
"epoch": 0.2525701858442072,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997327200465972,
|
||
|
|
"loss": 5.9495,
|
||
|
|
"mean_token_accuracy": 0.14631350934505463,
|
||
|
|
"num_tokens": 5844088.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044297885894776,
|
||
|
|
"epoch": 0.2530644523527086,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997309976747594,
|
||
|
|
"loss": 5.9573,
|
||
|
|
"mean_token_accuracy": 0.14688198566436766,
|
||
|
|
"num_tokens": 5854546.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021563720703125,
|
||
|
|
"epoch": 0.25355871886120995,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004997292697745042,
|
||
|
|
"loss": 5.9678,
|
||
|
|
"mean_token_accuracy": 0.1491776056587696,
|
||
|
|
"num_tokens": 5865326.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.958045911788941,
|
||
|
|
"epoch": 0.2540529853697113,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997275363458741,
|
||
|
|
"loss": 5.8473,
|
||
|
|
"mean_token_accuracy": 0.15538029223680497,
|
||
|
|
"num_tokens": 5876487.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.87638292312622,
|
||
|
|
"epoch": 0.25454725187821275,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997257973889118,
|
||
|
|
"loss": 5.9644,
|
||
|
|
"mean_token_accuracy": 0.1473582237958908,
|
||
|
|
"num_tokens": 5887846.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070141983032227,
|
||
|
|
"epoch": 0.25504151838671413,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997240529036599,
|
||
|
|
"loss": 5.9291,
|
||
|
|
"mean_token_accuracy": 0.15152573585510254,
|
||
|
|
"num_tokens": 5898572.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943347215652466,
|
||
|
|
"epoch": 0.2555357848952155,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997223028901615,
|
||
|
|
"loss": 5.9881,
|
||
|
|
"mean_token_accuracy": 0.147307687997818,
|
||
|
|
"num_tokens": 5908927.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011348485946655,
|
||
|
|
"epoch": 0.2560300514037169,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997205473484596,
|
||
|
|
"loss": 5.9445,
|
||
|
|
"mean_token_accuracy": 0.15191105753183365,
|
||
|
|
"num_tokens": 5919807.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907250547409058,
|
||
|
|
"epoch": 0.25652431791221825,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997187862785974,
|
||
|
|
"loss": 5.9658,
|
||
|
|
"mean_token_accuracy": 0.1462295152246952,
|
||
|
|
"num_tokens": 5931160.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10115385055542,
|
||
|
|
"epoch": 0.2570185844207197,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004997170196806181,
|
||
|
|
"loss": 6.0318,
|
||
|
|
"mean_token_accuracy": 0.1433812215924263,
|
||
|
|
"num_tokens": 5943694.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997008323669434,
|
||
|
|
"epoch": 0.25751285092922105,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997152475545652,
|
||
|
|
"loss": 5.9217,
|
||
|
|
"mean_token_accuracy": 0.15245338678359985,
|
||
|
|
"num_tokens": 5954543.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928089141845703,
|
||
|
|
"epoch": 0.2580071174377224,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997134699004825,
|
||
|
|
"loss": 5.9711,
|
||
|
|
"mean_token_accuracy": 0.15140919685363768,
|
||
|
|
"num_tokens": 5965080.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.030034875869751,
|
||
|
|
"epoch": 0.2585013839462238,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997116867184136,
|
||
|
|
"loss": 5.9596,
|
||
|
|
"mean_token_accuracy": 0.14527809023857116,
|
||
|
|
"num_tokens": 5975314.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075863838195801,
|
||
|
|
"epoch": 0.25899565045472517,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997098980084022,
|
||
|
|
"loss": 5.9608,
|
||
|
|
"mean_token_accuracy": 0.15068442970514298,
|
||
|
|
"num_tokens": 5985927.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970658540725708,
|
||
|
|
"epoch": 0.2594899169632266,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004997081037704926,
|
||
|
|
"loss": 5.9918,
|
||
|
|
"mean_token_accuracy": 0.1449235573410988,
|
||
|
|
"num_tokens": 5997311.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985719108581543,
|
||
|
|
"epoch": 0.25998418347172797,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997063040047288,
|
||
|
|
"loss": 6.0031,
|
||
|
|
"mean_token_accuracy": 0.14268471747636796,
|
||
|
|
"num_tokens": 6008595.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088737916946411,
|
||
|
|
"epoch": 0.26047844998022934,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004997044987111548,
|
||
|
|
"loss": 5.922,
|
||
|
|
"mean_token_accuracy": 0.15082555562257766,
|
||
|
|
"num_tokens": 6019055.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966479921340943,
|
||
|
|
"epoch": 0.2609727164887307,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997026878898155,
|
||
|
|
"loss": 6.0759,
|
||
|
|
"mean_token_accuracy": 0.14157000482082366,
|
||
|
|
"num_tokens": 6030029.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052847242355346,
|
||
|
|
"epoch": 0.2614669829972321,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997008715407552,
|
||
|
|
"loss": 5.9986,
|
||
|
|
"mean_token_accuracy": 0.14628120064735411,
|
||
|
|
"num_tokens": 6041495.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003971576690674,
|
||
|
|
"epoch": 0.2619612495057335,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996990496640185,
|
||
|
|
"loss": 5.9248,
|
||
|
|
"mean_token_accuracy": 0.145329150557518,
|
||
|
|
"num_tokens": 6052307.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980241584777832,
|
||
|
|
"epoch": 0.2624555160142349,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004996972222596505,
|
||
|
|
"loss": 5.8715,
|
||
|
|
"mean_token_accuracy": 0.14947706907987596,
|
||
|
|
"num_tokens": 6062550.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.895832157135009,
|
||
|
|
"epoch": 0.26294978252273626,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004996953893276958,
|
||
|
|
"loss": 5.9181,
|
||
|
|
"mean_token_accuracy": 0.14338184967637063,
|
||
|
|
"num_tokens": 6074450.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935929584503174,
|
||
|
|
"epoch": 0.26344404903123764,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004996935508681997,
|
||
|
|
"loss": 5.946,
|
||
|
|
"mean_token_accuracy": 0.15009101033210753,
|
||
|
|
"num_tokens": 6085749.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.020921468734741,
|
||
|
|
"epoch": 0.263938315539739,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004996917068812075,
|
||
|
|
"loss": 5.8797,
|
||
|
|
"mean_token_accuracy": 0.15113400667905807,
|
||
|
|
"num_tokens": 6096438.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.895879888534546,
|
||
|
|
"epoch": 0.26443258204824044,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996898573667643,
|
||
|
|
"loss": 5.9112,
|
||
|
|
"mean_token_accuracy": 0.14206297248601912,
|
||
|
|
"num_tokens": 6108386.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9754492282867435,
|
||
|
|
"epoch": 0.2649268485567418,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004996880023249158,
|
||
|
|
"loss": 5.8484,
|
||
|
|
"mean_token_accuracy": 0.15836597830057145,
|
||
|
|
"num_tokens": 6118771.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955278968811035,
|
||
|
|
"epoch": 0.2654211150652432,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996861417557076,
|
||
|
|
"loss": 5.9421,
|
||
|
|
"mean_token_accuracy": 0.14734932035207748,
|
||
|
|
"num_tokens": 6130718.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95388970375061,
|
||
|
|
"epoch": 0.26591538157374456,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004996842756591855,
|
||
|
|
"loss": 5.9554,
|
||
|
|
"mean_token_accuracy": 0.1494845539331436,
|
||
|
|
"num_tokens": 6142086.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938243436813354,
|
||
|
|
"epoch": 0.26640964808224593,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004996824040353953,
|
||
|
|
"loss": 5.9354,
|
||
|
|
"mean_token_accuracy": 0.15002545490860938,
|
||
|
|
"num_tokens": 6153857.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137029409408569,
|
||
|
|
"epoch": 0.2669039145907473,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004996805268843832,
|
||
|
|
"loss": 6.0742,
|
||
|
|
"mean_token_accuracy": 0.14526341632008552,
|
||
|
|
"num_tokens": 6166796.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962703704833984,
|
||
|
|
"epoch": 0.26739818109924873,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004996786442061952,
|
||
|
|
"loss": 5.9051,
|
||
|
|
"mean_token_accuracy": 0.15364588052034378,
|
||
|
|
"num_tokens": 6178046.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966248846054077,
|
||
|
|
"epoch": 0.2678924476077501,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996767560008777,
|
||
|
|
"loss": 5.9462,
|
||
|
|
"mean_token_accuracy": 0.1494138464331627,
|
||
|
|
"num_tokens": 6190455.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.906340456008911,
|
||
|
|
"epoch": 0.2683867141162515,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996748622684771,
|
||
|
|
"loss": 5.844,
|
||
|
|
"mean_token_accuracy": 0.1549997463822365,
|
||
|
|
"num_tokens": 6201659.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938996124267578,
|
||
|
|
"epoch": 0.26888098062475285,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004996729630090401,
|
||
|
|
"loss": 5.9393,
|
||
|
|
"mean_token_accuracy": 0.14477128982543946,
|
||
|
|
"num_tokens": 6213870.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021756029129028,
|
||
|
|
"epoch": 0.2693752471332542,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004996710582226133,
|
||
|
|
"loss": 5.893,
|
||
|
|
"mean_token_accuracy": 0.15294766575098037,
|
||
|
|
"num_tokens": 6224237.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941773462295532,
|
||
|
|
"epoch": 0.26986951364175565,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004996691479092437,
|
||
|
|
"loss": 5.9327,
|
||
|
|
"mean_token_accuracy": 0.15066806226968765,
|
||
|
|
"num_tokens": 6235868.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.996233558654785,
|
||
|
|
"epoch": 0.270363780150257,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996672320689782,
|
||
|
|
"loss": 5.9842,
|
||
|
|
"mean_token_accuracy": 0.14511353448033332,
|
||
|
|
"num_tokens": 6247994.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8160927295684814,
|
||
|
|
"epoch": 0.2708580466587584,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004996653107018638,
|
||
|
|
"loss": 5.8288,
|
||
|
|
"mean_token_accuracy": 0.15872183442115784,
|
||
|
|
"num_tokens": 6259654.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9965247631073,
|
||
|
|
"epoch": 0.2713523131672598,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000499663383807948,
|
||
|
|
"loss": 5.8996,
|
||
|
|
"mean_token_accuracy": 0.15124866664409636,
|
||
|
|
"num_tokens": 6270582.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9945306301116945,
|
||
|
|
"epoch": 0.27184657967576115,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996614513872781,
|
||
|
|
"loss": 5.8936,
|
||
|
|
"mean_token_accuracy": 0.15215572118759155,
|
||
|
|
"num_tokens": 6281088.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010760736465454,
|
||
|
|
"epoch": 0.2723408461842626,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004996595134399017,
|
||
|
|
"loss": 6.0405,
|
||
|
|
"mean_token_accuracy": 0.14413226768374443,
|
||
|
|
"num_tokens": 6292920.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003849840164184,
|
||
|
|
"epoch": 0.27283511269276395,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996575699658664,
|
||
|
|
"loss": 5.9022,
|
||
|
|
"mean_token_accuracy": 0.15507553070783614,
|
||
|
|
"num_tokens": 6304980.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.87095456123352,
|
||
|
|
"epoch": 0.2733293792012653,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996556209652199,
|
||
|
|
"loss": 5.8908,
|
||
|
|
"mean_token_accuracy": 0.15234376043081282,
|
||
|
|
"num_tokens": 6316175.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.022763919830322,
|
||
|
|
"epoch": 0.2738236457097667,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004996536664380104,
|
||
|
|
"loss": 5.9295,
|
||
|
|
"mean_token_accuracy": 0.15449850261211395,
|
||
|
|
"num_tokens": 6327590.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929254007339478,
|
||
|
|
"epoch": 0.27431791221826807,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996517063842859,
|
||
|
|
"loss": 5.9702,
|
||
|
|
"mean_token_accuracy": 0.148074409365654,
|
||
|
|
"num_tokens": 6339066.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97588005065918,
|
||
|
|
"epoch": 0.2748121787267695,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004996497408040944,
|
||
|
|
"loss": 5.8847,
|
||
|
|
"mean_token_accuracy": 0.1522267282009125,
|
||
|
|
"num_tokens": 6349485.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.857022619247436,
|
||
|
|
"epoch": 0.27530644523527087,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004996477696974845,
|
||
|
|
"loss": 5.8515,
|
||
|
|
"mean_token_accuracy": 0.15315285325050354,
|
||
|
|
"num_tokens": 6360775.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924341249465942,
|
||
|
|
"epoch": 0.27580071174377224,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996457930645046,
|
||
|
|
"loss": 5.8797,
|
||
|
|
"mean_token_accuracy": 0.14784021377563478,
|
||
|
|
"num_tokens": 6371645.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961717844009399,
|
||
|
|
"epoch": 0.2762949782522736,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996438109052034,
|
||
|
|
"loss": 5.9057,
|
||
|
|
"mean_token_accuracy": 0.15450873523950576,
|
||
|
|
"num_tokens": 6383877.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938359642028809,
|
||
|
|
"epoch": 0.276789244760775,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004996418232196296,
|
||
|
|
"loss": 5.9717,
|
||
|
|
"mean_token_accuracy": 0.14536341279745102,
|
||
|
|
"num_tokens": 6394488.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965596675872803,
|
||
|
|
"epoch": 0.2772835112692764,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996398300078321,
|
||
|
|
"loss": 5.8937,
|
||
|
|
"mean_token_accuracy": 0.15151161327958107,
|
||
|
|
"num_tokens": 6404948.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985800123214721,
|
||
|
|
"epoch": 0.2777777777777778,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004996378312698598,
|
||
|
|
"loss": 5.9242,
|
||
|
|
"mean_token_accuracy": 0.15609420835971832,
|
||
|
|
"num_tokens": 6416273.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.980525493621826,
|
||
|
|
"epoch": 0.27827204428627916,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004996358270057622,
|
||
|
|
"loss": 5.9467,
|
||
|
|
"mean_token_accuracy": 0.1465024471282959,
|
||
|
|
"num_tokens": 6427091.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935784530639649,
|
||
|
|
"epoch": 0.27876631079478054,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996338172155883,
|
||
|
|
"loss": 5.9,
|
||
|
|
"mean_token_accuracy": 0.1473314046859741,
|
||
|
|
"num_tokens": 6438254.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910728025436401,
|
||
|
|
"epoch": 0.2792605773032819,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996318018993876,
|
||
|
|
"loss": 5.8093,
|
||
|
|
"mean_token_accuracy": 0.154463279992342,
|
||
|
|
"num_tokens": 6450618.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929387474060059,
|
||
|
|
"epoch": 0.27975484381178334,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996297810572098,
|
||
|
|
"loss": 5.8817,
|
||
|
|
"mean_token_accuracy": 0.15034469366073608,
|
||
|
|
"num_tokens": 6462467.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926810073852539,
|
||
|
|
"epoch": 0.2802491103202847,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996277546891045,
|
||
|
|
"loss": 5.8437,
|
||
|
|
"mean_token_accuracy": 0.16171519756317138,
|
||
|
|
"num_tokens": 6474206.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9044997215271,
|
||
|
|
"epoch": 0.2807433768287861,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004996257227951216,
|
||
|
|
"loss": 5.9464,
|
||
|
|
"mean_token_accuracy": 0.14483694285154342,
|
||
|
|
"num_tokens": 6486405.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932437944412231,
|
||
|
|
"epoch": 0.28123764333728746,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499623685375311,
|
||
|
|
"loss": 5.923,
|
||
|
|
"mean_token_accuracy": 0.148922698199749,
|
||
|
|
"num_tokens": 6496949.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9565729141235355,
|
||
|
|
"epoch": 0.28173190984578883,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499621642429723,
|
||
|
|
"loss": 5.863,
|
||
|
|
"mean_token_accuracy": 0.15510103851556778,
|
||
|
|
"num_tokens": 6508913.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917425680160522,
|
||
|
|
"epoch": 0.28222617635429026,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996195939584078,
|
||
|
|
"loss": 5.8928,
|
||
|
|
"mean_token_accuracy": 0.15061276629567147,
|
||
|
|
"num_tokens": 6519837.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975556659698486,
|
||
|
|
"epoch": 0.28272044286279163,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004996175399614156,
|
||
|
|
"loss": 5.8432,
|
||
|
|
"mean_token_accuracy": 0.15526246130466462,
|
||
|
|
"num_tokens": 6531409.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881858968734742,
|
||
|
|
"epoch": 0.283214709371293,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996154804387972,
|
||
|
|
"loss": 5.8993,
|
||
|
|
"mean_token_accuracy": 0.15337033718824386,
|
||
|
|
"num_tokens": 6543433.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934616756439209,
|
||
|
|
"epoch": 0.2837089758797944,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499613415390603,
|
||
|
|
"loss": 5.965,
|
||
|
|
"mean_token_accuracy": 0.14815206974744796,
|
||
|
|
"num_tokens": 6554511.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024463081359864,
|
||
|
|
"epoch": 0.28420324238829575,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499611344816884,
|
||
|
|
"loss": 5.887,
|
||
|
|
"mean_token_accuracy": 0.1526951164007187,
|
||
|
|
"num_tokens": 6564591.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907624053955078,
|
||
|
|
"epoch": 0.2846975088967972,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000499609268717691,
|
||
|
|
"loss": 5.8531,
|
||
|
|
"mean_token_accuracy": 0.15778098329901696,
|
||
|
|
"num_tokens": 6575684.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987070751190186,
|
||
|
|
"epoch": 0.28519177540529855,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996071870930753,
|
||
|
|
"loss": 6.0029,
|
||
|
|
"mean_token_accuracy": 0.14871793240308762,
|
||
|
|
"num_tokens": 6588504.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.84205117225647,
|
||
|
|
"epoch": 0.2856860419137999,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004996050999430878,
|
||
|
|
"loss": 5.8066,
|
||
|
|
"mean_token_accuracy": 0.15269346982240678,
|
||
|
|
"num_tokens": 6599969.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972145843505859,
|
||
|
|
"epoch": 0.2861803084223013,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004996030072677802,
|
||
|
|
"loss": 5.881,
|
||
|
|
"mean_token_accuracy": 0.15568554848432542,
|
||
|
|
"num_tokens": 6611430.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.903538656234741,
|
||
|
|
"epoch": 0.2866745749308027,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004996009090672037,
|
||
|
|
"loss": 5.8829,
|
||
|
|
"mean_token_accuracy": 0.14915536642074584,
|
||
|
|
"num_tokens": 6623247.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922404146194458,
|
||
|
|
"epoch": 0.28716884143930405,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004995988053414098,
|
||
|
|
"loss": 6.0124,
|
||
|
|
"mean_token_accuracy": 0.1436807170510292,
|
||
|
|
"num_tokens": 6635508.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928386068344116,
|
||
|
|
"epoch": 0.2876631079478055,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004995966960904506,
|
||
|
|
"loss": 5.9045,
|
||
|
|
"mean_token_accuracy": 0.15161576271057128,
|
||
|
|
"num_tokens": 6646020.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991296815872192,
|
||
|
|
"epoch": 0.28815737445630685,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004995945813143778,
|
||
|
|
"loss": 5.9453,
|
||
|
|
"mean_token_accuracy": 0.14310827925801278,
|
||
|
|
"num_tokens": 6658194.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920190143585205,
|
||
|
|
"epoch": 0.2886516409648082,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004995924610132435,
|
||
|
|
"loss": 5.9082,
|
||
|
|
"mean_token_accuracy": 0.15037593692541124,
|
||
|
|
"num_tokens": 6670582.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.909224367141723,
|
||
|
|
"epoch": 0.2891459074733096,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995903351870998,
|
||
|
|
"loss": 5.8579,
|
||
|
|
"mean_token_accuracy": 0.15290144979953765,
|
||
|
|
"num_tokens": 6680836.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.069664573669433,
|
||
|
|
"epoch": 0.28964017398181097,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000499588203835999,
|
||
|
|
"loss": 5.951,
|
||
|
|
"mean_token_accuracy": 0.14863116592168807,
|
||
|
|
"num_tokens": 6693045.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917825651168823,
|
||
|
|
"epoch": 0.2901344404903124,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004995860669599935,
|
||
|
|
"loss": 5.9023,
|
||
|
|
"mean_token_accuracy": 0.14530773907899858,
|
||
|
|
"num_tokens": 6704006.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.847810173034668,
|
||
|
|
"epoch": 0.29062870699881377,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499583924559136,
|
||
|
|
"loss": 5.8625,
|
||
|
|
"mean_token_accuracy": 0.15067874863743783,
|
||
|
|
"num_tokens": 6717027.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.972024059295654,
|
||
|
|
"epoch": 0.29112297350731514,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000499581776633479,
|
||
|
|
"loss": 5.8631,
|
||
|
|
"mean_token_accuracy": 0.1507817655801773,
|
||
|
|
"num_tokens": 6728107.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.884723329544068,
|
||
|
|
"epoch": 0.2916172400158165,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004995796231830756,
|
||
|
|
"loss": 5.8867,
|
||
|
|
"mean_token_accuracy": 0.15070785731077194,
|
||
|
|
"num_tokens": 6738628.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.934596347808838,
|
||
|
|
"epoch": 0.2921115065243179,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004995774642079786,
|
||
|
|
"loss": 5.8212,
|
||
|
|
"mean_token_accuracy": 0.15888403803110124,
|
||
|
|
"num_tokens": 6749416.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9203996658325195,
|
||
|
|
"epoch": 0.2926057730328193,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000499575299708241,
|
||
|
|
"loss": 5.9282,
|
||
|
|
"mean_token_accuracy": 0.14471902549266816,
|
||
|
|
"num_tokens": 6761663.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951605176925659,
|
||
|
|
"epoch": 0.2931000395413207,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004995731296839163,
|
||
|
|
"loss": 5.8733,
|
||
|
|
"mean_token_accuracy": 0.15479613989591598,
|
||
|
|
"num_tokens": 6773557.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780427742004394,
|
||
|
|
"epoch": 0.29359430604982206,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995709541350578,
|
||
|
|
"loss": 5.8109,
|
||
|
|
"mean_token_accuracy": 0.16143585443496705,
|
||
|
|
"num_tokens": 6782832.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95885968208313,
|
||
|
|
"epoch": 0.29408857255832344,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499568773061719,
|
||
|
|
"loss": 5.9063,
|
||
|
|
"mean_token_accuracy": 0.15120915472507476,
|
||
|
|
"num_tokens": 6795165.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0116026401519775,
|
||
|
|
"epoch": 0.2945828390668248,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004995665864639534,
|
||
|
|
"loss": 5.9459,
|
||
|
|
"mean_token_accuracy": 0.15338853895664215,
|
||
|
|
"num_tokens": 6807054.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.834550189971924,
|
||
|
|
"epoch": 0.29507710557532624,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004995643943418149,
|
||
|
|
"loss": 5.718,
|
||
|
|
"mean_token_accuracy": 0.1583849608898163,
|
||
|
|
"num_tokens": 6817681.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.885439348220825,
|
||
|
|
"epoch": 0.2955713720838276,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004995621966953576,
|
||
|
|
"loss": 5.8952,
|
||
|
|
"mean_token_accuracy": 0.15299865156412124,
|
||
|
|
"num_tokens": 6829387.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902294540405274,
|
||
|
|
"epoch": 0.296065638592329,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004995599935246355,
|
||
|
|
"loss": 5.8656,
|
||
|
|
"mean_token_accuracy": 0.15363962203264236,
|
||
|
|
"num_tokens": 6842023.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916921710968017,
|
||
|
|
"epoch": 0.29655990510083036,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004995577848297026,
|
||
|
|
"loss": 5.8835,
|
||
|
|
"mean_token_accuracy": 0.14771389216184616,
|
||
|
|
"num_tokens": 6853189.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.29655990510083036,
|
||
|
|
"eval_entropy": 5.767380985269394,
|
||
|
|
"eval_loss": 5.943864822387695,
|
||
|
|
"eval_mean_token_accuracy": 0.1555859555654127,
|
||
|
|
"eval_num_tokens": 6853189.0,
|
||
|
|
"eval_runtime": 26.8519,
|
||
|
|
"eval_samples_per_second": 1210.826,
|
||
|
|
"eval_steps_per_second": 151.386,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 101150,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1.07246089728e+16,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|