48123 lines
1.3 MiB
48123 lines
1.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.372479240806643,
|
|
"eval_steps": 3000,
|
|
"global_step": 24000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.941728830337524,
|
|
"epoch": 0.29705417160933173,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995555706106134,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.14472154006361962,
|
|
"num_tokens": 6864338.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.924271774291992,
|
|
"epoch": 0.29754843811783316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995533508674223,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.1535579651594162,
|
|
"num_tokens": 6875409.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.885432004928589,
|
|
"epoch": 0.29804270462633453,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995511256001839,
|
|
"loss": 5.8385,
|
|
"mean_token_accuracy": 0.1549509957432747,
|
|
"num_tokens": 6885757.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.900880670547485,
|
|
"epoch": 0.2985369711348359,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499548894808953,
|
|
"loss": 5.9136,
|
|
"mean_token_accuracy": 0.15322157591581345,
|
|
"num_tokens": 6896440.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.984965991973877,
|
|
"epoch": 0.2990312376433373,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995466584937846,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.14928727969527245,
|
|
"num_tokens": 6907319.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.897944688796997,
|
|
"epoch": 0.29952550415183865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995444166547333,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.15314857736229898,
|
|
"num_tokens": 6918683.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.877795934677124,
|
|
"epoch": 0.3000197706603401,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995421692918547,
|
|
"loss": 5.8554,
|
|
"mean_token_accuracy": 0.15081824511289596,
|
|
"num_tokens": 6929974.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.993351888656616,
|
|
"epoch": 0.30051403716884145,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995399164052038,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.1560599312186241,
|
|
"num_tokens": 6941213.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.9789103984832765,
|
|
"epoch": 0.3010083036773428,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995376579948362,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.1490655228495598,
|
|
"num_tokens": 6952880.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.918725919723511,
|
|
"epoch": 0.3015025701858442,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995353940608074,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.15353438258171082,
|
|
"num_tokens": 6964344.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.841410827636719,
|
|
"epoch": 0.30199683669434557,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499533124603173,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.1524859130382538,
|
|
"num_tokens": 6976042.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.898250865936279,
|
|
"epoch": 0.302491103202847,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499530849621989,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.16080887168645858,
|
|
"num_tokens": 6988137.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.851520204544068,
|
|
"epoch": 0.3029853697113484,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995285691173111,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.15679416730999945,
|
|
"num_tokens": 6999858.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.931128454208374,
|
|
"epoch": 0.30347963621984975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995262830891957,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.15451431274414062,
|
|
"num_tokens": 7012756.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.902743005752564,
|
|
"epoch": 0.3039739027283511,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995239915376988,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.14535871669650077,
|
|
"num_tokens": 7024769.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.939968156814575,
|
|
"epoch": 0.3044681692368525,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995216944628769,
|
|
"loss": 5.8974,
|
|
"mean_token_accuracy": 0.14800761342048646,
|
|
"num_tokens": 7035422.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.890863418579102,
|
|
"epoch": 0.3049624357453539,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995193918647865,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.1606992155313492,
|
|
"num_tokens": 7046923.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.998715543746949,
|
|
"epoch": 0.3054567022538553,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995170837434844,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.1498694308102131,
|
|
"num_tokens": 7058241.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.879198217391968,
|
|
"epoch": 0.30595096876235667,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995147700990269,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.15815785378217698,
|
|
"num_tokens": 7070028.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.959123277664185,
|
|
"epoch": 0.30644523527085804,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995124509314714,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.14877841621637344,
|
|
"num_tokens": 7082641.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.89489049911499,
|
|
"epoch": 0.3069395017793594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995101262408748,
|
|
"loss": 5.8809,
|
|
"mean_token_accuracy": 0.1492926746606827,
|
|
"num_tokens": 7094462.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.901105356216431,
|
|
"epoch": 0.3074337682878608,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995077960272943,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.15002985745668412,
|
|
"num_tokens": 7106598.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.837995338439941,
|
|
"epoch": 0.3079280347963622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995054602907871,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.15309320390224457,
|
|
"num_tokens": 7117006.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.834504079818726,
|
|
"epoch": 0.3084223013048636,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995031190314107,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.1503136932849884,
|
|
"num_tokens": 7128071.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.906392431259155,
|
|
"epoch": 0.30891656781336496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995007722492228,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1538877457380295,
|
|
"num_tokens": 7139896.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.838178634643555,
|
|
"epoch": 0.30941083432186633,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994984199442811,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.1608680948615074,
|
|
"num_tokens": 7151479.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.007550811767578,
|
|
"epoch": 0.3099051008303677,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994960621166434,
|
|
"loss": 5.8608,
|
|
"mean_token_accuracy": 0.15519229918718339,
|
|
"num_tokens": 7162942.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.771294021606446,
|
|
"epoch": 0.31039936733886914,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994936987663678,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.16309035569429398,
|
|
"num_tokens": 7174572.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.983310222625732,
|
|
"epoch": 0.3108936338473705,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994913298935124,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.1505669616162777,
|
|
"num_tokens": 7186352.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.8565832614898685,
|
|
"epoch": 0.3113879003558719,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994889554981353,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.1553249478340149,
|
|
"num_tokens": 7197849.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.825970077514649,
|
|
"epoch": 0.31188216686437326,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994865755802953,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.15467593371868132,
|
|
"num_tokens": 7207897.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.961812973022461,
|
|
"epoch": 0.31237643337287463,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994841901400505,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.1542205974459648,
|
|
"num_tokens": 7219148.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.039529848098755,
|
|
"epoch": 0.31287069988137606,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994817991774599,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.13728998899459838,
|
|
"num_tokens": 7230690.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.9867349624633786,
|
|
"epoch": 0.31336496638987743,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994794026925822,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.15264340341091157,
|
|
"num_tokens": 7240935.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.885019731521607,
|
|
"epoch": 0.3138592328983788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994770006854763,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.15242002829909324,
|
|
"num_tokens": 7253345.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.00883846282959,
|
|
"epoch": 0.3143534994068802,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994745931562015,
|
|
"loss": 5.9152,
|
|
"mean_token_accuracy": 0.15274256765842437,
|
|
"num_tokens": 7265355.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.781323051452636,
|
|
"epoch": 0.31484776591538155,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994721801048168,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.15737686455249786,
|
|
"num_tokens": 7277355.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.907363510131836,
|
|
"epoch": 0.315342032423883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994697615313817,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.15245499312877656,
|
|
"num_tokens": 7288754.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.992982864379883,
|
|
"epoch": 0.31583629893238435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994673374359556,
|
|
"loss": 5.9404,
|
|
"mean_token_accuracy": 0.1448553428053856,
|
|
"num_tokens": 7301158.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.910148286819458,
|
|
"epoch": 0.3163305654408857,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994649078185982,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.14837377592921258,
|
|
"num_tokens": 7314420.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.890511560440063,
|
|
"epoch": 0.3168248319493871,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994624726793693,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.1511936292052269,
|
|
"num_tokens": 7325459.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.913376188278198,
|
|
"epoch": 0.31731909845788847,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994600320183286,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.1497473254799843,
|
|
"num_tokens": 7336016.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.8314368724823,
|
|
"epoch": 0.3178133649663899,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994575858355364,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.1572605401277542,
|
|
"num_tokens": 7346716.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.981982803344726,
|
|
"epoch": 0.3183076314748913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994551341310526,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.14895788654685022,
|
|
"num_tokens": 7357246.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.957204103469849,
|
|
"epoch": 0.31880189798339265,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994526769049379,
|
|
"loss": 5.9513,
|
|
"mean_token_accuracy": 0.14142561778426171,
|
|
"num_tokens": 7369173.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.98886661529541,
|
|
"epoch": 0.319296164491894,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994502141572524,
|
|
"loss": 5.9243,
|
|
"mean_token_accuracy": 0.1421774610877037,
|
|
"num_tokens": 7381118.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.851865005493164,
|
|
"epoch": 0.3197904310003954,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994477458880568,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.15489398539066315,
|
|
"num_tokens": 7391874.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.857757806777954,
|
|
"epoch": 0.3202846975088968,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994452720974119,
|
|
"loss": 5.858,
|
|
"mean_token_accuracy": 0.16053914725780488,
|
|
"num_tokens": 7403474.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.889669609069824,
|
|
"epoch": 0.3207789640173982,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994427927853785,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.15908098816871644,
|
|
"num_tokens": 7415173.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.833272552490234,
|
|
"epoch": 0.32127323052589957,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994403079520175,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.154155196249485,
|
|
"num_tokens": 7426965.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.866478157043457,
|
|
"epoch": 0.32176749703440094,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994378175973902,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.15770491510629653,
|
|
"num_tokens": 7438162.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.854317283630371,
|
|
"epoch": 0.3222617635429023,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994353217215577,
|
|
"loss": 5.8665,
|
|
"mean_token_accuracy": 0.14918979927897452,
|
|
"num_tokens": 7450241.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.008141946792603,
|
|
"epoch": 0.32275603005140374,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994328203245814,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.14616363793611525,
|
|
"num_tokens": 7462236.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.9597837924957275,
|
|
"epoch": 0.3232502965599051,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994303134065231,
|
|
"loss": 5.8484,
|
|
"mean_token_accuracy": 0.15048831403255464,
|
|
"num_tokens": 7472811.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.759082984924317,
|
|
"epoch": 0.3237445630684065,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994278009674442,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.1658716917037964,
|
|
"num_tokens": 7484837.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.967455244064331,
|
|
"epoch": 0.32423882957690786,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994252830074064,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.1491083323955536,
|
|
"num_tokens": 7496712.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.823682641983032,
|
|
"epoch": 0.32473309608540923,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499422759526472,
|
|
"loss": 5.8691,
|
|
"mean_token_accuracy": 0.15019640177488328,
|
|
"num_tokens": 7508014.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.9390296459198,
|
|
"epoch": 0.32522736259391066,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994202305247029,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.15077922493219376,
|
|
"num_tokens": 7519466.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.046651697158813,
|
|
"epoch": 0.32572162910241204,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994176960021613,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.14533828049898148,
|
|
"num_tokens": 7531661.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.883288049697876,
|
|
"epoch": 0.3262158956109134,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994151559589095,
|
|
"loss": 5.8637,
|
|
"mean_token_accuracy": 0.14735180884599686,
|
|
"num_tokens": 7544096.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.8945191383361815,
|
|
"epoch": 0.3267101621194148,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994126103950101,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.15424130111932755,
|
|
"num_tokens": 7556022.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.917681932449341,
|
|
"epoch": 0.32720442862791616,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994100593105257,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.16104441434144973,
|
|
"num_tokens": 7567399.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.825264310836792,
|
|
"epoch": 0.3276986951364176,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994075027055189,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.1534079447388649,
|
|
"num_tokens": 7580673.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.949448728561402,
|
|
"epoch": 0.32819296164491896,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994049405800529,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.15269462168216705,
|
|
"num_tokens": 7591799.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.915449619293213,
|
|
"epoch": 0.32868722815342033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994023729341904,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.15147226452827453,
|
|
"num_tokens": 7603663.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.852406072616577,
|
|
"epoch": 0.3291814946619217,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993997997679949,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.1594110384583473,
|
|
"num_tokens": 7615651.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.771063375473022,
|
|
"epoch": 0.3296757611704231,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993972210815292,
|
|
"loss": 5.8231,
|
|
"mean_token_accuracy": 0.16265821754932402,
|
|
"num_tokens": 7628033.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.029174518585205,
|
|
"epoch": 0.33017002767892445,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993946368748573,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.15178661793470383,
|
|
"num_tokens": 7640227.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.9302881240844725,
|
|
"epoch": 0.3306642941874259,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993920471480424,
|
|
"loss": 5.825,
|
|
"mean_token_accuracy": 0.1560687780380249,
|
|
"num_tokens": 7651684.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.905597257614136,
|
|
"epoch": 0.33115856069592725,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993894519011484,
|
|
"loss": 5.8677,
|
|
"mean_token_accuracy": 0.15230380296707152,
|
|
"num_tokens": 7662721.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.887778663635254,
|
|
"epoch": 0.3316528272044286,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993868511342391,
|
|
"loss": 5.8277,
|
|
"mean_token_accuracy": 0.15545755326747895,
|
|
"num_tokens": 7674060.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.8394380569458,
|
|
"epoch": 0.33214709371293,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993842448473783,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.15769010037183762,
|
|
"num_tokens": 7685054.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.923034238815307,
|
|
"epoch": 0.33264136022143137,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993816330406304,
|
|
"loss": 5.9015,
|
|
"mean_token_accuracy": 0.14595306515693665,
|
|
"num_tokens": 7696554.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.918173456192017,
|
|
"epoch": 0.3331356267299328,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993790157140595,
|
|
"loss": 5.7644,
|
|
"mean_token_accuracy": 0.15410953015089035,
|
|
"num_tokens": 7707000.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.899510145187378,
|
|
"epoch": 0.33362989323843417,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993763928677299,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.15338640213012694,
|
|
"num_tokens": 7718898.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.912793684005737,
|
|
"epoch": 0.33412415974693555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993737645017064,
|
|
"loss": 5.8981,
|
|
"mean_token_accuracy": 0.15049479752779008,
|
|
"num_tokens": 7730493.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.861591482162476,
|
|
"epoch": 0.3346184262554369,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993711306160534,
|
|
"loss": 5.7928,
|
|
"mean_token_accuracy": 0.15264424309134483,
|
|
"num_tokens": 7742177.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.903600597381592,
|
|
"epoch": 0.3351126927639383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993684912108358,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.15599142163991928,
|
|
"num_tokens": 7753386.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.826287651062012,
|
|
"epoch": 0.3356069592724397,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993658462861184,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.1573371484875679,
|
|
"num_tokens": 7764259.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.883145761489868,
|
|
"epoch": 0.3361012257809411,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993631958419666,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.16076951324939728,
|
|
"num_tokens": 7775853.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.877940082550049,
|
|
"epoch": 0.33659549228944247,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993605398784451,
|
|
"loss": 5.8913,
|
|
"mean_token_accuracy": 0.14438531473278998,
|
|
"num_tokens": 7787116.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.90986123085022,
|
|
"epoch": 0.33708975879794384,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993578783956198,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.14547135159373284,
|
|
"num_tokens": 7799666.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.890929126739502,
|
|
"epoch": 0.3375840253064452,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993552113935557,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.16242305785417557,
|
|
"num_tokens": 7812454.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.818965673446655,
|
|
"epoch": 0.33807829181494664,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993525388723186,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.15251174420118332,
|
|
"num_tokens": 7824427.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.873156499862671,
|
|
"epoch": 0.338572558323448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993498608319742,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.15613105297088622,
|
|
"num_tokens": 7835382.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.876656866073608,
|
|
"epoch": 0.3390668248319494,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993471772725886,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1595821961760521,
|
|
"num_tokens": 7846618.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.858217859268189,
|
|
"epoch": 0.33956109134045076,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993444881942274,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.15757436901330948,
|
|
"num_tokens": 7859160.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.807432222366333,
|
|
"epoch": 0.34005535784895213,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993417935969572,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.15975862145423889,
|
|
"num_tokens": 7870628.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.929854488372802,
|
|
"epoch": 0.34054962435745356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499339093480844,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.15878143012523652,
|
|
"num_tokens": 7883016.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.847107791900635,
|
|
"epoch": 0.34104389086595494,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993363878459542,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14758880883455278,
|
|
"num_tokens": 7895940.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.929977703094482,
|
|
"epoch": 0.3415381573744563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993336766923546,
|
|
"loss": 5.8772,
|
|
"mean_token_accuracy": 0.15185581892728806,
|
|
"num_tokens": 7907920.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.917331314086914,
|
|
"epoch": 0.3420324238829577,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993309600201117,
|
|
"loss": 5.8713,
|
|
"mean_token_accuracy": 0.15559243634343148,
|
|
"num_tokens": 7920181.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.8601508140563965,
|
|
"epoch": 0.34252669039145905,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993282378292923,
|
|
"loss": 5.8077,
|
|
"mean_token_accuracy": 0.16380880624055863,
|
|
"num_tokens": 7931135.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.8562602519989015,
|
|
"epoch": 0.3430209568999605,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993255101199635,
|
|
"loss": 5.8135,
|
|
"mean_token_accuracy": 0.1568136341869831,
|
|
"num_tokens": 7941002.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.913082456588745,
|
|
"epoch": 0.34351522340846186,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993227768921924,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.15693581849336624,
|
|
"num_tokens": 7950393.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.833450269699097,
|
|
"epoch": 0.34400948991696323,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993200381460461,
|
|
"loss": 5.7888,
|
|
"mean_token_accuracy": 0.1580388590693474,
|
|
"num_tokens": 7961468.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.810800075531006,
|
|
"epoch": 0.3445037564254646,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993172938815922,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16963228583335876,
|
|
"num_tokens": 7973783.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.780912065505982,
|
|
"epoch": 0.344998022933966,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993145440988979,
|
|
"loss": 5.7119,
|
|
"mean_token_accuracy": 0.16313014328479766,
|
|
"num_tokens": 7984099.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.9509059429168705,
|
|
"epoch": 0.3454922894424674,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993117887980311,
|
|
"loss": 5.8542,
|
|
"mean_token_accuracy": 0.15276896506547927,
|
|
"num_tokens": 7995115.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.8740997314453125,
|
|
"epoch": 0.3459865559509688,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993090279790596,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.15205026119947435,
|
|
"num_tokens": 8006103.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.778691911697388,
|
|
"epoch": 0.34648082245947015,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499306261642051,
|
|
"loss": 5.7645,
|
|
"mean_token_accuracy": 0.15258922874927522,
|
|
"num_tokens": 8018228.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.861861801147461,
|
|
"epoch": 0.3469750889679715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993034897870737,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.16017963737249374,
|
|
"num_tokens": 8029808.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.792195177078247,
|
|
"epoch": 0.3474693554764729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993007124141958,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.1510699026286602,
|
|
"num_tokens": 8041136.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.911326551437378,
|
|
"epoch": 0.3479636219849743,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992979295234854,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.15028350055217743,
|
|
"num_tokens": 8053013.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.871226358413696,
|
|
"epoch": 0.3484578884934757,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992951411150112,
|
|
"loss": 5.8396,
|
|
"mean_token_accuracy": 0.1514429286122322,
|
|
"num_tokens": 8065139.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.870586299896241,
|
|
"epoch": 0.34895215500197707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992923471888418,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.16702560633420943,
|
|
"num_tokens": 8075719.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.87115797996521,
|
|
"epoch": 0.34944642151047844,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992895477450459,
|
|
"loss": 5.8332,
|
|
"mean_token_accuracy": 0.15578304529190062,
|
|
"num_tokens": 8087821.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.784120893478393,
|
|
"epoch": 0.3499406880189798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992867427836923,
|
|
"loss": 5.7207,
|
|
"mean_token_accuracy": 0.16107594221830368,
|
|
"num_tokens": 8099861.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.980808734893799,
|
|
"epoch": 0.3504349545274812,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992839323048501,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.14747335836291314,
|
|
"num_tokens": 8111671.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.025852108001709,
|
|
"epoch": 0.3509292210359826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992811163085882,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.15158916562795638,
|
|
"num_tokens": 8123569.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.943529224395752,
|
|
"epoch": 0.351423487544484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992782947949761,
|
|
"loss": 5.9201,
|
|
"mean_token_accuracy": 0.15296451300382613,
|
|
"num_tokens": 8135621.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.8535606384277346,
|
|
"epoch": 0.35191775405298537,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992754677640831,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.15590618997812272,
|
|
"num_tokens": 8147012.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.875855875015259,
|
|
"epoch": 0.35241202056148674,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992726352159789,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.16125949323177338,
|
|
"num_tokens": 8158686.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.809343528747559,
|
|
"epoch": 0.3529062870699881,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992697971507331,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.16253531575202942,
|
|
"num_tokens": 8170188.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.916712617874145,
|
|
"epoch": 0.35340055357848954,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992669535684155,
|
|
"loss": 5.845,
|
|
"mean_token_accuracy": 0.1516784906387329,
|
|
"num_tokens": 8182467.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.9004051208496096,
|
|
"epoch": 0.3538948200869909,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992641044690959,
|
|
"loss": 5.9516,
|
|
"mean_token_accuracy": 0.15347133725881576,
|
|
"num_tokens": 8193433.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.90702543258667,
|
|
"epoch": 0.3543890865954923,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992612498528447,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.1608864337205887,
|
|
"num_tokens": 8204220.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.733348655700683,
|
|
"epoch": 0.35488335310399366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992583897197319,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.16712767481803895,
|
|
"num_tokens": 8214203.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.926308727264404,
|
|
"epoch": 0.35537761961249503,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992555240698279,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.1513360023498535,
|
|
"num_tokens": 8225143.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.865612745285034,
|
|
"epoch": 0.35587188612099646,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992526529032032,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.15890935957431793,
|
|
"num_tokens": 8237715.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.796522569656372,
|
|
"epoch": 0.35636615262949783,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992497762199285,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.16253170371055603,
|
|
"num_tokens": 8249645.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.9066503047943115,
|
|
"epoch": 0.3568604191379992,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992468940200745,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.1625254422426224,
|
|
"num_tokens": 8260624.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.881762313842773,
|
|
"epoch": 0.3573546856465006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992440063037121,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.1510698080062866,
|
|
"num_tokens": 8272526.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.772908687591553,
|
|
"epoch": 0.35784895215500195,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992411130709124,
|
|
"loss": 5.7672,
|
|
"mean_token_accuracy": 0.15798913985490798,
|
|
"num_tokens": 8284270.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.927992677688598,
|
|
"epoch": 0.3583432186635034,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992382143217466,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.155224272608757,
|
|
"num_tokens": 8296407.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.820270538330078,
|
|
"epoch": 0.35883748517200476,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992353100562858,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.16635552942752838,
|
|
"num_tokens": 8307695.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.780315256118774,
|
|
"epoch": 0.35933175168050613,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992324002746016,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.15945776998996736,
|
|
"num_tokens": 8319458.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.846246194839478,
|
|
"epoch": 0.3598260181890075,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992294849767656,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.1644335940480232,
|
|
"num_tokens": 8330284.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.8710369110107425,
|
|
"epoch": 0.3603202846975089,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992265641628495,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.15665259212255478,
|
|
"num_tokens": 8343622.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.8542005062103275,
|
|
"epoch": 0.3608145512060103,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992236378329252,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.15466896295547486,
|
|
"num_tokens": 8354079.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.817864513397216,
|
|
"epoch": 0.3613088177145117,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992207059870645,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.15928452759981154,
|
|
"num_tokens": 8364876.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.903332376480103,
|
|
"epoch": 0.36180308422301305,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992177686253396,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.1597756490111351,
|
|
"num_tokens": 8375095.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.810576248168945,
|
|
"epoch": 0.3622973507315144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499214825747823,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1586653247475624,
|
|
"num_tokens": 8385934.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.8042961120605465,
|
|
"epoch": 0.3627916172400158,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992118773545868,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.16549597829580306,
|
|
"num_tokens": 8397018.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.797084665298462,
|
|
"epoch": 0.3632858837485172,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992089234457036,
|
|
"loss": 5.7777,
|
|
"mean_token_accuracy": 0.16120913326740266,
|
|
"num_tokens": 8406668.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.93126482963562,
|
|
"epoch": 0.3637801502570186,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992059640212461,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.15915808826684952,
|
|
"num_tokens": 8417471.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.813851451873779,
|
|
"epoch": 0.36427441676551997,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992029990812872,
|
|
"loss": 5.8772,
|
|
"mean_token_accuracy": 0.1514885924756527,
|
|
"num_tokens": 8430073.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.880608034133911,
|
|
"epoch": 0.36476868327402134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992000286258997,
|
|
"loss": 5.7869,
|
|
"mean_token_accuracy": 0.1555901736021042,
|
|
"num_tokens": 8442573.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.892967176437378,
|
|
"epoch": 0.3652629497825227,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991970526551567,
|
|
"loss": 5.8245,
|
|
"mean_token_accuracy": 0.15636747181415558,
|
|
"num_tokens": 8453920.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.859745454788208,
|
|
"epoch": 0.36575721629102415,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991940711691314,
|
|
"loss": 5.8759,
|
|
"mean_token_accuracy": 0.15241969227790833,
|
|
"num_tokens": 8466652.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.925513553619385,
|
|
"epoch": 0.3662514827995255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991910841678972,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.1531624436378479,
|
|
"num_tokens": 8480203.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.80959038734436,
|
|
"epoch": 0.3667457493080269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991880916515275,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1566888988018036,
|
|
"num_tokens": 8491396.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.917858362197876,
|
|
"epoch": 0.36724001581652826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499185093620096,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.15452895760536195,
|
|
"num_tokens": 8501838.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.74103364944458,
|
|
"epoch": 0.36773428232502964,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991820900736765,
|
|
"loss": 5.6462,
|
|
"mean_token_accuracy": 0.16674904972314836,
|
|
"num_tokens": 8512113.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.814356470108033,
|
|
"epoch": 0.36822854883353107,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991790810123427,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.158477546274662,
|
|
"num_tokens": 8523888.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.709980535507202,
|
|
"epoch": 0.36872281534203244,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991760664361688,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.17031886726617812,
|
|
"num_tokens": 8536078.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.881398248672485,
|
|
"epoch": 0.3692170818505338,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991730463452288,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.15253925025463105,
|
|
"num_tokens": 8547131.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.834741306304932,
|
|
"epoch": 0.3697113483590352,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991700207395971,
|
|
"loss": 5.6694,
|
|
"mean_token_accuracy": 0.16964461356401445,
|
|
"num_tokens": 8557269.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.914246368408203,
|
|
"epoch": 0.37020561486753656,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991669896193482,
|
|
"loss": 5.8485,
|
|
"mean_token_accuracy": 0.15194341987371446,
|
|
"num_tokens": 8569193.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.824883604049683,
|
|
"epoch": 0.370699881376038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991639529845565,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.16252467632293702,
|
|
"num_tokens": 8580888.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.793751382827759,
|
|
"epoch": 0.37119414788453936,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991609108352968,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.15922664999961852,
|
|
"num_tokens": 8591868.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.821220350265503,
|
|
"epoch": 0.37168841439304073,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991578631716438,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.15707653909921646,
|
|
"num_tokens": 8602338.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.849247789382934,
|
|
"epoch": 0.3721826809015421,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991548099936727,
|
|
"loss": 5.702,
|
|
"mean_token_accuracy": 0.16648323237895965,
|
|
"num_tokens": 8611698.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.777154874801636,
|
|
"epoch": 0.3726769474100435,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991517513014585,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.1603090301156044,
|
|
"num_tokens": 8623537.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.790181875228882,
|
|
"epoch": 0.37317121391854485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991486870950765,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.15842668041586877,
|
|
"num_tokens": 8634678.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.8642578125,
|
|
"epoch": 0.3736654804270463,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991456173746021,
|
|
"loss": 5.7605,
|
|
"mean_token_accuracy": 0.1605370044708252,
|
|
"num_tokens": 8646207.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.909278631210327,
|
|
"epoch": 0.37415974693554765,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991425421401105,
|
|
"loss": 5.8191,
|
|
"mean_token_accuracy": 0.15462346822023393,
|
|
"num_tokens": 8657069.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.700467300415039,
|
|
"epoch": 0.374654013444049,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991394613916777,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.1636354148387909,
|
|
"num_tokens": 8668296.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.811421251296997,
|
|
"epoch": 0.3751482799525504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991363751293795,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.15516011863946916,
|
|
"num_tokens": 8680626.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.895889759063721,
|
|
"epoch": 0.3756425464610518,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991332833532915,
|
|
"loss": 5.7315,
|
|
"mean_token_accuracy": 0.16446105986833573,
|
|
"num_tokens": 8691571.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.8011803150177,
|
|
"epoch": 0.3761368129695532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049913018606349,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.1651549756526947,
|
|
"num_tokens": 8703262.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.897200345993042,
|
|
"epoch": 0.3766310794780546,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991270832600512,
|
|
"loss": 5.8758,
|
|
"mean_token_accuracy": 0.14848244041204453,
|
|
"num_tokens": 8714799.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.923844480514527,
|
|
"epoch": 0.37712534598655595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991239749430514,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.151717808842659,
|
|
"num_tokens": 8726417.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.789443016052246,
|
|
"epoch": 0.3776196124950573,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499120861112567,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.15911877155303955,
|
|
"num_tokens": 8738572.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.971363210678101,
|
|
"epoch": 0.3781138790035587,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991177417686747,
|
|
"loss": 5.9029,
|
|
"mean_token_accuracy": 0.15064865499734878,
|
|
"num_tokens": 8750557.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.821292972564697,
|
|
"epoch": 0.3786081455120601,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991146169114511,
|
|
"loss": 5.6784,
|
|
"mean_token_accuracy": 0.15679405629634857,
|
|
"num_tokens": 8761921.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.702373886108399,
|
|
"epoch": 0.3791024120205615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991114865409732,
|
|
"loss": 5.7624,
|
|
"mean_token_accuracy": 0.1606692612171173,
|
|
"num_tokens": 8772705.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.849508285522461,
|
|
"epoch": 0.37959667852906287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499108350657318,
|
|
"loss": 5.7795,
|
|
"mean_token_accuracy": 0.15726618468761444,
|
|
"num_tokens": 8783563.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.795090913772583,
|
|
"epoch": 0.38009094503756424,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991052092605627,
|
|
"loss": 5.6751,
|
|
"mean_token_accuracy": 0.16537606865167617,
|
|
"num_tokens": 8794171.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.7758220672607425,
|
|
"epoch": 0.3805852115460656,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991020623507842,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.1554715558886528,
|
|
"num_tokens": 8806487.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.860504293441773,
|
|
"epoch": 0.38107947805456704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990989099280604,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.15712819695472718,
|
|
"num_tokens": 8817819.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.856230592727661,
|
|
"epoch": 0.3815737445630684,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990957519924686,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.1554050475358963,
|
|
"num_tokens": 8828485.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.825079774856567,
|
|
"epoch": 0.3820680110715698,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990925885440865,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.15726663023233414,
|
|
"num_tokens": 8840179.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.8790511131286625,
|
|
"epoch": 0.38256227758007116,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990894195829921,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.16634585410356523,
|
|
"num_tokens": 8851813.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.788227510452271,
|
|
"epoch": 0.38305654408857254,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990862451092631,
|
|
"loss": 5.7471,
|
|
"mean_token_accuracy": 0.1537475511431694,
|
|
"num_tokens": 8863072.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.887831783294677,
|
|
"epoch": 0.38355081059707397,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990830651229776,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.16181204468011856,
|
|
"num_tokens": 8873510.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.7546227931976315,
|
|
"epoch": 0.38404507710557534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990798796242142,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.16202120184898378,
|
|
"num_tokens": 8884296.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.77656741142273,
|
|
"epoch": 0.3845393436140767,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990766886130508,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.16052468121051788,
|
|
"num_tokens": 8894208.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.967237949371338,
|
|
"epoch": 0.3850336101225781,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990734920895662,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.15229002386331558,
|
|
"num_tokens": 8905703.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.785888719558716,
|
|
"epoch": 0.38552787663107946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990702900538388,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.15727529525756836,
|
|
"num_tokens": 8918077.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.760852956771851,
|
|
"epoch": 0.3860221431395809,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990670825059477,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.15778315514326097,
|
|
"num_tokens": 8930240.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.849574375152588,
|
|
"epoch": 0.38651640964808226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990638694459715,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.15975721180438995,
|
|
"num_tokens": 8941421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.815521955490112,
|
|
"epoch": 0.38701067615658363,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990606508739893,
|
|
"loss": 5.7904,
|
|
"mean_token_accuracy": 0.1570130318403244,
|
|
"num_tokens": 8952296.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.822608852386475,
|
|
"epoch": 0.387504942665085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990574267900804,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.1552998512983322,
|
|
"num_tokens": 8963167.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.77293381690979,
|
|
"epoch": 0.3879992091735864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990541971943241,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.15987713485956193,
|
|
"num_tokens": 8974405.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.8097466945648195,
|
|
"epoch": 0.3884934756820878,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990509620867997,
|
|
"loss": 5.6611,
|
|
"mean_token_accuracy": 0.16726437956094742,
|
|
"num_tokens": 8986012.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.735893583297729,
|
|
"epoch": 0.3889877421905892,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990477214675868,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.16344075053930282,
|
|
"num_tokens": 8996759.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.811870765686035,
|
|
"epoch": 0.38948200869909055,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990444753367653,
|
|
"loss": 5.8012,
|
|
"mean_token_accuracy": 0.1557467386126518,
|
|
"num_tokens": 9007215.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.742000150680542,
|
|
"epoch": 0.3899762752075919,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990412236944149,
|
|
"loss": 5.685,
|
|
"mean_token_accuracy": 0.1727793276309967,
|
|
"num_tokens": 9018281.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.904224014282226,
|
|
"epoch": 0.3904705417160933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990379665406157,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.15684255361557006,
|
|
"num_tokens": 9029312.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.8928080081939695,
|
|
"epoch": 0.39096480822459473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990347038754477,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.15501338243484497,
|
|
"num_tokens": 9040273.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.858111047744751,
|
|
"epoch": 0.3914590747330961,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990314356989912,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.1548047624528408,
|
|
"num_tokens": 9052571.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.743644952774048,
|
|
"epoch": 0.3919533412415975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990281620113268,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.16003586873412132,
|
|
"num_tokens": 9063531.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.872672271728516,
|
|
"epoch": 0.39244760775009885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990248828125347,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.15706233382225038,
|
|
"num_tokens": 9075404.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.700307941436767,
|
|
"epoch": 0.3929418742586002,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990215981026958,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.16441157907247544,
|
|
"num_tokens": 9086570.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.857178735733032,
|
|
"epoch": 0.3934361407671016,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990183078818908,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.16164011061191558,
|
|
"num_tokens": 9097993.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.7998147964477536,
|
|
"epoch": 0.393930407275603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990150121502007,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.1636693224310875,
|
|
"num_tokens": 9108783.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.75751485824585,
|
|
"epoch": 0.3944246737841044,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990117109077066,
|
|
"loss": 5.7945,
|
|
"mean_token_accuracy": 0.157828751206398,
|
|
"num_tokens": 9120039.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.822016763687134,
|
|
"epoch": 0.39491894029260577,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990084041544895,
|
|
"loss": 5.7335,
|
|
"mean_token_accuracy": 0.1619053989648819,
|
|
"num_tokens": 9131543.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.786256408691406,
|
|
"epoch": 0.39541320680110714,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499005091890631,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.15745581239461898,
|
|
"num_tokens": 9142968.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.785356140136718,
|
|
"epoch": 0.3959074733096085,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990017741162125,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.1567891702055931,
|
|
"num_tokens": 9155705.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.893890714645385,
|
|
"epoch": 0.39640173981810994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989984508313156,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.1497024416923523,
|
|
"num_tokens": 9167575.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.799427080154419,
|
|
"epoch": 0.3968960063266113,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498995122036022,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.15816699117422103,
|
|
"num_tokens": 9178493.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.916858148574829,
|
|
"epoch": 0.3973902728351127,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989917877304138,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.1506086468696594,
|
|
"num_tokens": 9189677.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.808521127700805,
|
|
"epoch": 0.39788453934361406,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989884479145727,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.16316084712743759,
|
|
"num_tokens": 9199179.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.842542600631714,
|
|
"epoch": 0.39837880585211544,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989851025885812,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.15409234464168547,
|
|
"num_tokens": 9210689.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.803835105895996,
|
|
"epoch": 0.39887307236061686,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989817517525212,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.16191910058259965,
|
|
"num_tokens": 9221710.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.845252990722656,
|
|
"epoch": 0.39936733886911824,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989783954064755,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.155524642765522,
|
|
"num_tokens": 9234079.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.77306547164917,
|
|
"epoch": 0.3998616053776196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989750335505265,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.1601504072546959,
|
|
"num_tokens": 9245050.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.915594863891601,
|
|
"epoch": 0.400355871886121,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004989716661847571,
|
|
"loss": 5.8285,
|
|
"mean_token_accuracy": 0.15581722557544708,
|
|
"num_tokens": 9256455.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.760847520828247,
|
|
"epoch": 0.40085013839462236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989682933092497,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.163893423974514,
|
|
"num_tokens": 9267722.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.750236940383911,
|
|
"epoch": 0.4013444049031238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989649149240877,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.15310631990432738,
|
|
"num_tokens": 9277533.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.853094959259034,
|
|
"epoch": 0.40183867141162516,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498961531029354,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.16159014403820038,
|
|
"num_tokens": 9290052.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.863904905319214,
|
|
"epoch": 0.40233293792012653,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498958141625132,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.16401766538619994,
|
|
"num_tokens": 9302201.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.886966180801392,
|
|
"epoch": 0.4028272044286279,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989547467115047,
|
|
"loss": 5.8442,
|
|
"mean_token_accuracy": 0.15359732061624526,
|
|
"num_tokens": 9313215.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.878138017654419,
|
|
"epoch": 0.4033214709371293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989513462885561,
|
|
"loss": 5.8918,
|
|
"mean_token_accuracy": 0.15000276416540145,
|
|
"num_tokens": 9324098.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.91675820350647,
|
|
"epoch": 0.4038157374456307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989479403563696,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.15627101063728333,
|
|
"num_tokens": 9336048.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.826158332824707,
|
|
"epoch": 0.4043100039541321,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989445289150289,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.15732008814811707,
|
|
"num_tokens": 9347723.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.770714950561524,
|
|
"epoch": 0.40480427046263345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989411119646183,
|
|
"loss": 5.7684,
|
|
"mean_token_accuracy": 0.153267540037632,
|
|
"num_tokens": 9360588.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.817790699005127,
|
|
"epoch": 0.4052985369711348,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989376895052214,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.16015778928995134,
|
|
"num_tokens": 9371798.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.825340509414673,
|
|
"epoch": 0.4057928034796362,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989342615369226,
|
|
"loss": 5.7399,
|
|
"mean_token_accuracy": 0.1631551891565323,
|
|
"num_tokens": 9382421.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.802740907669067,
|
|
"epoch": 0.40628706998813763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989308280598063,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.16391124129295348,
|
|
"num_tokens": 9392832.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.688262796401977,
|
|
"epoch": 0.406781336496639,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989273890739569,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.16319992393255234,
|
|
"num_tokens": 9405309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.755043363571167,
|
|
"epoch": 0.4072756030051404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498923944579459,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16950154751539231,
|
|
"num_tokens": 9416707.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.873722553253174,
|
|
"epoch": 0.40776986951364175,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989204945763972,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.15709468871355056,
|
|
"num_tokens": 9427684.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.77530312538147,
|
|
"epoch": 0.4082641360221431,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989170390648567,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.15686920583248137,
|
|
"num_tokens": 9439073.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.788780212402344,
|
|
"epoch": 0.40875840253064455,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989135780449222,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.16519829630851746,
|
|
"num_tokens": 9450266.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.71133131980896,
|
|
"epoch": 0.4092526690391459,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989101115166789,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.1646081805229187,
|
|
"num_tokens": 9462662.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.829580879211425,
|
|
"epoch": 0.4097469355476473,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989066394802122,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.1528080627322197,
|
|
"num_tokens": 9474338.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.802671289443969,
|
|
"epoch": 0.41024120205614867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989031619356074,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.16050966531038285,
|
|
"num_tokens": 9486353.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.791127109527588,
|
|
"epoch": 0.41073546856465004,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049889967888295,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.1575098380446434,
|
|
"num_tokens": 9497464.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.795160436630249,
|
|
"epoch": 0.41122973507315147,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988961903223258,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.16694964617490768,
|
|
"num_tokens": 9508037.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.7243417263031,
|
|
"epoch": 0.41172400158165284,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988926962538207,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.1623264119029045,
|
|
"num_tokens": 9518653.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.788403463363648,
|
|
"epoch": 0.4122182680901542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988891966775204,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.1636090949177742,
|
|
"num_tokens": 9529225.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.858669328689575,
|
|
"epoch": 0.4127125345986556,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988856915935112,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.15599008947610854,
|
|
"num_tokens": 9541010.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.734855461120605,
|
|
"epoch": 0.41320680110715696,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988821810018791,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.15410167798399926,
|
|
"num_tokens": 9552061.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.996918535232544,
|
|
"epoch": 0.41370106761565834,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988786649027108,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15064665377140046,
|
|
"num_tokens": 9563970.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.801588916778565,
|
|
"epoch": 0.41419533412415976,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988751432960926,
|
|
"loss": 5.6543,
|
|
"mean_token_accuracy": 0.16652969568967818,
|
|
"num_tokens": 9575381.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.775399017333984,
|
|
"epoch": 0.41468960063266114,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988716161821111,
|
|
"loss": 5.6964,
|
|
"mean_token_accuracy": 0.16737551093101502,
|
|
"num_tokens": 9586821.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.832442951202393,
|
|
"epoch": 0.4151838671411625,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988680835608531,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.1541001558303833,
|
|
"num_tokens": 9599580.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.78385853767395,
|
|
"epoch": 0.4156781336496639,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988645454324055,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.15373665243387222,
|
|
"num_tokens": 9611495.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.912009525299072,
|
|
"epoch": 0.41617240015816526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988610017968554,
|
|
"loss": 5.7402,
|
|
"mean_token_accuracy": 0.15970574468374252,
|
|
"num_tokens": 9623713.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.74974308013916,
|
|
"epoch": 0.4166666666666667,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988574526542899,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.16981375813484192,
|
|
"num_tokens": 9633922.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.799626684188842,
|
|
"epoch": 0.41716093317516806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988538980047963,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.15966415107250215,
|
|
"num_tokens": 9645641.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.8504174709320065,
|
|
"epoch": 0.41765519968366943,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988503378484622,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.16511618047952653,
|
|
"num_tokens": 9656927.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.727043724060058,
|
|
"epoch": 0.4181494661921708,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498846772185375,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.1685078665614128,
|
|
"num_tokens": 9669148.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.857232141494751,
|
|
"epoch": 0.4186437327006722,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988432010156224,
|
|
"loss": 5.8014,
|
|
"mean_token_accuracy": 0.15451167672872543,
|
|
"num_tokens": 9680620.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.896617031097412,
|
|
"epoch": 0.4191379992091736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988396243392924,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.15929511785507203,
|
|
"num_tokens": 9690984.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.776767206192017,
|
|
"epoch": 0.419632265717675,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498836042156473,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.1683742955327034,
|
|
"num_tokens": 9701561.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.795158529281617,
|
|
"epoch": 0.42012653222617635,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988324544672521,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.15636030286550523,
|
|
"num_tokens": 9712780.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.829728841781616,
|
|
"epoch": 0.4206207987346777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988288612717182,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.1592632934451103,
|
|
"num_tokens": 9724547.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.761361074447632,
|
|
"epoch": 0.4211150652431791,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988252625699594,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15530276745557786,
|
|
"num_tokens": 9736897.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.807239818572998,
|
|
"epoch": 0.4216093317516805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988216583620647,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.15987664163112641,
|
|
"num_tokens": 9748214.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.848560905456543,
|
|
"epoch": 0.4221035982601819,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988180486481223,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.16157542020082474,
|
|
"num_tokens": 9759602.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.761154127120972,
|
|
"epoch": 0.4225978647686833,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004988144334282211,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.16323730796575547,
|
|
"num_tokens": 9771645.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.810856628417969,
|
|
"epoch": 0.42309213127718465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988108127024503,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.16007653027772903,
|
|
"num_tokens": 9783504.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.878114652633667,
|
|
"epoch": 0.423586397785686,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988071864708987,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.15786612033843994,
|
|
"num_tokens": 9795572.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.803246736526489,
|
|
"epoch": 0.42408066429418745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988035547336555,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.16104598045349122,
|
|
"num_tokens": 9806398.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.755563163757325,
|
|
"epoch": 0.4245749308026888,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987999174908104,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.1597637802362442,
|
|
"num_tokens": 9817171.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.823905038833618,
|
|
"epoch": 0.4250691973111902,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004987962747424524,
|
|
"loss": 5.7551,
|
|
"mean_token_accuracy": 0.15554096400737763,
|
|
"num_tokens": 9827535.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.705531167984009,
|
|
"epoch": 0.42556346381969157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987926264886713,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.15889684706926346,
|
|
"num_tokens": 9839619.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.864329671859741,
|
|
"epoch": 0.42605773032819294,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498788972729557,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.15859341621398926,
|
|
"num_tokens": 9850100.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.8547258377075195,
|
|
"epoch": 0.42655199683669437,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987853134651992,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.14900276213884353,
|
|
"num_tokens": 9862228.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.743969917297363,
|
|
"epoch": 0.42704626334519574,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498781648695688,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16254492849111557,
|
|
"num_tokens": 9873080.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.757338809967041,
|
|
"epoch": 0.4275405298536971,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987779784211135,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.15808013081550598,
|
|
"num_tokens": 9884735.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.805332279205322,
|
|
"epoch": 0.4280347963621985,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498774302641566,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.15854816511273384,
|
|
"num_tokens": 9895018.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.847778940200806,
|
|
"epoch": 0.42852906287069986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987706213571359,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.15894026160240174,
|
|
"num_tokens": 9906838.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.796541547775268,
|
|
"epoch": 0.4290233293792013,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987669345679139,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.16102389693260194,
|
|
"num_tokens": 9919556.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.761550331115723,
|
|
"epoch": 0.42951759588770266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987632422739904,
|
|
"loss": 5.6342,
|
|
"mean_token_accuracy": 0.16379210501909255,
|
|
"num_tokens": 9929783.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.750921630859375,
|
|
"epoch": 0.43001186239620404,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987595444754567,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15950363278388976,
|
|
"num_tokens": 9940894.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.78188042640686,
|
|
"epoch": 0.4305061289047054,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987558411724032,
|
|
"loss": 5.6852,
|
|
"mean_token_accuracy": 0.1718315064907074,
|
|
"num_tokens": 9951973.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.851124858856201,
|
|
"epoch": 0.4310003954132068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987521323649215,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.15510926842689515,
|
|
"num_tokens": 9963304.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.810867404937744,
|
|
"epoch": 0.4314946619217082,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987484180531026,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.1658098503947258,
|
|
"num_tokens": 9973981.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.8423220157623295,
|
|
"epoch": 0.4319889284302096,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987446982370379,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.15710315406322478,
|
|
"num_tokens": 9986461.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.7948016166687015,
|
|
"epoch": 0.43248319493871096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498740972916819,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.1577886864542961,
|
|
"num_tokens": 9997973.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.792349863052368,
|
|
"epoch": 0.43297746144721233,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987372420925373,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.1599084995687008,
|
|
"num_tokens": 10009572.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.781804180145263,
|
|
"epoch": 0.4334717279557137,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987335057642847,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.1711675927042961,
|
|
"num_tokens": 10020437.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.734922313690186,
|
|
"epoch": 0.43396599446421513,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004987297639321533,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1576806277036667,
|
|
"num_tokens": 10031827.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.772050285339356,
|
|
"epoch": 0.4344602609727165,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987260165962349,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.15794049948453903,
|
|
"num_tokens": 10043833.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.808005380630493,
|
|
"epoch": 0.4349545274812179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987222637566218,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.1611488029360771,
|
|
"num_tokens": 10054645.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.749887275695801,
|
|
"epoch": 0.43544879398971925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987185054134064,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.15768925100564957,
|
|
"num_tokens": 10065178.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.760057401657105,
|
|
"epoch": 0.4359430604982206,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498714741566681,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.16662850975990295,
|
|
"num_tokens": 10076701.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.730797958374024,
|
|
"epoch": 0.436437327006722,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987109722165383,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.16437997817993164,
|
|
"num_tokens": 10087959.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.833425378799438,
|
|
"epoch": 0.4369315935152234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987071973630708,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.16239218264818192,
|
|
"num_tokens": 10099463.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.75164384841919,
|
|
"epoch": 0.4374258600237248,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987034170063717,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.15755711495876312,
|
|
"num_tokens": 10111384.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.796598291397094,
|
|
"epoch": 0.4379201265322262,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986996311465338,
|
|
"loss": 5.6966,
|
|
"mean_token_accuracy": 0.1650578111410141,
|
|
"num_tokens": 10121838.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.797725677490234,
|
|
"epoch": 0.43841439304072755,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986958397836503,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.1639087453484535,
|
|
"num_tokens": 10132225.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.722563362121582,
|
|
"epoch": 0.4389086595492289,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986920429178144,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.16035064905881882,
|
|
"num_tokens": 10143114.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.831698942184448,
|
|
"epoch": 0.43940292605773035,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004986882405491195,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.14863617867231368,
|
|
"num_tokens": 10155057.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.728516912460327,
|
|
"epoch": 0.4398971925662317,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986844326776593,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.17418619990348816,
|
|
"num_tokens": 10166816.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.733769941329956,
|
|
"epoch": 0.4403914590747331,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986806193035272,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.17027612924575805,
|
|
"num_tokens": 10179433.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.783415746688843,
|
|
"epoch": 0.44088572558323447,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986768004268173,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.16360337436199188,
|
|
"num_tokens": 10190784.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.793423366546631,
|
|
"epoch": 0.44137999209173584,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986729760476234,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.15802907198667526,
|
|
"num_tokens": 10201941.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.767525148391724,
|
|
"epoch": 0.44187425860023727,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986691461660394,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.16569736674427987,
|
|
"num_tokens": 10214029.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.797163724899292,
|
|
"epoch": 0.44236852510873864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986653107821599,
|
|
"loss": 5.7286,
|
|
"mean_token_accuracy": 0.16338905394077302,
|
|
"num_tokens": 10225585.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.7489540576934814,
|
|
"epoch": 0.44286279161724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986614698960789,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.16797255575656891,
|
|
"num_tokens": 10237753.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.824925899505615,
|
|
"epoch": 0.4433570581257414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986576235078913,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.14952940344810486,
|
|
"num_tokens": 10251522.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.859293985366821,
|
|
"epoch": 0.44385132463424276,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986537716176912,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.1659579500555992,
|
|
"num_tokens": 10263319.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.647326421737671,
|
|
"epoch": 0.4443455911427442,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986499142255738,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.16761216074228286,
|
|
"num_tokens": 10274899.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.815342140197754,
|
|
"epoch": 0.44483985765124556,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004986460513316338,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.1651053950190544,
|
|
"num_tokens": 10286110.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.749167633056641,
|
|
"epoch": 0.44533412415974694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986421829359662,
|
|
"loss": 5.7867,
|
|
"mean_token_accuracy": 0.15793402642011642,
|
|
"num_tokens": 10298870.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.795179224014282,
|
|
"epoch": 0.4458283906682483,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986383090386661,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.16252816915512086,
|
|
"num_tokens": 10310326.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.8107678413391115,
|
|
"epoch": 0.4463226571767497,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498634429639829,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.16348832696676255,
|
|
"num_tokens": 10320899.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.695652627944947,
|
|
"epoch": 0.4468169236852511,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986305447395502,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.16677896082401275,
|
|
"num_tokens": 10331669.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.792504978179932,
|
|
"epoch": 0.4473111901937525,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986266543379254,
|
|
"loss": 5.6699,
|
|
"mean_token_accuracy": 0.16341660767793656,
|
|
"num_tokens": 10343120.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.75168924331665,
|
|
"epoch": 0.44780545670225386,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004986227584350501,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.16456840187311172,
|
|
"num_tokens": 10354806.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.8492063045501705,
|
|
"epoch": 0.44829972321075523,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986188570310203,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.16331523805856704,
|
|
"num_tokens": 10366453.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.800158882141114,
|
|
"epoch": 0.4487939897192566,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986149501259319,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.15668026208877564,
|
|
"num_tokens": 10378095.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.756777906417847,
|
|
"epoch": 0.44928825622775803,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986110377198812,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.16681426465511323,
|
|
"num_tokens": 10389620.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.860169076919556,
|
|
"epoch": 0.4497825227362594,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498607119812964,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.15686686635017394,
|
|
"num_tokens": 10400166.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.743602180480957,
|
|
"epoch": 0.4502767892447608,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986031964052772,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.1612066611647606,
|
|
"num_tokens": 10411116.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.783570146560669,
|
|
"epoch": 0.45077105575326215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985992674969169,
|
|
"loss": 5.7289,
|
|
"mean_token_accuracy": 0.1575294703245163,
|
|
"num_tokens": 10423484.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.857646560668945,
|
|
"epoch": 0.4512653222617635,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985953330879801,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.150855603069067,
|
|
"num_tokens": 10435636.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.835836172103882,
|
|
"epoch": 0.45175958877026495,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985913931785633,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.1639969229698181,
|
|
"num_tokens": 10447586.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.745838642120361,
|
|
"epoch": 0.4522538552787663,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985874477687636,
|
|
"loss": 5.7711,
|
|
"mean_token_accuracy": 0.15540753155946732,
|
|
"num_tokens": 10460678.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.787776041030884,
|
|
"epoch": 0.4527481217872677,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985834968586779,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.1577146142721176,
|
|
"num_tokens": 10472738.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.804813575744629,
|
|
"epoch": 0.45324238829576907,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985795404484037,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.1691010922193527,
|
|
"num_tokens": 10483716.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.7478948593139645,
|
|
"epoch": 0.45373665480427045,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004985755785380379,
|
|
"loss": 5.7472,
|
|
"mean_token_accuracy": 0.15642405301332474,
|
|
"num_tokens": 10495287.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.799208736419677,
|
|
"epoch": 0.4542309213127719,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985716111276781,
|
|
"loss": 5.6868,
|
|
"mean_token_accuracy": 0.16505905836820603,
|
|
"num_tokens": 10506332.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.821527051925659,
|
|
"epoch": 0.45472518782127325,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985676382174223,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.15854078382253647,
|
|
"num_tokens": 10517574.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.773885297775268,
|
|
"epoch": 0.4552194543297746,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985636598073677,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.16572566628456115,
|
|
"num_tokens": 10528998.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.804497909545899,
|
|
"epoch": 0.455713720838276,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985596758976125,
|
|
"loss": 5.7047,
|
|
"mean_token_accuracy": 0.1570952504873276,
|
|
"num_tokens": 10539669.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.751265573501587,
|
|
"epoch": 0.45620798734677737,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985556864882545,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.15958641171455384,
|
|
"num_tokens": 10550005.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.747312879562378,
|
|
"epoch": 0.45670225385527874,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498551691579392,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.15987961143255233,
|
|
"num_tokens": 10561122.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.835789346694947,
|
|
"epoch": 0.45719652036378017,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985476911711232,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.16188775897026061,
|
|
"num_tokens": 10572081.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.646384572982788,
|
|
"epoch": 0.45769078687228154,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004985436852635465,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.17081398516893387,
|
|
"num_tokens": 10582297.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.854415464401245,
|
|
"epoch": 0.4581850533807829,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985396738567604,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.15702760070562363,
|
|
"num_tokens": 10593161.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.822171974182129,
|
|
"epoch": 0.4586793198892843,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985356569508638,
|
|
"loss": 5.7417,
|
|
"mean_token_accuracy": 0.16531843990087508,
|
|
"num_tokens": 10603900.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.818403148651123,
|
|
"epoch": 0.45917358639778566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985316345459551,
|
|
"loss": 5.7298,
|
|
"mean_token_accuracy": 0.1646069422364235,
|
|
"num_tokens": 10614946.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.754018831253052,
|
|
"epoch": 0.4596678529062871,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985276066421338,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.1583070144057274,
|
|
"num_tokens": 10625073.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.8119361877441404,
|
|
"epoch": 0.46016211941478846,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985235732394986,
|
|
"loss": 5.8252,
|
|
"mean_token_accuracy": 0.15195816159248351,
|
|
"num_tokens": 10636942.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.875297594070434,
|
|
"epoch": 0.46065638592328984,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004985195343381487,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.15495458543300628,
|
|
"num_tokens": 10647608.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.911948251724243,
|
|
"epoch": 0.4611506524317912,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985154899381837,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.1571880340576172,
|
|
"num_tokens": 10659532.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.820354795455932,
|
|
"epoch": 0.4616449189402926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985114400397029,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.15816500782966614,
|
|
"num_tokens": 10670342.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.7802811622619625,
|
|
"epoch": 0.462139185448794,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985073846428061,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.15955777317285538,
|
|
"num_tokens": 10682984.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.814119529724121,
|
|
"epoch": 0.4626334519572954,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985033237475929,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.1571871355175972,
|
|
"num_tokens": 10694235.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.872252941131592,
|
|
"epoch": 0.46312771846579676,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984992573541633,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.15945093631744384,
|
|
"num_tokens": 10704508.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.654449701309204,
|
|
"epoch": 0.46362198497429813,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984951854626173,
|
|
"loss": 5.6338,
|
|
"mean_token_accuracy": 0.16828023940324782,
|
|
"num_tokens": 10716927.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.773769235610962,
|
|
"epoch": 0.4641162514827995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984911080730551,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.16356825679540635,
|
|
"num_tokens": 10728396.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.775106287002563,
|
|
"epoch": 0.46461051799130093,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984870251855769,
|
|
"loss": 5.7346,
|
|
"mean_token_accuracy": 0.16223948150873185,
|
|
"num_tokens": 10739001.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.779851245880127,
|
|
"epoch": 0.4651047844998023,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004984829368002831,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.16134137362241746,
|
|
"num_tokens": 10748768.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.801807165145874,
|
|
"epoch": 0.4655990510083037,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984788429172745,
|
|
"loss": 5.7485,
|
|
"mean_token_accuracy": 0.1603395089507103,
|
|
"num_tokens": 10760582.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.743312978744507,
|
|
"epoch": 0.46609331751680505,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984747435366517,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.17206057906150818,
|
|
"num_tokens": 10772537.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.731701993942261,
|
|
"epoch": 0.4665875840253064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984706386585156,
|
|
"loss": 5.5844,
|
|
"mean_token_accuracy": 0.17241816222667694,
|
|
"num_tokens": 10783740.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.7779685974121096,
|
|
"epoch": 0.46708185053380785,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498466528282967,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.1602986589074135,
|
|
"num_tokens": 10794793.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.839662694931031,
|
|
"epoch": 0.4675761170423092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984624124101072,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.16011293828487397,
|
|
"num_tokens": 10805944.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.865648412704468,
|
|
"epoch": 0.4680703835508106,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004984582910400374,
|
|
"loss": 5.7341,
|
|
"mean_token_accuracy": 0.16009406596422196,
|
|
"num_tokens": 10818362.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.716548871994019,
|
|
"epoch": 0.46856465005931197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498454164172859,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.16666487604379654,
|
|
"num_tokens": 10831306.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.755958795547485,
|
|
"epoch": 0.46905891656781334,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984500318086733,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.1630124643445015,
|
|
"num_tokens": 10841671.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.7693455696105955,
|
|
"epoch": 0.4695531830763148,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984458939475824,
|
|
"loss": 5.6599,
|
|
"mean_token_accuracy": 0.15788134336471557,
|
|
"num_tokens": 10852754.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.762604236602783,
|
|
"epoch": 0.47004744958481615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984417505896877,
|
|
"loss": 5.7199,
|
|
"mean_token_accuracy": 0.16277106404304503,
|
|
"num_tokens": 10864812.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.829414367675781,
|
|
"epoch": 0.4705417160933175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984376017350913,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.1621460199356079,
|
|
"num_tokens": 10875967.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.735864305496216,
|
|
"epoch": 0.4710359826018189,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984334473838953,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.16421130001544954,
|
|
"num_tokens": 10889575.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.83205509185791,
|
|
"epoch": 0.47153024911032027,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984292875362018,
|
|
"loss": 5.7718,
|
|
"mean_token_accuracy": 0.1608981028199196,
|
|
"num_tokens": 10900751.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.824170255661011,
|
|
"epoch": 0.4720245156188217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984251221921131,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.16092055588960646,
|
|
"num_tokens": 10912618.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.7384556293487545,
|
|
"epoch": 0.47251878212732307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984209513517317,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.16043095514178277,
|
|
"num_tokens": 10925286.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.770280981063843,
|
|
"epoch": 0.47301304863582444,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984167750151603,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.1644046798348427,
|
|
"num_tokens": 10936033.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.793165397644043,
|
|
"epoch": 0.4735073151443258,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984125931825018,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.16621741503477097,
|
|
"num_tokens": 10947055.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.775673675537109,
|
|
"epoch": 0.4740015816528272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984084058538585,
|
|
"loss": 5.6709,
|
|
"mean_token_accuracy": 0.1618171975016594,
|
|
"num_tokens": 10957468.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.818755626678467,
|
|
"epoch": 0.4744958481613286,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984042130293339,
|
|
"loss": 5.8,
|
|
"mean_token_accuracy": 0.1592056468129158,
|
|
"num_tokens": 10970273.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.82786979675293,
|
|
"epoch": 0.47499011466983,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984000147090311,
|
|
"loss": 5.7687,
|
|
"mean_token_accuracy": 0.15505611896514893,
|
|
"num_tokens": 10981842.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.8316010475158695,
|
|
"epoch": 0.47548438117833136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004983958108930531,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.16365816742181777,
|
|
"num_tokens": 10993615.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.7944940567016605,
|
|
"epoch": 0.47597864768683273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983916015815036,
|
|
"loss": 5.7722,
|
|
"mean_token_accuracy": 0.15765168368816376,
|
|
"num_tokens": 11004451.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.838356590270996,
|
|
"epoch": 0.4764729141953341,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498387386774486,
|
|
"loss": 5.6973,
|
|
"mean_token_accuracy": 0.15701130777597427,
|
|
"num_tokens": 11014834.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.7037660598754885,
|
|
"epoch": 0.4769671807038355,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498383166472104,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.1630084276199341,
|
|
"num_tokens": 11026116.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.781487035751343,
|
|
"epoch": 0.4774614472123369,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983789406744615,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.16110067516565324,
|
|
"num_tokens": 11038780.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.808997869491577,
|
|
"epoch": 0.4779557137208383,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983747093816625,
|
|
"loss": 5.7632,
|
|
"mean_token_accuracy": 0.16238407641649247,
|
|
"num_tokens": 11049824.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.763619089126587,
|
|
"epoch": 0.47844998022933966,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983704725938108,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.16971166133880616,
|
|
"num_tokens": 11060863.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.708709287643432,
|
|
"epoch": 0.47894424673784103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498366230311011,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.1674087181687355,
|
|
"num_tokens": 11072533.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.672757482528686,
|
|
"epoch": 0.4794385132463424,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983619825333671,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.168568417429924,
|
|
"num_tokens": 11083627.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.834180927276611,
|
|
"epoch": 0.47993277975484383,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983577292609839,
|
|
"loss": 5.8074,
|
|
"mean_token_accuracy": 0.15414674282073976,
|
|
"num_tokens": 11096421.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.711428308486939,
|
|
"epoch": 0.4804270462633452,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983534704939659,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.16372432112693786,
|
|
"num_tokens": 11109053.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.711614799499512,
|
|
"epoch": 0.4809213127718466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983492062324179,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.16856001317501068,
|
|
"num_tokens": 11120431.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.7900557041168215,
|
|
"epoch": 0.48141557928034795,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983449364764447,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.16389783173799516,
|
|
"num_tokens": 11132767.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.663289642333984,
|
|
"epoch": 0.4819098457888493,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983406612261514,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.16376278325915336,
|
|
"num_tokens": 11144508.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.727054023742676,
|
|
"epoch": 0.48240411229735075,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983363804816433,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.16261004209518432,
|
|
"num_tokens": 11156905.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.801562690734864,
|
|
"epoch": 0.4828983788058521,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983320942430256,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.16727310717105864,
|
|
"num_tokens": 11169383.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.699421072006226,
|
|
"epoch": 0.4833926453143535,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983278025104036,
|
|
"loss": 5.5902,
|
|
"mean_token_accuracy": 0.17361047565937043,
|
|
"num_tokens": 11179795.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.741180562973023,
|
|
"epoch": 0.48388691182285487,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498323505283883,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.159314888715744,
|
|
"num_tokens": 11190783.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.812034463882446,
|
|
"epoch": 0.48438117833135624,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983192025635698,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.1591508463025093,
|
|
"num_tokens": 11203000.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.7700944423675535,
|
|
"epoch": 0.48487544483985767,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983148943495693,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.15941910743713378,
|
|
"num_tokens": 11213721.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.771741151809692,
|
|
"epoch": 0.48536971134835905,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983105806419878,
|
|
"loss": 5.7521,
|
|
"mean_token_accuracy": 0.15759332329034806,
|
|
"num_tokens": 11224490.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.740262269973755,
|
|
"epoch": 0.4858639778568604,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983062614409314,
|
|
"loss": 5.6615,
|
|
"mean_token_accuracy": 0.16810956597328186,
|
|
"num_tokens": 11235022.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.814758539199829,
|
|
"epoch": 0.4863582443653618,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983019367465064,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.1636986628174782,
|
|
"num_tokens": 11247485.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.768625164031983,
|
|
"epoch": 0.48685251087386316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498297606558819,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.16861545741558076,
|
|
"num_tokens": 11258488.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.707114553451538,
|
|
"epoch": 0.4873467773823646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004982932708779759,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.1659485936164856,
|
|
"num_tokens": 11270786.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.838079977035522,
|
|
"epoch": 0.48784104389086597,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982889297040836,
|
|
"loss": 5.6656,
|
|
"mean_token_accuracy": 0.16345455199480058,
|
|
"num_tokens": 11282434.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.726280975341797,
|
|
"epoch": 0.48833531039936734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982845830372491,
|
|
"loss": 5.6582,
|
|
"mean_token_accuracy": 0.15919594019651412,
|
|
"num_tokens": 11292406.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.867124938964844,
|
|
"epoch": 0.4888295769078687,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982802308775791,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.15510911792516707,
|
|
"num_tokens": 11304491.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.7834679126739506,
|
|
"epoch": 0.4893238434163701,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498275873225181,
|
|
"loss": 5.725,
|
|
"mean_token_accuracy": 0.16178398281335832,
|
|
"num_tokens": 11317038.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.81882872581482,
|
|
"epoch": 0.4898181099248715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982715100801616,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.15895454287528993,
|
|
"num_tokens": 11329354.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.753229475021362,
|
|
"epoch": 0.4903123764333729,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982671414426285,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.1597677230834961,
|
|
"num_tokens": 11340508.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.751951360702515,
|
|
"epoch": 0.49080664294187426,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982627673126889,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.167711241543293,
|
|
"num_tokens": 11352608.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.742062711715699,
|
|
"epoch": 0.49130090945037563,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004982583876904508,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.1655659407377243,
|
|
"num_tokens": 11364089.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.681409502029419,
|
|
"epoch": 0.491795175958877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982540025760217,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.1689285919070244,
|
|
"num_tokens": 11375521.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.74716477394104,
|
|
"epoch": 0.49228944246737844,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004982496119695094,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.16345907747745514,
|
|
"num_tokens": 11387721.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.863518381118775,
|
|
"epoch": 0.4927837089758798,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498245215871022,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.15801465660333633,
|
|
"num_tokens": 11398688.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.683114624023437,
|
|
"epoch": 0.4932779754843812,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982408142806678,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1611632600426674,
|
|
"num_tokens": 11410420.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.662859630584717,
|
|
"epoch": 0.49377224199288255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982364071985549,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.16756909042596818,
|
|
"num_tokens": 11420521.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.83459062576294,
|
|
"epoch": 0.4942665085013839,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982319946247917,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.15849525034427642,
|
|
"num_tokens": 11432550.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.80623869895935,
|
|
"epoch": 0.49476077500988536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982275765594869,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.1586284965276718,
|
|
"num_tokens": 11444602.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.705633115768433,
|
|
"epoch": 0.49525504151838673,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982231530027489,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17297993898391723,
|
|
"num_tokens": 11456187.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.711807775497436,
|
|
"epoch": 0.4957493080268881,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982187239546868,
|
|
"loss": 5.7439,
|
|
"mean_token_accuracy": 0.16142086535692216,
|
|
"num_tokens": 11468615.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.8034735202789305,
|
|
"epoch": 0.4962435745353895,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982142894154095,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.16297703385353088,
|
|
"num_tokens": 11480865.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.797510480880737,
|
|
"epoch": 0.49673784104389085,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498209849385026,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.15575276762247087,
|
|
"num_tokens": 11492590.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.787820625305176,
|
|
"epoch": 0.4972321075523923,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982054038636456,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1674128480255604,
|
|
"num_tokens": 11503481.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.704435110092163,
|
|
"epoch": 0.49772637406089365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982009528513776,
|
|
"loss": 5.6349,
|
|
"mean_token_accuracy": 0.16376303732395173,
|
|
"num_tokens": 11515083.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.742786502838134,
|
|
"epoch": 0.498220640569395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981964963483316,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.15938208550214766,
|
|
"num_tokens": 11527923.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.802856588363648,
|
|
"epoch": 0.4987149070778964,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981920343546171,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.16608707308769227,
|
|
"num_tokens": 11539456.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.759442949295044,
|
|
"epoch": 0.49920917358639777,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498187566870344,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.17132781744003295,
|
|
"num_tokens": 11550809.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.852121448516845,
|
|
"epoch": 0.49970344009489914,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004981830938956221,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.15544925183057784,
|
|
"num_tokens": 11562545.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.73180832862854,
|
|
"epoch": 0.5001977066034006,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981786154305615,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.1661169022321701,
|
|
"num_tokens": 11574479.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.766800594329834,
|
|
"epoch": 0.500691973111902,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004981741314752722,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.16941096633672714,
|
|
"num_tokens": 11583942.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.753709220886231,
|
|
"epoch": 0.5011862396204033,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981696420298647,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.16306612491607667,
|
|
"num_tokens": 11596745.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.636108541488648,
|
|
"epoch": 0.5016805061289047,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981651470944495,
|
|
"loss": 5.578,
|
|
"mean_token_accuracy": 0.16858351230621338,
|
|
"num_tokens": 11608950.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.736128568649292,
|
|
"epoch": 0.5021747726374061,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498160646669137,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.1624613121151924,
|
|
"num_tokens": 11619996.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.716293525695801,
|
|
"epoch": 0.5026690391459074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981561407540379,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.1706862285733223,
|
|
"num_tokens": 11632167.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.708092594146729,
|
|
"epoch": 0.5031633056544088,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981516293492632,
|
|
"loss": 5.6266,
|
|
"mean_token_accuracy": 0.1664534792304039,
|
|
"num_tokens": 11643722.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.733836507797241,
|
|
"epoch": 0.5036575721629103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981471124549237,
|
|
"loss": 5.627,
|
|
"mean_token_accuracy": 0.16822732090950013,
|
|
"num_tokens": 11654890.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.755518960952759,
|
|
"epoch": 0.5041518386714117,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981425900711308,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1597890555858612,
|
|
"num_tokens": 11665485.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.756056594848633,
|
|
"epoch": 0.504646105179913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981380621979954,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.16995342820882797,
|
|
"num_tokens": 11676145.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.682284259796143,
|
|
"epoch": 0.5051403716884144,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981335288356291,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.16167705059051513,
|
|
"num_tokens": 11687777.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.762973070144653,
|
|
"epoch": 0.5056346381969158,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981289899841434,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.16730411797761918,
|
|
"num_tokens": 11699703.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.770497465133667,
|
|
"epoch": 0.5061289047054172,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981244456436499,
|
|
"loss": 5.7393,
|
|
"mean_token_accuracy": 0.1541164644062519,
|
|
"num_tokens": 11711632.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.836890697479248,
|
|
"epoch": 0.5066231712139185,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981198958142604,
|
|
"loss": 5.7381,
|
|
"mean_token_accuracy": 0.1642602264881134,
|
|
"num_tokens": 11723763.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.7833198547363285,
|
|
"epoch": 0.5071174377224199,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981153404960869,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.15563536882400514,
|
|
"num_tokens": 11736061.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.744949007034302,
|
|
"epoch": 0.5076117042309213,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981107796892414,
|
|
"loss": 5.7453,
|
|
"mean_token_accuracy": 0.1615115612745285,
|
|
"num_tokens": 11749342.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.83615140914917,
|
|
"epoch": 0.5081059707394227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981062133938361,
|
|
"loss": 5.6647,
|
|
"mean_token_accuracy": 0.1639019250869751,
|
|
"num_tokens": 11760441.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.644511032104492,
|
|
"epoch": 0.508600237247924,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004981016416099834,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.16845064908266066,
|
|
"num_tokens": 11772191.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.84206805229187,
|
|
"epoch": 0.5090945037564255,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980970643377956,
|
|
"loss": 5.8356,
|
|
"mean_token_accuracy": 0.1525135561823845,
|
|
"num_tokens": 11786347.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.780380630493164,
|
|
"epoch": 0.5095887702649269,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980924815773855,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.16874918341636658,
|
|
"num_tokens": 11797741.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.774152660369873,
|
|
"epoch": 0.5100830367734283,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980878933288657,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.15581934452056884,
|
|
"num_tokens": 11809728.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.758777236938476,
|
|
"epoch": 0.5105773032819296,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000498083299592349,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15986347645521165,
|
|
"num_tokens": 11822000.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.75777587890625,
|
|
"epoch": 0.511071569790431,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004980787003679486,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.16140363365411758,
|
|
"num_tokens": 11834059.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.649407386779785,
|
|
"epoch": 0.5115658362989324,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980740956557776,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17640244960784912,
|
|
"num_tokens": 11844001.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.747405290603638,
|
|
"epoch": 0.5120601028074337,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980694854559493,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.16585945934057236,
|
|
"num_tokens": 11855991.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.826808309555053,
|
|
"epoch": 0.5125543693159351,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498064869768577,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.16362146735191346,
|
|
"num_tokens": 11867975.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.683806848526001,
|
|
"epoch": 0.5130486358244365,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980602485937743,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.16472838968038558,
|
|
"num_tokens": 11880034.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.812743043899536,
|
|
"epoch": 0.5135429023329379,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004980556219316549,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.15492210984230043,
|
|
"num_tokens": 11891490.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.767824268341064,
|
|
"epoch": 0.5140371688414394,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004980509897823326,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.17005866169929504,
|
|
"num_tokens": 11902988.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.732963562011719,
|
|
"epoch": 0.5145314353499407,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980463521459212,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.16476522088050843,
|
|
"num_tokens": 11915088.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.739437246322632,
|
|
"epoch": 0.5150257018584421,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980417090225351,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.16606741696596145,
|
|
"num_tokens": 11926789.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.821782779693604,
|
|
"epoch": 0.5155199683669435,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980370604122883,
|
|
"loss": 5.7177,
|
|
"mean_token_accuracy": 0.15862758457660675,
|
|
"num_tokens": 11938876.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.814732074737549,
|
|
"epoch": 0.5160142348754448,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980324063152952,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.16394247710704804,
|
|
"num_tokens": 11950099.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.78986086845398,
|
|
"epoch": 0.5165085013839462,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980277467316704,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.15911942571401597,
|
|
"num_tokens": 11962585.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.7590710639953615,
|
|
"epoch": 0.5170027678924476,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980230816615282,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.16958839148283006,
|
|
"num_tokens": 11972579.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.711051082611084,
|
|
"epoch": 0.517497034400949,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980184111049837,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.1705365940928459,
|
|
"num_tokens": 11983337.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.775261640548706,
|
|
"epoch": 0.5179913009094503,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980137350621518,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.15906553566455842,
|
|
"num_tokens": 11995086.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.8062793731689455,
|
|
"epoch": 0.5184855674179517,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980090535331473,
|
|
"loss": 5.7299,
|
|
"mean_token_accuracy": 0.1654836893081665,
|
|
"num_tokens": 12007814.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.690533542633057,
|
|
"epoch": 0.5189798339264532,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980043665180857,
|
|
"loss": 5.5762,
|
|
"mean_token_accuracy": 0.17120739668607712,
|
|
"num_tokens": 12020714.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.709106588363648,
|
|
"epoch": 0.5194741004349546,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979996740170819,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.1649314805865288,
|
|
"num_tokens": 12031994.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.821861791610718,
|
|
"epoch": 0.5199683669434559,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979949760302515,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.16028733998537065,
|
|
"num_tokens": 12042887.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.821678256988525,
|
|
"epoch": 0.5204626334519573,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979902725577101,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.16626618951559066,
|
|
"num_tokens": 12054426.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.709708261489868,
|
|
"epoch": 0.5209568999604587,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979855635995735,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.15980634838342667,
|
|
"num_tokens": 12066360.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.870700263977051,
|
|
"epoch": 0.5214511664689601,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004979808491559573,
|
|
"loss": 5.7203,
|
|
"mean_token_accuracy": 0.15794931054115297,
|
|
"num_tokens": 12076651.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.737508630752563,
|
|
"epoch": 0.5219454329774614,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004979761292269778,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.16551420837640762,
|
|
"num_tokens": 12087522.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.752012109756469,
|
|
"epoch": 0.5224396994859628,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979714038127508,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.166099651157856,
|
|
"num_tokens": 12097999.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.718552923202514,
|
|
"epoch": 0.5229339659944642,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979666729133927,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.16256896108388902,
|
|
"num_tokens": 12108080.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.861055469512939,
|
|
"epoch": 0.5234282325029656,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979619365290199,
|
|
"loss": 5.8532,
|
|
"mean_token_accuracy": 0.14619144648313523,
|
|
"num_tokens": 12122705.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.828919124603272,
|
|
"epoch": 0.523922499011467,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979571946597488,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.1642012283205986,
|
|
"num_tokens": 12134000.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.696564960479736,
|
|
"epoch": 0.5244167655199684,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004979524473056961,
|
|
"loss": 5.6723,
|
|
"mean_token_accuracy": 0.16008542180061341,
|
|
"num_tokens": 12144825.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.77923994064331,
|
|
"epoch": 0.5249110320284698,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004979476944669787,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.1614455610513687,
|
|
"num_tokens": 12156590.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.82336163520813,
|
|
"epoch": 0.5254052985369712,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979429361437134,
|
|
"loss": 5.5978,
|
|
"mean_token_accuracy": 0.16800351887941362,
|
|
"num_tokens": 12167478.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.746910524368286,
|
|
"epoch": 0.5258995650454725,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004979381723360173,
|
|
"loss": 5.6003,
|
|
"mean_token_accuracy": 0.1723802626132965,
|
|
"num_tokens": 12178728.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.6658868312835695,
|
|
"epoch": 0.5263938315539739,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979334030440076,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.16042406857013702,
|
|
"num_tokens": 12190061.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.728970718383789,
|
|
"epoch": 0.5268880980624753,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979286282678015,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.16720897555351258,
|
|
"num_tokens": 12200867.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.832201623916626,
|
|
"epoch": 0.5273823645709766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979238480075166,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16285530030727385,
|
|
"num_tokens": 12212681.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.696088171005249,
|
|
"epoch": 0.527876631079478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979190622632705,
|
|
"loss": 5.6787,
|
|
"mean_token_accuracy": 0.16312499195337296,
|
|
"num_tokens": 12224279.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.600846910476685,
|
|
"epoch": 0.5283708975879794,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979142710351809,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.1839956372976303,
|
|
"num_tokens": 12235754.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.750243616104126,
|
|
"epoch": 0.5288651640964809,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004979094743233656,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.16275203377008438,
|
|
"num_tokens": 12246014.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.725225782394409,
|
|
"epoch": 0.5293594306049823,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004979046721279426,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.1670306295156479,
|
|
"num_tokens": 12257519.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.725249099731445,
|
|
"epoch": 0.5298536971134836,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978998644490302,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.16509622931480408,
|
|
"num_tokens": 12269806.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.765331983566284,
|
|
"epoch": 0.530347963621985,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978950512867465,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.15928092896938323,
|
|
"num_tokens": 12281612.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.7670210838317875,
|
|
"epoch": 0.5308422301304864,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978902326412099,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.16511386185884475,
|
|
"num_tokens": 12293022.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.713943767547607,
|
|
"epoch": 0.5313364966389877,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497885408512539,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.1661032520234585,
|
|
"num_tokens": 12304414.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.900142526626587,
|
|
"epoch": 0.5318307631474891,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004978805789008526,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.15470698326826096,
|
|
"num_tokens": 12315618.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.69836311340332,
|
|
"epoch": 0.5323250296559905,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004978757438062692,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.17326654493808746,
|
|
"num_tokens": 12328026.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.680259704589844,
|
|
"epoch": 0.5328192961644919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004978709032289081,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.16148552894592286,
|
|
"num_tokens": 12339441.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.869100761413574,
|
|
"epoch": 0.5333135626729932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978660571688881,
|
|
"loss": 5.6914,
|
|
"mean_token_accuracy": 0.16318709999322892,
|
|
"num_tokens": 12351005.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.788716650009155,
|
|
"epoch": 0.5338078291814946,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004978612056263286,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.16630602926015853,
|
|
"num_tokens": 12363147.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.737411022186279,
|
|
"epoch": 0.5343020956899961,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978563486013488,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.16777381002902986,
|
|
"num_tokens": 12373446.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.729855060577393,
|
|
"epoch": 0.5347963621984975,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978514860940683,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.16629474312067033,
|
|
"num_tokens": 12384591.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.70512752532959,
|
|
"epoch": 0.5352906287069988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978466181046067,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.16822653859853745,
|
|
"num_tokens": 12396117.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.700036239624024,
|
|
"epoch": 0.5357848952155002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978417446330837,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.16791554689407348,
|
|
"num_tokens": 12407400.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.702632999420166,
|
|
"epoch": 0.5362791617240016,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978368656796191,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.17252375483512877,
|
|
"num_tokens": 12417629.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.65844087600708,
|
|
"epoch": 0.536773428232503,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978319812443331,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.17382462620735167,
|
|
"num_tokens": 12428522.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.766690969467163,
|
|
"epoch": 0.5372676947410043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978270913273458,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.15800946354866027,
|
|
"num_tokens": 12440390.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.723415994644165,
|
|
"epoch": 0.5377619612495057,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004978221959287775,
|
|
"loss": 5.6097,
|
|
"mean_token_accuracy": 0.164577679336071,
|
|
"num_tokens": 12451846.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.676789951324463,
|
|
"epoch": 0.5382562277580071,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004978172950487486,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.16925608962774277,
|
|
"num_tokens": 12462051.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.684180641174317,
|
|
"epoch": 0.5387504942665085,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978123886873797,
|
|
"loss": 5.545,
|
|
"mean_token_accuracy": 0.17861524373292922,
|
|
"num_tokens": 12472730.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.683681583404541,
|
|
"epoch": 0.5392447607750099,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978074768447915,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.1749737024307251,
|
|
"num_tokens": 12482719.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.748501873016357,
|
|
"epoch": 0.5397390272835113,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978025595211048,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.1683576837182045,
|
|
"num_tokens": 12492659.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.790758562088013,
|
|
"epoch": 0.5402332937920127,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977976367164404,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.1665663555264473,
|
|
"num_tokens": 12504381.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.6942610263824465,
|
|
"epoch": 0.540727560300514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977927084309198,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1772288739681244,
|
|
"num_tokens": 12515041.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.691267204284668,
|
|
"epoch": 0.5412218268090154,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977877746646639,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.16722013652324677,
|
|
"num_tokens": 12526313.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.7907003402709964,
|
|
"epoch": 0.5417160933175168,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977828354177941,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.15498405396938325,
|
|
"num_tokens": 12538268.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.777811098098755,
|
|
"epoch": 0.5422103598260182,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977778906904321,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.16466692537069322,
|
|
"num_tokens": 12548365.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.849130344390869,
|
|
"epoch": 0.5427046263345195,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977729404826995,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.15030242949724198,
|
|
"num_tokens": 12560652.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.714632272720337,
|
|
"epoch": 0.5431988928430209,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977679847947179,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.16829998344182967,
|
|
"num_tokens": 12572079.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.679509258270263,
|
|
"epoch": 0.5436931593515223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977630236266093,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.1743745058774948,
|
|
"num_tokens": 12582601.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.77316460609436,
|
|
"epoch": 0.5441874258600238,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977580569784958,
|
|
"loss": 5.6635,
|
|
"mean_token_accuracy": 0.16144387871026994,
|
|
"num_tokens": 12595176.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.757938575744629,
|
|
"epoch": 0.5446816923685251,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977530848504994,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.16181547343730926,
|
|
"num_tokens": 12608161.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.699899101257325,
|
|
"epoch": 0.5451759588770265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977481072427427,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.16553007513284684,
|
|
"num_tokens": 12620109.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.766800355911255,
|
|
"epoch": 0.5456702253855279,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497743124155348,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.16293988972902299,
|
|
"num_tokens": 12630339.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.765465974807739,
|
|
"epoch": 0.5461644918940293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004977381355884379,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.16255575716495513,
|
|
"num_tokens": 12642101.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.8416228771209715,
|
|
"epoch": 0.5466587584025306,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977331415421351,
|
|
"loss": 5.7781,
|
|
"mean_token_accuracy": 0.1493564158678055,
|
|
"num_tokens": 12655436.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.6495123386383055,
|
|
"epoch": 0.547153024911032,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977281420165624,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.17330996543169022,
|
|
"num_tokens": 12667100.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.7650047779083256,
|
|
"epoch": 0.5476472914195334,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497723137011843,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.15992749333381653,
|
|
"num_tokens": 12678788.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.7259876251220705,
|
|
"epoch": 0.5481415579280348,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977181265280997,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.1725109562277794,
|
|
"num_tokens": 12690980.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.7729026794433596,
|
|
"epoch": 0.5486358244365361,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497713110565456,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.16004567444324494,
|
|
"num_tokens": 12702642.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.6960389614105225,
|
|
"epoch": 0.5491300909450376,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977080891240352,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.17500390708446503,
|
|
"num_tokens": 12712750.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.659052562713623,
|
|
"epoch": 0.549624357453539,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497703062203961,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1729139879345894,
|
|
"num_tokens": 12724464.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.704907751083374,
|
|
"epoch": 0.5501186239620404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976980298053567,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.1709088146686554,
|
|
"num_tokens": 12735419.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.834803247451783,
|
|
"epoch": 0.5506128904705417,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004976929919283465,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.1661352351307869,
|
|
"num_tokens": 12746279.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.742338514328003,
|
|
"epoch": 0.5511071569790431,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976879485730541,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.16276242285966874,
|
|
"num_tokens": 12758107.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.6818274974823,
|
|
"epoch": 0.5516014234875445,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976828997396036,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.17275306284427644,
|
|
"num_tokens": 12769354.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.77205867767334,
|
|
"epoch": 0.5520956899960459,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004976778454281193,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.1661728262901306,
|
|
"num_tokens": 12780926.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.774640798568726,
|
|
"epoch": 0.5525899565045472,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976727856387253,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16497422531247138,
|
|
"num_tokens": 12792423.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.633692646026612,
|
|
"epoch": 0.5530842230130486,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004976677203715464,
|
|
"loss": 5.53,
|
|
"mean_token_accuracy": 0.17567701190710067,
|
|
"num_tokens": 12803688.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.649878311157226,
|
|
"epoch": 0.55357848952155,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497662649626707,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.17458135932683944,
|
|
"num_tokens": 12814617.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.685574197769165,
|
|
"epoch": 0.5540727560300513,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004976575734043318,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.16831536889076232,
|
|
"num_tokens": 12826027.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.6816685676574705,
|
|
"epoch": 0.5545670225385528,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976524917045457,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.16218171268701553,
|
|
"num_tokens": 12837454.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.696161699295044,
|
|
"epoch": 0.5550612890470542,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000497647404527474,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.164781853556633,
|
|
"num_tokens": 12848550.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.724854278564453,
|
|
"epoch": 0.5555555555555556,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976423118732413,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.17227403670549393,
|
|
"num_tokens": 12858270.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.63793978691101,
|
|
"epoch": 0.556049822064057,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004976372137419733,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.16868496388196946,
|
|
"num_tokens": 12869507.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.715847730636597,
|
|
"epoch": 0.5565440885725583,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004976321101337954,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.1710936591029167,
|
|
"num_tokens": 12880097.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.646582412719726,
|
|
"epoch": 0.5570383550810597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497627001048833,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.17379364520311355,
|
|
"num_tokens": 12891302.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.685064888000488,
|
|
"epoch": 0.5575326215895611,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976218864872118,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.17701308131217958,
|
|
"num_tokens": 12903950.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.656121778488159,
|
|
"epoch": 0.5580268880980624,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976167664490576,
|
|
"loss": 5.5884,
|
|
"mean_token_accuracy": 0.16899484097957612,
|
|
"num_tokens": 12915713.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.704486417770386,
|
|
"epoch": 0.5585211546065638,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976116409344966,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.16963341385126113,
|
|
"num_tokens": 12926655.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.652594375610351,
|
|
"epoch": 0.5590154211150652,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976065099436546,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.1710340917110443,
|
|
"num_tokens": 12938144.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.7415131568908695,
|
|
"epoch": 0.5595096876235667,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976013734766579,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.16178013682365416,
|
|
"num_tokens": 12950486.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.723533725738525,
|
|
"epoch": 0.560003954132068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497596231533633,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17364926040172576,
|
|
"num_tokens": 12960966.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.601023530960083,
|
|
"epoch": 0.5604982206405694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497591084114706,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.1665319785475731,
|
|
"num_tokens": 12971960.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.735977697372436,
|
|
"epoch": 0.5609924871490708,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497585931220004,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.16618375331163407,
|
|
"num_tokens": 12984186.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.706265687942505,
|
|
"epoch": 0.5614867536575722,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975807728496535,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.1756299391388893,
|
|
"num_tokens": 12994205.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.668552684783935,
|
|
"epoch": 0.5619810201660735,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975756090037815,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.1694076254963875,
|
|
"num_tokens": 13006143.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.817729330062866,
|
|
"epoch": 0.5624752866745749,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497570439682515,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.16744023710489273,
|
|
"num_tokens": 13017849.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.620022344589233,
|
|
"epoch": 0.5629695531830763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497565264885981,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.17454515099525453,
|
|
"num_tokens": 13030301.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.698946809768676,
|
|
"epoch": 0.5634638196915777,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975600846143072,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.1720413014292717,
|
|
"num_tokens": 13040229.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.683069324493408,
|
|
"epoch": 0.563958086200079,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975548988676206,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.17362231016159058,
|
|
"num_tokens": 13050752.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.699236249923706,
|
|
"epoch": 0.5644523527085805,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975497076460491,
|
|
"loss": 5.7391,
|
|
"mean_token_accuracy": 0.1612805739045143,
|
|
"num_tokens": 13062003.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.7396767139434814,
|
|
"epoch": 0.5649466192170819,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004975445109497202,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.16006017327308655,
|
|
"num_tokens": 13073746.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.834419918060303,
|
|
"epoch": 0.5654408857255833,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004975393087787617,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.1578728273510933,
|
|
"num_tokens": 13086068.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.740988731384277,
|
|
"epoch": 0.5659351522340846,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975341011333019,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.16349433213472367,
|
|
"num_tokens": 13097078.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.699727344512939,
|
|
"epoch": 0.566429418742586,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004975288880134685,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.1612154707312584,
|
|
"num_tokens": 13108450.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.720275020599365,
|
|
"epoch": 0.5669236852510874,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004975236694193901,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.1629218801856041,
|
|
"num_tokens": 13120216.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.742605304718017,
|
|
"epoch": 0.5674179517595888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004975184453511948,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.1631760776042938,
|
|
"num_tokens": 13131214.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.742444276809692,
|
|
"epoch": 0.5679122182680901,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004975132158090112,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.15738303810358048,
|
|
"num_tokens": 13143792.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.668050956726074,
|
|
"epoch": 0.5684064847765915,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000497507980792968,
|
|
"loss": 5.6573,
|
|
"mean_token_accuracy": 0.16028801202774048,
|
|
"num_tokens": 13156022.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.73960542678833,
|
|
"epoch": 0.5689007512850929,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000497502740303194,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.1732250466942787,
|
|
"num_tokens": 13167374.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.648099613189697,
|
|
"epoch": 0.5693950177935944,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497497494339818,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.17195493578910828,
|
|
"num_tokens": 13177662.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.709104871749878,
|
|
"epoch": 0.5698892843020957,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974922429029692,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.16826786249876022,
|
|
"num_tokens": 13188375.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.758110857009887,
|
|
"epoch": 0.5703835508105971,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004974869859927767,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.17076949924230575,
|
|
"num_tokens": 13198988.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.720084142684937,
|
|
"epoch": 0.5708778173190985,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004974817236093697,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.1592240959405899,
|
|
"num_tokens": 13210699.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.637733507156372,
|
|
"epoch": 0.5713720838275999,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974764557528779,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.1717037871479988,
|
|
"num_tokens": 13221925.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.680887079238891,
|
|
"epoch": 0.5718663503361012,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004974711824234308,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.16421301513910294,
|
|
"num_tokens": 13233278.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.773726081848144,
|
|
"epoch": 0.5723606168446026,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497465903621158,
|
|
"loss": 5.6253,
|
|
"mean_token_accuracy": 0.16673623025417328,
|
|
"num_tokens": 13245423.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.731890487670898,
|
|
"epoch": 0.572854883353104,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974606193461895,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.1693289190530777,
|
|
"num_tokens": 13256312.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.704548072814942,
|
|
"epoch": 0.5733491498616053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974553295986553,
|
|
"loss": 5.6262,
|
|
"mean_token_accuracy": 0.16829162538051606,
|
|
"num_tokens": 13268158.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.713368701934814,
|
|
"epoch": 0.5738434163701067,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974500343786854,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.16920052766799926,
|
|
"num_tokens": 13279625.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.799105310440064,
|
|
"epoch": 0.5743376828786081,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974447336864102,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.1672863930463791,
|
|
"num_tokens": 13291967.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.614661169052124,
|
|
"epoch": 0.5748319493871096,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049743942752196,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.18089475929737092,
|
|
"num_tokens": 13303641.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.658901023864746,
|
|
"epoch": 0.575326215895611,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974341158854654,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.17077338099479675,
|
|
"num_tokens": 13314754.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.722897005081177,
|
|
"epoch": 0.5758204824041123,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004974287987770571,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.16417178958654405,
|
|
"num_tokens": 13325574.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.6547017097473145,
|
|
"epoch": 0.5763147489126137,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004974234761968658,
|
|
"loss": 5.5772,
|
|
"mean_token_accuracy": 0.17608380019664766,
|
|
"num_tokens": 13335946.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.674869012832642,
|
|
"epoch": 0.5768090154211151,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974181481450224,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.17105835527181626,
|
|
"num_tokens": 13347812.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.629445028305054,
|
|
"epoch": 0.5773032819296164,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974128146216581,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.16943568140268325,
|
|
"num_tokens": 13358492.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.758224630355835,
|
|
"epoch": 0.5777975484381178,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974074756269042,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.15702314525842667,
|
|
"num_tokens": 13370465.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.73775086402893,
|
|
"epoch": 0.5782918149466192,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974021311608917,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.17760482877492906,
|
|
"num_tokens": 13382328.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.69470067024231,
|
|
"epoch": 0.5787860814551206,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973967812237523,
|
|
"loss": 5.678,
|
|
"mean_token_accuracy": 0.1595865696668625,
|
|
"num_tokens": 13393439.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.7086540222167965,
|
|
"epoch": 0.5792803479636219,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973914258156177,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.16765545457601547,
|
|
"num_tokens": 13404778.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.7404036045074465,
|
|
"epoch": 0.5797746144721234,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004973860649366195,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.16709479689598083,
|
|
"num_tokens": 13417031.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.672768402099609,
|
|
"epoch": 0.5802688809806248,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004973806985868895,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.16846947371959686,
|
|
"num_tokens": 13428030.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.712587213516235,
|
|
"epoch": 0.5807631474891262,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973753267665599,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.17411057651042938,
|
|
"num_tokens": 13438934.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.72086501121521,
|
|
"epoch": 0.5812574139976275,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973699494757627,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.16572324186563492,
|
|
"num_tokens": 13450542.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.622107124328613,
|
|
"epoch": 0.5817516805061289,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004973645667146302,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.17441771924495697,
|
|
"num_tokens": 13462382.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.7249480247497555,
|
|
"epoch": 0.5822459470146303,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973591784832949,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.16247452050447464,
|
|
"num_tokens": 13473852.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.7773271083831785,
|
|
"epoch": 0.5827402135231317,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973537847818894,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.1639012798666954,
|
|
"num_tokens": 13485763.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.649251317977905,
|
|
"epoch": 0.583234480031633,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973483856105462,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.1607826381921768,
|
|
"num_tokens": 13498154.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.829303026199341,
|
|
"epoch": 0.5837287465401344,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004973429809693983,
|
|
"loss": 5.656,
|
|
"mean_token_accuracy": 0.16186068207025528,
|
|
"num_tokens": 13510563.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.863223314285278,
|
|
"epoch": 0.5842230130486358,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004973375708585785,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.16485862880945207,
|
|
"num_tokens": 13521987.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.714617109298706,
|
|
"epoch": 0.5847172795571373,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973321552782201,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.16140466630458833,
|
|
"num_tokens": 13534075.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.746452903747558,
|
|
"epoch": 0.5852115460656386,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000497326734228456,
|
|
"loss": 5.7727,
|
|
"mean_token_accuracy": 0.15622720271348953,
|
|
"num_tokens": 13546201.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.772160863876342,
|
|
"epoch": 0.58570581257414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973213077094199,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.16938103139400482,
|
|
"num_tokens": 13556985.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.77082633972168,
|
|
"epoch": 0.5862000790826414,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973158757212451,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.1655562251806259,
|
|
"num_tokens": 13568617.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.623540163040161,
|
|
"epoch": 0.5866943455911428,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973104382640652,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.16755346357822418,
|
|
"num_tokens": 13581326.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.649063301086426,
|
|
"epoch": 0.5871886120996441,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973049953380141,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.1678655058145523,
|
|
"num_tokens": 13591776.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.829496955871582,
|
|
"epoch": 0.5876828786081455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004972995469432256,
|
|
"loss": 5.7422,
|
|
"mean_token_accuracy": 0.15844642072916032,
|
|
"num_tokens": 13603475.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.6994654655456545,
|
|
"epoch": 0.5881771451166469,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972940930798338,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16453129053115845,
|
|
"num_tokens": 13615348.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.62861909866333,
|
|
"epoch": 0.5886714116251482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972886337479727,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.17441523522138597,
|
|
"num_tokens": 13625982.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.766676044464111,
|
|
"epoch": 0.5891656781336496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972831689477768,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.16168273687362672,
|
|
"num_tokens": 13637203.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.737567996978759,
|
|
"epoch": 0.5896599446421511,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004972776986793806,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.17017118036746978,
|
|
"num_tokens": 13648880.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.728174495697021,
|
|
"epoch": 0.5901542111506525,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004972722229429184,
|
|
"loss": 5.6425,
|
|
"mean_token_accuracy": 0.16740593761205674,
|
|
"num_tokens": 13660266.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.82950177192688,
|
|
"epoch": 0.5906484776591538,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497266741738525,
|
|
"loss": 5.7098,
|
|
"mean_token_accuracy": 0.15919240713119506,
|
|
"num_tokens": 13672063.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.756301355361939,
|
|
"epoch": 0.5911427441676552,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004972612550663353,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.17046781480312348,
|
|
"num_tokens": 13683379.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.682527637481689,
|
|
"epoch": 0.5916370106761566,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972557629264842,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.17318414598703386,
|
|
"num_tokens": 13694512.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.669981288909912,
|
|
"epoch": 0.592131277184658,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972502653191069,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1699911579489708,
|
|
"num_tokens": 13705642.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.609452962875366,
|
|
"epoch": 0.5926255436931593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972447622443387,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.17686308175325394,
|
|
"num_tokens": 13717367.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.6450916767120365,
|
|
"epoch": 0.5931198102016607,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004972392537023147,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.17079807072877884,
|
|
"num_tokens": 13728577.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5931198102016607,
|
|
"eval_entropy": 5.623000582264505,
|
|
"eval_loss": 5.650084972381592,
|
|
"eval_mean_token_accuracy": 0.17154138551756903,
|
|
"eval_num_tokens": 13728577.0,
|
|
"eval_runtime": 26.6267,
|
|
"eval_samples_per_second": 1221.067,
|
|
"eval_steps_per_second": 152.666,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.725990629196167,
|
|
"epoch": 0.5936140767101621,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004972337396931707,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.16376649141311644,
|
|
"num_tokens": 13739016.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.725795793533325,
|
|
"epoch": 0.5941083432186635,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004972282202170421,
|
|
"loss": 5.6033,
|
|
"mean_token_accuracy": 0.16022278890013694,
|
|
"num_tokens": 13749971.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.725154304504395,
|
|
"epoch": 0.5946026097271648,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000497222695274065,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16687688678503038,
|
|
"num_tokens": 13760927.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.707194089889526,
|
|
"epoch": 0.5950968762356663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004972171648643749,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.16560511887073517,
|
|
"num_tokens": 13772725.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.712656164169312,
|
|
"epoch": 0.5955911427441677,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972116289881082,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.16957129240036012,
|
|
"num_tokens": 13783427.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.677296209335327,
|
|
"epoch": 0.5960854092526691,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497206087645401,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.1751245602965355,
|
|
"num_tokens": 13794045.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.697005558013916,
|
|
"epoch": 0.5965796757611704,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972005408363894,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.1742756336927414,
|
|
"num_tokens": 13805629.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.67787880897522,
|
|
"epoch": 0.5970739422696718,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971949885612102,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.1641991913318634,
|
|
"num_tokens": 13817526.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.795112180709839,
|
|
"epoch": 0.5975682087781732,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971894308199997,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.17338454872369766,
|
|
"num_tokens": 13828553.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.720971584320068,
|
|
"epoch": 0.5980624752866746,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971838676128947,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.17017324715852739,
|
|
"num_tokens": 13840323.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.596181154251099,
|
|
"epoch": 0.5985567417951759,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971782989400323,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.17224780172109605,
|
|
"num_tokens": 13853524.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.675794219970703,
|
|
"epoch": 0.5990510083036773,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004971727248015491,
|
|
"loss": 5.5485,
|
|
"mean_token_accuracy": 0.16877291947603226,
|
|
"num_tokens": 13864462.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.714971303939819,
|
|
"epoch": 0.5995452748121787,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971671451975823,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.17197156250476836,
|
|
"num_tokens": 13876615.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.712807703018188,
|
|
"epoch": 0.6000395413206802,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971615601282695,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.16570689976215364,
|
|
"num_tokens": 13887652.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.717807340621948,
|
|
"epoch": 0.6005338078291815,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971559695937477,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.17209246903657913,
|
|
"num_tokens": 13898961.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.744140768051148,
|
|
"epoch": 0.6010280743376829,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004971503735941547,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.1705047830939293,
|
|
"num_tokens": 13909904.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.776770496368409,
|
|
"epoch": 0.6015223408461843,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497144772129628,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.16055092066526414,
|
|
"num_tokens": 13921376.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.678348445892334,
|
|
"epoch": 0.6020166073546857,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971391652003054,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.17085177153348924,
|
|
"num_tokens": 13932925.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.703034973144531,
|
|
"epoch": 0.602510873863187,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000497133552806325,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.16667504459619523,
|
|
"num_tokens": 13945010.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.706571960449219,
|
|
"epoch": 0.6030051403716884,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971279349478245,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.15993823260068893,
|
|
"num_tokens": 13957710.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.610738515853882,
|
|
"epoch": 0.6034994068801898,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971223116249424,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.18548814803361893,
|
|
"num_tokens": 13967819.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.82705340385437,
|
|
"epoch": 0.6039936733886911,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004971166828378172,
|
|
"loss": 5.773,
|
|
"mean_token_accuracy": 0.15484535545110703,
|
|
"num_tokens": 13980342.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.797467565536499,
|
|
"epoch": 0.6044879398971925,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497111048586587,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.16763532161712646,
|
|
"num_tokens": 13990370.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.715801668167114,
|
|
"epoch": 0.604982206405694,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971054088713905,
|
|
"loss": 5.622,
|
|
"mean_token_accuracy": 0.17192617505788804,
|
|
"num_tokens": 14001761.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.728423643112182,
|
|
"epoch": 0.6054764729141954,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970997636923665,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.16754135489463806,
|
|
"num_tokens": 14012980.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.72521653175354,
|
|
"epoch": 0.6059707394226967,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497094113049654,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.1669625982642174,
|
|
"num_tokens": 14023609.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.694964075088501,
|
|
"epoch": 0.6064650059311981,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004970884569433917,
|
|
"loss": 5.6946,
|
|
"mean_token_accuracy": 0.16381505131721497,
|
|
"num_tokens": 14036052.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.6773027896881105,
|
|
"epoch": 0.6069592724396995,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000497082795373719,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.17903590500354766,
|
|
"num_tokens": 14047932.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.732246541976929,
|
|
"epoch": 0.6074535389482009,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970771283407749,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1745848461985588,
|
|
"num_tokens": 14059674.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.743846273422241,
|
|
"epoch": 0.6079478054567022,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004970714558446992,
|
|
"loss": 5.6577,
|
|
"mean_token_accuracy": 0.1661330431699753,
|
|
"num_tokens": 14070753.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.700803804397583,
|
|
"epoch": 0.6084420719652036,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004970657778856312,
|
|
"loss": 5.6227,
|
|
"mean_token_accuracy": 0.16640214622020721,
|
|
"num_tokens": 14083565.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.82107515335083,
|
|
"epoch": 0.608936338473705,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004970600944637106,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.15941301435232164,
|
|
"num_tokens": 14095008.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.633291912078858,
|
|
"epoch": 0.6094306049822064,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004970544055790772,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16983198821544648,
|
|
"num_tokens": 14106586.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.591522598266602,
|
|
"epoch": 0.6099248714907078,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000497048711231871,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.1780157968401909,
|
|
"num_tokens": 14117778.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.6862329006195065,
|
|
"epoch": 0.6104191379992092,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970430114222319,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.17020316869020463,
|
|
"num_tokens": 14129644.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.59258017539978,
|
|
"epoch": 0.6109134045077106,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004970373061503005,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.17041065245866777,
|
|
"num_tokens": 14141230.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.72203049659729,
|
|
"epoch": 0.611407671016212,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004970315954162169,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.16771750748157502,
|
|
"num_tokens": 14151622.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.773579788208008,
|
|
"epoch": 0.6119019375247133,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970258792201214,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.16711233407258988,
|
|
"num_tokens": 14163641.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.682190322875977,
|
|
"epoch": 0.6123962040332147,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000497020157562155,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.17137633711099626,
|
|
"num_tokens": 14175154.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.710550832748413,
|
|
"epoch": 0.6128904705417161,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004970144304424582,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.1691551387310028,
|
|
"num_tokens": 14185472.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.692292404174805,
|
|
"epoch": 0.6133847370502175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497008697861172,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.16872512251138688,
|
|
"num_tokens": 14196992.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.660149669647216,
|
|
"epoch": 0.6138790035587188,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004970029598184375,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.16924096643924713,
|
|
"num_tokens": 14207732.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.8436925411224365,
|
|
"epoch": 0.6143732700672202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969972163143956,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.15913701802492142,
|
|
"num_tokens": 14219164.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.745255947113037,
|
|
"epoch": 0.6148675365757216,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969914673491878,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.1608384668827057,
|
|
"num_tokens": 14231687.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.698350954055786,
|
|
"epoch": 0.6153618030842231,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969857129229555,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.17509960234165192,
|
|
"num_tokens": 14243099.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.7591224193573,
|
|
"epoch": 0.6158560695927244,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004969799530358402,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.16131601333618165,
|
|
"num_tokens": 14255835.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.6425926208496096,
|
|
"epoch": 0.6163503361012258,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969741876879835,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.168407578766346,
|
|
"num_tokens": 14266661.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.693798398971557,
|
|
"epoch": 0.6168446026097272,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004969684168795275,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.16673884838819503,
|
|
"num_tokens": 14278474.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.739871311187744,
|
|
"epoch": 0.6173388691182286,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969626406106139,
|
|
"loss": 5.5718,
|
|
"mean_token_accuracy": 0.17126580476760864,
|
|
"num_tokens": 14289516.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.6545881748199465,
|
|
"epoch": 0.6178331356267299,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969568588813851,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.17091088145971298,
|
|
"num_tokens": 14301312.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.725562572479248,
|
|
"epoch": 0.6183274021352313,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004969510716919829,
|
|
"loss": 5.5571,
|
|
"mean_token_accuracy": 0.17008514255285262,
|
|
"num_tokens": 14312009.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.651212072372436,
|
|
"epoch": 0.6188216686437327,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00049694527904255,
|
|
"loss": 5.604,
|
|
"mean_token_accuracy": 0.17439033538103105,
|
|
"num_tokens": 14322754.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.61071286201477,
|
|
"epoch": 0.619315935152234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969394809332287,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.17389941662549974,
|
|
"num_tokens": 14333939.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.712346601486206,
|
|
"epoch": 0.6198102016607354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969336773641619,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.1710933431982994,
|
|
"num_tokens": 14345987.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.740022897720337,
|
|
"epoch": 0.6203044681692369,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004969278683354921,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16085884869098663,
|
|
"num_tokens": 14356974.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.695273113250733,
|
|
"epoch": 0.6207987346777383,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969220538473625,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.15960700064897537,
|
|
"num_tokens": 14368175.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.678928327560425,
|
|
"epoch": 0.6212930011862396,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969162338999157,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.1624092549085617,
|
|
"num_tokens": 14379067.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.763182163238525,
|
|
"epoch": 0.621787267694741,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969104084932953,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.16225227415561677,
|
|
"num_tokens": 14390483.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.760966491699219,
|
|
"epoch": 0.6222815342032424,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969045776276443,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.16652594655752181,
|
|
"num_tokens": 14402757.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.6970720291137695,
|
|
"epoch": 0.6227758007117438,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004968987413031063,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.1684049814939499,
|
|
"num_tokens": 14413829.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.724343252182007,
|
|
"epoch": 0.6232700672202451,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968928995198249,
|
|
"loss": 5.6837,
|
|
"mean_token_accuracy": 0.1591377727687359,
|
|
"num_tokens": 14425165.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.753953886032105,
|
|
"epoch": 0.6237643337287465,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004968870522779437,
|
|
"loss": 5.6162,
|
|
"mean_token_accuracy": 0.16411857903003693,
|
|
"num_tokens": 14436264.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.647160291671753,
|
|
"epoch": 0.6242586002372479,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004968811995776066,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.16551996320486068,
|
|
"num_tokens": 14447384.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.815277624130249,
|
|
"epoch": 0.6247528667457493,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004968753414189576,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1634001538157463,
|
|
"num_tokens": 14460013.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.746469306945801,
|
|
"epoch": 0.6252471332542507,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968694778021408,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.1704400897026062,
|
|
"num_tokens": 14472452.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.66473126411438,
|
|
"epoch": 0.6257413997627521,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968636087273003,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.16714949011802674,
|
|
"num_tokens": 14484487.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.646205759048462,
|
|
"epoch": 0.6262356662712535,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004968577341945806,
|
|
"loss": 5.5247,
|
|
"mean_token_accuracy": 0.1705595314502716,
|
|
"num_tokens": 14496043.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.681616544723511,
|
|
"epoch": 0.6267299327797549,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004968518542041264,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.16577404588460923,
|
|
"num_tokens": 14508089.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.821450901031494,
|
|
"epoch": 0.6272241992882562,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496845968756082,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.16220155507326126,
|
|
"num_tokens": 14519480.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.704720592498779,
|
|
"epoch": 0.6277184657967576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968400778505925,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.17199382930994034,
|
|
"num_tokens": 14531214.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.756743717193603,
|
|
"epoch": 0.628212732305259,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004968341814878025,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.1700585663318634,
|
|
"num_tokens": 14544118.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.804705667495727,
|
|
"epoch": 0.6287069988137604,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004968282796678573,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.1700154185295105,
|
|
"num_tokens": 14555545.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.642587280273437,
|
|
"epoch": 0.6292012653222617,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000496822372390902,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.16984758973121644,
|
|
"num_tokens": 14567157.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.634347820281983,
|
|
"epoch": 0.6296955318307631,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496816459657082,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.17711049914360047,
|
|
"num_tokens": 14577074.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.691836547851563,
|
|
"epoch": 0.6301897983392646,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968105414665426,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.1702039822936058,
|
|
"num_tokens": 14589133.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.6907792568206785,
|
|
"epoch": 0.630684064847766,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004968046178194295,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.16890185922384263,
|
|
"num_tokens": 14600985.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.733117151260376,
|
|
"epoch": 0.6311783313562673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004967986887158884,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.1713898241519928,
|
|
"num_tokens": 14612163.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.679244136810302,
|
|
"epoch": 0.6316725978647687,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967927541560651,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.17176640033721924,
|
|
"num_tokens": 14623045.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.71518087387085,
|
|
"epoch": 0.6321668643732701,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004967868141401056,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.16551804542541504,
|
|
"num_tokens": 14634696.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.792819881439209,
|
|
"epoch": 0.6326611308817714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004967808686681562,
|
|
"loss": 5.6193,
|
|
"mean_token_accuracy": 0.1628395602107048,
|
|
"num_tokens": 14645589.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.725550842285156,
|
|
"epoch": 0.6331553973902728,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967749177403629,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.16820747405290604,
|
|
"num_tokens": 14657199.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.695582056045533,
|
|
"epoch": 0.6336496638987742,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004967689613568723,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.16525799185037612,
|
|
"num_tokens": 14668767.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.6568522453308105,
|
|
"epoch": 0.6341439304072756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967629995178309,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.1723042234778404,
|
|
"num_tokens": 14680860.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.607360792160034,
|
|
"epoch": 0.6346381969157769,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004967570322233852,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.17480553239583968,
|
|
"num_tokens": 14692134.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.652781629562378,
|
|
"epoch": 0.6351324634242784,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004967510594736822,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.1665668785572052,
|
|
"num_tokens": 14703323.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.692604732513428,
|
|
"epoch": 0.6356267299327798,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967450812688686,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.17291828244924545,
|
|
"num_tokens": 14714453.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.721577596664429,
|
|
"epoch": 0.6361209964412812,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004967390976090917,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.16869455575942993,
|
|
"num_tokens": 14726562.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.607173681259155,
|
|
"epoch": 0.6366152629497825,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004967331084944986,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.17830694168806077,
|
|
"num_tokens": 14738054.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.652015161514282,
|
|
"epoch": 0.6371095294582839,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004967271139252365,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.1684100016951561,
|
|
"num_tokens": 14749037.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.696839761734009,
|
|
"epoch": 0.6376037959667853,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004967211139014531,
|
|
"loss": 5.5301,
|
|
"mean_token_accuracy": 0.17051022201776506,
|
|
"num_tokens": 14759667.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.687182235717773,
|
|
"epoch": 0.6380980624752867,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000496715108423296,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.16854980289936067,
|
|
"num_tokens": 14770866.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.719784164428711,
|
|
"epoch": 0.638592328983788,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004967090974909127,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.16890285909175873,
|
|
"num_tokens": 14783095.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.72447624206543,
|
|
"epoch": 0.6390865954922894,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004967030811044512,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.16301210075616837,
|
|
"num_tokens": 14794046.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.6843085289001465,
|
|
"epoch": 0.6395808620007908,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004966970592640596,
|
|
"loss": 5.6291,
|
|
"mean_token_accuracy": 0.16662883162498474,
|
|
"num_tokens": 14807295.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.692246198654175,
|
|
"epoch": 0.6400751285092922,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004966910319698859,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.1773160293698311,
|
|
"num_tokens": 14819109.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.701455974578858,
|
|
"epoch": 0.6405693950177936,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004966849992220784,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.17304152399301528,
|
|
"num_tokens": 14830719.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.721877765655518,
|
|
"epoch": 0.641063661526295,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004966789610207856,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.16639412492513656,
|
|
"num_tokens": 14843392.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.688205289840698,
|
|
"epoch": 0.6415579280347964,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004966729173661559,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.1772479608654976,
|
|
"num_tokens": 14855745.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.7421760082244875,
|
|
"epoch": 0.6420521945432978,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000496666868258338,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.16403735429048538,
|
|
"num_tokens": 14868053.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.630947303771973,
|
|
"epoch": 0.6425464610517991,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966608136974809,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.1717897355556488,
|
|
"num_tokens": 14880095.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.743942451477051,
|
|
"epoch": 0.6430407275603005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004966547536837333,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.16163052916526793,
|
|
"num_tokens": 14891013.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.752167367935181,
|
|
"epoch": 0.6435349940688019,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966486882172444,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.17326559424400328,
|
|
"num_tokens": 14901875.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.628373670578003,
|
|
"epoch": 0.6440292605773033,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966426172981634,
|
|
"loss": 5.5831,
|
|
"mean_token_accuracy": 0.17210329324007034,
|
|
"num_tokens": 14912620.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.598806619644165,
|
|
"epoch": 0.6445235270858046,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004966365409266396,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.1745615616440773,
|
|
"num_tokens": 14923128.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.710566520690918,
|
|
"epoch": 0.645017793594306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966304591028225,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.17126042395830154,
|
|
"num_tokens": 14933621.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.5962084293365475,
|
|
"epoch": 0.6455120601028075,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004966243718268617,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.17190637886524202,
|
|
"num_tokens": 14943292.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.62079086303711,
|
|
"epoch": 0.6460063266113089,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496618279098907,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.16562688797712327,
|
|
"num_tokens": 14953998.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.76866455078125,
|
|
"epoch": 0.6465005931198102,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004966121809191083,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.16886703073978424,
|
|
"num_tokens": 14965430.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.670724630355835,
|
|
"epoch": 0.6469948596283116,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004966060772876156,
|
|
"loss": 5.4729,
|
|
"mean_token_accuracy": 0.1737997591495514,
|
|
"num_tokens": 14977124.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.655364227294922,
|
|
"epoch": 0.647489126136813,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004965999682045788,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.1760694295167923,
|
|
"num_tokens": 14987069.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.57450680732727,
|
|
"epoch": 0.6479833926453143,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004965938536701486,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.18012892007827758,
|
|
"num_tokens": 14997919.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.664482736587525,
|
|
"epoch": 0.6484776591538157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004965877336844752,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.17142418771982193,
|
|
"num_tokens": 15010042.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.747743415832519,
|
|
"epoch": 0.6489719256623171,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004965816082477091,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.17967990189790725,
|
|
"num_tokens": 15021166.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.6996564865112305,
|
|
"epoch": 0.6494661921708185,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965754773600011,
|
|
"loss": 5.5766,
|
|
"mean_token_accuracy": 0.1690806195139885,
|
|
"num_tokens": 15032182.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.625746250152588,
|
|
"epoch": 0.6499604586793198,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000496569341021502,
|
|
"loss": 5.5359,
|
|
"mean_token_accuracy": 0.17030431479215621,
|
|
"num_tokens": 15043054.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.604121541976928,
|
|
"epoch": 0.6504547251878213,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004965631992323628,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1802733212709427,
|
|
"num_tokens": 15055462.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.696477317810059,
|
|
"epoch": 0.6509489916963227,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004965570519927345,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.1704359844326973,
|
|
"num_tokens": 15066849.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.6346546649932865,
|
|
"epoch": 0.6514432582048241,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004965508993027682,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.17232700437307358,
|
|
"num_tokens": 15078388.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.7419990539550785,
|
|
"epoch": 0.6519375247133254,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004965447411626156,
|
|
"loss": 5.5811,
|
|
"mean_token_accuracy": 0.1668103128671646,
|
|
"num_tokens": 15090474.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.771066284179687,
|
|
"epoch": 0.6524317912218268,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004965385775724279,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.16424890607595444,
|
|
"num_tokens": 15101104.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.688560438156128,
|
|
"epoch": 0.6529260577303282,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004965324085323569,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.1623062625527382,
|
|
"num_tokens": 15112036.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.785910415649414,
|
|
"epoch": 0.6534203242388296,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004965262340425541,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.15628962367773055,
|
|
"num_tokens": 15124913.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.818976545333863,
|
|
"epoch": 0.6539145907473309,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004965200541031717,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.17008298635482788,
|
|
"num_tokens": 15135555.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.7481255531311035,
|
|
"epoch": 0.6544088572558323,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004965138687143616,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.1591961607336998,
|
|
"num_tokens": 15146646.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.676590156555176,
|
|
"epoch": 0.6549031237643337,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004965076778762759,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.16743184477090836,
|
|
"num_tokens": 15157101.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.744027900695801,
|
|
"epoch": 0.6553973902728352,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004965014815890671,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.16433080434799194,
|
|
"num_tokens": 15169645.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.719748592376709,
|
|
"epoch": 0.6558916567813365,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004964952798528874,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.1727913200855255,
|
|
"num_tokens": 15181018.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.652181386947632,
|
|
"epoch": 0.6563859232898379,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004964890726678894,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.16674931943416596,
|
|
"num_tokens": 15191880.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.6022193908691404,
|
|
"epoch": 0.6568801897983393,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964828600342259,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.17405013740062714,
|
|
"num_tokens": 15203886.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.728973245620727,
|
|
"epoch": 0.6573744563068407,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964766419520497,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.1757522001862526,
|
|
"num_tokens": 15215837.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.715732431411743,
|
|
"epoch": 0.657868722815342,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004964704184215138,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.1645362287759781,
|
|
"num_tokens": 15226833.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.68477349281311,
|
|
"epoch": 0.6583629893238434,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004964641894427712,
|
|
"loss": 5.6733,
|
|
"mean_token_accuracy": 0.16279211789369583,
|
|
"num_tokens": 15239312.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.7367973804473875,
|
|
"epoch": 0.6588572558323448,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004964579550159752,
|
|
"loss": 5.5362,
|
|
"mean_token_accuracy": 0.16548051536083222,
|
|
"num_tokens": 15250348.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.663200378417969,
|
|
"epoch": 0.6593515223408462,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004964517151412791,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.17534725666046141,
|
|
"num_tokens": 15261445.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.695224714279175,
|
|
"epoch": 0.6598457888493475,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004964454698188364,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.16742885261774063,
|
|
"num_tokens": 15271606.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.69695816040039,
|
|
"epoch": 0.6603400553578489,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496439219048801,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.16876146495342254,
|
|
"num_tokens": 15283690.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.661836957931518,
|
|
"epoch": 0.6608343218663504,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004964329628313263,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.1714664250612259,
|
|
"num_tokens": 15294792.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.746123790740967,
|
|
"epoch": 0.6613285883748518,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004964267011665664,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.16992074251174927,
|
|
"num_tokens": 15305636.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.6776879787445065,
|
|
"epoch": 0.6618228548833531,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004964204340546753,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.16541284769773484,
|
|
"num_tokens": 15316495.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.676077222824096,
|
|
"epoch": 0.6623171213918545,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964141614958071,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17242127060890197,
|
|
"num_tokens": 15328246.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.753052282333374,
|
|
"epoch": 0.6628113879003559,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004964078834901163,
|
|
"loss": 5.528,
|
|
"mean_token_accuracy": 0.17213574200868606,
|
|
"num_tokens": 15339229.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.641156196594238,
|
|
"epoch": 0.6633056544088572,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000496401600037757,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.16682853996753694,
|
|
"num_tokens": 15350591.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.766100883483887,
|
|
"epoch": 0.6637999209173586,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004963953111388842,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.16456732600927354,
|
|
"num_tokens": 15363726.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.724007415771484,
|
|
"epoch": 0.66429418742586,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004963890167936524,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.17285250574350358,
|
|
"num_tokens": 15375569.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.6379697799682615,
|
|
"epoch": 0.6647884539343614,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004963827170022164,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.1602582663297653,
|
|
"num_tokens": 15387323.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.6698465824127195,
|
|
"epoch": 0.6652827204428627,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004963764117647311,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.16892581135034562,
|
|
"num_tokens": 15397912.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.569158935546875,
|
|
"epoch": 0.6657769869513642,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004963701010813519,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.18234732151031494,
|
|
"num_tokens": 15409469.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.628192329406739,
|
|
"epoch": 0.6662712534598656,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004963637849522338,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.17636486291885375,
|
|
"num_tokens": 15419681.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.751703310012817,
|
|
"epoch": 0.666765519968367,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004963574633775323,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.16640164852142333,
|
|
"num_tokens": 15431237.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.708220529556274,
|
|
"epoch": 0.6672597864768683,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963511363574027,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.16540784239768982,
|
|
"num_tokens": 15442366.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.690873384475708,
|
|
"epoch": 0.6677540529853697,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004963448038920009,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16518406718969345,
|
|
"num_tokens": 15453121.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.697871541976928,
|
|
"epoch": 0.6682483194938711,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004963384659814827,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17436859309673308,
|
|
"num_tokens": 15463489.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.7000960350036625,
|
|
"epoch": 0.6687425860023725,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004963321226260038,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.16324128359556198,
|
|
"num_tokens": 15475217.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.6706031322479244,
|
|
"epoch": 0.6692368525108738,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004963257738257203,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.16546722054481505,
|
|
"num_tokens": 15485844.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.702503204345703,
|
|
"epoch": 0.6697311190193752,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004963194195807886,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.17011529058218003,
|
|
"num_tokens": 15496835.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.651086235046387,
|
|
"epoch": 0.6702253855278766,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004963130598913646,
|
|
"loss": 5.6017,
|
|
"mean_token_accuracy": 0.17146068960428237,
|
|
"num_tokens": 15508087.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.7437934398651125,
|
|
"epoch": 0.6707196520363781,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004963066947576051,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.16306409239768982,
|
|
"num_tokens": 15519596.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.745526933670044,
|
|
"epoch": 0.6712139185448794,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004963003241796666,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.16260937750339508,
|
|
"num_tokens": 15530830.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.687871932983398,
|
|
"epoch": 0.6717081850533808,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004962939481577059,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.18101657927036285,
|
|
"num_tokens": 15543195.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.68351378440857,
|
|
"epoch": 0.6722024515618822,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004962875666918796,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.16793282330036163,
|
|
"num_tokens": 15554465.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.586322879791259,
|
|
"epoch": 0.6726967180703836,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962811797823448,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.16648100763559343,
|
|
"num_tokens": 15566016.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.765206003189087,
|
|
"epoch": 0.6731909845788849,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004962747874292588,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.16617136001586913,
|
|
"num_tokens": 15576843.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.7528962135314945,
|
|
"epoch": 0.6736852510873863,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004962683896327786,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.16992761045694352,
|
|
"num_tokens": 15588390.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.767729043960571,
|
|
"epoch": 0.6741795175958877,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004962619863930616,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.16351630240678788,
|
|
"num_tokens": 15600270.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.742923021316528,
|
|
"epoch": 0.674673784104389,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004962555777102656,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.17313138097524644,
|
|
"num_tokens": 15611617.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.625177431106567,
|
|
"epoch": 0.6751680506128904,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000496249163584548,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.17480342835187912,
|
|
"num_tokens": 15622128.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.801233100891113,
|
|
"epoch": 0.6756623171213919,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004962427440160665,
|
|
"loss": 5.5968,
|
|
"mean_token_accuracy": 0.16322340220212936,
|
|
"num_tokens": 15635250.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.789019441604614,
|
|
"epoch": 0.6761565836298933,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004962363190049794,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.161036416888237,
|
|
"num_tokens": 15646535.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.717751216888428,
|
|
"epoch": 0.6766508501383947,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962298885514444,
|
|
"loss": 5.6254,
|
|
"mean_token_accuracy": 0.17236242443323135,
|
|
"num_tokens": 15658399.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.696306562423706,
|
|
"epoch": 0.677145116646896,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962234526556199,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.17180620431900023,
|
|
"num_tokens": 15669321.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.686220741271972,
|
|
"epoch": 0.6776393831553974,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000496217011317664,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.16887103766202927,
|
|
"num_tokens": 15681666.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.63595666885376,
|
|
"epoch": 0.6781336496638988,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962105645377354,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1718195393681526,
|
|
"num_tokens": 15693432.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.655316257476807,
|
|
"epoch": 0.6786279161724001,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004962041123159926,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.1707765594124794,
|
|
"num_tokens": 15705151.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.681346988677978,
|
|
"epoch": 0.6791221826809015,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961976546525943,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.17340683341026306,
|
|
"num_tokens": 15716549.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.715093994140625,
|
|
"epoch": 0.6796164491894029,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961911915476994,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.16783855706453324,
|
|
"num_tokens": 15727499.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.657302808761597,
|
|
"epoch": 0.6801107156979043,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961847230014668,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.1739605262875557,
|
|
"num_tokens": 15739196.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.664815139770508,
|
|
"epoch": 0.6806049822064056,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961782490140558,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.17313780933618544,
|
|
"num_tokens": 15750890.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.71727614402771,
|
|
"epoch": 0.6810992487149071,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004961717695856256,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.17172631174325942,
|
|
"num_tokens": 15762366.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.685516834259033,
|
|
"epoch": 0.6815935152234085,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961652847163354,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.17113929241895676,
|
|
"num_tokens": 15773962.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.577894163131714,
|
|
"epoch": 0.6820877817319099,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000496158794406345,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.18303312808275224,
|
|
"num_tokens": 15784563.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.6565086364746096,
|
|
"epoch": 0.6825820482404112,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961522986558139,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.16684933453798295,
|
|
"num_tokens": 15796461.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.723315286636352,
|
|
"epoch": 0.6830763147489126,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496145797464902,
|
|
"loss": 5.5663,
|
|
"mean_token_accuracy": 0.16663715243339539,
|
|
"num_tokens": 15807303.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.6627425193786625,
|
|
"epoch": 0.683570581257414,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004961392908337691,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.1778472349047661,
|
|
"num_tokens": 15818964.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.65058445930481,
|
|
"epoch": 0.6840648477659154,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961327787625754,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.16614602208137513,
|
|
"num_tokens": 15831181.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.629097318649292,
|
|
"epoch": 0.6845591142744167,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496126261251481,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.17381258457899093,
|
|
"num_tokens": 15842442.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.73041181564331,
|
|
"epoch": 0.6850533807829181,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004961197383006463,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.1682095631957054,
|
|
"num_tokens": 15854755.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.5883571147918705,
|
|
"epoch": 0.6855476472914195,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961132099102316,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.1779046356678009,
|
|
"num_tokens": 15866300.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.65306077003479,
|
|
"epoch": 0.686041913799921,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004961066760803978,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.1762435957789421,
|
|
"num_tokens": 15877165.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.709772348403931,
|
|
"epoch": 0.6865361803084223,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004961001368113054,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.16317206025123596,
|
|
"num_tokens": 15888893.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.712954187393189,
|
|
"epoch": 0.6870304468169237,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004960935921031153,
|
|
"loss": 5.5881,
|
|
"mean_token_accuracy": 0.16636597663164138,
|
|
"num_tokens": 15899994.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.65991792678833,
|
|
"epoch": 0.6875247133254251,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004960870419559887,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.17744628936052323,
|
|
"num_tokens": 15911330.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.649380826950074,
|
|
"epoch": 0.6880189798339265,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004960804863700864,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.17815470993518828,
|
|
"num_tokens": 15922397.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.6634126663208,
|
|
"epoch": 0.6885132463424278,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960739253455699,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.1716514453291893,
|
|
"num_tokens": 15934628.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.657694911956787,
|
|
"epoch": 0.6890075128509292,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004960673588826005,
|
|
"loss": 5.5283,
|
|
"mean_token_accuracy": 0.17367980182170867,
|
|
"num_tokens": 15946599.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.7271201610565186,
|
|
"epoch": 0.6895017793594306,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004960607869813398,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.17368923276662826,
|
|
"num_tokens": 15957402.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.6690332889556885,
|
|
"epoch": 0.689996045867932,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004960542096419494,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.171751768887043,
|
|
"num_tokens": 15968091.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.646782255172729,
|
|
"epoch": 0.6904903123764333,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004960476268645912,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.16528935730457306,
|
|
"num_tokens": 15980809.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.706490516662598,
|
|
"epoch": 0.6909845788849348,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004960410386494271,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.16814272701740265,
|
|
"num_tokens": 15992701.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.799052286148071,
|
|
"epoch": 0.6914788453934362,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004960344449966191,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.16487115770578384,
|
|
"num_tokens": 16005871.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.76276912689209,
|
|
"epoch": 0.6919731119019376,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004960278459063296,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15949301570653915,
|
|
"num_tokens": 16018126.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.6182605743408205,
|
|
"epoch": 0.6924673784104389,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004960212413787206,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.17488146275281907,
|
|
"num_tokens": 16028694.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.688834476470947,
|
|
"epoch": 0.6929616449189403,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000496014631413955,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.1664009854197502,
|
|
"num_tokens": 16040354.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.718057155609131,
|
|
"epoch": 0.6934559114274417,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004960080160121951,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.17501124292612075,
|
|
"num_tokens": 16051713.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.681963872909546,
|
|
"epoch": 0.693950177935943,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004960013951736036,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.16454512923955916,
|
|
"num_tokens": 16064737.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.66145601272583,
|
|
"epoch": 0.6944444444444444,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959947688983436,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1752382442355156,
|
|
"num_tokens": 16075515.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.702970361709594,
|
|
"epoch": 0.6949387109529458,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004959881371865779,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.16676198542118073,
|
|
"num_tokens": 16088702.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.635191774368286,
|
|
"epoch": 0.6954329774614472,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004959815000384699,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.1688504084944725,
|
|
"num_tokens": 16101122.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.7044408321380615,
|
|
"epoch": 0.6959272439699487,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004959748574541826,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.1709022715687752,
|
|
"num_tokens": 16112817.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.748203563690185,
|
|
"epoch": 0.69642151047845,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004959682094338795,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.16054249852895736,
|
|
"num_tokens": 16124827.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.644714879989624,
|
|
"epoch": 0.6969157769869514,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004959615559777243,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.17443423420190812,
|
|
"num_tokens": 16136940.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.690960311889649,
|
|
"epoch": 0.6974100434954528,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959548970858805,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.17349713295698166,
|
|
"num_tokens": 16147541.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.6403632164001465,
|
|
"epoch": 0.6979043100039541,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004959482327585119,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.16503626555204393,
|
|
"num_tokens": 16157626.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.6378120422363285,
|
|
"epoch": 0.6983985765124555,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959415629957824,
|
|
"loss": 5.5295,
|
|
"mean_token_accuracy": 0.17656915336847306,
|
|
"num_tokens": 16168494.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.702786445617676,
|
|
"epoch": 0.6988928430209569,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004959348877978563,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.17018162608146667,
|
|
"num_tokens": 16180749.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.7330821514129635,
|
|
"epoch": 0.6993871095294583,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959282071648977,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.17312479317188262,
|
|
"num_tokens": 16193204.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.638060855865478,
|
|
"epoch": 0.6998813760379596,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000495921521097071,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.18740448951721192,
|
|
"num_tokens": 16204303.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.615123128890991,
|
|
"epoch": 0.700375642546461,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959148295945405,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.17712208330631257,
|
|
"num_tokens": 16215261.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.67879958152771,
|
|
"epoch": 0.7008699090549624,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004959081326574708,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.17279428988695145,
|
|
"num_tokens": 16226973.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.531974363327026,
|
|
"epoch": 0.7013641755634639,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959014302860271,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.1865630865097046,
|
|
"num_tokens": 16239152.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.65028944015503,
|
|
"epoch": 0.7018584420719652,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958947224803737,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.1720507934689522,
|
|
"num_tokens": 16251884.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.680198812484742,
|
|
"epoch": 0.7023527085804666,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004958880092406759,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.1591331258416176,
|
|
"num_tokens": 16262497.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.6649425506591795,
|
|
"epoch": 0.702846975088968,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958812905670988,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.17490684390068054,
|
|
"num_tokens": 16274624.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.738008213043213,
|
|
"epoch": 0.7033412415974694,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004958745664598077,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1701007217168808,
|
|
"num_tokens": 16286096.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.634075260162353,
|
|
"epoch": 0.7038355081059707,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004958678369189679,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.1769155368208885,
|
|
"num_tokens": 16297853.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.667545175552368,
|
|
"epoch": 0.7043297746144721,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004958611019447452,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.1669813796877861,
|
|
"num_tokens": 16310708.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.7172314643859865,
|
|
"epoch": 0.7048240411229735,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004958543615373051,
|
|
"loss": 5.5549,
|
|
"mean_token_accuracy": 0.16853716522455214,
|
|
"num_tokens": 16321216.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.679724979400635,
|
|
"epoch": 0.7053183076314749,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004958476156968134,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.17553720921278,
|
|
"num_tokens": 16331982.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.65666184425354,
|
|
"epoch": 0.7058125741399762,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000495840864423436,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.16790152937173844,
|
|
"num_tokens": 16343001.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.757568120956421,
|
|
"epoch": 0.7063068406484777,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004958341077173392,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.16865454167127608,
|
|
"num_tokens": 16355519.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.680486869812012,
|
|
"epoch": 0.7068011071569791,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004958273455786892,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17001449018716813,
|
|
"num_tokens": 16366342.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.705984020233155,
|
|
"epoch": 0.7072953736654805,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958205780076521,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.16321229785680771,
|
|
"num_tokens": 16378395.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.656873369216919,
|
|
"epoch": 0.7077896401739818,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004958138050043945,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.17417750507593155,
|
|
"num_tokens": 16388946.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.607640409469605,
|
|
"epoch": 0.7082839066824832,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004958070265690831,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.17076540887355804,
|
|
"num_tokens": 16399824.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.7382011890411375,
|
|
"epoch": 0.7087781731909846,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004958002427018845,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16803077310323716,
|
|
"num_tokens": 16411932.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.737635898590088,
|
|
"epoch": 0.709272439699486,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004957934534029658,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.16884183436632155,
|
|
"num_tokens": 16423634.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.673824596405029,
|
|
"epoch": 0.7097667062079873,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004957866586724938,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.17113861590623855,
|
|
"num_tokens": 16434700.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.731975889205932,
|
|
"epoch": 0.7102609727164887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004957798585106359,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.1687067300081253,
|
|
"num_tokens": 16445829.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.657315063476562,
|
|
"epoch": 0.7107552392249901,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000495773052917559,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1864163398742676,
|
|
"num_tokens": 16456352.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.620011281967163,
|
|
"epoch": 0.7112495057334915,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004957662418934309,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17442054748535157,
|
|
"num_tokens": 16467542.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.575371503829956,
|
|
"epoch": 0.7117437722419929,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004957594254384189,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.1830355703830719,
|
|
"num_tokens": 16478614.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.686612176895141,
|
|
"epoch": 0.7122380387504943,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004957526035526908,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.17437213361263276,
|
|
"num_tokens": 16489929.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.751833915710449,
|
|
"epoch": 0.7127323052589957,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004957457762364146,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.16255887895822524,
|
|
"num_tokens": 16502532.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.745519351959229,
|
|
"epoch": 0.713226571767497,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957389434897578,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.16755123287439347,
|
|
"num_tokens": 16513805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.75234055519104,
|
|
"epoch": 0.7137208382759984,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957321053128889,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.16722760647535323,
|
|
"num_tokens": 16525189.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.704683780670166,
|
|
"epoch": 0.7142151047844998,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004957252617059759,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.16636962890625,
|
|
"num_tokens": 16538246.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.70558729171753,
|
|
"epoch": 0.7147093712930012,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004957184126691873,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.1652435541152954,
|
|
"num_tokens": 16550036.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.653769636154175,
|
|
"epoch": 0.7152036378015025,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004957115582026915,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.17487559765577315,
|
|
"num_tokens": 16562262.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.653202819824219,
|
|
"epoch": 0.7156979043100039,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000495704698306657,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.17890413701534272,
|
|
"num_tokens": 16574213.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.717773485183716,
|
|
"epoch": 0.7161921708185054,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956978329812528,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.17178545147180557,
|
|
"num_tokens": 16586063.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.705108308792115,
|
|
"epoch": 0.7166864373270068,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004956909622266476,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1671637400984764,
|
|
"num_tokens": 16598014.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.692685794830322,
|
|
"epoch": 0.7171807038355081,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004956840860430104,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.1731526017189026,
|
|
"num_tokens": 16609128.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.653377103805542,
|
|
"epoch": 0.7176749703440095,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004956772044305106,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.17933865934610366,
|
|
"num_tokens": 16620095.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.677466535568238,
|
|
"epoch": 0.7181692368525109,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956703173893173,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.17270681411027908,
|
|
"num_tokens": 16630919.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.658146619796753,
|
|
"epoch": 0.7186635033610123,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004956634249196001,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.1669278249144554,
|
|
"num_tokens": 16642111.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.692594385147094,
|
|
"epoch": 0.7191577698695136,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004956565270215282,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.16662524044513702,
|
|
"num_tokens": 16654805.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.798805618286133,
|
|
"epoch": 0.719652036378015,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004956496236952716,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.15945585817098618,
|
|
"num_tokens": 16664735.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.760529518127441,
|
|
"epoch": 0.7201463028865164,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495642714941,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.16981687098741532,
|
|
"num_tokens": 16676163.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.769009399414062,
|
|
"epoch": 0.7206405693950177,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004956358007588834,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.1609443947672844,
|
|
"num_tokens": 16689683.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.74858980178833,
|
|
"epoch": 0.7211348359035191,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004956288811490919,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.1654474213719368,
|
|
"num_tokens": 16702193.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.586774444580078,
|
|
"epoch": 0.7216291024120206,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004956219561117955,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.18653778731822968,
|
|
"num_tokens": 16713489.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.700645399093628,
|
|
"epoch": 0.722123368920522,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000495615025647165,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.1715669795870781,
|
|
"num_tokens": 16725103.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.7161589622497555,
|
|
"epoch": 0.7226176354290234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004956080897553705,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17071547955274582,
|
|
"num_tokens": 16737056.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.6266826629638675,
|
|
"epoch": 0.7231119019375247,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004956011484365829,
|
|
"loss": 5.5003,
|
|
"mean_token_accuracy": 0.18188880681991576,
|
|
"num_tokens": 16747347.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.607901477813721,
|
|
"epoch": 0.7236061684460261,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955942016909728,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.17627400457859038,
|
|
"num_tokens": 16758738.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.663641548156738,
|
|
"epoch": 0.7241004349545275,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000495587249518711,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.1681002900004387,
|
|
"num_tokens": 16770867.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.704881048202514,
|
|
"epoch": 0.7245947014630288,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004955802919199687,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.17597900927066804,
|
|
"num_tokens": 16781537.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.651275110244751,
|
|
"epoch": 0.7250889679715302,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000495573328894917,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.16847781091928482,
|
|
"num_tokens": 16792250.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.638693380355835,
|
|
"epoch": 0.7255832344800316,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955663604437272,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.17257506996393204,
|
|
"num_tokens": 16803673.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.698217582702637,
|
|
"epoch": 0.726077500988533,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004955593865665707,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.16655504405498506,
|
|
"num_tokens": 16815484.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.699980401992798,
|
|
"epoch": 0.7265717674970344,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000495552407263619,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16984114795923233,
|
|
"num_tokens": 16827097.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.729072046279907,
|
|
"epoch": 0.7270660340055358,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004955454225350441,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.169184547662735,
|
|
"num_tokens": 16838235.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.667525053024292,
|
|
"epoch": 0.7275603005140372,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004955384323810174,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1674315631389618,
|
|
"num_tokens": 16847831.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.702484607696533,
|
|
"epoch": 0.7280545670225386,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495531436801711,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.16682376563549042,
|
|
"num_tokens": 16859607.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.7699038028717045,
|
|
"epoch": 0.7285488335310399,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004955244357972972,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.16271971464157103,
|
|
"num_tokens": 16869787.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.620062637329101,
|
|
"epoch": 0.7290431000395413,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000495517429367948,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17938583493232726,
|
|
"num_tokens": 16880819.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.699731063842774,
|
|
"epoch": 0.7295373665480427,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004955104175138358,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.16814658790826797,
|
|
"num_tokens": 16893247.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.7402268409729,
|
|
"epoch": 0.7300316330565441,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004955034002351332,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.17082692831754684,
|
|
"num_tokens": 16904469.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.719659376144409,
|
|
"epoch": 0.7305258995650454,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004954963775320127,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.16452192515134811,
|
|
"num_tokens": 16918433.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.718959140777588,
|
|
"epoch": 0.7310201660735468,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000495489349404647,
|
|
"loss": 5.5771,
|
|
"mean_token_accuracy": 0.16617431193590165,
|
|
"num_tokens": 16930905.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.729434585571289,
|
|
"epoch": 0.7315144325820483,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004954823158532093,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.16522528529167174,
|
|
"num_tokens": 16943461.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.661287260055542,
|
|
"epoch": 0.7320086990905497,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954752768778723,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.16712260842323304,
|
|
"num_tokens": 16955539.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.66557765007019,
|
|
"epoch": 0.732502965599051,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004954682324788093,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1716550886631012,
|
|
"num_tokens": 16967508.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.665964555740357,
|
|
"epoch": 0.7329972321075524,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004954611826561935,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.174430450797081,
|
|
"num_tokens": 16979033.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.651474285125732,
|
|
"epoch": 0.7334914986160538,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004954541274101985,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.17606626749038695,
|
|
"num_tokens": 16991874.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.729908609390259,
|
|
"epoch": 0.7339857651245552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004954470667409978,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.16645253002643584,
|
|
"num_tokens": 17003160.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.7120636940002445,
|
|
"epoch": 0.7344800316330565,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000495440000648765,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.17463336735963822,
|
|
"num_tokens": 17014043.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.744620990753174,
|
|
"epoch": 0.7349742981415579,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004954329291336739,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17078086435794831,
|
|
"num_tokens": 17025117.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.625200510025024,
|
|
"epoch": 0.7354685646500593,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004954258521958988,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.17175479084253312,
|
|
"num_tokens": 17037366.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.695043468475342,
|
|
"epoch": 0.7359628311585606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954187698356133,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.16630513817071915,
|
|
"num_tokens": 17050683.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.601901865005493,
|
|
"epoch": 0.7364570976670621,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004954116820529921,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.17984959185123445,
|
|
"num_tokens": 17062403.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.615469360351563,
|
|
"epoch": 0.7369513641755635,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004954045888482091,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.17693626284599304,
|
|
"num_tokens": 17072688.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.702804613113403,
|
|
"epoch": 0.7374456306840649,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953974902214391,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.1696712613105774,
|
|
"num_tokens": 17084118.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.701924419403076,
|
|
"epoch": 0.7379398971925663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004953903861728567,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.1695810228586197,
|
|
"num_tokens": 17095600.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.829625225067138,
|
|
"epoch": 0.7384341637010676,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004953832767026365,
|
|
"loss": 5.7016,
|
|
"mean_token_accuracy": 0.16444838643074036,
|
|
"num_tokens": 17107934.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.724228239059448,
|
|
"epoch": 0.738928430209569,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004953761618109535,
|
|
"loss": 5.608,
|
|
"mean_token_accuracy": 0.16929296255111695,
|
|
"num_tokens": 17119578.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.655234289169312,
|
|
"epoch": 0.7394226967180704,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004953690414979828,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.16562922596931456,
|
|
"num_tokens": 17129928.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.699646663665772,
|
|
"epoch": 0.7399169632265717,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953619157638995,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.16472893506288527,
|
|
"num_tokens": 17141149.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.674083662033081,
|
|
"epoch": 0.7404112297350731,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004953547846088789,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1701727882027626,
|
|
"num_tokens": 17152577.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.650682544708252,
|
|
"epoch": 0.7409054962435745,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004953476480330964,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.1676240235567093,
|
|
"num_tokens": 17163997.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.624829816818237,
|
|
"epoch": 0.741399762752076,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004953405060367276,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17183479219675063,
|
|
"num_tokens": 17175317.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.639388179779052,
|
|
"epoch": 0.7418940292605773,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004953333586199481,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.175498928129673,
|
|
"num_tokens": 17185615.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.769753932952881,
|
|
"epoch": 0.7423882957690787,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004953262057829338,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.16500901132822038,
|
|
"num_tokens": 17198160.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.669407987594605,
|
|
"epoch": 0.7428825622775801,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953190475258607,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.17211966216564178,
|
|
"num_tokens": 17209652.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.721667098999023,
|
|
"epoch": 0.7433768287860815,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004953118838489049,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.169851915538311,
|
|
"num_tokens": 17220832.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.665209865570068,
|
|
"epoch": 0.7438710952945828,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004953047147522424,
|
|
"loss": 5.4807,
|
|
"mean_token_accuracy": 0.17047237008810043,
|
|
"num_tokens": 17231952.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.605232763290405,
|
|
"epoch": 0.7443653618030842,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004952975402360499,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17854121327400208,
|
|
"num_tokens": 17242705.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.726447105407715,
|
|
"epoch": 0.7448596283115856,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952903603005037,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.1656436502933502,
|
|
"num_tokens": 17253946.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.742275857925415,
|
|
"epoch": 0.745353894820087,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004952831749457804,
|
|
"loss": 5.5984,
|
|
"mean_token_accuracy": 0.17964797616004943,
|
|
"num_tokens": 17265732.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.6813929080963135,
|
|
"epoch": 0.7458481613285883,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004952759841720569,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.17792211174964906,
|
|
"num_tokens": 17277154.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.671400022506714,
|
|
"epoch": 0.7463424278370897,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952687879795101,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.1707177683711052,
|
|
"num_tokens": 17288179.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.645062828063965,
|
|
"epoch": 0.7468366943455912,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004952615863683167,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.17368994057178497,
|
|
"num_tokens": 17299435.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.5492799282073975,
|
|
"epoch": 0.7473309608540926,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004952543793386543,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.19212514609098436,
|
|
"num_tokens": 17309442.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.711370754241943,
|
|
"epoch": 0.7478252273625939,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004952471668906999,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.16596472561359404,
|
|
"num_tokens": 17322072.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.671098899841309,
|
|
"epoch": 0.7483194938710953,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004952399490246311,
|
|
"loss": 5.4984,
|
|
"mean_token_accuracy": 0.17515178471803666,
|
|
"num_tokens": 17333458.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.613835620880127,
|
|
"epoch": 0.7488137603795967,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004952327257406253,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.1753479778766632,
|
|
"num_tokens": 17344319.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.663324165344238,
|
|
"epoch": 0.749308026888098,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004952254970388603,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.1709291785955429,
|
|
"num_tokens": 17357016.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.586757516860962,
|
|
"epoch": 0.7498022933965994,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000495218262919514,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.1761627122759819,
|
|
"num_tokens": 17368574.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.626720523834228,
|
|
"epoch": 0.7502965599051008,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004952110233827642,
|
|
"loss": 5.4222,
|
|
"mean_token_accuracy": 0.17727595418691636,
|
|
"num_tokens": 17379858.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.725009965896606,
|
|
"epoch": 0.7507908264136022,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004952037784287891,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.17105319648981093,
|
|
"num_tokens": 17391543.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.6827479839324955,
|
|
"epoch": 0.7512850929221035,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951965280577668,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.17575259655714034,
|
|
"num_tokens": 17403193.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.673610353469849,
|
|
"epoch": 0.751779359430605,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004951892722698759,
|
|
"loss": 5.6522,
|
|
"mean_token_accuracy": 0.17027204483747482,
|
|
"num_tokens": 17415866.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.6282610416412355,
|
|
"epoch": 0.7522736259391064,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951820110652946,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.17405735105276107,
|
|
"num_tokens": 17427880.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.659762001037597,
|
|
"epoch": 0.7527678924476078,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951747444442017,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.17544294893741608,
|
|
"num_tokens": 17440295.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.67684850692749,
|
|
"epoch": 0.7532621589561092,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004951674724067759,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.17699250280857087,
|
|
"num_tokens": 17451636.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.724844026565552,
|
|
"epoch": 0.7537564254646105,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004951601949531962,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.17140300273895265,
|
|
"num_tokens": 17464376.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.704115581512451,
|
|
"epoch": 0.7542506919731119,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951529120836416,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.17221028208732606,
|
|
"num_tokens": 17475098.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.561688852310181,
|
|
"epoch": 0.7547449584816133,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004951456237982911,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.1716049477458,
|
|
"num_tokens": 17486176.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.617137765884399,
|
|
"epoch": 0.7552392249901146,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951383300973242,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.1760372057557106,
|
|
"num_tokens": 17498386.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.685978031158447,
|
|
"epoch": 0.755733491498616,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004951310309809201,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.16719303131103516,
|
|
"num_tokens": 17510409.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.67445011138916,
|
|
"epoch": 0.7562277580071174,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004951237264492585,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.17563256919384002,
|
|
"num_tokens": 17521803.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.614430618286133,
|
|
"epoch": 0.7567220245156189,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004951164165025192,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17758907973766327,
|
|
"num_tokens": 17532974.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.668708086013794,
|
|
"epoch": 0.7572162910241202,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.0004951091011408818,
|
|
"loss": 5.5374,
|
|
"mean_token_accuracy": 0.16978293806314468,
|
|
"num_tokens": 17544309.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.6210895538330075,
|
|
"epoch": 0.7577105575326216,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004951017803645264,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.17720346301794052,
|
|
"num_tokens": 17555395.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.662569665908814,
|
|
"epoch": 0.758204824041123,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495094454173633,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.17480202317237853,
|
|
"num_tokens": 17567434.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.760444164276123,
|
|
"epoch": 0.7586990905496244,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004950871225683819,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.17089351862668992,
|
|
"num_tokens": 17578381.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.64264440536499,
|
|
"epoch": 0.7591933570581257,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950797855489535,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.17635507881641388,
|
|
"num_tokens": 17589732.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.670360469818116,
|
|
"epoch": 0.7596876235666271,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004950724431155283,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.17108551859855653,
|
|
"num_tokens": 17601092.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.640645360946655,
|
|
"epoch": 0.7601818900751285,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950650952682867,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.17071157991886138,
|
|
"num_tokens": 17613268.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.719383907318115,
|
|
"epoch": 0.7606761565836299,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004950577420074098,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.17953412383794784,
|
|
"num_tokens": 17623500.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.730420398712158,
|
|
"epoch": 0.7611704230921312,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004950503833330781,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1683741554617882,
|
|
"num_tokens": 17636151.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.717834711074829,
|
|
"epoch": 0.7616646896006327,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004950430192454729,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.1692216843366623,
|
|
"num_tokens": 17648392.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.657883024215698,
|
|
"epoch": 0.7621589561091341,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004950356497447754,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.17200473994016646,
|
|
"num_tokens": 17659777.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.697988510131836,
|
|
"epoch": 0.7626532226176355,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004950282748311666,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.16775745898485184,
|
|
"num_tokens": 17671986.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.661674547195434,
|
|
"epoch": 0.7631474891261368,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004950208945048283,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.17257063537836076,
|
|
"num_tokens": 17683740.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.665504503250122,
|
|
"epoch": 0.7636417556346382,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004950135087659417,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.17203018218278884,
|
|
"num_tokens": 17696034.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.641619873046875,
|
|
"epoch": 0.7641360221431396,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004950061176146887,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.17655879110097886,
|
|
"num_tokens": 17707783.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.63834810256958,
|
|
"epoch": 0.764630288651641,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004949987210512511,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.17860381603240966,
|
|
"num_tokens": 17718127.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.720082950592041,
|
|
"epoch": 0.7651245551601423,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004949913190758109,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.16444182246923447,
|
|
"num_tokens": 17729798.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.734863376617431,
|
|
"epoch": 0.7656188216686437,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004949839116885499,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.17160144895315171,
|
|
"num_tokens": 17741989.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.651919841766357,
|
|
"epoch": 0.7661130881771451,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004949764988896508,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.17137914299964904,
|
|
"num_tokens": 17753737.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.590790510177612,
|
|
"epoch": 0.7666073546856464,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004949690806792955,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.17661221474409103,
|
|
"num_tokens": 17764158.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.696534919738769,
|
|
"epoch": 0.7671016211941479,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004949616570576668,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.17195841521024705,
|
|
"num_tokens": 17775878.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.66746678352356,
|
|
"epoch": 0.7675958877026493,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004949542280249473,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.17493368238210677,
|
|
"num_tokens": 17786107.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.609028387069702,
|
|
"epoch": 0.7680901542111507,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004949467935813196,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.17034906446933745,
|
|
"num_tokens": 17798470.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.715080261230469,
|
|
"epoch": 0.768584420719652,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004949393537269666,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.16859101951122285,
|
|
"num_tokens": 17811125.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.60887508392334,
|
|
"epoch": 0.7690786872281534,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004949319084620714,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.18001473993062972,
|
|
"num_tokens": 17821535.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.743619298934936,
|
|
"epoch": 0.7695729537366548,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000494924457786817,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.1605602905154228,
|
|
"num_tokens": 17833493.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.802642297744751,
|
|
"epoch": 0.7700672202451562,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949170017013871,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.16530414223670958,
|
|
"num_tokens": 17844705.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.728057718276977,
|
|
"epoch": 0.7705614867536575,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004949095402059646,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.1651466593146324,
|
|
"num_tokens": 17856088.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.751260614395141,
|
|
"epoch": 0.7710557532621589,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004949020733007334,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.17053290605545043,
|
|
"num_tokens": 17867602.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.706641101837159,
|
|
"epoch": 0.7715500197706603,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000494894600985877,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.1631287470459938,
|
|
"num_tokens": 17880487.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.753086185455322,
|
|
"epoch": 0.7720442862791618,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948871232615794,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16994065195322036,
|
|
"num_tokens": 17891690.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.751199722290039,
|
|
"epoch": 0.7725385527876631,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004948796401280244,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.1635550558567047,
|
|
"num_tokens": 17903165.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.6475396156311035,
|
|
"epoch": 0.7730328192961645,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004948721515853962,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.1780988797545433,
|
|
"num_tokens": 17914492.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.672312021255493,
|
|
"epoch": 0.7735270858046659,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004948646576338789,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.16495712995529174,
|
|
"num_tokens": 17926231.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.654861688613892,
|
|
"epoch": 0.7740213523131673,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494857158273657,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.17660849094390868,
|
|
"num_tokens": 17937167.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.695403242111206,
|
|
"epoch": 0.7745156188216686,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004948496535049148,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1697646915912628,
|
|
"num_tokens": 17948939.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.693153810501099,
|
|
"epoch": 0.77500988533017,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000494842143327837,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.18618129193782806,
|
|
"num_tokens": 17959250.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.601862192153931,
|
|
"epoch": 0.7755041518386714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004948346277426084,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.16691216230392455,
|
|
"num_tokens": 17970191.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.719114828109741,
|
|
"epoch": 0.7759984183471728,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494827106749414,
|
|
"loss": 5.5188,
|
|
"mean_token_accuracy": 0.17392174601554872,
|
|
"num_tokens": 17982114.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.78126335144043,
|
|
"epoch": 0.7764926848556741,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004948195803484385,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.16853119432926178,
|
|
"num_tokens": 17994066.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.661632633209228,
|
|
"epoch": 0.7769869513641756,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004948120485398673,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16824090778827666,
|
|
"num_tokens": 18005406.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.651668500900269,
|
|
"epoch": 0.777481217872677,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004948045113238856,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.1691005766391754,
|
|
"num_tokens": 18016773.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.739258575439453,
|
|
"epoch": 0.7779754843811784,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004947969687006787,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.1685599997639656,
|
|
"num_tokens": 18028682.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.725970506668091,
|
|
"epoch": 0.7784697508896797,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004947894206704324,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.1687220498919487,
|
|
"num_tokens": 18039525.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.6620887279510494,
|
|
"epoch": 0.7789640173981811,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004947818672333323,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.17013707160949706,
|
|
"num_tokens": 18049918.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.757622766494751,
|
|
"epoch": 0.7794582839066825,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000494774308389564,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.16335499435663223,
|
|
"num_tokens": 18061019.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.704455423355102,
|
|
"epoch": 0.7799525504151839,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004947667441393138,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.1736235111951828,
|
|
"num_tokens": 18072123.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.615215206146241,
|
|
"epoch": 0.7804468169236852,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004947591744827674,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.1699620306491852,
|
|
"num_tokens": 18083354.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.7237965106964115,
|
|
"epoch": 0.7809410834321866,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004947515994201113,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.16344162672758103,
|
|
"num_tokens": 18094188.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.710861730575561,
|
|
"epoch": 0.781435349940688,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004947440189515318,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.16924724578857422,
|
|
"num_tokens": 18106198.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.71050271987915,
|
|
"epoch": 0.7819296164491895,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004947364330772154,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17532664835453032,
|
|
"num_tokens": 18117137.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.599886798858643,
|
|
"epoch": 0.7824238829576908,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004947288417973486,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16764724105596543,
|
|
"num_tokens": 18127341.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.663480186462403,
|
|
"epoch": 0.7829181494661922,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004947212451121182,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.17105976194143296,
|
|
"num_tokens": 18138333.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.75397424697876,
|
|
"epoch": 0.7834124159746936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000494713643021711,
|
|
"loss": 5.7696,
|
|
"mean_token_accuracy": 0.15086156725883484,
|
|
"num_tokens": 18150961.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.749459457397461,
|
|
"epoch": 0.783906682483195,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004947060355263142,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.16852100789546967,
|
|
"num_tokens": 18162604.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.715012836456299,
|
|
"epoch": 0.7844009489916963,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004946984226261149,
|
|
"loss": 5.5757,
|
|
"mean_token_accuracy": 0.1679299145936966,
|
|
"num_tokens": 18174202.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.795772361755371,
|
|
"epoch": 0.7848952155001977,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004946908043213001,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.16609162986278533,
|
|
"num_tokens": 18185942.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.676000452041626,
|
|
"epoch": 0.7853894820086991,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004946831806120576,
|
|
"loss": 5.5168,
|
|
"mean_token_accuracy": 0.1706746831536293,
|
|
"num_tokens": 18198897.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.643487739562988,
|
|
"epoch": 0.7858837485172004,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004946755514985748,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.17641528993844985,
|
|
"num_tokens": 18211439.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.599884414672852,
|
|
"epoch": 0.7863780150257018,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004946679169810392,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.18004480600357056,
|
|
"num_tokens": 18221864.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.6497749328613285,
|
|
"epoch": 0.7868722815342032,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000494660277059639,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.1679001957178116,
|
|
"num_tokens": 18234005.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.682629823684692,
|
|
"epoch": 0.7873665480427047,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004946526317345617,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.17590866684913636,
|
|
"num_tokens": 18246804.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.656999349594116,
|
|
"epoch": 0.787860814551206,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004946449810059957,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.17166247069835663,
|
|
"num_tokens": 18259192.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.653470611572265,
|
|
"epoch": 0.7883550810597074,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004946373248741289,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.17158437371253968,
|
|
"num_tokens": 18271073.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.66881742477417,
|
|
"epoch": 0.7888493475682088,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00049462966333915,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.17324157059192657,
|
|
"num_tokens": 18281650.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.669822692871094,
|
|
"epoch": 0.7893436140767102,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004946219964012473,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.17195811122655869,
|
|
"num_tokens": 18292217.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.645072937011719,
|
|
"epoch": 0.7898378805852115,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004946143240606095,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.17821820080280304,
|
|
"num_tokens": 18305210.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.605085849761963,
|
|
"epoch": 0.7903321470937129,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004946066463174251,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.18137718886137008,
|
|
"num_tokens": 18316418.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.565552425384522,
|
|
"epoch": 0.7908264136022143,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004945989631718831,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.17460388094186782,
|
|
"num_tokens": 18328637.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.690286922454834,
|
|
"epoch": 0.7913206801107157,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945912746241727,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.17971017807722092,
|
|
"num_tokens": 18340292.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.649618291854859,
|
|
"epoch": 0.791814946619217,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004945835806744828,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.1772964894771576,
|
|
"num_tokens": 18350784.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.736659908294678,
|
|
"epoch": 0.7923092131277185,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004945758813230028,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.16675881445407867,
|
|
"num_tokens": 18363147.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.713673210144043,
|
|
"epoch": 0.7928034796362199,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000494568176569922,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.16932568252086638,
|
|
"num_tokens": 18374152.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.617963647842407,
|
|
"epoch": 0.7932977461447213,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00049456046641543,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.17836926728487015,
|
|
"num_tokens": 18385321.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.650886154174804,
|
|
"epoch": 0.7937920126532226,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004945527508597165,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.16794346868991852,
|
|
"num_tokens": 18397072.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.677497291564942,
|
|
"epoch": 0.794286279161724,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004945450299029713,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.17020296007394792,
|
|
"num_tokens": 18408172.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.668938827514649,
|
|
"epoch": 0.7947805456702254,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004945373035453842,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.17529940605163574,
|
|
"num_tokens": 18419350.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.603577280044556,
|
|
"epoch": 0.7952748121787268,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004945295717871454,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17170027643442154,
|
|
"num_tokens": 18430907.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.644772005081177,
|
|
"epoch": 0.7957690786872281,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004945218346284451,
|
|
"loss": 5.5093,
|
|
"mean_token_accuracy": 0.17607943266630172,
|
|
"num_tokens": 18441167.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.613923597335815,
|
|
"epoch": 0.7962633451957295,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004945140920694736,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.17939645498991014,
|
|
"num_tokens": 18452025.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.686951065063477,
|
|
"epoch": 0.7967576117042309,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004945063441104214,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.15695639997720717,
|
|
"num_tokens": 18464305.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.724312400817871,
|
|
"epoch": 0.7972518782127324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004944985907514791,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.17479383200407028,
|
|
"num_tokens": 18476217.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.754207801818848,
|
|
"epoch": 0.7977461447212337,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004944908319928372,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.17306375950574876,
|
|
"num_tokens": 18486967.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.635362815856934,
|
|
"epoch": 0.7982404112297351,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004944830678346871,
|
|
"loss": 5.5095,
|
|
"mean_token_accuracy": 0.16895417869091034,
|
|
"num_tokens": 18498918.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.674768447875977,
|
|
"epoch": 0.7987346777382365,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004944752982772194,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.175442174077034,
|
|
"num_tokens": 18509424.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.6082305908203125,
|
|
"epoch": 0.7992289442467378,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004944675233206252,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.1775177538394928,
|
|
"num_tokens": 18520444.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.632602643966675,
|
|
"epoch": 0.7997232107552392,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000494459742965096,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.17504426687955857,
|
|
"num_tokens": 18531874.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.703139448165894,
|
|
"epoch": 0.8002174772637406,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000494451957210823,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.1685916692018509,
|
|
"num_tokens": 18542492.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.750231456756592,
|
|
"epoch": 0.800711743772242,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004944441660579979,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.16148541644215583,
|
|
"num_tokens": 18554477.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.711266899108887,
|
|
"epoch": 0.8012060102807433,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004944363695068121,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.1779920130968094,
|
|
"num_tokens": 18565416.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.634377098083496,
|
|
"epoch": 0.8017002767892447,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004944285675574576,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.17572838962078094,
|
|
"num_tokens": 18575949.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.602584791183472,
|
|
"epoch": 0.8021945432977462,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004944207602101265,
|
|
"loss": 5.5746,
|
|
"mean_token_accuracy": 0.17144881337881088,
|
|
"num_tokens": 18588177.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.666587162017822,
|
|
"epoch": 0.8026888098062476,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004944129474650104,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.16863043010234832,
|
|
"num_tokens": 18599112.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.508049774169922,
|
|
"epoch": 0.803183076314749,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000494405129322302,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.18161139041185378,
|
|
"num_tokens": 18610432.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.684536552429199,
|
|
"epoch": 0.8036773428232503,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004943973057821931,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16530260890722276,
|
|
"num_tokens": 18621739.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.707551908493042,
|
|
"epoch": 0.8041716093317517,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004943894768448768,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.17255666553974153,
|
|
"num_tokens": 18631983.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.662142419815064,
|
|
"epoch": 0.8046658758402531,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000494381642510545,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.16358405947685242,
|
|
"num_tokens": 18643507.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.707227754592895,
|
|
"epoch": 0.8051601423487544,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004943738027793909,
|
|
"loss": 5.6,
|
|
"mean_token_accuracy": 0.1730455905199051,
|
|
"num_tokens": 18654516.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.8120239734649655,
|
|
"epoch": 0.8056544088572558,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004943659576516072,
|
|
"loss": 5.6164,
|
|
"mean_token_accuracy": 0.16328000277280807,
|
|
"num_tokens": 18666855.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.722058248519898,
|
|
"epoch": 0.8061486753657572,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943581071273869,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.16468441486358643,
|
|
"num_tokens": 18679105.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.689639949798584,
|
|
"epoch": 0.8066429418742586,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004943502512069232,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.17410830706357955,
|
|
"num_tokens": 18691349.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.7563886642456055,
|
|
"epoch": 0.8071372083827599,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004943423898904092,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.16359055638313294,
|
|
"num_tokens": 18703773.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.709823417663574,
|
|
"epoch": 0.8076314748912614,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004943345231780385,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.1701025500893593,
|
|
"num_tokens": 18715281.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.6754413604736325,
|
|
"epoch": 0.8081257413997628,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004943266510700043,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.17722506076097488,
|
|
"num_tokens": 18726446.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.592026424407959,
|
|
"epoch": 0.8086200079082642,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943187735665007,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.188413342833519,
|
|
"num_tokens": 18737348.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.634600496292114,
|
|
"epoch": 0.8091142744167655,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004943108906677211,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.17402384132146836,
|
|
"num_tokens": 18748921.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.652138805389404,
|
|
"epoch": 0.8096085409252669,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943030023738595,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.1803518444299698,
|
|
"num_tokens": 18761252.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.641749668121338,
|
|
"epoch": 0.8101028074337683,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004942951086851102,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.17346426844596863,
|
|
"num_tokens": 18772915.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.700555753707886,
|
|
"epoch": 0.8105970739422697,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004942872096016671,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.17532410472631454,
|
|
"num_tokens": 18783533.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.657323980331421,
|
|
"epoch": 0.811091340450771,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004942793051237247,
|
|
"loss": 5.4862,
|
|
"mean_token_accuracy": 0.16847143173217774,
|
|
"num_tokens": 18795068.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.729863834381104,
|
|
"epoch": 0.8115856069592724,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004942713952514773,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.1557537943124771,
|
|
"num_tokens": 18808105.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.6933183670043945,
|
|
"epoch": 0.8120798734677738,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004942634799851196,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.1690622314810753,
|
|
"num_tokens": 18819275.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.665697336196899,
|
|
"epoch": 0.8125741399762753,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004942555593248463,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.18206111639738082,
|
|
"num_tokens": 18828535.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.650947093963623,
|
|
"epoch": 0.8130684064847766,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004942476332708522,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.17597778141498566,
|
|
"num_tokens": 18839983.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.724194478988648,
|
|
"epoch": 0.813562672993278,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004942397018233322,
|
|
"loss": 5.5472,
|
|
"mean_token_accuracy": 0.17307500839233397,
|
|
"num_tokens": 18851875.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.67059736251831,
|
|
"epoch": 0.8140569395017794,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004942317649824816,
|
|
"loss": 5.5516,
|
|
"mean_token_accuracy": 0.1704033851623535,
|
|
"num_tokens": 18863629.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.637253904342652,
|
|
"epoch": 0.8145512060102807,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004942238227484956,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.17963588535785674,
|
|
"num_tokens": 18875660.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.6646583557128904,
|
|
"epoch": 0.8150454725187821,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004942158751215696,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.1697225898504257,
|
|
"num_tokens": 18887140.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.641614103317261,
|
|
"epoch": 0.8155397390272835,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942079221018989,
|
|
"loss": 5.5572,
|
|
"mean_token_accuracy": 0.1688000813126564,
|
|
"num_tokens": 18899386.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.7228028774261475,
|
|
"epoch": 0.8160340055357849,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004941999636896795,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.1619180202484131,
|
|
"num_tokens": 18911187.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.696290397644043,
|
|
"epoch": 0.8165282720442862,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004941919998851068,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.1729051098227501,
|
|
"num_tokens": 18922522.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.545044898986816,
|
|
"epoch": 0.8170225385527876,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004941840306883771,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.18000025004148484,
|
|
"num_tokens": 18932689.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.7167548656463625,
|
|
"epoch": 0.8175168050612891,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004941760560996861,
|
|
"loss": 5.6472,
|
|
"mean_token_accuracy": 0.16177235543727875,
|
|
"num_tokens": 18944296.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.779918670654297,
|
|
"epoch": 0.8180110715697905,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004941680761192302,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.16921962797641754,
|
|
"num_tokens": 18955449.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.764803266525268,
|
|
"epoch": 0.8185053380782918,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004941600907472055,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.17207979261875153,
|
|
"num_tokens": 18969065.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.650646209716797,
|
|
"epoch": 0.8189996045867932,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004941520999838088,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.17849107533693315,
|
|
"num_tokens": 18979801.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.719054412841797,
|
|
"epoch": 0.8194938710952946,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004941441038292363,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.16619429141283035,
|
|
"num_tokens": 18990795.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.736597633361816,
|
|
"epoch": 0.819988137603796,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004941361022836847,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.1690972164273262,
|
|
"num_tokens": 19002318.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.651871919631958,
|
|
"epoch": 0.8204824041122973,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004941280953473513,
|
|
"loss": 5.5642,
|
|
"mean_token_accuracy": 0.17649328112602233,
|
|
"num_tokens": 19014977.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.77757887840271,
|
|
"epoch": 0.8209766706207987,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004941200830204325,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.16748668402433395,
|
|
"num_tokens": 19026081.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.722622108459473,
|
|
"epoch": 0.8214709371293001,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004941120653031256,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.16707528978586197,
|
|
"num_tokens": 19037694.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.622165155410767,
|
|
"epoch": 0.8219652036378015,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004941040421956282,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17968087047338485,
|
|
"num_tokens": 19048344.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.742125415802002,
|
|
"epoch": 0.8224594701463029,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004940960136981372,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.170555417239666,
|
|
"num_tokens": 19060213.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.661463260650635,
|
|
"epoch": 0.8229537366548043,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004940879798108503,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.18449685573577881,
|
|
"num_tokens": 19070881.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.61786904335022,
|
|
"epoch": 0.8234480031633057,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004940799405339651,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.176091730594635,
|
|
"num_tokens": 19082206.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.573992156982422,
|
|
"epoch": 0.8239422696718071,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004940718958676794,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.17775189280509948,
|
|
"num_tokens": 19094014.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.6662375926971436,
|
|
"epoch": 0.8244365361803084,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000494063845812191,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.17497734874486923,
|
|
"num_tokens": 19106859.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.60374608039856,
|
|
"epoch": 0.8249308026888098,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004940557903676981,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17188245207071304,
|
|
"num_tokens": 19118296.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.6431556224823,
|
|
"epoch": 0.8254250691973112,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004940477295343988,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.1766101375222206,
|
|
"num_tokens": 19130212.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.624119997024536,
|
|
"epoch": 0.8259193357058126,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940396633124912,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18628134727478027,
|
|
"num_tokens": 19140798.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.7340943813323975,
|
|
"epoch": 0.8264136022143139,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004940315917021742,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.17279937416315078,
|
|
"num_tokens": 19151875.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.761490154266357,
|
|
"epoch": 0.8269078687228153,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004940235147036457,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.15962200313806535,
|
|
"num_tokens": 19164532.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.642462921142578,
|
|
"epoch": 0.8274021352313167,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000494015432317105,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.1695497676730156,
|
|
"num_tokens": 19176828.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.541879367828369,
|
|
"epoch": 0.8278964017398182,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004940073445427506,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.18652730584144592,
|
|
"num_tokens": 19188118.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.694701719284057,
|
|
"epoch": 0.8283906682483195,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004939992513807816,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.16807282567024232,
|
|
"num_tokens": 19201009.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.697178983688355,
|
|
"epoch": 0.8288849347568209,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004939911528313971,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.1720028042793274,
|
|
"num_tokens": 19212747.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.678915691375733,
|
|
"epoch": 0.8293792012653223,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000493983048894796,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.16764711439609528,
|
|
"num_tokens": 19224043.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.667695331573486,
|
|
"epoch": 0.8298734677738236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004939749395711782,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.17074278146028518,
|
|
"num_tokens": 19235475.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.770517253875733,
|
|
"epoch": 0.830367734282325,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939668248607428,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.17239191383123398,
|
|
"num_tokens": 19247208.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.62474365234375,
|
|
"epoch": 0.8308620007908264,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004939587047636896,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.17368660867214203,
|
|
"num_tokens": 19260172.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.639910078048706,
|
|
"epoch": 0.8313562672993278,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004939505792802182,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.1730119988322258,
|
|
"num_tokens": 19271173.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.687192630767822,
|
|
"epoch": 0.8318505338078291,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939424484105287,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.17810605764389037,
|
|
"num_tokens": 19282693.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.708861827850342,
|
|
"epoch": 0.8323448003163305,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004939343121548209,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.16783239245414733,
|
|
"num_tokens": 19293883.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.57232403755188,
|
|
"epoch": 0.832839066824832,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004939261705132951,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.1765552431344986,
|
|
"num_tokens": 19304530.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.56617956161499,
|
|
"epoch": 0.8333333333333334,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004939180234861516,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.17674677968025207,
|
|
"num_tokens": 19315765.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.656292200088501,
|
|
"epoch": 0.8338275998418347,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004939098710735906,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.17715407609939576,
|
|
"num_tokens": 19328484.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.601895809173584,
|
|
"epoch": 0.8343218663503361,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004939017132758129,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.17597944736480714,
|
|
"num_tokens": 19340594.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.759700965881348,
|
|
"epoch": 0.8348161328588375,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004938935500930192,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.1700374886393547,
|
|
"num_tokens": 19351105.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.672036647796631,
|
|
"epoch": 0.8353103993673389,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938853815254101,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.1790565937757492,
|
|
"num_tokens": 19361619.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.697433996200561,
|
|
"epoch": 0.8358046658758402,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004938772075731867,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.16585847437381745,
|
|
"num_tokens": 19374251.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.800330114364624,
|
|
"epoch": 0.8362989323843416,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004938690282365499,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.16334002017974852,
|
|
"num_tokens": 19386300.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.648759984970093,
|
|
"epoch": 0.836793198892843,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004938608435157012,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.17601901590824126,
|
|
"num_tokens": 19397082.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.609850835800171,
|
|
"epoch": 0.8372874654013444,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004938526534108417,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.172125880420208,
|
|
"num_tokens": 19409123.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.513226079940796,
|
|
"epoch": 0.8377817319098458,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938444579221732,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.19035523533821105,
|
|
"num_tokens": 19419854.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.6588239669799805,
|
|
"epoch": 0.8382759984183472,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004938362570498969,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.1751474916934967,
|
|
"num_tokens": 19430825.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.687922525405884,
|
|
"epoch": 0.8387702649268486,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004938280507942146,
|
|
"loss": 5.5535,
|
|
"mean_token_accuracy": 0.16172091662883759,
|
|
"num_tokens": 19442617.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.7297430515289305,
|
|
"epoch": 0.83926453143535,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004938198391553285,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.16270775496959686,
|
|
"num_tokens": 19453911.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.628610372543335,
|
|
"epoch": 0.8397587979438513,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004938116221334404,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.17665126770734788,
|
|
"num_tokens": 19464837.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.557174825668335,
|
|
"epoch": 0.8402530644523527,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004938033997287524,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.17976142317056656,
|
|
"num_tokens": 19477067.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.5940389156341555,
|
|
"epoch": 0.8407473309608541,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004937951719414668,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.1744459703564644,
|
|
"num_tokens": 19489442.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.623184585571289,
|
|
"epoch": 0.8412415974693555,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004937869387717861,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.17329140454530717,
|
|
"num_tokens": 19501197.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.735953950881958,
|
|
"epoch": 0.8417358639778568,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004937787002199127,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.1754767641425133,
|
|
"num_tokens": 19513311.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.722685098648071,
|
|
"epoch": 0.8422301304863582,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004937704562860493,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.16155761629343032,
|
|
"num_tokens": 19525643.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.555091285705567,
|
|
"epoch": 0.8427243969948597,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004937622069703988,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.17726874053478242,
|
|
"num_tokens": 19537478.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.689294099807739,
|
|
"epoch": 0.843218663503361,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004937539522731641,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.1734578624367714,
|
|
"num_tokens": 19549370.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.634274578094482,
|
|
"epoch": 0.8437129300118624,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004937456921945482,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.18307530730962754,
|
|
"num_tokens": 19561793.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.543313503265381,
|
|
"epoch": 0.8442071965203638,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004937374267347543,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.18986387252807618,
|
|
"num_tokens": 19573603.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.6509765625,
|
|
"epoch": 0.8447014630288652,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004937291558939858,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16782096773386002,
|
|
"num_tokens": 19584848.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.594746828079224,
|
|
"epoch": 0.8451957295373665,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004937208796724461,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.17140107303857804,
|
|
"num_tokens": 19594965.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.63441014289856,
|
|
"epoch": 0.8456899960458679,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004937125980703389,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18301255255937576,
|
|
"num_tokens": 19607347.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.646134853363037,
|
|
"epoch": 0.8461842625543693,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004937043110878678,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.17806421965360641,
|
|
"num_tokens": 19618614.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.651750564575195,
|
|
"epoch": 0.8466785290628707,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004936960187252367,
|
|
"loss": 5.4928,
|
|
"mean_token_accuracy": 0.17512255311012268,
|
|
"num_tokens": 19630409.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.62771430015564,
|
|
"epoch": 0.847172795571372,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004936877209826497,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.17044275254011154,
|
|
"num_tokens": 19642183.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.660381078720093,
|
|
"epoch": 0.8476670620798734,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004936794178603108,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.18137412369251252,
|
|
"num_tokens": 19653846.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.683066654205322,
|
|
"epoch": 0.8481613285883749,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004936711093584242,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.1724503979086876,
|
|
"num_tokens": 19664183.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.628864192962647,
|
|
"epoch": 0.8486555950968763,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004936627954771945,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.1722136214375496,
|
|
"num_tokens": 19675863.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.620277547836304,
|
|
"epoch": 0.8491498616053776,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004936544762168261,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.18317458629608155,
|
|
"num_tokens": 19688410.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.653277778625489,
|
|
"epoch": 0.849644128113879,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004936461515775237,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.1657837450504303,
|
|
"num_tokens": 19698849.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.752568101882934,
|
|
"epoch": 0.8501383946223804,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000493637821559492,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.16271449327468873,
|
|
"num_tokens": 19710761.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.675781154632569,
|
|
"epoch": 0.8506326611308818,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004936294861629358,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.17451393157243728,
|
|
"num_tokens": 19722530.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.658980655670166,
|
|
"epoch": 0.8511269276393831,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004936211453880606,
|
|
"loss": 5.4667,
|
|
"mean_token_accuracy": 0.1752152055501938,
|
|
"num_tokens": 19733352.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.70025749206543,
|
|
"epoch": 0.8516211941478845,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004936127992350712,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.1740539163351059,
|
|
"num_tokens": 19745071.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.660083150863647,
|
|
"epoch": 0.8521154606563859,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004936044477041729,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.17879742830991746,
|
|
"num_tokens": 19756039.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.643785572052002,
|
|
"epoch": 0.8526097271648873,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004935960907955715,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.16374452859163285,
|
|
"num_tokens": 19768728.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.65940113067627,
|
|
"epoch": 0.8531039936733887,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004935877285094722,
|
|
"loss": 5.5252,
|
|
"mean_token_accuracy": 0.16680628657341004,
|
|
"num_tokens": 19780010.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.686123085021973,
|
|
"epoch": 0.8535982601818901,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000493579360846081,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.17999246418476106,
|
|
"num_tokens": 19790082.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.694793796539306,
|
|
"epoch": 0.8540925266903915,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004935709878056034,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.17563139498233796,
|
|
"num_tokens": 19801702.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.674791669845581,
|
|
"epoch": 0.8545867931988929,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004935626093882457,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.17340081930160522,
|
|
"num_tokens": 19812173.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.641797876358032,
|
|
"epoch": 0.8550810597073942,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000493554225594214,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.17762336879968643,
|
|
"num_tokens": 19823286.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.693310689926148,
|
|
"epoch": 0.8555753262158956,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935458364237143,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.17430396527051925,
|
|
"num_tokens": 19834472.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.6719629764556885,
|
|
"epoch": 0.856069592724397,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004935374418769532,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.16794483363628387,
|
|
"num_tokens": 19845073.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.682649707794189,
|
|
"epoch": 0.8565638592328984,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935290419541371,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.1669248789548874,
|
|
"num_tokens": 19856762.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.65253005027771,
|
|
"epoch": 0.8570581257413997,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004935206366554726,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.17682776153087615,
|
|
"num_tokens": 19867358.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.604067850112915,
|
|
"epoch": 0.8575523922499011,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004935122259811667,
|
|
"loss": 5.5166,
|
|
"mean_token_accuracy": 0.1788840815424919,
|
|
"num_tokens": 19878527.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.7267461776733395,
|
|
"epoch": 0.8580466587584026,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000493503809931426,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.16696037501096725,
|
|
"num_tokens": 19889680.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.646886348724365,
|
|
"epoch": 0.858540925266904,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004934953885064577,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.18195306807756423,
|
|
"num_tokens": 19900569.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.561009359359741,
|
|
"epoch": 0.8590351917754053,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493486961706469,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.1788633018732071,
|
|
"num_tokens": 19912537.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.696732378005981,
|
|
"epoch": 0.8595294582839067,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004934785295316672,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.17364627569913865,
|
|
"num_tokens": 19923931.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.7013084411621096,
|
|
"epoch": 0.8600237247924081,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004934700919822596,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.1674872398376465,
|
|
"num_tokens": 19933956.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.581303405761719,
|
|
"epoch": 0.8605179913009094,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004934616490584538,
|
|
"loss": 5.4366,
|
|
"mean_token_accuracy": 0.18158658891916274,
|
|
"num_tokens": 19945603.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.733915519714356,
|
|
"epoch": 0.8610122578094108,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004934532007604577,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.17519815266132355,
|
|
"num_tokens": 19956358.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.6263923168182375,
|
|
"epoch": 0.8615065243179122,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004934447470884788,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.17969615906476974,
|
|
"num_tokens": 19967856.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.565762186050415,
|
|
"epoch": 0.8620007908264136,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004934362880427253,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.17692603319883346,
|
|
"num_tokens": 19979323.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.747442197799683,
|
|
"epoch": 0.8624950573349149,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004934278236234052,
|
|
"loss": 5.5417,
|
|
"mean_token_accuracy": 0.16721271723508835,
|
|
"num_tokens": 19991543.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.741176557540894,
|
|
"epoch": 0.8629893238434164,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004934193538307268,
|
|
"loss": 5.5236,
|
|
"mean_token_accuracy": 0.16932161748409272,
|
|
"num_tokens": 20003621.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.573808097839356,
|
|
"epoch": 0.8634835903519178,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004934108786648983,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.16532171964645387,
|
|
"num_tokens": 20015183.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.631617593765259,
|
|
"epoch": 0.8639778568604192,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004934023981261285,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.17356707006692887,
|
|
"num_tokens": 20026735.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.638874435424805,
|
|
"epoch": 0.8644721233689205,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004933939122146256,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.1751352906227112,
|
|
"num_tokens": 20037410.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.548995685577393,
|
|
"epoch": 0.8649663898774219,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004933854209305987,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.17556238025426865,
|
|
"num_tokens": 20048972.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.69189338684082,
|
|
"epoch": 0.8654606563859233,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004933769242742566,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.17641791552305222,
|
|
"num_tokens": 20059667.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.622850322723389,
|
|
"epoch": 0.8659549228944247,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004933684222458082,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.181125645339489,
|
|
"num_tokens": 20070612.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.5495133876800535,
|
|
"epoch": 0.866449189402926,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004933599148454628,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.1797967180609703,
|
|
"num_tokens": 20081445.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.7263764381408695,
|
|
"epoch": 0.8669434559114274,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004933514020734296,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.1631471872329712,
|
|
"num_tokens": 20094414.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.615201663970947,
|
|
"epoch": 0.8674377224199288,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004933428839299181,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.18938013762235642,
|
|
"num_tokens": 20106793.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.614346837997436,
|
|
"epoch": 0.8679319889284303,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004933343604151376,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.1780432254076004,
|
|
"num_tokens": 20118582.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.6606752395629885,
|
|
"epoch": 0.8684262554369316,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004933258315292982,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.17659486532211305,
|
|
"num_tokens": 20130548.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.6951737880706785,
|
|
"epoch": 0.868920521945433,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004933172972726094,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17046286761760712,
|
|
"num_tokens": 20141821.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.660837602615357,
|
|
"epoch": 0.8694147884539344,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004933087576452811,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.17788977026939393,
|
|
"num_tokens": 20152071.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.735357141494751,
|
|
"epoch": 0.8699090549624358,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004933002126475235,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.1748998686671257,
|
|
"num_tokens": 20163780.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.653436136245728,
|
|
"epoch": 0.8704033214709371,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004932916622795468,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.17343318462371826,
|
|
"num_tokens": 20175477.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.580180025100708,
|
|
"epoch": 0.8708975879794385,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004932831065415614,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.18109884411096572,
|
|
"num_tokens": 20189452.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.711127185821534,
|
|
"epoch": 0.8713918544879399,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932745454337778,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.17111276537179948,
|
|
"num_tokens": 20201250.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.61244912147522,
|
|
"epoch": 0.8718861209964412,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004932659789564065,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.1757502555847168,
|
|
"num_tokens": 20212394.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.644003438949585,
|
|
"epoch": 0.8723803875049426,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004932574071096581,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17748487293720244,
|
|
"num_tokens": 20223262.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.62183780670166,
|
|
"epoch": 0.872874654013444,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932488298937437,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.17424482703208924,
|
|
"num_tokens": 20234088.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.610445547103882,
|
|
"epoch": 0.8733689205219455,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004932402473088743,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.1774066835641861,
|
|
"num_tokens": 20245373.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.6938159465789795,
|
|
"epoch": 0.8738631870304469,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932316593552609,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.17774460315704346,
|
|
"num_tokens": 20255824.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.5992289066314695,
|
|
"epoch": 0.8743574535389482,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004932230660331148,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18336101472377778,
|
|
"num_tokens": 20266576.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.724429178237915,
|
|
"epoch": 0.8748517200474496,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004932144673426475,
|
|
"loss": 5.5354,
|
|
"mean_token_accuracy": 0.1652693435549736,
|
|
"num_tokens": 20277874.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.616672611236572,
|
|
"epoch": 0.875345986555951,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004932058632840705,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.17886368781328202,
|
|
"num_tokens": 20288403.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.690104055404663,
|
|
"epoch": 0.8758402530644523,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004931972538575952,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.17279107570648194,
|
|
"num_tokens": 20299564.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.634945726394653,
|
|
"epoch": 0.8763345195729537,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004931886390634338,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.180560639500618,
|
|
"num_tokens": 20312208.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.6448705196380615,
|
|
"epoch": 0.8768287860814551,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000493180018901798,
|
|
"loss": 5.5434,
|
|
"mean_token_accuracy": 0.1725859060883522,
|
|
"num_tokens": 20323486.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.673321294784546,
|
|
"epoch": 0.8773230525899565,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004931713933728997,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.17019882202148437,
|
|
"num_tokens": 20335806.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.6653523445129395,
|
|
"epoch": 0.8778173190984578,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004931627624769515,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.1753862500190735,
|
|
"num_tokens": 20347216.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.6569366455078125,
|
|
"epoch": 0.8783115856069593,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004931541262141653,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.16614073812961577,
|
|
"num_tokens": 20358938.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.653841829299926,
|
|
"epoch": 0.8788058521154607,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004931454845847539,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.1693306401371956,
|
|
"num_tokens": 20370742.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.5487298488616945,
|
|
"epoch": 0.8793001186239621,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004931368375889298,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1827306404709816,
|
|
"num_tokens": 20382100.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.719707345962524,
|
|
"epoch": 0.8797943851324634,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004931281852269054,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.17028920948505402,
|
|
"num_tokens": 20393348.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.666423749923706,
|
|
"epoch": 0.8802886516409648,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000493119527498894,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.1843515306711197,
|
|
"num_tokens": 20403471.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.62884783744812,
|
|
"epoch": 0.8807829181494662,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004931108644051084,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.184926076233387,
|
|
"num_tokens": 20415146.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.652925252914429,
|
|
"epoch": 0.8812771846579676,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004931021959457617,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.17115412801504135,
|
|
"num_tokens": 20425857.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.645883846282959,
|
|
"epoch": 0.8817714511664689,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000493093522121067,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.16593760401010513,
|
|
"num_tokens": 20437987.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.620006656646728,
|
|
"epoch": 0.8822657176749703,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004930848429312379,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1756638392806053,
|
|
"num_tokens": 20449079.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.7273438453674315,
|
|
"epoch": 0.8827599841834717,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004930761583764879,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.16756822913885117,
|
|
"num_tokens": 20461032.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.713757753372192,
|
|
"epoch": 0.8832542506919732,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004930674684570306,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.17375192940235137,
|
|
"num_tokens": 20471825.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.706273794174194,
|
|
"epoch": 0.8837485172004745,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004930587731730796,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.1788962870836258,
|
|
"num_tokens": 20483329.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.658165073394775,
|
|
"epoch": 0.8842427837089759,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000493050072524849,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.16730180829763414,
|
|
"num_tokens": 20494537.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.577196025848389,
|
|
"epoch": 0.8847370502174773,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004930413665125528,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.1796573668718338,
|
|
"num_tokens": 20506205.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.6702916622161865,
|
|
"epoch": 0.8852313167259787,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004930326551364052,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.17698878794908524,
|
|
"num_tokens": 20517447.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.658923196792602,
|
|
"epoch": 0.88572558323448,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004930239383966204,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.17149081826210022,
|
|
"num_tokens": 20529435.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.6230205535888675,
|
|
"epoch": 0.8862198497429814,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004930152162934128,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18569135814905166,
|
|
"num_tokens": 20540151.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.611609172821045,
|
|
"epoch": 0.8867141162514828,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004930064888269973,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.172835835814476,
|
|
"num_tokens": 20552355.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.7036388397216795,
|
|
"epoch": 0.8872083827599841,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004929977559975881,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.16786339730024338,
|
|
"num_tokens": 20562129.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.658351707458496,
|
|
"epoch": 0.8877026492684855,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004929890178054004,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.17283495664596557,
|
|
"num_tokens": 20573232.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.677739000320434,
|
|
"epoch": 0.888196915776987,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004929802742506491,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.17869616597890853,
|
|
"num_tokens": 20582986.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.644188785552979,
|
|
"epoch": 0.8886911822854884,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004929715253335492,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.17821491062641143,
|
|
"num_tokens": 20593619.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.5321368217468265,
|
|
"epoch": 0.8891854487939898,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004929627710543159,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.17839478254318236,
|
|
"num_tokens": 20604748.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.7237104892730715,
|
|
"epoch": 0.8896797153024911,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004929540114131647,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.1671297013759613,
|
|
"num_tokens": 20615915.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.8896797153024911,
|
|
"eval_entropy": 5.620288949874935,
|
|
"eval_loss": 5.530864715576172,
|
|
"eval_mean_token_accuracy": 0.17870993085782907,
|
|
"eval_num_tokens": 20615915.0,
|
|
"eval_runtime": 26.781,
|
|
"eval_samples_per_second": 1214.033,
|
|
"eval_steps_per_second": 151.787,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.664465379714966,
|
|
"epoch": 0.8901739818109925,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004929452464103109,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.1794435366988182,
|
|
"num_tokens": 20627127.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.6596856117248535,
|
|
"epoch": 0.8906682483194939,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004929364760459704,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16800501495599746,
|
|
"num_tokens": 20638568.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.63860936164856,
|
|
"epoch": 0.8911625148279952,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004929277003203586,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1792854979634285,
|
|
"num_tokens": 20650803.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.660701560974121,
|
|
"epoch": 0.8916567813364966,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004929189192336916,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.16742482036352158,
|
|
"num_tokens": 20663021.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.639539480209351,
|
|
"epoch": 0.892151047844998,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004929101327861854,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.17885432243347169,
|
|
"num_tokens": 20675144.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.622758960723877,
|
|
"epoch": 0.8926453143534994,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004929013409780562,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.17454684227705003,
|
|
"num_tokens": 20685941.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.606095027923584,
|
|
"epoch": 0.8931395808620007,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004928925438095202,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.16819752305746077,
|
|
"num_tokens": 20696996.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.657205247879029,
|
|
"epoch": 0.8936338473705022,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004928837412807938,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.17403752878308296,
|
|
"num_tokens": 20708571.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.670529365539551,
|
|
"epoch": 0.8941281138790036,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004928749333920935,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.17751703560352325,
|
|
"num_tokens": 20719816.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.650663995742798,
|
|
"epoch": 0.894622380387505,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000492866120143636,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.17444172203540803,
|
|
"num_tokens": 20731540.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.659335088729859,
|
|
"epoch": 0.8951166468960063,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004928573015356382,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.17949065268039704,
|
|
"num_tokens": 20742949.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.635886144638062,
|
|
"epoch": 0.8956109134045077,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928484775683171,
|
|
"loss": 5.501,
|
|
"mean_token_accuracy": 0.17609216123819352,
|
|
"num_tokens": 20752840.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.657244253158569,
|
|
"epoch": 0.8961051799130091,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004928396482418895,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.17294907867908477,
|
|
"num_tokens": 20763772.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.623147678375244,
|
|
"epoch": 0.8965994464215105,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004928308135565728,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.17851870208978654,
|
|
"num_tokens": 20775815.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.65240592956543,
|
|
"epoch": 0.8970937129300118,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004928219735125843,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.17476027607917785,
|
|
"num_tokens": 20787307.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.671117210388184,
|
|
"epoch": 0.8975879794385132,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004928131281101415,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.1694930836558342,
|
|
"num_tokens": 20798910.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.755664730072022,
|
|
"epoch": 0.8980822459470146,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000492804277349462,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.16892759650945663,
|
|
"num_tokens": 20808628.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.631669712066651,
|
|
"epoch": 0.8985765124555161,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004927954212307634,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.17186451107263565,
|
|
"num_tokens": 20820117.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.573411560058593,
|
|
"epoch": 0.8990707789640174,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004927865597542637,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.18375806957483293,
|
|
"num_tokens": 20830859.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.635799789428711,
|
|
"epoch": 0.8995650454725188,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004927776929201807,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17859603017568587,
|
|
"num_tokens": 20843016.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.6251397132873535,
|
|
"epoch": 0.9000593119810202,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004927688207287328,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1769520029425621,
|
|
"num_tokens": 20854873.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.6995679378509525,
|
|
"epoch": 0.9005535784895216,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004927599431801381,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.17443255633115767,
|
|
"num_tokens": 20866756.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.6219987869262695,
|
|
"epoch": 0.9010478449980229,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000492751060274615,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.18279479146003724,
|
|
"num_tokens": 20878859.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.637990570068359,
|
|
"epoch": 0.9015421115065243,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004927421720123821,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.17559082806110382,
|
|
"num_tokens": 20889188.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.616944265365601,
|
|
"epoch": 0.9020363780150257,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004927332783936579,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.1742814838886261,
|
|
"num_tokens": 20900318.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.634148406982422,
|
|
"epoch": 0.902530644523527,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004927243794186614,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.17254281640052796,
|
|
"num_tokens": 20912384.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.650771188735962,
|
|
"epoch": 0.9030249110320284,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004927154750876112,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.17335536777973176,
|
|
"num_tokens": 20923002.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.704449558258057,
|
|
"epoch": 0.9035191775405299,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004927065654007268,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.16887372136116027,
|
|
"num_tokens": 20934235.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.570590972900391,
|
|
"epoch": 0.9040134440490313,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004926976503582269,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.1754317283630371,
|
|
"num_tokens": 20946788.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.656965923309326,
|
|
"epoch": 0.9045077105575327,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000492688729960331,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.17601744085550308,
|
|
"num_tokens": 20958963.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.6977170467376705,
|
|
"epoch": 0.905001977066034,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004926798042072587,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.17442580908536912,
|
|
"num_tokens": 20969630.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.598630571365357,
|
|
"epoch": 0.9054962435745354,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004926708730992294,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.17667967528104783,
|
|
"num_tokens": 20980489.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.673406600952148,
|
|
"epoch": 0.9059905100830368,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004926619366364629,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1789981856942177,
|
|
"num_tokens": 20992199.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.711535358428955,
|
|
"epoch": 0.9064847765915381,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000492652994819179,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.1737860083580017,
|
|
"num_tokens": 21003680.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.590730667114258,
|
|
"epoch": 0.9069790431000395,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004926440476475975,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.18575989603996276,
|
|
"num_tokens": 21014191.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.583924388885498,
|
|
"epoch": 0.9074733096085409,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004926350951219388,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.17985556423664092,
|
|
"num_tokens": 21025692.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.63469557762146,
|
|
"epoch": 0.9079675761170423,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000492626137242423,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.18276708275079728,
|
|
"num_tokens": 21036643.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.603221988677978,
|
|
"epoch": 0.9084618426255437,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004926171740092704,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.16791126728057862,
|
|
"num_tokens": 21047509.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.640965986251831,
|
|
"epoch": 0.9089561091340451,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004926082054227016,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1727961301803589,
|
|
"num_tokens": 21059854.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.665026330947876,
|
|
"epoch": 0.9094503756425465,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004925992314829372,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.18288413882255555,
|
|
"num_tokens": 21069926.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.649865436553955,
|
|
"epoch": 0.9099446421510479,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000492590252190198,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.17416280806064605,
|
|
"num_tokens": 21081580.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.597933387756347,
|
|
"epoch": 0.9104389086595492,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004925812675447047,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.18710310161113738,
|
|
"num_tokens": 21092510.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.56190857887268,
|
|
"epoch": 0.9109331751680506,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004925722775466785,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.17702857851982118,
|
|
"num_tokens": 21103995.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.624056100845337,
|
|
"epoch": 0.911427441676552,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004925632821963406,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.17747506201267244,
|
|
"num_tokens": 21114949.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.640227174758911,
|
|
"epoch": 0.9119217081850534,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004925542814939121,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18280288726091384,
|
|
"num_tokens": 21125810.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.593082237243652,
|
|
"epoch": 0.9124159746935547,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004925452754396146,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.17193531692028047,
|
|
"num_tokens": 21137728.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.660928678512573,
|
|
"epoch": 0.9129102412020561,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004925362640336696,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1757681518793106,
|
|
"num_tokens": 21149249.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.6519818782806395,
|
|
"epoch": 0.9134045077105575,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004925272472762987,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.1695096731185913,
|
|
"num_tokens": 21162338.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.541433572769165,
|
|
"epoch": 0.913898774219059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004925182251677238,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.1917804554104805,
|
|
"num_tokens": 21172953.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.566143751144409,
|
|
"epoch": 0.9143930407275603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004925091977081668,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.17959160655736922,
|
|
"num_tokens": 21183835.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.553306961059571,
|
|
"epoch": 0.9148873072360617,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004925001648978498,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.18161672949790955,
|
|
"num_tokens": 21195392.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.770074987411499,
|
|
"epoch": 0.9153815737445631,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000492491126736995,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.16091953814029694,
|
|
"num_tokens": 21207213.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.724966335296631,
|
|
"epoch": 0.9158758402530645,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004924820832258248,
|
|
"loss": 5.5366,
|
|
"mean_token_accuracy": 0.17651855051517487,
|
|
"num_tokens": 21218843.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.578042650222779,
|
|
"epoch": 0.9163701067615658,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004924730343645614,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17366669923067093,
|
|
"num_tokens": 21229596.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.72225980758667,
|
|
"epoch": 0.9168643732700672,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004924639801534278,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.17350477129220962,
|
|
"num_tokens": 21240040.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.720537996292114,
|
|
"epoch": 0.9173586397785686,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004924549205926465,
|
|
"loss": 5.558,
|
|
"mean_token_accuracy": 0.1641571044921875,
|
|
"num_tokens": 21252046.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.706523704528808,
|
|
"epoch": 0.91785290628707,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004924458556824405,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.1673804134130478,
|
|
"num_tokens": 21263720.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.70160436630249,
|
|
"epoch": 0.9183471727955713,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004924367854230326,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.17138696759939193,
|
|
"num_tokens": 21275751.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.600690650939941,
|
|
"epoch": 0.9188414393040728,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004924277098146461,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.17766037136316298,
|
|
"num_tokens": 21287081.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.614874267578125,
|
|
"epoch": 0.9193357058125742,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004924186288575043,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.17617927938699723,
|
|
"num_tokens": 21298007.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.693537187576294,
|
|
"epoch": 0.9198299723210756,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004924095425518304,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.1732432633638382,
|
|
"num_tokens": 21309416.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.584036207199096,
|
|
"epoch": 0.9203242388295769,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000492400450897848,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.17522188872098923,
|
|
"num_tokens": 21321129.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.607754945755005,
|
|
"epoch": 0.9208185053380783,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004923913538957809,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.18010570257902145,
|
|
"num_tokens": 21331706.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.654061031341553,
|
|
"epoch": 0.9213127718465797,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004923822515458526,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.17492108345031737,
|
|
"num_tokens": 21343738.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.617898178100586,
|
|
"epoch": 0.921807038355081,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004923731438482873,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.17667113840579987,
|
|
"num_tokens": 21354714.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.695460557937622,
|
|
"epoch": 0.9223013048635824,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004923640308033088,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.17164982259273528,
|
|
"num_tokens": 21365947.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.76964316368103,
|
|
"epoch": 0.9227955713720838,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004923549124111416,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.16386353224515915,
|
|
"num_tokens": 21376729.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.650874519348145,
|
|
"epoch": 0.9232898378805852,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004923457886720098,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.185856232047081,
|
|
"num_tokens": 21388017.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.584950399398804,
|
|
"epoch": 0.9237841043890866,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004923366595861378,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.18857492059469222,
|
|
"num_tokens": 21399566.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.642866945266723,
|
|
"epoch": 0.924278370897588,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004923275251537503,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.17137212306261063,
|
|
"num_tokens": 21410276.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.593152761459351,
|
|
"epoch": 0.9247726374060894,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000492318385375072,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.18238348364830018,
|
|
"num_tokens": 21421090.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.5874590396881105,
|
|
"epoch": 0.9252669039145908,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004923092402503277,
|
|
"loss": 5.4197,
|
|
"mean_token_accuracy": 0.18241414278745652,
|
|
"num_tokens": 21431057.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.641859769821167,
|
|
"epoch": 0.9257611704230921,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004923000897797423,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.16767863780260087,
|
|
"num_tokens": 21443849.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.694657468795777,
|
|
"epoch": 0.9262554369315935,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004922909339635411,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.1650463104248047,
|
|
"num_tokens": 21454824.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.652933740615845,
|
|
"epoch": 0.9267497034400949,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004922817728019492,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.17989446520805358,
|
|
"num_tokens": 21466082.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.611528205871582,
|
|
"epoch": 0.9272439699485963,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004922726062951918,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.17435491532087327,
|
|
"num_tokens": 21477805.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.646695995330811,
|
|
"epoch": 0.9277382364570976,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004922634344434948,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.17008617222309114,
|
|
"num_tokens": 21490014.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.6554460525512695,
|
|
"epoch": 0.928232502965599,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004922542572470835,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.17542345970869064,
|
|
"num_tokens": 21501713.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.523402833938599,
|
|
"epoch": 0.9287267694741005,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004922450747061837,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18204877078533171,
|
|
"num_tokens": 21513258.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.585144901275635,
|
|
"epoch": 0.9292210359826019,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004922358868210214,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.17428692132234574,
|
|
"num_tokens": 21526259.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.589871883392334,
|
|
"epoch": 0.9297153024911032,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004922266935918227,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.1772995725274086,
|
|
"num_tokens": 21539144.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.728576707839966,
|
|
"epoch": 0.9302095689996046,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004922174950188136,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.17142476439476012,
|
|
"num_tokens": 21550550.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.622857666015625,
|
|
"epoch": 0.930703835508106,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004922082911022204,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.17634247690439225,
|
|
"num_tokens": 21562491.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.568187808990478,
|
|
"epoch": 0.9311981020166074,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004921990818422694,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.1731433629989624,
|
|
"num_tokens": 21573679.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.651641178131103,
|
|
"epoch": 0.9316923685251087,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004921898672391874,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18073923289775848,
|
|
"num_tokens": 21585491.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.655065584182739,
|
|
"epoch": 0.9321866350336101,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004921806472932011,
|
|
"loss": 5.4906,
|
|
"mean_token_accuracy": 0.1752477377653122,
|
|
"num_tokens": 21598302.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.571835899353028,
|
|
"epoch": 0.9326809015421115,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004921714220045371,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.17749978303909303,
|
|
"num_tokens": 21608442.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.677858924865722,
|
|
"epoch": 0.9331751680506128,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004921621913734223,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.17143500000238418,
|
|
"num_tokens": 21619594.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.746927928924561,
|
|
"epoch": 0.9336694345591142,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004921529554000841,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.17507430016994477,
|
|
"num_tokens": 21631065.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.568306875228882,
|
|
"epoch": 0.9341637010676157,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004921437140847493,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.18092049658298492,
|
|
"num_tokens": 21640949.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.7048204898834225,
|
|
"epoch": 0.9346579675761171,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004921344674276456,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.17367605715990067,
|
|
"num_tokens": 21651189.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.74881272315979,
|
|
"epoch": 0.9351522340846185,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004921252154290003,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.17106803953647615,
|
|
"num_tokens": 21662790.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.651603317260742,
|
|
"epoch": 0.9356465005931198,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000492115958089041,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.17030172795057297,
|
|
"num_tokens": 21674980.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.648375606536865,
|
|
"epoch": 0.9361407671016212,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004921066954079955,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1748890459537506,
|
|
"num_tokens": 21687721.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.6562072277069095,
|
|
"epoch": 0.9366350336101226,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004920974273860915,
|
|
"loss": 5.5907,
|
|
"mean_token_accuracy": 0.16451887488365174,
|
|
"num_tokens": 21699522.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.66521806716919,
|
|
"epoch": 0.9371293001186239,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004920881540235572,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.18285309374332429,
|
|
"num_tokens": 21709972.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.567029619216919,
|
|
"epoch": 0.9376235666271253,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004920788753206205,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.17965718358755112,
|
|
"num_tokens": 21722172.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.6089636325836185,
|
|
"epoch": 0.9381178331356267,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00049206959127751,
|
|
"loss": 5.4596,
|
|
"mean_token_accuracy": 0.1720864176750183,
|
|
"num_tokens": 21734314.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.670386838912964,
|
|
"epoch": 0.9386120996441281,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004920603018944537,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.18039499074220658,
|
|
"num_tokens": 21744031.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.587564516067505,
|
|
"epoch": 0.9391063661526295,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004920510071716803,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.17903241962194444,
|
|
"num_tokens": 21755653.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.694164514541626,
|
|
"epoch": 0.9396006326611309,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004920417071094186,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.17136247158050538,
|
|
"num_tokens": 21768513.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.680429553985595,
|
|
"epoch": 0.9400948991696323,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004920324017078971,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.1698097378015518,
|
|
"num_tokens": 21780857.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.587002420425415,
|
|
"epoch": 0.9405891656781337,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000492023090967345,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.17995813339948655,
|
|
"num_tokens": 21792514.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.681600952148438,
|
|
"epoch": 0.941083432186635,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000492013774887991,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.17993906438350676,
|
|
"num_tokens": 21803154.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.653595352172852,
|
|
"epoch": 0.9415776986951364,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004920044534700645,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.1739970088005066,
|
|
"num_tokens": 21814439.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.570891523361206,
|
|
"epoch": 0.9420719652036378,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004919951267137949,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.1848617061972618,
|
|
"num_tokens": 21826870.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.66672682762146,
|
|
"epoch": 0.9425662317121392,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004919857946194114,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.17601252496242523,
|
|
"num_tokens": 21837627.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.578862190246582,
|
|
"epoch": 0.9430604982206405,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004919764571871438,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.17311064004898072,
|
|
"num_tokens": 21848891.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.656141710281372,
|
|
"epoch": 0.9435547647291419,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004919671144172216,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.18114614337682725,
|
|
"num_tokens": 21860094.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.631308937072754,
|
|
"epoch": 0.9440490312376434,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004919577663098748,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.18117759078741075,
|
|
"num_tokens": 21870881.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.595368385314941,
|
|
"epoch": 0.9445432977461448,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919484128653333,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.177288955450058,
|
|
"num_tokens": 21882825.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.6762316703796385,
|
|
"epoch": 0.9450375642546461,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004919390540838271,
|
|
"loss": 5.5298,
|
|
"mean_token_accuracy": 0.17297825068235398,
|
|
"num_tokens": 21894952.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.693763351440429,
|
|
"epoch": 0.9455318307631475,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004919296899655866,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.17052432298660278,
|
|
"num_tokens": 21906893.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.63824725151062,
|
|
"epoch": 0.9460260972716489,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000491920320510842,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.17259104698896408,
|
|
"num_tokens": 21918571.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.554791259765625,
|
|
"epoch": 0.9465203637801503,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004919109457198239,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.17669611424207687,
|
|
"num_tokens": 21929488.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.5857383728027346,
|
|
"epoch": 0.9470146302886516,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004919015655927629,
|
|
"loss": 5.4104,
|
|
"mean_token_accuracy": 0.1780275136232376,
|
|
"num_tokens": 21940368.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.68807806968689,
|
|
"epoch": 0.947508896797153,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004918921801298897,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.1744363471865654,
|
|
"num_tokens": 21951171.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.714824056625366,
|
|
"epoch": 0.9480031633056544,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004918827893314353,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.18054762184619905,
|
|
"num_tokens": 21962312.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.64189076423645,
|
|
"epoch": 0.9484974298141557,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004918733931976305,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.173190638422966,
|
|
"num_tokens": 21971994.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.706475305557251,
|
|
"epoch": 0.9489916963226572,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004918639917287067,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.17018840461969376,
|
|
"num_tokens": 21983084.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.65327033996582,
|
|
"epoch": 0.9494859628311586,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004918545849248951,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.17137276232242585,
|
|
"num_tokens": 21995005.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.5678001880645756,
|
|
"epoch": 0.94998022933966,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000491845172786427,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.1827775329351425,
|
|
"num_tokens": 22006377.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.611626291275025,
|
|
"epoch": 0.9504744958481613,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004918357553135339,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.1742014080286026,
|
|
"num_tokens": 22019663.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.761830234527588,
|
|
"epoch": 0.9509687623566627,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004918263325064476,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.17054231464862823,
|
|
"num_tokens": 22030646.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.682726240158081,
|
|
"epoch": 0.9514630288651641,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004918169043654,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.17776699513196945,
|
|
"num_tokens": 22043563.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.602488708496094,
|
|
"epoch": 0.9519572953736655,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004918074708906229,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.17729507833719255,
|
|
"num_tokens": 22055224.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.55563006401062,
|
|
"epoch": 0.9524515618821668,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004917980320823483,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.17054194062948227,
|
|
"num_tokens": 22067445.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.646741580963135,
|
|
"epoch": 0.9529458283906682,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004917885879408085,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.17879243642091752,
|
|
"num_tokens": 22078565.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.527668905258179,
|
|
"epoch": 0.9534400948991696,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004917791384662359,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.18980238288640977,
|
|
"num_tokens": 22088658.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.586333179473877,
|
|
"epoch": 0.953934361407671,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004917696836588628,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.16969957053661347,
|
|
"num_tokens": 22100747.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.588864803314209,
|
|
"epoch": 0.9544286279161724,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004917602235189218,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.17156362235546113,
|
|
"num_tokens": 22113559.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.6766153335571286,
|
|
"epoch": 0.9549228944246738,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004917507580466457,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.17094597220420837,
|
|
"num_tokens": 22124678.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.62889986038208,
|
|
"epoch": 0.9554171609331752,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004917412872422674,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.18061300963163376,
|
|
"num_tokens": 22136462.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.661085414886474,
|
|
"epoch": 0.9559114274416766,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004917318111060198,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.1800421878695488,
|
|
"num_tokens": 22149101.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.631427145004272,
|
|
"epoch": 0.9564056939501779,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000491722329638136,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.17668211758136748,
|
|
"num_tokens": 22159574.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.638296890258789,
|
|
"epoch": 0.9568999604586793,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004917128428388492,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.17448242902755737,
|
|
"num_tokens": 22172308.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.611148977279663,
|
|
"epoch": 0.9573942269671807,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004917033507083929,
|
|
"loss": 5.4735,
|
|
"mean_token_accuracy": 0.17118606716394424,
|
|
"num_tokens": 22183714.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.526318025588989,
|
|
"epoch": 0.9578884934756821,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004916938532470006,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.1806464210152626,
|
|
"num_tokens": 22194785.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.606223392486572,
|
|
"epoch": 0.9583827599841834,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004916843504549058,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.17851941883563996,
|
|
"num_tokens": 22205998.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.6355915546417235,
|
|
"epoch": 0.9588770264926848,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004916748423323424,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.1747051402926445,
|
|
"num_tokens": 22216114.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.609882974624634,
|
|
"epoch": 0.9593712930011863,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004916653288795443,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.18151162564754486,
|
|
"num_tokens": 22226793.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.6867835998535154,
|
|
"epoch": 0.9598655595096877,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004916558100967455,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.1787579596042633,
|
|
"num_tokens": 22237444.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.652164554595947,
|
|
"epoch": 0.960359826018189,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004916462859841801,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.17634357661008834,
|
|
"num_tokens": 22250704.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.589794397354126,
|
|
"epoch": 0.9608540925266904,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004916367565420826,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.17492785304784775,
|
|
"num_tokens": 22264533.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.750013637542724,
|
|
"epoch": 0.9613483590351918,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004916272217706871,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.17749757915735245,
|
|
"num_tokens": 22276510.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.709933805465698,
|
|
"epoch": 0.9618426255436932,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004916176816702284,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.1737707570195198,
|
|
"num_tokens": 22288634.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.678020334243774,
|
|
"epoch": 0.9623368920521945,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004916081362409411,
|
|
"loss": 5.5136,
|
|
"mean_token_accuracy": 0.16810104846954346,
|
|
"num_tokens": 22299781.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.570801258087158,
|
|
"epoch": 0.9628311585606959,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00049159858548306,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18801674395799636,
|
|
"num_tokens": 22310666.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.726185464859009,
|
|
"epoch": 0.9633254250691973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004915890293968202,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.16640140861272812,
|
|
"num_tokens": 22322811.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.694197034835815,
|
|
"epoch": 0.9638196915776986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004915794679824567,
|
|
"loss": 5.502,
|
|
"mean_token_accuracy": 0.1670682266354561,
|
|
"num_tokens": 22335017.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.571982574462891,
|
|
"epoch": 0.9643139580862001,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004915699012402047,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.18211430609226226,
|
|
"num_tokens": 22346250.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.662329006195068,
|
|
"epoch": 0.9648082245947015,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004915603291702995,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.176455457508564,
|
|
"num_tokens": 22357436.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.629383325576782,
|
|
"epoch": 0.9653024911032029,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004915507517729765,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.18036729246377944,
|
|
"num_tokens": 22368312.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.642659759521484,
|
|
"epoch": 0.9657967576117042,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004915411690484715,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.17537642866373063,
|
|
"num_tokens": 22378659.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.627149391174316,
|
|
"epoch": 0.9662910241202056,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915315809970202,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.17512933015823365,
|
|
"num_tokens": 22390642.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.658911848068238,
|
|
"epoch": 0.966785290628707,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004915219876188583,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.16694911271333696,
|
|
"num_tokens": 22402484.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.621188354492188,
|
|
"epoch": 0.9672795571372084,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004915123889142221,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.17775926291942595,
|
|
"num_tokens": 22413315.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.655669736862182,
|
|
"epoch": 0.9677738236457097,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004915027848833472,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.16964565664529802,
|
|
"num_tokens": 22425123.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.575278425216675,
|
|
"epoch": 0.9682680901542111,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004914931755264705,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.17859213054180145,
|
|
"num_tokens": 22436437.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.612262296676636,
|
|
"epoch": 0.9687623566627125,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000491483560843828,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.18037744164466857,
|
|
"num_tokens": 22446677.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.605930757522583,
|
|
"epoch": 0.969256623171214,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004914739408356563,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18156837821006774,
|
|
"num_tokens": 22457597.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.71006498336792,
|
|
"epoch": 0.9697508896797153,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914643155021921,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.17689813673496246,
|
|
"num_tokens": 22469715.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.648087882995606,
|
|
"epoch": 0.9702451561882167,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004914546848436722,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.17551311999559402,
|
|
"num_tokens": 22479840.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.572621774673462,
|
|
"epoch": 0.9707394226967181,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004914450488603334,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.1777665674686432,
|
|
"num_tokens": 22491017.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.613515377044678,
|
|
"epoch": 0.9712336892052195,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004914354075524129,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.17831608951091765,
|
|
"num_tokens": 22502308.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.548488664627075,
|
|
"epoch": 0.9717279557137208,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004914257609201477,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.1860113888978958,
|
|
"num_tokens": 22513090.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.602565813064575,
|
|
"epoch": 0.9722222222222222,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004914161089637752,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.18140849471092224,
|
|
"num_tokens": 22523391.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.576293992996216,
|
|
"epoch": 0.9727164887307236,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004914064516835329,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.18281854093074798,
|
|
"num_tokens": 22536038.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.632722234725952,
|
|
"epoch": 0.973210755239225,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004913967890796583,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1830255076289177,
|
|
"num_tokens": 22546897.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.620423412322998,
|
|
"epoch": 0.9737050217477263,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004913871211523891,
|
|
"loss": 5.4941,
|
|
"mean_token_accuracy": 0.17419084012508393,
|
|
"num_tokens": 22558240.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.603524446487427,
|
|
"epoch": 0.9741992882562278,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004913774479019633,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.18259523212909698,
|
|
"num_tokens": 22570540.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.705389595031738,
|
|
"epoch": 0.9746935547647292,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004913677693286185,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1733954891562462,
|
|
"num_tokens": 22582657.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.7152163028717045,
|
|
"epoch": 0.9751878212732306,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004913580854325932,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.17601173371076584,
|
|
"num_tokens": 22593445.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.600386714935302,
|
|
"epoch": 0.9756820877817319,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004913483962141253,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.17900647073984147,
|
|
"num_tokens": 22604631.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.613440132141113,
|
|
"epoch": 0.9761763542902333,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004913387016734533,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.18142877370119095,
|
|
"num_tokens": 22615130.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.575758457183838,
|
|
"epoch": 0.9766706207987347,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004913290018108157,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.17330560833215714,
|
|
"num_tokens": 22627372.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.701968765258789,
|
|
"epoch": 0.977164887307236,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004913192966264511,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.17626784592866898,
|
|
"num_tokens": 22640354.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.683132123947144,
|
|
"epoch": 0.9776591538157374,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004913095861205982,
|
|
"loss": 5.5132,
|
|
"mean_token_accuracy": 0.17212907522916793,
|
|
"num_tokens": 22651717.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.744489288330078,
|
|
"epoch": 0.9781534203242388,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004912998702934961,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16533099859952927,
|
|
"num_tokens": 22663334.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.653548049926758,
|
|
"epoch": 0.9786476868327402,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004912901491453835,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.17924571931362152,
|
|
"num_tokens": 22675894.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.533517599105835,
|
|
"epoch": 0.9791419533412415,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004912804226764997,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.18809325844049454,
|
|
"num_tokens": 22687861.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.596302223205567,
|
|
"epoch": 0.979636219849743,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004912706908870838,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.17806506901979446,
|
|
"num_tokens": 22698346.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.659794712066651,
|
|
"epoch": 0.9801304863582444,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004912609537773755,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.1641388937830925,
|
|
"num_tokens": 22710665.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.683880233764649,
|
|
"epoch": 0.9806247528667458,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004912512113476142,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.18567754179239274,
|
|
"num_tokens": 22720989.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.591424036026001,
|
|
"epoch": 0.9811190193752471,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004912414635980395,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1811174124479294,
|
|
"num_tokens": 22732265.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.592992639541626,
|
|
"epoch": 0.9816132858837485,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004912317105288912,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.17795587927103043,
|
|
"num_tokens": 22742435.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.564639711380005,
|
|
"epoch": 0.9821075523922499,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004912219521404094,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.17624802589416505,
|
|
"num_tokens": 22753750.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.637186717987061,
|
|
"epoch": 0.9826018189007513,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000491212188432834,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.17695475667715072,
|
|
"num_tokens": 22765549.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.6219724178314205,
|
|
"epoch": 0.9830960854092526,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004912024194064052,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.16939083933830262,
|
|
"num_tokens": 22777882.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.701483106613159,
|
|
"epoch": 0.983590351917754,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004911926450613633,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.17296624481678008,
|
|
"num_tokens": 22789671.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.714775657653808,
|
|
"epoch": 0.9840846184262554,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004911828653979488,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.17101709693670272,
|
|
"num_tokens": 22801330.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.630458641052246,
|
|
"epoch": 0.9845788849347569,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004911730804164024,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.17183419018983842,
|
|
"num_tokens": 22813998.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.604803419113159,
|
|
"epoch": 0.9850731514432582,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004911632901169645,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.17776573598384857,
|
|
"num_tokens": 22825048.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.54912109375,
|
|
"epoch": 0.9855674179517596,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004911534944998762,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.18228334784507752,
|
|
"num_tokens": 22835450.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.609027099609375,
|
|
"epoch": 0.986061684460261,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004911436935653785,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.17957870066165924,
|
|
"num_tokens": 22847320.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.625209379196167,
|
|
"epoch": 0.9865559509687624,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004911338873137122,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.1836007833480835,
|
|
"num_tokens": 22857676.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.5501330375671385,
|
|
"epoch": 0.9870502174772637,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000491124075745119,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1824871450662613,
|
|
"num_tokens": 22869767.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.652879953384399,
|
|
"epoch": 0.9875444839857651,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004911142588598399,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.17623329609632493,
|
|
"num_tokens": 22880096.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.680643701553345,
|
|
"epoch": 0.9880387504942665,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004911044366581165,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1802273914217949,
|
|
"num_tokens": 22892436.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.645199012756348,
|
|
"epoch": 0.9885330170027679,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004910946091401903,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.17365059852600098,
|
|
"num_tokens": 22904641.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.594686126708984,
|
|
"epoch": 0.9890272835112692,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004910847763063033,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.17861274778842925,
|
|
"num_tokens": 22915372.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.646111059188843,
|
|
"epoch": 0.9895215500197707,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004910749381566973,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.16534574776887895,
|
|
"num_tokens": 22926583.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.628334045410156,
|
|
"epoch": 0.9900158165282721,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004910650946916143,
|
|
"loss": 5.4014,
|
|
"mean_token_accuracy": 0.17540746331214904,
|
|
"num_tokens": 22938103.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.583013868331909,
|
|
"epoch": 0.9905100830367735,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004910552459112964,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.18023100793361663,
|
|
"num_tokens": 22949475.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.605685424804688,
|
|
"epoch": 0.9910043495452748,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004910453918159861,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.1740788295865059,
|
|
"num_tokens": 22961404.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.604638957977295,
|
|
"epoch": 0.9914986160537762,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004910355324059255,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.1729053109884262,
|
|
"num_tokens": 22973009.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.687219476699829,
|
|
"epoch": 0.9919928825622776,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004910256676813572,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.17996587753295898,
|
|
"num_tokens": 22985104.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.649395847320557,
|
|
"epoch": 0.992487149070779,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004910157976425241,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.1751338317990303,
|
|
"num_tokens": 22997133.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.574246883392334,
|
|
"epoch": 0.9929814155792803,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004910059222896689,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.18995430320501328,
|
|
"num_tokens": 23007621.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.635257291793823,
|
|
"epoch": 0.9934756820877817,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004909960416230344,
|
|
"loss": 5.4949,
|
|
"mean_token_accuracy": 0.1700994238257408,
|
|
"num_tokens": 23018254.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.64134578704834,
|
|
"epoch": 0.9939699485962831,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004909861556428638,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.17943399846553804,
|
|
"num_tokens": 23030733.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.5889569282531735,
|
|
"epoch": 0.9944642151047846,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004909762643494003,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.17521629482507706,
|
|
"num_tokens": 23043086.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.693779993057251,
|
|
"epoch": 0.9949584816132859,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004909663677428872,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.16975110471248628,
|
|
"num_tokens": 23055281.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.5783497333526615,
|
|
"epoch": 0.9954527481217873,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004909564658235678,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.17908014506101608,
|
|
"num_tokens": 23067332.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.608730697631836,
|
|
"epoch": 0.9959470146302887,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000490946558591686,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.17446106374263765,
|
|
"num_tokens": 23079278.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.584893274307251,
|
|
"epoch": 0.99644128113879,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004909366460474852,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.18211872279644012,
|
|
"num_tokens": 23092177.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.530267763137817,
|
|
"epoch": 0.9969355476472914,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004909267281912095,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.18074651509523393,
|
|
"num_tokens": 23103249.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.639324951171875,
|
|
"epoch": 0.9974298141557928,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004909168050231029,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.18035073727369308,
|
|
"num_tokens": 23113821.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.687488698959351,
|
|
"epoch": 0.9979240806642942,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004909068765434093,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.17038414180278777,
|
|
"num_tokens": 23124819.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.604080247879028,
|
|
"epoch": 0.9984183471727955,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000490896942752373,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.17634031027555466,
|
|
"num_tokens": 23135590.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.673853826522827,
|
|
"epoch": 0.9989126136812969,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004908870036502384,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.17950760275125505,
|
|
"num_tokens": 23147290.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.672258615493774,
|
|
"epoch": 0.9994068801897983,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004908770592372501,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.17825300842523575,
|
|
"num_tokens": 23158276.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.602096843719482,
|
|
"epoch": 0.9999011466982998,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004908671095136526,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.1814672127366066,
|
|
"num_tokens": 23169174.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.639762878417969,
|
|
"epoch": 1.0003954132068011,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004908571544796908,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.17319916039705277,
|
|
"num_tokens": 23180377.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.618290758132934,
|
|
"epoch": 1.0008896797153024,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004908471941356094,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.181108196079731,
|
|
"num_tokens": 23191158.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.664190864562988,
|
|
"epoch": 1.001383946223804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004908372284816537,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.18112669438123702,
|
|
"num_tokens": 23201956.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.59355731010437,
|
|
"epoch": 1.0018782127323052,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004908272575180685,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.1822439342737198,
|
|
"num_tokens": 23213449.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.664408254623413,
|
|
"epoch": 1.0023724792408066,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004908172812450993,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.16890496611595154,
|
|
"num_tokens": 23226514.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.574967241287231,
|
|
"epoch": 1.0028667457493081,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004908072996629917,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.1734767347574234,
|
|
"num_tokens": 23239322.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.644293546676636,
|
|
"epoch": 1.0033610122578094,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004907973127719909,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.17767395675182343,
|
|
"num_tokens": 23250990.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.6032720565795895,
|
|
"epoch": 1.0038552787663109,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004907873205723427,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.17211208790540694,
|
|
"num_tokens": 23261630.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.6346588134765625,
|
|
"epoch": 1.0043495452748121,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000490777323064293,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.17707151621580125,
|
|
"num_tokens": 23272823.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.493404531478882,
|
|
"epoch": 1.0048438117833136,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004907673202480876,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.20150097459554672,
|
|
"num_tokens": 23282827.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.599911022186279,
|
|
"epoch": 1.0053380782918149,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004907573121239727,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.18009489625692368,
|
|
"num_tokens": 23295359.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.609464454650879,
|
|
"epoch": 1.0058323448003164,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004907472986921945,
|
|
"loss": 5.3604,
|
|
"mean_token_accuracy": 0.18086358904838562,
|
|
"num_tokens": 23305932.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.555482053756714,
|
|
"epoch": 1.0063266113088176,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004907372799529992,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.17666230499744415,
|
|
"num_tokens": 23317856.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.548413515090942,
|
|
"epoch": 1.006820877817319,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004907272559066334,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1940659299492836,
|
|
"num_tokens": 23328071.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.5887001037597654,
|
|
"epoch": 1.0073151443258206,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004907172265533436,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17844088226556779,
|
|
"num_tokens": 23339601.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.662234592437744,
|
|
"epoch": 1.0078094108343219,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004907071918933766,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.18063221126794815,
|
|
"num_tokens": 23351672.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.643001747131348,
|
|
"epoch": 1.0083036773428233,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004906971519269793,
|
|
"loss": 5.4223,
|
|
"mean_token_accuracy": 0.17885400503873825,
|
|
"num_tokens": 23361684.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.493925428390503,
|
|
"epoch": 1.0087979438513246,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004906871066543984,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18466863930225372,
|
|
"num_tokens": 23373969.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.682028102874756,
|
|
"epoch": 1.009292210359826,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004906770560758813,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.16908788233995437,
|
|
"num_tokens": 23384747.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.666090965270996,
|
|
"epoch": 1.0097864768683273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004906670001916752,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.17508322447538377,
|
|
"num_tokens": 23395900.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.624408197402954,
|
|
"epoch": 1.0102807433768288,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004906569390020274,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.17891043275594712,
|
|
"num_tokens": 23408912.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.63669605255127,
|
|
"epoch": 1.01077500988533,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004906468725071855,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.1832889661192894,
|
|
"num_tokens": 23419042.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.5805981159210205,
|
|
"epoch": 1.0112692763938316,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000490636800707397,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.18006039261817933,
|
|
"num_tokens": 23430861.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.708979511260987,
|
|
"epoch": 1.0117635429023328,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004906267236029099,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.17645823806524277,
|
|
"num_tokens": 23443489.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.633938360214233,
|
|
"epoch": 1.0122578094108343,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004906166411939718,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.18302291631698608,
|
|
"num_tokens": 23454327.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.547570705413818,
|
|
"epoch": 1.0127520759193358,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004906065534808309,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.1913238525390625,
|
|
"num_tokens": 23466684.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.585733652114868,
|
|
"epoch": 1.013246342427837,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004905964604637353,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.18500744551420212,
|
|
"num_tokens": 23478347.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.54525089263916,
|
|
"epoch": 1.0137406089363385,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004905863621429334,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.1864367038011551,
|
|
"num_tokens": 23489588.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.536070489883423,
|
|
"epoch": 1.0142348754448398,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004905762585186735,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.18262064307928086,
|
|
"num_tokens": 23501347.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.646728086471557,
|
|
"epoch": 1.0147291419533413,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004905661495912042,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.17704963088035583,
|
|
"num_tokens": 23513036.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.613691329956055,
|
|
"epoch": 1.0152234084618426,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004905560353607742,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.18304013311862946,
|
|
"num_tokens": 23524166.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.583169460296631,
|
|
"epoch": 1.015717674970344,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004905459158276323,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.17782323509454728,
|
|
"num_tokens": 23536638.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.567576122283936,
|
|
"epoch": 1.0162119414788453,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004905357909920275,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.17961832582950593,
|
|
"num_tokens": 23548567.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.638755798339844,
|
|
"epoch": 1.0167062079873468,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004905256608542086,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.1839924067258835,
|
|
"num_tokens": 23560108.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.599609231948852,
|
|
"epoch": 1.0172004744958483,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004905155254144251,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.1820736989378929,
|
|
"num_tokens": 23571542.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.4989618301391605,
|
|
"epoch": 1.0176947410043495,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004905053846729263,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.1795853853225708,
|
|
"num_tokens": 23582200.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.652921342849732,
|
|
"epoch": 1.018189007512851,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004904952386299616,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.1716245785355568,
|
|
"num_tokens": 23594530.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.594514989852906,
|
|
"epoch": 1.0186832740213523,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004904850872857805,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19320856630802155,
|
|
"num_tokens": 23605697.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.556019067764282,
|
|
"epoch": 1.0191775405298538,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000490474930640633,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.18057612776756288,
|
|
"num_tokens": 23615730.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.528661584854126,
|
|
"epoch": 1.019671807038355,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004904647686947687,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.18704380244016647,
|
|
"num_tokens": 23627242.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.555718898773193,
|
|
"epoch": 1.0201660735468565,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904546014484376,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.18604109585285186,
|
|
"num_tokens": 23639450.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.5946510314941404,
|
|
"epoch": 1.0206603400553578,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004904444289018898,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.18003058880567552,
|
|
"num_tokens": 23651154.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.609207391738892,
|
|
"epoch": 1.0211546065638593,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004904342510553758,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.17633230239152908,
|
|
"num_tokens": 23663996.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.62468695640564,
|
|
"epoch": 1.0216488730723605,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004904240679091458,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.18398423939943315,
|
|
"num_tokens": 23676270.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.633299016952515,
|
|
"epoch": 1.022143139580862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004904138794634502,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.18019284605979918,
|
|
"num_tokens": 23687483.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.61824893951416,
|
|
"epoch": 1.0226374060893635,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004904036857185398,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.17563215792179107,
|
|
"num_tokens": 23697956.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.612403631210327,
|
|
"epoch": 1.0231316725978647,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004903934866746653,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.18337382376194,
|
|
"num_tokens": 23709029.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.601914501190185,
|
|
"epoch": 1.0236259391063662,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004903832823320777,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.19016283452510835,
|
|
"num_tokens": 23719792.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.534942770004273,
|
|
"epoch": 1.0241202056148675,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004903730726910278,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.18136471807956694,
|
|
"num_tokens": 23730201.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.570589351654053,
|
|
"epoch": 1.024614472123369,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000490362857751767,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18271630108356476,
|
|
"num_tokens": 23741743.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.578035354614258,
|
|
"epoch": 1.0251087386318702,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004903526375145465,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.1829551339149475,
|
|
"num_tokens": 23753879.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.581305456161499,
|
|
"epoch": 1.0256030051403717,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004903424119796176,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.17224690467119216,
|
|
"num_tokens": 23765062.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.586255073547363,
|
|
"epoch": 1.026097271648873,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004903321811472321,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.18737316727638245,
|
|
"num_tokens": 23777261.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.612558078765869,
|
|
"epoch": 1.0265915381573745,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004903219450176413,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.1804007738828659,
|
|
"num_tokens": 23789247.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.602423620223999,
|
|
"epoch": 1.0270858046658757,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004903117035910975,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18375235944986343,
|
|
"num_tokens": 23798981.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.606297492980957,
|
|
"epoch": 1.0275800711743772,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004903014568678523,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17679834067821504,
|
|
"num_tokens": 23810856.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.654565811157227,
|
|
"epoch": 1.0280743376828787,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004902912048481579,
|
|
"loss": 5.3967,
|
|
"mean_token_accuracy": 0.17967783510684968,
|
|
"num_tokens": 23821544.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.594311380386353,
|
|
"epoch": 1.02856860419138,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004902809475322664,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.17983878403902054,
|
|
"num_tokens": 23831972.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.6540367603302,
|
|
"epoch": 1.0290628706998814,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004902706849204302,
|
|
"loss": 5.3353,
|
|
"mean_token_accuracy": 0.18282803297042846,
|
|
"num_tokens": 23843451.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.562797117233276,
|
|
"epoch": 1.0295571372083827,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004902604170129017,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.18182328343391418,
|
|
"num_tokens": 23854060.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.68224949836731,
|
|
"epoch": 1.0300514037168842,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004902501438099337,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.17100422233343124,
|
|
"num_tokens": 23865722.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.645337343215942,
|
|
"epoch": 1.0305456702253855,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004902398653117787,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.1800435721874237,
|
|
"num_tokens": 23875888.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.599168157577514,
|
|
"epoch": 1.031039936733887,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004902295815186896,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.17759353667497635,
|
|
"num_tokens": 23887816.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.604881620407104,
|
|
"epoch": 1.0315342032423882,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004902192924309193,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.17917980253696442,
|
|
"num_tokens": 23900468.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.661530256271362,
|
|
"epoch": 1.0320284697508897,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004902089980487211,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17786262482404708,
|
|
"num_tokens": 23912086.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.587360763549805,
|
|
"epoch": 1.032522736259391,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004901986983723483,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.1830502852797508,
|
|
"num_tokens": 23923262.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.530913352966309,
|
|
"epoch": 1.0330170027678924,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000490188393402054,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.18423015773296356,
|
|
"num_tokens": 23934660.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.569023084640503,
|
|
"epoch": 1.033511269276394,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004901780831380919,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.1839585855603218,
|
|
"num_tokens": 23945822.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.565365791320801,
|
|
"epoch": 1.0340055357848952,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004901677675807155,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.17760722637176513,
|
|
"num_tokens": 23957312.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.66640157699585,
|
|
"epoch": 1.0344998022933967,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004901574467301786,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18075919449329375,
|
|
"num_tokens": 23968477.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.540691804885864,
|
|
"epoch": 1.034994068801898,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004901471205867353,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.18083850294351578,
|
|
"num_tokens": 23979041.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.575230693817138,
|
|
"epoch": 1.0354883353103994,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004901367891506393,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.1812360554933548,
|
|
"num_tokens": 23990947.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.6211991786956785,
|
|
"epoch": 1.0359826018189007,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000490126452422145,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.18485706746578218,
|
|
"num_tokens": 24001652.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.617757320404053,
|
|
"epoch": 1.0364768683274022,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004901161104015066,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.17540715187788009,
|
|
"num_tokens": 24012707.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.481687927246094,
|
|
"epoch": 1.0369711348359034,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004901057630889784,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.1914891019463539,
|
|
"num_tokens": 24024136.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.64856538772583,
|
|
"epoch": 1.037465401344405,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004900954104848152,
|
|
"loss": 5.3768,
|
|
"mean_token_accuracy": 0.18491912484169007,
|
|
"num_tokens": 24035586.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.59693021774292,
|
|
"epoch": 1.0379596678529064,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004900850525892714,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.18535464853048325,
|
|
"num_tokens": 24045338.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.612761974334717,
|
|
"epoch": 1.0384539343614076,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000490074689402602,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1718156397342682,
|
|
"num_tokens": 24056898.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.542012453079224,
|
|
"epoch": 1.0389482008699091,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004900643209250619,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.1880309283733368,
|
|
"num_tokens": 24068998.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.575481700897217,
|
|
"epoch": 1.0394424673784104,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004900539471569061,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.18266068994998932,
|
|
"num_tokens": 24080301.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.6002143859863285,
|
|
"epoch": 1.0399367338869119,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049004356809839,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.1800027683377266,
|
|
"num_tokens": 24092601.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.687857007980346,
|
|
"epoch": 1.0404310003954131,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004900331837497686,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.17366955429315567,
|
|
"num_tokens": 24105621.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.569841909408569,
|
|
"epoch": 1.0409252669039146,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004900227941112976,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.18902141302824021,
|
|
"num_tokens": 24117926.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.5801934719085695,
|
|
"epoch": 1.0414195334124159,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004900123991832323,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.1830226868391037,
|
|
"num_tokens": 24129119.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.519017839431763,
|
|
"epoch": 1.0419137999209174,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004900019989658288,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.1779838502407074,
|
|
"num_tokens": 24141726.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.65352873802185,
|
|
"epoch": 1.0424080664294189,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004899915934593427,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.17922114431858063,
|
|
"num_tokens": 24152912.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.673704719543457,
|
|
"epoch": 1.0429023329379201,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004899811826640302,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.17175705283880233,
|
|
"num_tokens": 24163602.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.629202079772949,
|
|
"epoch": 1.0433965994464216,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004899707665801471,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.18362539857625962,
|
|
"num_tokens": 24175904.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.547493505477905,
|
|
"epoch": 1.0438908659549229,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004899603452079499,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.17251179963350297,
|
|
"num_tokens": 24186438.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.564514398574829,
|
|
"epoch": 1.0443851324634243,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004899499185476948,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.17909477800130844,
|
|
"num_tokens": 24198357.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.714317512512207,
|
|
"epoch": 1.0448793989719256,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004899394865996383,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.1723647564649582,
|
|
"num_tokens": 24211257.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.700878667831421,
|
|
"epoch": 1.045373665480427,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004899290493640371,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.16918903291225434,
|
|
"num_tokens": 24223189.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.5991840839385985,
|
|
"epoch": 1.0458679319889284,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004899186068411481,
|
|
"loss": 5.3721,
|
|
"mean_token_accuracy": 0.18176865577697754,
|
|
"num_tokens": 24234701.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.660954761505127,
|
|
"epoch": 1.0463621984974298,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004899081590312278,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.18434980511665344,
|
|
"num_tokens": 24245562.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.599382066726685,
|
|
"epoch": 1.046856465005931,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004898977059345336,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.1713985100388527,
|
|
"num_tokens": 24256479.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.623529434204102,
|
|
"epoch": 1.0473507315144326,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004898872475513225,
|
|
"loss": 5.4704,
|
|
"mean_token_accuracy": 0.16975690573453903,
|
|
"num_tokens": 24266900.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.6786552429199215,
|
|
"epoch": 1.047844998022934,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004898767838818517,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.17254967540502547,
|
|
"num_tokens": 24278915.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.567503261566162,
|
|
"epoch": 1.0483392645314353,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004898663149263787,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.18790926784276962,
|
|
"num_tokens": 24289584.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.589642333984375,
|
|
"epoch": 1.0488335310399368,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004898558406851611,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.18421768248081208,
|
|
"num_tokens": 24300922.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.563185310363769,
|
|
"epoch": 1.049327797548438,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004898453611584564,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.1812851533293724,
|
|
"num_tokens": 24311238.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.5658595085144045,
|
|
"epoch": 1.0498220640569396,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004898348763465226,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.18156313747167588,
|
|
"num_tokens": 24322417.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.602853536605835,
|
|
"epoch": 1.0503163305654408,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004898243862496173,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.18868836015462875,
|
|
"num_tokens": 24332751.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.63677225112915,
|
|
"epoch": 1.0508105970739423,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004898138908679989,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.1713208422064781,
|
|
"num_tokens": 24345082.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.572784519195556,
|
|
"epoch": 1.0513048635824436,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004898033902019255,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.18036195635795593,
|
|
"num_tokens": 24355863.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.7149464130401615,
|
|
"epoch": 1.051799130090945,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004897928842516553,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.16917538195848464,
|
|
"num_tokens": 24367763.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.617725992202759,
|
|
"epoch": 1.0522933965994463,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004897823730174468,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.17428689301013947,
|
|
"num_tokens": 24378943.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.62014946937561,
|
|
"epoch": 1.0527876631079478,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004897718564995587,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.17853184640407563,
|
|
"num_tokens": 24389508.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.555666875839234,
|
|
"epoch": 1.0532819296164493,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004897613346982495,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18500358015298843,
|
|
"num_tokens": 24400710.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.547687196731568,
|
|
"epoch": 1.0537761961249505,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004897508076137783,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.17965807914733886,
|
|
"num_tokens": 24412854.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.65095477104187,
|
|
"epoch": 1.054270462633452,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004897402752464037,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17982176393270494,
|
|
"num_tokens": 24423212.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.645588111877442,
|
|
"epoch": 1.0547647291419533,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004897297375963852,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.18033940494060516,
|
|
"num_tokens": 24436091.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.508688688278198,
|
|
"epoch": 1.0552589956504548,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004897191946639819,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.18529360890388488,
|
|
"num_tokens": 24448499.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.658615398406982,
|
|
"epoch": 1.055753262158956,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004897086464494529,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.1692500501871109,
|
|
"num_tokens": 24460732.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.665773200988769,
|
|
"epoch": 1.0562475286674575,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004896980929530579,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.18505216538906097,
|
|
"num_tokens": 24472460.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.564381885528564,
|
|
"epoch": 1.0567417951759588,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004896875341750567,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.18328477442264557,
|
|
"num_tokens": 24483820.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.533804988861084,
|
|
"epoch": 1.0572360616844603,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004896769701157087,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.1878838062286377,
|
|
"num_tokens": 24495775.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.610626459121704,
|
|
"epoch": 1.0577303281929615,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000489666400775274,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.18411868959665298,
|
|
"num_tokens": 24505589.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.543708276748657,
|
|
"epoch": 1.058224594701463,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004896558261540125,
|
|
"loss": 5.3439,
|
|
"mean_token_accuracy": 0.18093699514865874,
|
|
"num_tokens": 24515988.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.486443376541137,
|
|
"epoch": 1.0587188612099645,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004896452462521844,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.18438231945037842,
|
|
"num_tokens": 24528273.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.6971231460571286,
|
|
"epoch": 1.0592131277184658,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004896346610700498,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.18528537303209305,
|
|
"num_tokens": 24539014.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.5489684581756595,
|
|
"epoch": 1.0597073942269672,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004896240706078694,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18005328625440598,
|
|
"num_tokens": 24550210.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.553048515319825,
|
|
"epoch": 1.0602016607354685,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004896134748659036,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.185430845618248,
|
|
"num_tokens": 24560934.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.581753063201904,
|
|
"epoch": 1.06069592724397,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000489602873844413,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.17271746695041656,
|
|
"num_tokens": 24572274.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.629467535018921,
|
|
"epoch": 1.0611901937524713,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004895922675436583,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.1776210770010948,
|
|
"num_tokens": 24583950.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.5824049949646,
|
|
"epoch": 1.0616844602609727,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004895816559639006,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.18541269153356552,
|
|
"num_tokens": 24597058.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.495601463317871,
|
|
"epoch": 1.062178726769474,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004895710391054008,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19085879176855086,
|
|
"num_tokens": 24608604.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.587714147567749,
|
|
"epoch": 1.0626729932779755,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004895604169684203,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1789229229092598,
|
|
"num_tokens": 24619707.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.617729949951172,
|
|
"epoch": 1.063167259786477,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004895497895532202,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.17505383491516113,
|
|
"num_tokens": 24629579.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.5219849109649655,
|
|
"epoch": 1.0636615262949782,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004895391568600619,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.17266384959220887,
|
|
"num_tokens": 24641358.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.5368305206298825,
|
|
"epoch": 1.0641557928034797,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004895285188892071,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1786504343152046,
|
|
"num_tokens": 24652293.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.6338409900665285,
|
|
"epoch": 1.064650059311981,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004895178756409175,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.18196174800395964,
|
|
"num_tokens": 24663370.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.643576955795288,
|
|
"epoch": 1.0651443258204825,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004895072271154548,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.17478834241628646,
|
|
"num_tokens": 24675037.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.601250457763672,
|
|
"epoch": 1.0656385923289837,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004894965733130812,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.17706177532672882,
|
|
"num_tokens": 24685680.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.5316300868988035,
|
|
"epoch": 1.0661328588374852,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004894859142340585,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.18787552714347838,
|
|
"num_tokens": 24697831.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.573435592651367,
|
|
"epoch": 1.0666271253459865,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004894752498786491,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.18060458898544313,
|
|
"num_tokens": 24710226.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.61092176437378,
|
|
"epoch": 1.067121391854488,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004894645802471152,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.18193954229354858,
|
|
"num_tokens": 24721743.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.625250291824341,
|
|
"epoch": 1.0676156583629894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004894539053397194,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17382271736860275,
|
|
"num_tokens": 24733804.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.569423723220825,
|
|
"epoch": 1.0681099248714907,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004894432251567242,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.18820807188749314,
|
|
"num_tokens": 24745285.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.546831369400024,
|
|
"epoch": 1.0686041913799922,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004894325396983925,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17805953472852706,
|
|
"num_tokens": 24756069.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.544105100631714,
|
|
"epoch": 1.0690984578884934,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004894218489649869,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.18413197100162507,
|
|
"num_tokens": 24766935.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.581832838058472,
|
|
"epoch": 1.069592724396995,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004894111529567707,
|
|
"loss": 5.3464,
|
|
"mean_token_accuracy": 0.18298100233078002,
|
|
"num_tokens": 24777642.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.565897226333618,
|
|
"epoch": 1.0700869909054962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004894004516740069,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18629778772592545,
|
|
"num_tokens": 24788110.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.633518838882447,
|
|
"epoch": 1.0705812574139977,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004893897451169586,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.17368397861719131,
|
|
"num_tokens": 24799976.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.6292167663574215,
|
|
"epoch": 1.071075523922499,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004893790332858893,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.1805665373802185,
|
|
"num_tokens": 24811131.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.647142171859741,
|
|
"epoch": 1.0715697904310004,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004893683161810626,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.18082465827465058,
|
|
"num_tokens": 24822137.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.500767755508423,
|
|
"epoch": 1.0720640569395017,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004893575938027421,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.189617919921875,
|
|
"num_tokens": 24832369.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.566301488876343,
|
|
"epoch": 1.0725583234480032,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004893468661511914,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.18283522725105286,
|
|
"num_tokens": 24843351.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.703607749938965,
|
|
"epoch": 1.0730525899565047,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004893361332266746,
|
|
"loss": 5.4745,
|
|
"mean_token_accuracy": 0.17261989861726762,
|
|
"num_tokens": 24855019.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.590196180343628,
|
|
"epoch": 1.073546856465006,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004893253950294557,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.17957315891981124,
|
|
"num_tokens": 24866224.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.546037817001343,
|
|
"epoch": 1.0740411229735074,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004893146515597989,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.18676255494356156,
|
|
"num_tokens": 24876995.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.573471450805664,
|
|
"epoch": 1.0745353894820087,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004893039028179683,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.18076877295970917,
|
|
"num_tokens": 24887846.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.628023910522461,
|
|
"epoch": 1.0750296559905101,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004892931488042285,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.1691031724214554,
|
|
"num_tokens": 24899221.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.703494358062744,
|
|
"epoch": 1.0755239224990114,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000489282389518844,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.1752576306462288,
|
|
"num_tokens": 24912103.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.6805554866790775,
|
|
"epoch": 1.076018189007513,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004892716249620795,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.17436271160840988,
|
|
"num_tokens": 24925465.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.601455163955689,
|
|
"epoch": 1.0765124555160142,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004892608551341997,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.18283611536026,
|
|
"num_tokens": 24935136.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.551472091674805,
|
|
"epoch": 1.0770067220245156,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004892500800354697,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.174759379029274,
|
|
"num_tokens": 24946845.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.551084375381469,
|
|
"epoch": 1.077500988533017,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004892392996661544,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.1786414623260498,
|
|
"num_tokens": 24958337.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.60775842666626,
|
|
"epoch": 1.0779952550415184,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004892285140265192,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.17483609914779663,
|
|
"num_tokens": 24969505.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.584920930862427,
|
|
"epoch": 1.0784895215500199,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004892177231168292,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.1822478488087654,
|
|
"num_tokens": 24981577.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.663256502151489,
|
|
"epoch": 1.0789837880585211,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004892069269373502,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.18019595891237258,
|
|
"num_tokens": 24992758.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.646511507034302,
|
|
"epoch": 1.0794780545670226,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004891961254883474,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.18583132326602936,
|
|
"num_tokens": 25003057.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.573426151275635,
|
|
"epoch": 1.0799723210755239,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004891853187700867,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.1811237335205078,
|
|
"num_tokens": 25014900.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.534041023254394,
|
|
"epoch": 1.0804665875840254,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004891745067828339,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.1881041944026947,
|
|
"num_tokens": 25026313.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.631109714508057,
|
|
"epoch": 1.0809608540925266,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004891636895268551,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.18107526749372482,
|
|
"num_tokens": 25037014.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.6729213237762455,
|
|
"epoch": 1.081455120601028,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004891528670024162,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.17735380530357361,
|
|
"num_tokens": 25048051.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.537176179885864,
|
|
"epoch": 1.0819493871095294,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004891420392097837,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.19081701338291168,
|
|
"num_tokens": 25057825.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.496074867248535,
|
|
"epoch": 1.0824436536180309,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004891312061492236,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.18206021785736085,
|
|
"num_tokens": 25067702.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.575092458724976,
|
|
"epoch": 1.0829379201265321,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004891203678210027,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18799349814653396,
|
|
"num_tokens": 25078246.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.550699710845947,
|
|
"epoch": 1.0834321866350336,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004891095242253876,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.18111059069633484,
|
|
"num_tokens": 25089267.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.634660482406616,
|
|
"epoch": 1.083926453143535,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004890986753626449,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.17759272009134291,
|
|
"num_tokens": 25101392.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.653545665740967,
|
|
"epoch": 1.0844207196520363,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004890878212330418,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.17998944818973542,
|
|
"num_tokens": 25113309.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.565053129196167,
|
|
"epoch": 1.0849149861605378,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004890769618368448,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.192211577296257,
|
|
"num_tokens": 25124803.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.568624544143677,
|
|
"epoch": 1.085409252669039,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004890660971743215,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1810787945985794,
|
|
"num_tokens": 25136443.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.630527830123901,
|
|
"epoch": 1.0859035191775406,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004890552272457389,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.17480652332305907,
|
|
"num_tokens": 25147128.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.546853160858154,
|
|
"epoch": 1.0863977856860418,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004890443520513645,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17961681634187698,
|
|
"num_tokens": 25159420.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.5312940120697025,
|
|
"epoch": 1.0868920521945433,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004890334715914659,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.18755175918340683,
|
|
"num_tokens": 25171624.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.502357721328735,
|
|
"epoch": 1.0873863187030446,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004890225858663106,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.1913269966840744,
|
|
"num_tokens": 25181610.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.579279899597168,
|
|
"epoch": 1.087880585211546,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004890116948761666,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.180028735101223,
|
|
"num_tokens": 25191852.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.633179378509522,
|
|
"epoch": 1.0883748517200476,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004890007986213018,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.17043002918362618,
|
|
"num_tokens": 25204240.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.477516555786133,
|
|
"epoch": 1.0888691182285488,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004889898971019838,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.18740566372871398,
|
|
"num_tokens": 25215512.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.550324487686157,
|
|
"epoch": 1.0893633847370503,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004889789903184815,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.17589724212884902,
|
|
"num_tokens": 25227903.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.610426950454712,
|
|
"epoch": 1.0898576512455516,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004889680782710626,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.18965642154216766,
|
|
"num_tokens": 25240204.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.573281383514404,
|
|
"epoch": 1.090351917754053,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004889571609599958,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.18713442385196685,
|
|
"num_tokens": 25251978.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.582752752304077,
|
|
"epoch": 1.0908461842625543,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004889462383855498,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.18548388481140138,
|
|
"num_tokens": 25262496.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.575381183624268,
|
|
"epoch": 1.0913404507710558,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000488935310547993,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1829536408185959,
|
|
"num_tokens": 25272814.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.585187387466431,
|
|
"epoch": 1.091834717279557,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004889243774475945,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.1853860691189766,
|
|
"num_tokens": 25283749.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.541534948348999,
|
|
"epoch": 1.0923289837880585,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000488913439084623,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18632111102342605,
|
|
"num_tokens": 25295993.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.596709156036377,
|
|
"epoch": 1.09282325029656,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004889024954593477,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.1781999111175537,
|
|
"num_tokens": 25309011.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.597272634506226,
|
|
"epoch": 1.0933175168050613,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000488891546572038,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.1797708362340927,
|
|
"num_tokens": 25320901.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.590220785140991,
|
|
"epoch": 1.0938117833135628,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000488880592422963,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.19076840430498124,
|
|
"num_tokens": 25333042.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.511449813842773,
|
|
"epoch": 1.094306049822064,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004888696330123921,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.18207001835107803,
|
|
"num_tokens": 25346413.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.56815538406372,
|
|
"epoch": 1.0948003163305655,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004888586683405952,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.1792866915464401,
|
|
"num_tokens": 25358104.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.5989889144897464,
|
|
"epoch": 1.0952945828390668,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004888476984078419,
|
|
"loss": 5.352,
|
|
"mean_token_accuracy": 0.18152766674757004,
|
|
"num_tokens": 25369485.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.631257200241089,
|
|
"epoch": 1.0957888493475683,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000488836723214402,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.17592909038066865,
|
|
"num_tokens": 25380349.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.607117128372193,
|
|
"epoch": 1.0962831158560695,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004888257427605456,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.1732124999165535,
|
|
"num_tokens": 25393042.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.681882715225219,
|
|
"epoch": 1.096777382364571,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004888147570465426,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.17980571687221528,
|
|
"num_tokens": 25404470.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.52920389175415,
|
|
"epoch": 1.0972716488730723,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004888037660726635,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1911957934498787,
|
|
"num_tokens": 25415397.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.601304769515991,
|
|
"epoch": 1.0977659153815738,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004887927698391786,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.16960737258195877,
|
|
"num_tokens": 25427409.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.625826120376587,
|
|
"epoch": 1.0982601818900752,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004887817683463583,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.1789565473794937,
|
|
"num_tokens": 25438063.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.545429515838623,
|
|
"epoch": 1.0987544483985765,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004887707615944734,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.18865484297275542,
|
|
"num_tokens": 25449242.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.603923082351685,
|
|
"epoch": 1.099248714907078,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004887597495837946,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18018456250429155,
|
|
"num_tokens": 25461434.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.548195648193359,
|
|
"epoch": 1.0997429814155792,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004887487323145929,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.18582371473312378,
|
|
"num_tokens": 25472035.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.614398670196533,
|
|
"epoch": 1.1002372479240807,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000488737709787139,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.18664295971393585,
|
|
"num_tokens": 25483143.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.620625782012939,
|
|
"epoch": 1.100731514432582,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004887266820017044,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.172362120449543,
|
|
"num_tokens": 25496873.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.577845621109009,
|
|
"epoch": 1.1012257809410835,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004887156489585603,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.18765253871679305,
|
|
"num_tokens": 25508661.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.710248327255249,
|
|
"epoch": 1.1017200474495847,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000488704610657978,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.1718953639268875,
|
|
"num_tokens": 25520789.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.4901165008544925,
|
|
"epoch": 1.1022143139580862,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004886935671002293,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.19053345620632173,
|
|
"num_tokens": 25531131.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.615669250488281,
|
|
"epoch": 1.1027085804665875,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004886825182855855,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.17832743674516677,
|
|
"num_tokens": 25543803.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.64614953994751,
|
|
"epoch": 1.103202846975089,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004886714642143188,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.1950691357254982,
|
|
"num_tokens": 25553588.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.604764556884765,
|
|
"epoch": 1.1036971134835905,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004886604048867007,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.18168952763080598,
|
|
"num_tokens": 25566175.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.633071947097778,
|
|
"epoch": 1.1041913799920917,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004886493403030035,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.1712593615055084,
|
|
"num_tokens": 25578033.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.557466125488281,
|
|
"epoch": 1.1046856465005932,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004886382704634996,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18420130908489227,
|
|
"num_tokens": 25588759.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.522971534729004,
|
|
"epoch": 1.1051799130090945,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004886271953684609,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.19088909775018692,
|
|
"num_tokens": 25599200.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.547098302841187,
|
|
"epoch": 1.105674179517596,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004886161150181602,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.18297430276870727,
|
|
"num_tokens": 25610279.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.556465673446655,
|
|
"epoch": 1.1061684460260972,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004886050294128698,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.1838948979973793,
|
|
"num_tokens": 25622062.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.569022130966187,
|
|
"epoch": 1.1066627125345987,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004885939385528628,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.17735291123390198,
|
|
"num_tokens": 25633451.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.533872318267822,
|
|
"epoch": 1.1071569790431,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004885828424384114,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.1838160440325737,
|
|
"num_tokens": 25644537.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.549351453781128,
|
|
"epoch": 1.1076512455516014,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004885717410697892,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.18590883314609527,
|
|
"num_tokens": 25655570.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.681525135040284,
|
|
"epoch": 1.1081455120601027,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000488560634447269,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.17505040913820266,
|
|
"num_tokens": 25669470.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.641649913787842,
|
|
"epoch": 1.1086397785686042,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000488549522571124,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.17822419703006745,
|
|
"num_tokens": 25682347.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.683649301528931,
|
|
"epoch": 1.1091340450771057,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004885384054416276,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.1744300201535225,
|
|
"num_tokens": 25694038.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.553509330749511,
|
|
"epoch": 1.109628311585607,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004885272830590534,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.1861598640680313,
|
|
"num_tokens": 25705850.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.541153144836426,
|
|
"epoch": 1.1101225780941084,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004885161554236748,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.18622292280197145,
|
|
"num_tokens": 25716294.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.540984773635865,
|
|
"epoch": 1.1106168446026097,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004885050225357657,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.1897607386112213,
|
|
"num_tokens": 25727367.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.700591421127319,
|
|
"epoch": 1.1111111111111112,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004884938843955999,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.1695659041404724,
|
|
"num_tokens": 25738352.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.512058401107788,
|
|
"epoch": 1.1116053776196124,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004884827410034515,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.191677463054657,
|
|
"num_tokens": 25749940.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.529638624191284,
|
|
"epoch": 1.112099644128114,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004884715923595945,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1750607892870903,
|
|
"num_tokens": 25761251.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.59853343963623,
|
|
"epoch": 1.1125939106366152,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004884604384643032,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.18082778453826903,
|
|
"num_tokens": 25772382.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.581767845153808,
|
|
"epoch": 1.1130881771451167,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000488449279317852,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.18425520062446593,
|
|
"num_tokens": 25784960.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.6023924350738525,
|
|
"epoch": 1.113582443653618,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004884381149205154,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.18083285987377168,
|
|
"num_tokens": 25796644.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.5761950492858885,
|
|
"epoch": 1.1140767101621194,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004884269452725681,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.17960323989391327,
|
|
"num_tokens": 25807712.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.589300584793091,
|
|
"epoch": 1.1145709766706209,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004884157703742848,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.18594112992286682,
|
|
"num_tokens": 25817944.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.502328252792358,
|
|
"epoch": 1.1150652431791221,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004884045902259405,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.18922640532255172,
|
|
"num_tokens": 25830801.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.591400241851806,
|
|
"epoch": 1.1155595096876236,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004883934048278102,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.17663922756910325,
|
|
"num_tokens": 25843877.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.588077974319458,
|
|
"epoch": 1.116053776196125,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004883822141801689,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.18364302366971968,
|
|
"num_tokens": 25853763.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.598387670516968,
|
|
"epoch": 1.1165480427046264,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004883710182832921,
|
|
"loss": 5.4101,
|
|
"mean_token_accuracy": 0.17585887163877487,
|
|
"num_tokens": 25864759.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.6940020561218265,
|
|
"epoch": 1.1170423092131276,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004883598171374552,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17336486279964447,
|
|
"num_tokens": 25877325.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.592209196090698,
|
|
"epoch": 1.1175365757216291,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004883486107429337,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.18362141251564026,
|
|
"num_tokens": 25889308.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.549356698989868,
|
|
"epoch": 1.1180308422301304,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004883373991000031,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.18378340005874633,
|
|
"num_tokens": 25901721.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.664417123794555,
|
|
"epoch": 1.1185251087386319,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004883261822089395,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.17992370426654816,
|
|
"num_tokens": 25912399.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.559819746017456,
|
|
"epoch": 1.1190193752471334,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004883149600700188,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.19028822630643843,
|
|
"num_tokens": 25923560.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.60528450012207,
|
|
"epoch": 1.1195136417556346,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004883037326835169,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.18540242612361907,
|
|
"num_tokens": 25933408.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.608488845825195,
|
|
"epoch": 1.120007908264136,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004882925000497101,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.18425261378288268,
|
|
"num_tokens": 25944492.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.583755588531494,
|
|
"epoch": 1.1205021747726374,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004882812621688747,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.18590230047702788,
|
|
"num_tokens": 25956439.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.551418304443359,
|
|
"epoch": 1.1209964412811388,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004882700190412873,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.1775671899318695,
|
|
"num_tokens": 25968765.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.572483968734741,
|
|
"epoch": 1.12149070778964,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004882587706672242,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.17714335322380065,
|
|
"num_tokens": 25981300.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.590623378753662,
|
|
"epoch": 1.1219849742981416,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004882475170469622,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.18233055919408797,
|
|
"num_tokens": 25991655.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.594483709335327,
|
|
"epoch": 1.1224792408066429,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004882362581807783,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.1869218185544014,
|
|
"num_tokens": 26002989.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.525834941864014,
|
|
"epoch": 1.1229735073151443,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004882249940689494,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.18634771704673767,
|
|
"num_tokens": 26013807.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.658357048034668,
|
|
"epoch": 1.1234677738236458,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048821372471175245,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.17596905380487443,
|
|
"num_tokens": 26027099.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.679106569290161,
|
|
"epoch": 1.123962040332147,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048820245010946486,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.1784599393606186,
|
|
"num_tokens": 26039046.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.511088466644287,
|
|
"epoch": 1.1244563068406486,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004881911702623639,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.19728656709194184,
|
|
"num_tokens": 26049763.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.504108047485351,
|
|
"epoch": 1.1249505733491498,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004881798851707271,
|
|
"loss": 5.3653,
|
|
"mean_token_accuracy": 0.18451719284057616,
|
|
"num_tokens": 26062227.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.502964973449707,
|
|
"epoch": 1.1254448398576513,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048816859483483214,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.187775819003582,
|
|
"num_tokens": 26074019.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.672538375854492,
|
|
"epoch": 1.1259391063661526,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048815729925495656,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.17615680545568466,
|
|
"num_tokens": 26086169.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.5804894924163815,
|
|
"epoch": 1.126433372874654,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048814599843137837,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17373420894145966,
|
|
"num_tokens": 26097677.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.461653232574463,
|
|
"epoch": 1.1269276393831553,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004881346923643755,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.19110326021909713,
|
|
"num_tokens": 26108825.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.621091556549072,
|
|
"epoch": 1.1274219058916568,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004881233810542263,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.17362256795167924,
|
|
"num_tokens": 26120274.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.592575740814209,
|
|
"epoch": 1.127916172400158,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048811206450120875,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.18361420780420304,
|
|
"num_tokens": 26131964.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.592219448089599,
|
|
"epoch": 1.1284104389086596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004881007427056013,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.18057605177164077,
|
|
"num_tokens": 26143308.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.6114349365234375,
|
|
"epoch": 1.128904705417161,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004880894156676826,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17315853089094163,
|
|
"num_tokens": 26153951.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.571921968460083,
|
|
"epoch": 1.1293989719256623,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004880780833877312,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.1840114712715149,
|
|
"num_tokens": 26165951.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.587030410766602,
|
|
"epoch": 1.1298932384341638,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004880667458660259,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.17156201601028442,
|
|
"num_tokens": 26176751.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.59674916267395,
|
|
"epoch": 1.130387504942665,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004880554031028456,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.1768489584326744,
|
|
"num_tokens": 26187682.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.678967761993408,
|
|
"epoch": 1.1308817714511665,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048804405509846933,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.178824020922184,
|
|
"num_tokens": 26198960.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.5725830078125,
|
|
"epoch": 1.1313760379596678,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004880327018531762,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.17992646098136902,
|
|
"num_tokens": 26210198.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.550407886505127,
|
|
"epoch": 1.1318703044681693,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048802134336724566,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.18730719834566117,
|
|
"num_tokens": 26220817.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.562501049041748,
|
|
"epoch": 1.1323645709766705,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048800997964095687,
|
|
"loss": 5.2875,
|
|
"mean_token_accuracy": 0.18908135145902633,
|
|
"num_tokens": 26233657.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.563575601577758,
|
|
"epoch": 1.132858837485172,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004879986106745897,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.18275452256202698,
|
|
"num_tokens": 26245566.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.562390089035034,
|
|
"epoch": 1.1333531039936733,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048798723646842357,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.18999174535274505,
|
|
"num_tokens": 26256717.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.577755546569824,
|
|
"epoch": 1.1338473705021748,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004879758570227384,
|
|
"loss": 5.3887,
|
|
"mean_token_accuracy": 0.17574160546064377,
|
|
"num_tokens": 26267926.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.558171653747559,
|
|
"epoch": 1.1343416370106763,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048796447233781406,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.17869359850883484,
|
|
"num_tokens": 26278666.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.583252716064453,
|
|
"epoch": 1.1348359035191775,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004879530824139308,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.18476705849170685,
|
|
"num_tokens": 26289961.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.556405448913575,
|
|
"epoch": 1.135330170027679,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048794168725136854,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18057540953159332,
|
|
"num_tokens": 26301245.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.589726400375366,
|
|
"epoch": 1.1358244365361803,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004879302868504078,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.18166249394416809,
|
|
"num_tokens": 26312598.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.686584234237671,
|
|
"epoch": 1.1363187030446817,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004879188812113289,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.18346481770277023,
|
|
"num_tokens": 26324300.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.495983600616455,
|
|
"epoch": 1.136812969553183,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004879074703344125,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.1783588260412216,
|
|
"num_tokens": 26335789.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.578703165054321,
|
|
"epoch": 1.1373072360616845,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004878960542199394,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18232424855232238,
|
|
"num_tokens": 26347336.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.6952431201934814,
|
|
"epoch": 1.1378015025701858,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048788463286819037,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.17989937514066695,
|
|
"num_tokens": 26358176.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.546046447753906,
|
|
"epoch": 1.1382957690786872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004878732062794462,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.1803993359208107,
|
|
"num_tokens": 26368915.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.567814922332763,
|
|
"epoch": 1.1387900355871885,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048786177445398816,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1777668997645378,
|
|
"num_tokens": 26381687.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.585135650634766,
|
|
"epoch": 1.13928430209569,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004878503373920975,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.17791412472724916,
|
|
"num_tokens": 26394289.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.568810892105103,
|
|
"epoch": 1.1397785686041915,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004878388950940555,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1938604012131691,
|
|
"num_tokens": 26405743.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.653090620040894,
|
|
"epoch": 1.1402728351126927,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048782744756014365,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.17193194180727006,
|
|
"num_tokens": 26417255.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.627829647064209,
|
|
"epoch": 1.1407671016211942,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004878159947906436,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.17640241086483002,
|
|
"num_tokens": 26428992.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.556961297988892,
|
|
"epoch": 1.1412613681296955,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000487804536785837,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.18648060411214828,
|
|
"num_tokens": 26440375.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.606527423858642,
|
|
"epoch": 1.141755634638197,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048779307354600586,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.1797148734331131,
|
|
"num_tokens": 26452253.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.657362842559815,
|
|
"epoch": 1.1422499011466982,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048778160507143204,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.17455005794763565,
|
|
"num_tokens": 26463766.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.625282669067383,
|
|
"epoch": 1.1427441676551997,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004877701313623978,
|
|
"loss": 5.3851,
|
|
"mean_token_accuracy": 0.17827094495296478,
|
|
"num_tokens": 26475869.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.63450345993042,
|
|
"epoch": 1.1432384341637012,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004877586524191852,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.18026377856731415,
|
|
"num_tokens": 26487142.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.5530589580535885,
|
|
"epoch": 1.1437327006722025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004877471682420768,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.18458405882120132,
|
|
"num_tokens": 26499019.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.522027587890625,
|
|
"epoch": 1.1442269671807037,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004877356788313551,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.18956939727067948,
|
|
"num_tokens": 26510060.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.537207365036011,
|
|
"epoch": 1.1447212336892052,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004877241841873027,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.18305868655443192,
|
|
"num_tokens": 26520723.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.540590381622314,
|
|
"epoch": 1.1452155001977067,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004877126843102023,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.18336523324251175,
|
|
"num_tokens": 26532545.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.587394523620605,
|
|
"epoch": 1.145709766706208,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048770117920033697,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18959822207689286,
|
|
"num_tokens": 26542993.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.58393087387085,
|
|
"epoch": 1.1462040332147094,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004876896688579895,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.18506054878234862,
|
|
"num_tokens": 26554658.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.58514633178711,
|
|
"epoch": 1.1466982997232107,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004876781532834433,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.18765341341495514,
|
|
"num_tokens": 26565925.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.533881664276123,
|
|
"epoch": 1.1471925662317122,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004876666324769815,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.18549070805311202,
|
|
"num_tokens": 26577045.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.6012187004089355,
|
|
"epoch": 1.1476868327402134,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004876551064388875,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.1737242341041565,
|
|
"num_tokens": 26587773.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.603348445892334,
|
|
"epoch": 1.148181099248715,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048764357516944485,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.18865224123001098,
|
|
"num_tokens": 26597861.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.6030073165893555,
|
|
"epoch": 1.1486753657572164,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048763203866893735,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.18135232627391815,
|
|
"num_tokens": 26607695.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.594368982315063,
|
|
"epoch": 1.1491696322657177,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048762049693764866,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1704888418316841,
|
|
"num_tokens": 26619845.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.680289316177368,
|
|
"epoch": 1.1496638987742192,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048760894997586284,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.18127831667661667,
|
|
"num_tokens": 26630279.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.484417295455932,
|
|
"epoch": 1.1501581652827204,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004875973977838639,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.18762538433074952,
|
|
"num_tokens": 26640996.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.458321857452392,
|
|
"epoch": 1.150652431791222,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048758584036193587,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.18733675181865692,
|
|
"num_tokens": 26652416.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.611387109756469,
|
|
"epoch": 1.1511466982997232,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004875742777103632,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.17985933274030685,
|
|
"num_tokens": 26663649.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.664259386062622,
|
|
"epoch": 1.1516409648082246,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048756270982943035,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.17566278278827668,
|
|
"num_tokens": 26676138.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.641987276077271,
|
|
"epoch": 1.152135231316726,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004875511367194219,
|
|
"loss": 5.4054,
|
|
"mean_token_accuracy": 0.1738479882478714,
|
|
"num_tokens": 26687364.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.619873857498169,
|
|
"epoch": 1.1526294978252274,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004875395583806225,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.18151208758354187,
|
|
"num_tokens": 26698135.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.563333797454834,
|
|
"epoch": 1.1531237643337287,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004875279748133169,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.19189535081386566,
|
|
"num_tokens": 26710495.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.639256858825684,
|
|
"epoch": 1.1536180308422301,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004875163860177902,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16882919520139694,
|
|
"num_tokens": 26722876.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.603716278076172,
|
|
"epoch": 1.1541122973507316,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048750479199432753,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.1823055014014244,
|
|
"num_tokens": 26733548.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.498085021972656,
|
|
"epoch": 1.1546065638592329,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004874931927432139,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.188260318338871,
|
|
"num_tokens": 26744754.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.563128852844239,
|
|
"epoch": 1.1551008303677344,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004874815882647348,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17965440601110458,
|
|
"num_tokens": 26757416.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.611495590209961,
|
|
"epoch": 1.1555950968762356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004874699785591756,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.18310626447200776,
|
|
"num_tokens": 26768572.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.52976622581482,
|
|
"epoch": 1.1560893633847371,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048745836362682203,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.18748028427362443,
|
|
"num_tokens": 26779309.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.639537334442139,
|
|
"epoch": 1.1565836298932384,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004874467434679598,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.18084171414375305,
|
|
"num_tokens": 26791107.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.5660899639129635,
|
|
"epoch": 1.1570778964017399,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004874351180828746,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18567055761814116,
|
|
"num_tokens": 26801334.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.5808515548706055,
|
|
"epoch": 1.1575721629102411,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004874234874718526,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.18173010349273683,
|
|
"num_tokens": 26812972.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.632566499710083,
|
|
"epoch": 1.1580664294187426,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048741185163517984,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17722982317209243,
|
|
"num_tokens": 26823683.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.584451675415039,
|
|
"epoch": 1.1585606959272439,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048740021057314267,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.1898304983973503,
|
|
"num_tokens": 26835898.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.558908748626709,
|
|
"epoch": 1.1590549624357454,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048738856428602736,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18448386043310167,
|
|
"num_tokens": 26847363.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.557189226150513,
|
|
"epoch": 1.1595492289442468,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004873769127741203,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18409740030765534,
|
|
"num_tokens": 26859081.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.563222599029541,
|
|
"epoch": 1.160043495452748,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004873652560377083,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.18631775081157684,
|
|
"num_tokens": 26869966.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.534902715682984,
|
|
"epoch": 1.1605377619612496,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000487353594077078,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18627515733242034,
|
|
"num_tokens": 26880673.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.581589937210083,
|
|
"epoch": 1.1610320284697508,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048734192689251643,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.1827446848154068,
|
|
"num_tokens": 26892306.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.696859693527221,
|
|
"epoch": 1.1615262949782523,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004873302544843104,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.1765613377094269,
|
|
"num_tokens": 26904655.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.574914407730103,
|
|
"epoch": 1.1620205614867536,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004873185768527473,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.18094775974750518,
|
|
"num_tokens": 26916580.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.575309801101684,
|
|
"epoch": 1.162514827995255,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048730689399811427,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.18189455568790436,
|
|
"num_tokens": 26927033.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.6183654308319095,
|
|
"epoch": 1.1630090945037563,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004872952059206986,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1783847063779831,
|
|
"num_tokens": 26938594.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.5629730224609375,
|
|
"epoch": 1.1635033610122578,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004872835126207881,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.1881747916340828,
|
|
"num_tokens": 26949595.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.658031177520752,
|
|
"epoch": 1.163997627520759,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004872718140986701,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.17578874081373214,
|
|
"num_tokens": 26961692.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.577623414993286,
|
|
"epoch": 1.1644918940292606,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048726011035463265,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.18392960876226425,
|
|
"num_tokens": 26972062.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.596024656295777,
|
|
"epoch": 1.164986160537762,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004872484013889635,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.18435379713773728,
|
|
"num_tokens": 26983353.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.650908708572388,
|
|
"epoch": 1.1654804270462633,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048723668720195067,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.17794129848480225,
|
|
"num_tokens": 26994828.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.540834236145019,
|
|
"epoch": 1.1659746935547648,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004872249677938825,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.18295509070158006,
|
|
"num_tokens": 27008311.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.519434070587158,
|
|
"epoch": 1.166468960063266,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004872132431650472,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.18507014214992523,
|
|
"num_tokens": 27018984.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.648067665100098,
|
|
"epoch": 1.1669632265717675,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048720151331573317,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.17217807322740555,
|
|
"num_tokens": 27029183.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.541958475112915,
|
|
"epoch": 1.1674574930802688,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000487189778246229,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.18852966725826265,
|
|
"num_tokens": 27039661.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.610924911499024,
|
|
"epoch": 1.1679517595887703,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048717803795682334,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1745486557483673,
|
|
"num_tokens": 27051685.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.656801223754883,
|
|
"epoch": 1.1684460260972718,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004871662924478051,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.18566256910562515,
|
|
"num_tokens": 27062096.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.58103609085083,
|
|
"epoch": 1.168940292605773,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004871545417194631,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.18435896039009095,
|
|
"num_tokens": 27073059.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.660785055160522,
|
|
"epoch": 1.1694345591142743,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048714278577208643,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.1801055535674095,
|
|
"num_tokens": 27085272.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.618304777145386,
|
|
"epoch": 1.1699288256227758,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004871310246059644,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.17959039360284806,
|
|
"num_tokens": 27096651.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.581056880950928,
|
|
"epoch": 1.1704230921312773,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048711925822138627,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.18388130217790605,
|
|
"num_tokens": 27108180.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.688440752029419,
|
|
"epoch": 1.1709173586397785,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048710748661864135,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.18205199092626573,
|
|
"num_tokens": 27118902.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.628070878982544,
|
|
"epoch": 1.17141162514828,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048709570979801946,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.18548022508621215,
|
|
"num_tokens": 27131279.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.537890911102295,
|
|
"epoch": 1.1719058916567813,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048708392775981014,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.18598783910274505,
|
|
"num_tokens": 27142983.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.588888263702392,
|
|
"epoch": 1.1724001581652828,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004870721405043033,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.18390939235687256,
|
|
"num_tokens": 27154516.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.6401184558868405,
|
|
"epoch": 1.172894424673784,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004870603480317889,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18291078358888627,
|
|
"num_tokens": 27164717.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.609223127365112,
|
|
"epoch": 1.1733886911822855,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048704855034255713,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.18257137835025788,
|
|
"num_tokens": 27174830.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.5595231533050535,
|
|
"epoch": 1.173882957690787,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048703674743689806,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.18172823190689086,
|
|
"num_tokens": 27186724.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.471775102615356,
|
|
"epoch": 1.1743772241992882,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004870249393151021,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.1854598268866539,
|
|
"num_tokens": 27198416.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.555958318710327,
|
|
"epoch": 1.1748714907077897,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048701312597745986,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18433498442173005,
|
|
"num_tokens": 27209347.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.632469606399536,
|
|
"epoch": 1.175365757216291,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048700130742426165,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.1784347340464592,
|
|
"num_tokens": 27221061.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.507503366470337,
|
|
"epoch": 1.1758600237247925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004869894836557985,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.19138661921024322,
|
|
"num_tokens": 27233436.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.55709319114685,
|
|
"epoch": 1.1763542902332937,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048697765467236117,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.19233071953058242,
|
|
"num_tokens": 27246308.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.5899444103240965,
|
|
"epoch": 1.1768485567417952,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048696582047424053,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.17691414654254914,
|
|
"num_tokens": 27258187.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.56017804145813,
|
|
"epoch": 1.1773428232502965,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048695398106172793,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.18764493614435196,
|
|
"num_tokens": 27269411.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.538213396072388,
|
|
"epoch": 1.177837089758798,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004869421364351145,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.1841817870736122,
|
|
"num_tokens": 27280592.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.685888719558716,
|
|
"epoch": 1.1783313562672992,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048693028659469156,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.17028467804193498,
|
|
"num_tokens": 27292151.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.626926469802856,
|
|
"epoch": 1.1788256227758007,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048691843154075075,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.1844504401087761,
|
|
"num_tokens": 27305371.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.582646322250366,
|
|
"epoch": 1.1793198892843022,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048690657127358367,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1738284170627594,
|
|
"num_tokens": 27316810.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.565650415420532,
|
|
"epoch": 1.1798141557928035,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048689470579348207,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.1779235154390335,
|
|
"num_tokens": 27328412.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.634607648849487,
|
|
"epoch": 1.180308422301305,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048688283510073775,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.1787986785173416,
|
|
"num_tokens": 27340216.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.564865255355835,
|
|
"epoch": 1.1808026888098062,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004868709591956429,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.1859789565205574,
|
|
"num_tokens": 27350290.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.568687772750854,
|
|
"epoch": 1.1812969553183077,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048685907807848955,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.17881934046745301,
|
|
"num_tokens": 27360639.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.569512748718262,
|
|
"epoch": 1.181791221826809,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048684719174957005,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.18802181631326675,
|
|
"num_tokens": 27372059.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.621206521987915,
|
|
"epoch": 1.1822854883353104,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004868353002091767,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.1699448123574257,
|
|
"num_tokens": 27384308.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.510255527496338,
|
|
"epoch": 1.1827797548438117,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004868234034576021,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.2061369985342026,
|
|
"num_tokens": 27395510.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.536326837539673,
|
|
"epoch": 1.1832740213523132,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000486811501495139,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.1765746384859085,
|
|
"num_tokens": 27406697.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.540236520767212,
|
|
"epoch": 1.1837682878608144,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004867995943220801,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.18787411004304885,
|
|
"num_tokens": 27418047.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.666848087310791,
|
|
"epoch": 1.184262554369316,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048678768193871825,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.1761319875717163,
|
|
"num_tokens": 27430044.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.609213590621948,
|
|
"epoch": 1.1847568208778174,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004867757643453466,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.17706237733364105,
|
|
"num_tokens": 27441392.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.6267026424407955,
|
|
"epoch": 1.1852510873863187,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048676384154225827,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.17451757043600083,
|
|
"num_tokens": 27451356.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.569549894332885,
|
|
"epoch": 1.1857453538948202,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004867519135297466,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.1884775012731552,
|
|
"num_tokens": 27462358.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.509878253936767,
|
|
"epoch": 1.1862396204033214,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048673998030810507,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.18457881808280946,
|
|
"num_tokens": 27474144.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.1862396204033214,
|
|
"eval_entropy": 5.408019847212976,
|
|
"eval_loss": 5.44186544418335,
|
|
"eval_mean_token_accuracy": 0.18564739158379343,
|
|
"eval_num_tokens": 27474144.0,
|
|
"eval_runtime": 26.682,
|
|
"eval_samples_per_second": 1218.537,
|
|
"eval_steps_per_second": 152.35,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.6408296585083,
|
|
"epoch": 1.186733886911823,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048672804187762704,
|
|
"loss": 5.444,
|
|
"mean_token_accuracy": 0.170842444896698,
|
|
"num_tokens": 27486337.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.614845943450928,
|
|
"epoch": 1.1872281534203242,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004867160982386065,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18840381503105164,
|
|
"num_tokens": 27498686.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.616654634475708,
|
|
"epoch": 1.1877224199288257,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048670414939133694,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18076305985450744,
|
|
"num_tokens": 27509850.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.71806378364563,
|
|
"epoch": 1.188216686437327,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004866921953361125,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.17184257060289382,
|
|
"num_tokens": 27521994.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.600837278366089,
|
|
"epoch": 1.1887109529458284,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004866802360732273,
|
|
"loss": 5.4028,
|
|
"mean_token_accuracy": 0.1818103313446045,
|
|
"num_tokens": 27534980.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.566476345062256,
|
|
"epoch": 1.1892052194543297,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004866682716029754,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.1825313612818718,
|
|
"num_tokens": 27546461.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.570589017868042,
|
|
"epoch": 1.1896994859628311,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048665630192565117,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.18850645273923874,
|
|
"num_tokens": 27557076.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.53256459236145,
|
|
"epoch": 1.1901937524713326,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004866443270415491,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.18890914022922517,
|
|
"num_tokens": 27569807.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.570080327987671,
|
|
"epoch": 1.190688018979834,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004866323469509637,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.18604394793510437,
|
|
"num_tokens": 27579858.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.596007394790649,
|
|
"epoch": 1.1911822854883354,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004866203616541898,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.17857668846845626,
|
|
"num_tokens": 27590192.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.550975370407104,
|
|
"epoch": 1.1916765519968366,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048660837115152214,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.18500436693429947,
|
|
"num_tokens": 27601756.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.533020782470703,
|
|
"epoch": 1.1921708185053381,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004865963754432557,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1884780451655388,
|
|
"num_tokens": 27614019.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.545301055908203,
|
|
"epoch": 1.1926650850138394,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004865843745296856,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.18816456347703933,
|
|
"num_tokens": 27626900.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.530590486526489,
|
|
"epoch": 1.1931593515223409,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048657236841110707,
|
|
"loss": 5.2689,
|
|
"mean_token_accuracy": 0.18813544511795044,
|
|
"num_tokens": 27637897.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.587797832489014,
|
|
"epoch": 1.1936536180308421,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004865603570878155,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.18048583269119262,
|
|
"num_tokens": 27649523.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.646619081497192,
|
|
"epoch": 1.1941478845393436,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004865483405601063,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.1775821790099144,
|
|
"num_tokens": 27659406.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.56503324508667,
|
|
"epoch": 1.1946421510478449,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004865363188282751,
|
|
"loss": 5.2804,
|
|
"mean_token_accuracy": 0.18576981127262115,
|
|
"num_tokens": 27670912.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.547097635269165,
|
|
"epoch": 1.1951364175563464,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048652429189261767,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.1867876723408699,
|
|
"num_tokens": 27681667.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.586563158035278,
|
|
"epoch": 1.1956306840648478,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004865122597534298,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1881226643919945,
|
|
"num_tokens": 27692170.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.498534679412842,
|
|
"epoch": 1.196124950573349,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004865002224110075,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.19350004941225052,
|
|
"num_tokens": 27702533.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.5307989597320555,
|
|
"epoch": 1.1966192170818506,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000486488179865647,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.192794768512249,
|
|
"num_tokens": 27713795.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.636001348495483,
|
|
"epoch": 1.1971134835903519,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004864761321176444,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.1841748461127281,
|
|
"num_tokens": 27725404.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.509871149063111,
|
|
"epoch": 1.1976077500988533,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004864640791672962,
|
|
"loss": 5.2606,
|
|
"mean_token_accuracy": 0.18193129897117616,
|
|
"num_tokens": 27737537.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.554890060424805,
|
|
"epoch": 1.1981020166073546,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004864520210148988,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.1895693689584732,
|
|
"num_tokens": 27749841.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.63652925491333,
|
|
"epoch": 1.198596283115856,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004864399576607489,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.18433279693126678,
|
|
"num_tokens": 27760302.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.5462809085845945,
|
|
"epoch": 1.1990905496243576,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.00048642788910514324,
|
|
"loss": 5.3791,
|
|
"mean_token_accuracy": 0.18089869767427444,
|
|
"num_tokens": 27770989.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.601260614395142,
|
|
"epoch": 1.1995848161328588,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048641581534837863,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18624016344547273,
|
|
"num_tokens": 27785196.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.582710933685303,
|
|
"epoch": 1.2000790826413603,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048640373639075225,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.1873287409543991,
|
|
"num_tokens": 27795588.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.499791049957276,
|
|
"epoch": 1.2005733491498616,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048639165223256117,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18426734060049058,
|
|
"num_tokens": 27807204.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.559156227111816,
|
|
"epoch": 1.201067615658363,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048637956287410263,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.19315142333507537,
|
|
"num_tokens": 27817959.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.6193492889404295,
|
|
"epoch": 1.2015618821668643,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048636746831567403,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.17938842475414277,
|
|
"num_tokens": 27830736.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.597246932983398,
|
|
"epoch": 1.2020561486753658,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004863553685575729,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.17698883414268493,
|
|
"num_tokens": 27840992.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.625234746932984,
|
|
"epoch": 1.202550415183867,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004863432636000969,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.18445145785808564,
|
|
"num_tokens": 27852747.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.5693542003631595,
|
|
"epoch": 1.2030446816923686,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004863311534435439,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.17719276249408722,
|
|
"num_tokens": 27865136.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.651133632659912,
|
|
"epoch": 1.2035389482008698,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048631903808821176,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.18870144933462143,
|
|
"num_tokens": 27876489.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.518201780319214,
|
|
"epoch": 1.2040332147093713,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048630691753439844,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.18893287181854249,
|
|
"num_tokens": 27886478.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.488151216506958,
|
|
"epoch": 1.2045274812178728,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004862947917824022,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.18935781568288804,
|
|
"num_tokens": 27897473.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.568810319900512,
|
|
"epoch": 1.205021747726374,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048628266083252124,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.18282202929258345,
|
|
"num_tokens": 27908390.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.650491714477539,
|
|
"epoch": 1.2055160142348755,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004862705246850541,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.18094149082899094,
|
|
"num_tokens": 27919372.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.550237560272217,
|
|
"epoch": 1.2060102807433768,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004862583833402993,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.18235913217067717,
|
|
"num_tokens": 27931294.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.570109605789185,
|
|
"epoch": 1.2065045472518783,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004862462367985554,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.18267378509044646,
|
|
"num_tokens": 27941782.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.557882165908813,
|
|
"epoch": 1.2069988137603795,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004862340850601214,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19842779785394668,
|
|
"num_tokens": 27951703.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.6137120723724365,
|
|
"epoch": 1.207493080268881,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004862219281252961,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.18706037551164628,
|
|
"num_tokens": 27962049.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.5929406642913815,
|
|
"epoch": 1.2079873467773823,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004862097659943786,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.18474950939416884,
|
|
"num_tokens": 27973502.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.482417726516724,
|
|
"epoch": 1.2084816132858838,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048619759866766807,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.1910111591219902,
|
|
"num_tokens": 27984653.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.579201602935791,
|
|
"epoch": 1.208975879794385,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048618542614546384,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.1744750112295151,
|
|
"num_tokens": 27995152.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.688761568069458,
|
|
"epoch": 1.2094701463028865,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048617324842806545,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17789370566606522,
|
|
"num_tokens": 28006928.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.615796661376953,
|
|
"epoch": 1.209964412811388,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048616106551577226,
|
|
"loss": 5.3101,
|
|
"mean_token_accuracy": 0.17652284502983093,
|
|
"num_tokens": 28018004.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.623444700241089,
|
|
"epoch": 1.2104586793198893,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048614887740888426,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.17015210390090943,
|
|
"num_tokens": 28030645.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.595191717147827,
|
|
"epoch": 1.2109529458283907,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000486136684107701,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.18091525733470917,
|
|
"num_tokens": 28042591.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.574539375305176,
|
|
"epoch": 1.211447212336892,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004861244856125226,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.19049396812915803,
|
|
"num_tokens": 28053285.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.469430017471313,
|
|
"epoch": 1.2119414788453935,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004861122819236491,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.19045482128858565,
|
|
"num_tokens": 28065747.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.549232816696167,
|
|
"epoch": 1.2124357453538948,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048610007304138067,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.18723124861717225,
|
|
"num_tokens": 28077112.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.534961795806884,
|
|
"epoch": 1.2129300118623962,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004860878589660177,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.1907817766070366,
|
|
"num_tokens": 28088835.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.654833364486694,
|
|
"epoch": 1.2134242783708975,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004860756396978607,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.17498757392168046,
|
|
"num_tokens": 28100921.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.586423873901367,
|
|
"epoch": 1.213918544879399,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004860634152372102,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18445428609848022,
|
|
"num_tokens": 28112531.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.6383744239807125,
|
|
"epoch": 1.2144128113879002,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004860511855843669,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.17983583807945253,
|
|
"num_tokens": 28123821.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.556241607666015,
|
|
"epoch": 1.2149070778964017,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048603895073963177,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18249187916517257,
|
|
"num_tokens": 28135046.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.5406852722167965,
|
|
"epoch": 1.2154013444049032,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048602671070330564,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.18329827338457108,
|
|
"num_tokens": 28145870.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.622204971313477,
|
|
"epoch": 1.2158956109134045,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048601446547568973,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.18197769224643706,
|
|
"num_tokens": 28156078.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.5825948238372805,
|
|
"epoch": 1.216389877421906,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004860022150570852,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.18159942030906678,
|
|
"num_tokens": 28166658.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.557736587524414,
|
|
"epoch": 1.2168841439304072,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048598995944779344,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.18206374049186708,
|
|
"num_tokens": 28178890.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.574904918670654,
|
|
"epoch": 1.2173784104389087,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048597769864811604,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.19261688143014907,
|
|
"num_tokens": 28191101.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.569365692138672,
|
|
"epoch": 1.21787267694741,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004859654326583544,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.1832367643713951,
|
|
"num_tokens": 28202877.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.641600036621094,
|
|
"epoch": 1.2183669434559115,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004859531614788105,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.17897997200489044,
|
|
"num_tokens": 28214762.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.5829322814941404,
|
|
"epoch": 1.2188612099644127,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000485940885109786,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.1810897782444954,
|
|
"num_tokens": 28225830.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.492567777633667,
|
|
"epoch": 1.2193554764729142,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048592860355158306,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.1886066675186157,
|
|
"num_tokens": 28237302.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.611252784729004,
|
|
"epoch": 1.2198497429814155,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004859163168045038,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.187969172000885,
|
|
"num_tokens": 28247658.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.573402023315429,
|
|
"epoch": 1.220344009489917,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004859040248688503,
|
|
"loss": 5.3641,
|
|
"mean_token_accuracy": 0.1861501857638359,
|
|
"num_tokens": 28258473.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.659816884994507,
|
|
"epoch": 1.2208382759984184,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048589172774492515,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.17479440569877625,
|
|
"num_tokens": 28270167.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.552976131439209,
|
|
"epoch": 1.2213325425069197,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048587942543303075,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18498091846704484,
|
|
"num_tokens": 28282047.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.5951131820678714,
|
|
"epoch": 1.2218268090154212,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004858671179334698,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.19039668440818786,
|
|
"num_tokens": 28292868.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.6432984352111815,
|
|
"epoch": 1.2223210755239224,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048585480524654504,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.17257506549358367,
|
|
"num_tokens": 28303816.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.666061592102051,
|
|
"epoch": 1.222815342032424,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004858424873725593,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.1762702062726021,
|
|
"num_tokens": 28315191.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.578766584396362,
|
|
"epoch": 1.2233096085409252,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004858301643118157,
|
|
"loss": 5.2942,
|
|
"mean_token_accuracy": 0.18394652307033538,
|
|
"num_tokens": 28325312.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.630446052551269,
|
|
"epoch": 1.2238038750494267,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004858178360646174,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.1781016245484352,
|
|
"num_tokens": 28336171.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.590862655639649,
|
|
"epoch": 1.2242981415579282,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048580550263126757,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.17877858579158784,
|
|
"num_tokens": 28347488.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.565862560272217,
|
|
"epoch": 1.2247924080664294,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004857931640120697,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1897214472293854,
|
|
"num_tokens": 28358653.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.556038427352905,
|
|
"epoch": 1.2252866745749307,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048578082020732724,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.1980975016951561,
|
|
"num_tokens": 28369588.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.551000547409058,
|
|
"epoch": 1.2257809410834322,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000485768471217344,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18792791813611984,
|
|
"num_tokens": 28382009.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.620642042160034,
|
|
"epoch": 1.2262752075919336,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004857561170424235,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.1767384812235832,
|
|
"num_tokens": 28394376.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.612491035461426,
|
|
"epoch": 1.226769474100435,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048574375768286996,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.17645420283079147,
|
|
"num_tokens": 28406453.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.578579616546631,
|
|
"epoch": 1.2272637406089364,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048573139313898723,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.1853025287389755,
|
|
"num_tokens": 28417178.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.608728456497192,
|
|
"epoch": 1.2277580071174377,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004857190234110795,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.18441293090581895,
|
|
"num_tokens": 28428396.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.50726351737976,
|
|
"epoch": 1.2282522736259391,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004857066484994512,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.18663573563098906,
|
|
"num_tokens": 28441239.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.62546215057373,
|
|
"epoch": 1.2287465401344404,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004856942684044067,
|
|
"loss": 5.4717,
|
|
"mean_token_accuracy": 0.1820055589079857,
|
|
"num_tokens": 28453671.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.592067050933838,
|
|
"epoch": 1.2292408066429419,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048568188312625037,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.18714504987001418,
|
|
"num_tokens": 28465922.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.5871364116668705,
|
|
"epoch": 1.2297350731514434,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004856694926652871,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.1866641640663147,
|
|
"num_tokens": 28477559.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.548101091384888,
|
|
"epoch": 1.2302293396599446,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048565709702182164,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.17915310859680175,
|
|
"num_tokens": 28489276.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.613680267333985,
|
|
"epoch": 1.2307236061684461,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004856446961961589,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.17933043390512465,
|
|
"num_tokens": 28500821.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.628465557098389,
|
|
"epoch": 1.2312178726769474,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048563229018860394,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.18521609157323837,
|
|
"num_tokens": 28513646.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.608298349380493,
|
|
"epoch": 1.2317121391854489,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048561987899946204,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18143515139818192,
|
|
"num_tokens": 28525508.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.676467657089233,
|
|
"epoch": 1.2322064056939501,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00048560746262903836,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.18189581334590912,
|
|
"num_tokens": 28537863.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.604188108444214,
|
|
"epoch": 1.2327006722024516,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004855950410776385,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.18361279666423796,
|
|
"num_tokens": 28550163.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.536881017684936,
|
|
"epoch": 1.2331949387109529,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004855826143455678,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.18760112673044205,
|
|
"num_tokens": 28560501.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.637031936645508,
|
|
"epoch": 1.2336892052194544,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004855701824331323,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.17387507110834122,
|
|
"num_tokens": 28573057.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.633245658874512,
|
|
"epoch": 1.2341834717279556,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048555774534063753,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.17813500314950942,
|
|
"num_tokens": 28585147.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.526788997650146,
|
|
"epoch": 1.234677738236457,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004855453030683896,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17654805183410643,
|
|
"num_tokens": 28597774.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.628738498687744,
|
|
"epoch": 1.2351720047449586,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004855328556166945,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.18712398707866668,
|
|
"num_tokens": 28610031.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.646877193450928,
|
|
"epoch": 1.2356662712534598,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004855204029858586,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18192318975925445,
|
|
"num_tokens": 28621485.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.499594879150391,
|
|
"epoch": 1.2361605377619613,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004855079451761881,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.18737354278564453,
|
|
"num_tokens": 28632213.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.611305522918701,
|
|
"epoch": 1.2366548042704626,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004854954821879894,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.1784612536430359,
|
|
"num_tokens": 28643994.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.701003360748291,
|
|
"epoch": 1.237149070778964,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048548301402156927,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18292042911052703,
|
|
"num_tokens": 28656556.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.593617343902588,
|
|
"epoch": 1.2376433372874653,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004854705406772343,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.19130636900663375,
|
|
"num_tokens": 28668022.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.573183965682984,
|
|
"epoch": 1.2381376037959668,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048545806215529136,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.17529191970825195,
|
|
"num_tokens": 28679074.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.569527959823608,
|
|
"epoch": 1.238631870304468,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048544557845604753,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.18430576771497725,
|
|
"num_tokens": 28691872.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.647966480255127,
|
|
"epoch": 1.2391261368129696,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048543308957980973,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18368193209171296,
|
|
"num_tokens": 28703367.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.5452429294586185,
|
|
"epoch": 1.2396204033214708,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004854205955268853,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.19505686610937117,
|
|
"num_tokens": 28713841.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.59499454498291,
|
|
"epoch": 1.2401146698299723,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048540809629758167,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17560525238513947,
|
|
"num_tokens": 28724924.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.5898213386535645,
|
|
"epoch": 1.2406089363384738,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004853955918922061,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.1808501124382019,
|
|
"num_tokens": 28736236.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.647509527206421,
|
|
"epoch": 1.241103202846975,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004853830823110663,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.18240760117769242,
|
|
"num_tokens": 28748841.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.589984512329101,
|
|
"epoch": 1.2415974693554765,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004853705675544702,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.18851782977581025,
|
|
"num_tokens": 28759491.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.480178308486939,
|
|
"epoch": 1.2420917358639778,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004853580476227254,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.18840326368808746,
|
|
"num_tokens": 28771668.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.573764181137085,
|
|
"epoch": 1.2425860023724793,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048534552251614,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1838576078414917,
|
|
"num_tokens": 28783102.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.615123558044433,
|
|
"epoch": 1.2430802688809806,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048533299223502217,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.18511160910129548,
|
|
"num_tokens": 28794643.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.604236745834351,
|
|
"epoch": 1.243574535389482,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004853204567796801,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18012989014387132,
|
|
"num_tokens": 28806597.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.6076452255249025,
|
|
"epoch": 1.2440688018979833,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000485307916150422,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.18460925817489623,
|
|
"num_tokens": 28817379.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.565638303756714,
|
|
"epoch": 1.2445630684064848,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004852953703475567,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.1769740328192711,
|
|
"num_tokens": 28828412.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.523271799087524,
|
|
"epoch": 1.245057334914986,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048528281937139264,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.1885426312685013,
|
|
"num_tokens": 28839888.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.660965538024902,
|
|
"epoch": 1.2455516014234875,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048527026322223854,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.17436221837997437,
|
|
"num_tokens": 28852113.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.638073587417603,
|
|
"epoch": 1.246045867931989,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004852577019004035,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.17834651321172715,
|
|
"num_tokens": 28864715.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.551070928573608,
|
|
"epoch": 1.2465401344404903,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004852451354061962,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1897892564535141,
|
|
"num_tokens": 28875166.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.540621042251587,
|
|
"epoch": 1.2470344009489918,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048523256373992604,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.1864522248506546,
|
|
"num_tokens": 28885946.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.573683261871338,
|
|
"epoch": 1.247528667457493,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004852199869019021,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18768272548913956,
|
|
"num_tokens": 28896654.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.616667604446411,
|
|
"epoch": 1.2480229339659945,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048520740489243396,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.18361743092536925,
|
|
"num_tokens": 28908306.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.627946901321411,
|
|
"epoch": 1.2485172004744958,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048519481771183107,
|
|
"loss": 5.3634,
|
|
"mean_token_accuracy": 0.17520041912794113,
|
|
"num_tokens": 28921044.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.552964115142823,
|
|
"epoch": 1.2490114669829973,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000485182225360403,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.19077340811491011,
|
|
"num_tokens": 28932290.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.6018634796142575,
|
|
"epoch": 1.2495057334914987,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004851696278384596,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.1880711629986763,
|
|
"num_tokens": 28943482.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.558258056640625,
|
|
"epoch": 1.25,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004851570251463107,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.18833411186933519,
|
|
"num_tokens": 28954749.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.633076763153076,
|
|
"epoch": 1.2504942665085013,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048514441728426646,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.16969874799251555,
|
|
"num_tokens": 28965304.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.573804569244385,
|
|
"epoch": 1.2509885330170027,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004851318042526369,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.1868330121040344,
|
|
"num_tokens": 28976267.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.6532751560211185,
|
|
"epoch": 1.2514827995255042,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004851191860517324,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.17951694279909133,
|
|
"num_tokens": 28986492.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.564417695999145,
|
|
"epoch": 1.2519770660340055,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048510656268186325,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.18639400750398635,
|
|
"num_tokens": 28996693.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.584259366989135,
|
|
"epoch": 1.252471332542507,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004850939341433401,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.188372340798378,
|
|
"num_tokens": 29008498.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.653533840179444,
|
|
"epoch": 1.2529655990510082,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048508130043647366,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.1794237956404686,
|
|
"num_tokens": 29018563.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.5723248481750485,
|
|
"epoch": 1.2534598655595097,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004850686615615745,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18849997222423553,
|
|
"num_tokens": 29029204.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.576719284057617,
|
|
"epoch": 1.253954132068011,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048505601751895383,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.17809175401926042,
|
|
"num_tokens": 29041112.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.685457849502564,
|
|
"epoch": 1.2544483985765125,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004850433683089224,
|
|
"loss": 5.3399,
|
|
"mean_token_accuracy": 0.1817344069480896,
|
|
"num_tokens": 29052791.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.594283485412598,
|
|
"epoch": 1.254942665085014,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004850307139317916,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.17893716990947722,
|
|
"num_tokens": 29064525.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.487346029281616,
|
|
"epoch": 1.2554369315935152,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004850180543878726,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19257403612136842,
|
|
"num_tokens": 29077265.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.56507363319397,
|
|
"epoch": 1.2559311981020165,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004850053896774769,
|
|
"loss": 5.2739,
|
|
"mean_token_accuracy": 0.18577852696180344,
|
|
"num_tokens": 29088022.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.597731065750122,
|
|
"epoch": 1.256425464610518,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004849927198009161,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.1830385610461235,
|
|
"num_tokens": 29099901.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.604904460906982,
|
|
"epoch": 1.2569197311190194,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048498004475850174,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.18693469017744063,
|
|
"num_tokens": 29111249.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.526698923110962,
|
|
"epoch": 1.2574139976275207,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048496736455054567,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.18535425364971161,
|
|
"num_tokens": 29121261.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.644039106369019,
|
|
"epoch": 1.2579082641360222,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048495467917736003,
|
|
"loss": 5.4768,
|
|
"mean_token_accuracy": 0.1790138453245163,
|
|
"num_tokens": 29133987.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.669992399215698,
|
|
"epoch": 1.2584025306445235,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004849419886392565,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.18415045291185378,
|
|
"num_tokens": 29146499.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.549259328842163,
|
|
"epoch": 1.258896797153025,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004849292929365476,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.18913623094558715,
|
|
"num_tokens": 29157892.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.581544351577759,
|
|
"epoch": 1.2593910636615262,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004849165920695455,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.18168802410364152,
|
|
"num_tokens": 29169823.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.698968362808228,
|
|
"epoch": 1.2598853301700277,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004849038860385627,
|
|
"loss": 5.4011,
|
|
"mean_token_accuracy": 0.17849196195602418,
|
|
"num_tokens": 29181065.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.545875597000122,
|
|
"epoch": 1.2603795966785292,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004848911748439117,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.18356641680002211,
|
|
"num_tokens": 29192711.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.503417205810547,
|
|
"epoch": 1.2608738631870304,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004848784584859052,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.18506819754838943,
|
|
"num_tokens": 29204688.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.535116243362427,
|
|
"epoch": 1.2613681296955317,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004848657369648561,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.1867343306541443,
|
|
"num_tokens": 29216326.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.548879194259643,
|
|
"epoch": 1.2618623962040332,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048485301028107736,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.19101449400186538,
|
|
"num_tokens": 29226805.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.469796943664551,
|
|
"epoch": 1.2623566627125347,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000484840278434882,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.18365480601787568,
|
|
"num_tokens": 29239334.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.618602848052978,
|
|
"epoch": 1.262850929221036,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004848275414265832,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.18460337668657303,
|
|
"num_tokens": 29250443.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.548525714874268,
|
|
"epoch": 1.2633451957295374,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048481479925649435,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.1845996007323265,
|
|
"num_tokens": 29261209.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.601257467269898,
|
|
"epoch": 1.2638394622380387,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048480205192492887,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.17617404460906982,
|
|
"num_tokens": 29273761.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.649270296096802,
|
|
"epoch": 1.2643337287465402,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004847892994322004,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.1779158040881157,
|
|
"num_tokens": 29285157.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.5683245182037355,
|
|
"epoch": 1.2648279952550414,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004847765417786226,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.1826732188463211,
|
|
"num_tokens": 29295903.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.658011245727539,
|
|
"epoch": 1.265322261763543,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004847637789645093,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17874892801046371,
|
|
"num_tokens": 29307865.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.732969808578491,
|
|
"epoch": 1.2658165282720444,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004847510109901745,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.17270038425922393,
|
|
"num_tokens": 29319614.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.585379219055175,
|
|
"epoch": 1.2663107947805456,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004847382378559323,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.18013598173856735,
|
|
"num_tokens": 29330306.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.565851926803589,
|
|
"epoch": 1.2668050612890471,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048472545956209696,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.183504718542099,
|
|
"num_tokens": 29341611.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.499501371383667,
|
|
"epoch": 1.2672993277975484,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004847126761089827,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.1935607075691223,
|
|
"num_tokens": 29353481.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.554169464111328,
|
|
"epoch": 1.2677935943060499,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004846998874969041,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19204880446195602,
|
|
"num_tokens": 29365388.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.606723690032959,
|
|
"epoch": 1.2682878608145511,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004846870937261758,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.17250200361013412,
|
|
"num_tokens": 29377805.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.544978237152099,
|
|
"epoch": 1.2687821273230526,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048467429479711233,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.19001945704221726,
|
|
"num_tokens": 29389736.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.566472578048706,
|
|
"epoch": 1.269276393831554,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048466149071002876,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.19445980489253997,
|
|
"num_tokens": 29401256.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.587284708023072,
|
|
"epoch": 1.2697706603400554,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048464868146524,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18817368298768997,
|
|
"num_tokens": 29413287.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.554240703582764,
|
|
"epoch": 1.2702649268485566,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048463586706306113,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.18643374592065812,
|
|
"num_tokens": 29424151.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.614323377609253,
|
|
"epoch": 1.2707591933570581,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004846230475038074,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.18442035764455794,
|
|
"num_tokens": 29435006.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.523758172988892,
|
|
"epoch": 1.2712534598655596,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004846102227877942,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.18923098146915435,
|
|
"num_tokens": 29446453.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.613656234741211,
|
|
"epoch": 1.2717477263740609,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048459739291533706,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.17651629596948623,
|
|
"num_tokens": 29458468.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.667193269729614,
|
|
"epoch": 1.2722419928825623,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004845845578867514,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.1745690181851387,
|
|
"num_tokens": 29471167.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.600724172592163,
|
|
"epoch": 1.2727362593910636,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048457171770235327,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.18976950645446777,
|
|
"num_tokens": 29482668.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.639466571807861,
|
|
"epoch": 1.273230525899565,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004845588723624582,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.18047666549682617,
|
|
"num_tokens": 29495424.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.609357595443726,
|
|
"epoch": 1.2737247924080664,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004845460218673825,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.1836478143930435,
|
|
"num_tokens": 29508388.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.5844673156738285,
|
|
"epoch": 1.2742190589165678,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004845331662174421,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18585314154624938,
|
|
"num_tokens": 29519884.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.629808855056763,
|
|
"epoch": 1.2747133254250693,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004845203054129533,
|
|
"loss": 5.4741,
|
|
"mean_token_accuracy": 0.17494066804647446,
|
|
"num_tokens": 29532398.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.616901445388794,
|
|
"epoch": 1.2752075919335706,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048450743945423246,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.19050912708044052,
|
|
"num_tokens": 29544394.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.617944955825806,
|
|
"epoch": 1.2757018584420718,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004844945683415961,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.181037437915802,
|
|
"num_tokens": 29555027.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.562717294692993,
|
|
"epoch": 1.2761961249505733,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000484481692075361,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.18328929096460342,
|
|
"num_tokens": 29567386.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.679293584823609,
|
|
"epoch": 1.2766903914590748,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048446881065584367,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.1714109644293785,
|
|
"num_tokens": 29577832.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.513924169540405,
|
|
"epoch": 1.277184657967576,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048445592408336106,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.1933138370513916,
|
|
"num_tokens": 29590163.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.58849949836731,
|
|
"epoch": 1.2776789244760776,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048444303235823023,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.19103237241506577,
|
|
"num_tokens": 29601531.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.62832293510437,
|
|
"epoch": 1.2781731909845788,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004844301354807683,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.18370076268911362,
|
|
"num_tokens": 29612417.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.587715911865234,
|
|
"epoch": 1.2786674574930803,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048441723345129265,
|
|
"loss": 5.3778,
|
|
"mean_token_accuracy": 0.1835567131638527,
|
|
"num_tokens": 29622087.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.720718860626221,
|
|
"epoch": 1.2791617240015816,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004844043262701205,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.17603792250156403,
|
|
"num_tokens": 29633564.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.5489363193511965,
|
|
"epoch": 1.279655990510083,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004843914139375695,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.18811144679784775,
|
|
"num_tokens": 29644626.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.493628215789795,
|
|
"epoch": 1.2801502570185845,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048437849645395714,
|
|
"loss": 5.2727,
|
|
"mean_token_accuracy": 0.18894368708133696,
|
|
"num_tokens": 29655587.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.60671558380127,
|
|
"epoch": 1.2806445235270858,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004843655738196013,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.18553899526596068,
|
|
"num_tokens": 29665067.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.632060384750366,
|
|
"epoch": 1.281138790035587,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004843526460348199,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.18921743035316468,
|
|
"num_tokens": 29676663.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.480577754974365,
|
|
"epoch": 1.2816330565440885,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004843397130999309,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18828362971544266,
|
|
"num_tokens": 29688242.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.626586008071899,
|
|
"epoch": 1.28212732305259,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048432677501525253,
|
|
"loss": 5.3738,
|
|
"mean_token_accuracy": 0.17732333838939668,
|
|
"num_tokens": 29699184.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.552196836471557,
|
|
"epoch": 1.2826215895610913,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000484313831781103,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.18757932186126708,
|
|
"num_tokens": 29709610.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.504291152954101,
|
|
"epoch": 1.2831158560695928,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004843008833978007,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.18915001451969146,
|
|
"num_tokens": 29720359.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.642166614532471,
|
|
"epoch": 1.283610122578094,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048428792986566425,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.17518003135919571,
|
|
"num_tokens": 29732411.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.5938026905059814,
|
|
"epoch": 1.2841043890865955,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004842749711850122,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.19674361795186995,
|
|
"num_tokens": 29743394.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.576366758346557,
|
|
"epoch": 1.2845986555950968,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048426200735616343,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.18369031548500062,
|
|
"num_tokens": 29754798.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.536837244033814,
|
|
"epoch": 1.2850929221035983,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004842490383794368,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.1865644559264183,
|
|
"num_tokens": 29767891.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.552197217941284,
|
|
"epoch": 1.2855871886120998,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048423606425515136,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.19526944309473038,
|
|
"num_tokens": 29780264.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.607273292541504,
|
|
"epoch": 1.286081455120601,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048422308498362635,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.18163120597600937,
|
|
"num_tokens": 29792184.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.588546943664551,
|
|
"epoch": 1.2865757216291023,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004842101005651809,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18226567506790162,
|
|
"num_tokens": 29802651.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.542715454101563,
|
|
"epoch": 1.2870699881376038,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004841971110001346,
|
|
"loss": 5.2935,
|
|
"mean_token_accuracy": 0.1932521268725395,
|
|
"num_tokens": 29814172.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.602364110946655,
|
|
"epoch": 1.2875642546461052,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048418411628880684,
|
|
"loss": 5.3997,
|
|
"mean_token_accuracy": 0.17574526220560074,
|
|
"num_tokens": 29826636.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.572009801864624,
|
|
"epoch": 1.2880585211546065,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004841711164315174,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.18259814232587815,
|
|
"num_tokens": 29838532.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.563751602172852,
|
|
"epoch": 1.288552787663108,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000484158111428586,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18530286699533463,
|
|
"num_tokens": 29849889.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.635432195663452,
|
|
"epoch": 1.2890470541716093,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048414510128033265,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.17304231375455856,
|
|
"num_tokens": 29860856.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.559816503524781,
|
|
"epoch": 1.2895413206801107,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004841320859870774,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18880550116300582,
|
|
"num_tokens": 29871921.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.529505252838135,
|
|
"epoch": 1.290035587188612,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048411906554914037,
|
|
"loss": 5.302,
|
|
"mean_token_accuracy": 0.18277501910924912,
|
|
"num_tokens": 29883410.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.698047924041748,
|
|
"epoch": 1.2905298536971135,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048410603996684184,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.175324510037899,
|
|
"num_tokens": 29895640.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.575852155685425,
|
|
"epoch": 1.291024120205615,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004840930092405023,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19245994985103607,
|
|
"num_tokens": 29907797.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.46444993019104,
|
|
"epoch": 1.2915183867141162,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048407997337044235,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.18560926914215087,
|
|
"num_tokens": 29919085.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.61507396697998,
|
|
"epoch": 1.2920126532226177,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004840669323569826,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.1813542664051056,
|
|
"num_tokens": 29930658.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.614296722412109,
|
|
"epoch": 1.292506919731119,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048405388620044383,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.19131631404161453,
|
|
"num_tokens": 29942550.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.5114250659942625,
|
|
"epoch": 1.2930011862396205,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004840408349011471,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1884584680199623,
|
|
"num_tokens": 29953600.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.631883811950684,
|
|
"epoch": 1.2934954527481217,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004840277784594133,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.18667013794183732,
|
|
"num_tokens": 29965694.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.562025165557861,
|
|
"epoch": 1.2939897192566232,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004840147168755638,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.18241239637136458,
|
|
"num_tokens": 29977216.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.493104362487793,
|
|
"epoch": 1.2944839857651247,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004840016501499198,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.19349801689386367,
|
|
"num_tokens": 29988036.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.621885871887207,
|
|
"epoch": 1.294978252273626,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048398857828280286,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.1875185877084732,
|
|
"num_tokens": 30000711.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.596889352798462,
|
|
"epoch": 1.2954725187821272,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048397550127453445,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.18260823786258698,
|
|
"num_tokens": 30013607.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.552574634552002,
|
|
"epoch": 1.2959667852906287,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004839624191254362,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.18989617824554444,
|
|
"num_tokens": 30024375.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.631224012374878,
|
|
"epoch": 1.2964610517991302,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048394933183583004,
|
|
"loss": 5.3541,
|
|
"mean_token_accuracy": 0.18200013786554337,
|
|
"num_tokens": 30035476.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.6631995677948,
|
|
"epoch": 1.2969553183076314,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000483936239406038,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.18115097284317017,
|
|
"num_tokens": 30047193.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.624677085876465,
|
|
"epoch": 1.297449584816133,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000483923141836382,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.17891710698604585,
|
|
"num_tokens": 30059873.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.581372499465942,
|
|
"epoch": 1.2979438513246342,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004839100391271843,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.18588975816965103,
|
|
"num_tokens": 30071318.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.558609437942505,
|
|
"epoch": 1.2984381178331357,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004838969312787672,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.1865167573094368,
|
|
"num_tokens": 30082750.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.5829182147979735,
|
|
"epoch": 1.298932384341637,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004838838182914532,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.1808755561709404,
|
|
"num_tokens": 30093730.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.644095611572266,
|
|
"epoch": 1.2994266508501384,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004838707001655649,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.18389277309179305,
|
|
"num_tokens": 30104776.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.468333911895752,
|
|
"epoch": 1.29992091735864,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004838575769014249,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.1945190042257309,
|
|
"num_tokens": 30115110.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.538907814025879,
|
|
"epoch": 1.3004151838671412,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004838444484993562,
|
|
"loss": 5.2867,
|
|
"mean_token_accuracy": 0.19144085943698883,
|
|
"num_tokens": 30126678.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.585387897491455,
|
|
"epoch": 1.3009094503756424,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048383131495968165,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.18727052062749863,
|
|
"num_tokens": 30137703.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.5331824779510494,
|
|
"epoch": 1.301403716884144,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048381817628272427,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.1826944887638092,
|
|
"num_tokens": 30147624.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.564120769500732,
|
|
"epoch": 1.3018979833926454,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004838050324688074,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18814228475093842,
|
|
"num_tokens": 30158863.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.536690759658813,
|
|
"epoch": 1.3023922499011467,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004837918835182544,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.18162029087543488,
|
|
"num_tokens": 30170876.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.597613048553467,
|
|
"epoch": 1.3028865164096481,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004837787294313886,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.19113404750823976,
|
|
"num_tokens": 30182267.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.5531378269195555,
|
|
"epoch": 1.3033807829181494,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004837655702085337,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.18300452530384065,
|
|
"num_tokens": 30193572.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.48090443611145,
|
|
"epoch": 1.303875049426651,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004837524058500134,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.19296275675296784,
|
|
"num_tokens": 30206341.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.637471437454224,
|
|
"epoch": 1.3043693159351522,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048373923635615146,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.1855029955506325,
|
|
"num_tokens": 30216067.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.566336154937744,
|
|
"epoch": 1.3048635824436536,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048372606172727197,
|
|
"loss": 5.3895,
|
|
"mean_token_accuracy": 0.1784699648618698,
|
|
"num_tokens": 30227033.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.609153747558594,
|
|
"epoch": 1.3053578489521551,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000483712881963699,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.18542856723070145,
|
|
"num_tokens": 30238766.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.613398170471191,
|
|
"epoch": 1.3058521154606564,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048369969706575666,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.18022770136594773,
|
|
"num_tokens": 30250180.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.543482446670533,
|
|
"epoch": 1.3063463819691576,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048368650703376956,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.2000505208969116,
|
|
"num_tokens": 30260704.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.527899312973022,
|
|
"epoch": 1.3068406484776591,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004836733118680619,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.1882590815424919,
|
|
"num_tokens": 30273547.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.488944673538208,
|
|
"epoch": 1.3073349149861606,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004836601115689584,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18358598202466964,
|
|
"num_tokens": 30284872.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.506593894958496,
|
|
"epoch": 1.3078291814946619,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004836469061367838,
|
|
"loss": 5.3334,
|
|
"mean_token_accuracy": 0.18612879663705825,
|
|
"num_tokens": 30296768.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.528110933303833,
|
|
"epoch": 1.3083234480031634,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048363369557186293,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.19344475120306015,
|
|
"num_tokens": 30308307.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.647311401367188,
|
|
"epoch": 1.3088177145116646,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048362047987452085,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.17930016070604324,
|
|
"num_tokens": 30318987.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.612217617034912,
|
|
"epoch": 1.309311981020166,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004836072590450825,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.18675102442502975,
|
|
"num_tokens": 30330401.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.541235303878784,
|
|
"epoch": 1.3098062475286674,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048359403308387327,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.18839216530323027,
|
|
"num_tokens": 30341485.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.6009338855743405,
|
|
"epoch": 1.3103005140371689,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048358080199121845,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.17426563501358033,
|
|
"num_tokens": 30352854.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.56042513847351,
|
|
"epoch": 1.3107947805456703,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048356756576744354,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.18697816431522368,
|
|
"num_tokens": 30363944.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.639027452468872,
|
|
"epoch": 1.3112890470541716,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004835543244128742,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.177656289935112,
|
|
"num_tokens": 30375678.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.6770322799682615,
|
|
"epoch": 1.3117833135626729,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004835410779278361,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.1903293326497078,
|
|
"num_tokens": 30387206.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.546335315704345,
|
|
"epoch": 1.3122775800711743,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004835278263126551,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.1863785743713379,
|
|
"num_tokens": 30398769.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.55128846168518,
|
|
"epoch": 1.3127718465796758,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004835145695676572,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.1943705976009369,
|
|
"num_tokens": 30409626.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.546380853652954,
|
|
"epoch": 1.313266113088177,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004835013076931686,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.18097612261772156,
|
|
"num_tokens": 30421142.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.567991495132446,
|
|
"epoch": 1.3137603795966786,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048348804068951547,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20425085723400116,
|
|
"num_tokens": 30430438.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.621165418624878,
|
|
"epoch": 1.3142546461051798,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048347476855702413,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.17983296513557434,
|
|
"num_tokens": 30442351.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.539897155761719,
|
|
"epoch": 1.3147489126136813,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048346149129602125,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.1778470143675804,
|
|
"num_tokens": 30454987.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.532633924484253,
|
|
"epoch": 1.3152431791221826,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048344820890683333,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.1915357902646065,
|
|
"num_tokens": 30466186.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.599523305892944,
|
|
"epoch": 1.315737445630684,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048343492138978704,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18334044367074967,
|
|
"num_tokens": 30477944.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.563941192626953,
|
|
"epoch": 1.3162317121391856,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004834216287452094,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.1885995462536812,
|
|
"num_tokens": 30489922.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.585392475128174,
|
|
"epoch": 1.3167259786476868,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004834083309734274,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.18913669288158416,
|
|
"num_tokens": 30501739.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.618761825561523,
|
|
"epoch": 1.3172202451561883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004833950280747681,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.17857423722743987,
|
|
"num_tokens": 30512213.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.621655654907227,
|
|
"epoch": 1.3177145116646896,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004833817200495588,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.17998804301023483,
|
|
"num_tokens": 30524300.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.592460680007934,
|
|
"epoch": 1.318208778173191,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048336840689812676,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.17888545989990234,
|
|
"num_tokens": 30536137.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.539377307891845,
|
|
"epoch": 1.3187030446816923,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048335508862079975,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.17478720247745513,
|
|
"num_tokens": 30548657.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.591573810577392,
|
|
"epoch": 1.3191973111901938,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048334176521790513,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.18069755882024766,
|
|
"num_tokens": 30560274.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.532292222976684,
|
|
"epoch": 1.3196915776986953,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004833284366897707,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.19901436418294907,
|
|
"num_tokens": 30571026.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.524319982528686,
|
|
"epoch": 1.3201858442071965,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048331510303672456,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.19312808960676192,
|
|
"num_tokens": 30582210.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.576966333389282,
|
|
"epoch": 1.3206801107156978,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004833017642590945,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.17685349732637407,
|
|
"num_tokens": 30594049.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.62827696800232,
|
|
"epoch": 1.3211743772241993,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048328842035720863,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.17821426689624786,
|
|
"num_tokens": 30604713.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.5506078720092775,
|
|
"epoch": 1.3216686437327008,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004832750713313954,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.18718644976615906,
|
|
"num_tokens": 30615906.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.542311429977417,
|
|
"epoch": 1.322162910241202,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048326171718198315,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.183139568567276,
|
|
"num_tokens": 30628191.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.682043790817261,
|
|
"epoch": 1.3226571767497035,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048324835790930027,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.18023661673069,
|
|
"num_tokens": 30640667.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.599970912933349,
|
|
"epoch": 1.3231514432582048,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004832349935136755,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.18111353367567062,
|
|
"num_tokens": 30651779.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.457780075073242,
|
|
"epoch": 1.3236457097667063,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004832216239954376,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.1960521548986435,
|
|
"num_tokens": 30662396.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.5778007984161375,
|
|
"epoch": 1.3241399762752075,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004832082493549154,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.18714046180248262,
|
|
"num_tokens": 30674476.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.55853238105774,
|
|
"epoch": 1.324634242783709,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004831948695924381,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.18489651530981063,
|
|
"num_tokens": 30687417.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.5827961444854735,
|
|
"epoch": 1.3251285092922105,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004831814847083346,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.18381934612989426,
|
|
"num_tokens": 30698925.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.597514724731445,
|
|
"epoch": 1.3256227758007118,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048316809470293426,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.18669430315494537,
|
|
"num_tokens": 30711237.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.628702974319458,
|
|
"epoch": 1.326117042309213,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048315469957656656,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.1801370471715927,
|
|
"num_tokens": 30721900.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.596040916442871,
|
|
"epoch": 1.3266113088177145,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004831412993295609,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.1810799241065979,
|
|
"num_tokens": 30734738.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.623744344711303,
|
|
"epoch": 1.327105575326216,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048312789396224697,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.18441015630960464,
|
|
"num_tokens": 30745849.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.594388008117676,
|
|
"epoch": 1.3275998418347172,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048311448347495466,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.18293600529432297,
|
|
"num_tokens": 30757118.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.6022705078125,
|
|
"epoch": 1.3280941083432187,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004831010678680137,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.18311455547809602,
|
|
"num_tokens": 30768692.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.650684833526611,
|
|
"epoch": 1.32858837485172,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004830876471417542,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.18243027627468109,
|
|
"num_tokens": 30780241.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.5737175941467285,
|
|
"epoch": 1.3290826413602215,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004830742212965063,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.183657868206501,
|
|
"num_tokens": 30792733.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.532139635086059,
|
|
"epoch": 1.3295769078687227,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004830607903326003,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.18831610530614853,
|
|
"num_tokens": 30803997.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.536646986007691,
|
|
"epoch": 1.3300711743772242,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004830473542503665,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.19157848209142686,
|
|
"num_tokens": 30815322.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.547467851638794,
|
|
"epoch": 1.3305654408857257,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048303391305013556,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1834270775318146,
|
|
"num_tokens": 30825572.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.488988542556763,
|
|
"epoch": 1.331059707394227,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048302046673223816,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.19306015074253083,
|
|
"num_tokens": 30837451.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.523415756225586,
|
|
"epoch": 1.3315539739027282,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004830070152970049,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.18667556941509247,
|
|
"num_tokens": 30849418.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.711820888519287,
|
|
"epoch": 1.3320482404112297,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048299355874476685,
|
|
"loss": 5.3937,
|
|
"mean_token_accuracy": 0.17609770148992537,
|
|
"num_tokens": 30860387.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.549403190612793,
|
|
"epoch": 1.3325425069197312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000482980097075855,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.19157841205596923,
|
|
"num_tokens": 30871599.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.490998935699463,
|
|
"epoch": 1.3330367734282325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048296663029060046,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.19256742298603058,
|
|
"num_tokens": 30882298.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.49026927947998,
|
|
"epoch": 1.333531039936734,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004829531583893345,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.19060448557138443,
|
|
"num_tokens": 30893589.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.572388362884522,
|
|
"epoch": 1.3340253064452352,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004829396813723886,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.18731513172388076,
|
|
"num_tokens": 30905041.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.595463609695434,
|
|
"epoch": 1.3345195729537367,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004829261992400944,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.18252125084400178,
|
|
"num_tokens": 30916244.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.605492639541626,
|
|
"epoch": 1.335013839462238,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004829127119927833,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18466252833604813,
|
|
"num_tokens": 30927444.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.561847257614136,
|
|
"epoch": 1.3355081059707394,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004828992196307873,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.19060091376304628,
|
|
"num_tokens": 30939402.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.611426115036011,
|
|
"epoch": 1.336002372479241,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048288572215443825,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.1800771713256836,
|
|
"num_tokens": 30951598.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.575377702713013,
|
|
"epoch": 1.3364966389877422,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004828722195640681,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.1841629460453987,
|
|
"num_tokens": 30963897.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.531616592407227,
|
|
"epoch": 1.3369909054962434,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048285871186000916,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.19010904133319856,
|
|
"num_tokens": 30975143.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.621841287612915,
|
|
"epoch": 1.337485172004745,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048284519904259374,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.1805231377482414,
|
|
"num_tokens": 30986656.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.6166597366333,
|
|
"epoch": 1.3379794385132464,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004828316811121541,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.18380712419748307,
|
|
"num_tokens": 30999904.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.581716108322143,
|
|
"epoch": 1.3384737050217477,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048281815806902286,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.1951906129717827,
|
|
"num_tokens": 31012287.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.559448528289795,
|
|
"epoch": 1.3389679715302492,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048280462991353267,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.18894658535718917,
|
|
"num_tokens": 31023954.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.507368803024292,
|
|
"epoch": 1.3394622380387504,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004827910966460164,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.18764253556728364,
|
|
"num_tokens": 31035365.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.571511554718017,
|
|
"epoch": 1.339956504547252,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004827775582668069,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.18836550265550614,
|
|
"num_tokens": 31046814.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.518642234802246,
|
|
"epoch": 1.3404507710557532,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004827640147762372,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.1885582536458969,
|
|
"num_tokens": 31058112.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.4901340961456295,
|
|
"epoch": 1.3409450375642546,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048275046617464055,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.19007809907197953,
|
|
"num_tokens": 31068703.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.558464241027832,
|
|
"epoch": 1.3414393040727561,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004827369124623502,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.1897701218724251,
|
|
"num_tokens": 31080018.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.606843042373657,
|
|
"epoch": 1.3419335705812574,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048272335363969956,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.1832766965031624,
|
|
"num_tokens": 31091103.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.665033626556396,
|
|
"epoch": 1.3424278370897589,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004827097897070222,
|
|
"loss": 5.3717,
|
|
"mean_token_accuracy": 0.17755989879369735,
|
|
"num_tokens": 31102731.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.446692085266113,
|
|
"epoch": 1.3429221035982601,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004826962206646518,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19685572236776352,
|
|
"num_tokens": 31114080.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.479043817520141,
|
|
"epoch": 1.3434163701067616,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048268264651292215,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.18116212338209153,
|
|
"num_tokens": 31125875.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.572889995574951,
|
|
"epoch": 1.3439106366152629,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048266906725216713,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.18604280799627304,
|
|
"num_tokens": 31139246.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.613872241973877,
|
|
"epoch": 1.3444049031237644,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048265548288272086,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.18893948048353196,
|
|
"num_tokens": 31150606.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.508626413345337,
|
|
"epoch": 1.3448991696322659,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048264189340491755,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.18396053910255433,
|
|
"num_tokens": 31162413.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.567545938491821,
|
|
"epoch": 1.3453934361407671,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048262829881909135,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18579374700784684,
|
|
"num_tokens": 31172832.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.592158365249634,
|
|
"epoch": 1.3458877026492684,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048261469912557685,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.18132582753896714,
|
|
"num_tokens": 31186172.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.5743927478790285,
|
|
"epoch": 1.3463819691577699,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048260109432470856,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1906236380338669,
|
|
"num_tokens": 31197580.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.545495128631591,
|
|
"epoch": 1.3468762356662713,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048258748441682114,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18882938027381896,
|
|
"num_tokens": 31209262.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.544550895690918,
|
|
"epoch": 1.3473705021747726,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004825738694022494,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.18533801883459092,
|
|
"num_tokens": 31221722.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.528980302810669,
|
|
"epoch": 1.347864768683274,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048256024928132826,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.19781983643770218,
|
|
"num_tokens": 31232871.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.534906911849975,
|
|
"epoch": 1.3483590351917754,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004825466240543928,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.18928706347942353,
|
|
"num_tokens": 31244010.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.538941335678101,
|
|
"epoch": 1.3488533017002768,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004825329937217782,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.18693839609622956,
|
|
"num_tokens": 31255643.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.628931045532227,
|
|
"epoch": 1.349347568208778,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004825193582838196,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.1806727260351181,
|
|
"num_tokens": 31266764.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.641424560546875,
|
|
"epoch": 1.3498418347172796,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004825057177408528,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.190157687664032,
|
|
"num_tokens": 31277533.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.589084768295288,
|
|
"epoch": 1.350336101225781,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000482492072093213,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.18363741934299468,
|
|
"num_tokens": 31289509.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.5560815811157225,
|
|
"epoch": 1.3508303677342823,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048247842134123615,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.18432536870241165,
|
|
"num_tokens": 31300909.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.5915015697479244,
|
|
"epoch": 1.3513246342427836,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004824647654852579,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.17835255563259125,
|
|
"num_tokens": 31312148.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.527994537353516,
|
|
"epoch": 1.351818900751285,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004824511045256142,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.19583797603845596,
|
|
"num_tokens": 31323388.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.516686582565308,
|
|
"epoch": 1.3523131672597866,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048243743846264125,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.19454219192266464,
|
|
"num_tokens": 31334103.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.512790870666504,
|
|
"epoch": 1.3528074337682878,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004824237672966751,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18227531909942626,
|
|
"num_tokens": 31345456.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.498084640502929,
|
|
"epoch": 1.3533017002767893,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000482410091028052,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.2036672815680504,
|
|
"num_tokens": 31356482.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.592561292648315,
|
|
"epoch": 1.3537959667852906,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048239640965710854,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1788662552833557,
|
|
"num_tokens": 31367103.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.649016714096069,
|
|
"epoch": 1.354290233293792,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048238272318418127,
|
|
"loss": 5.3234,
|
|
"mean_token_accuracy": 0.18342381715774536,
|
|
"num_tokens": 31378564.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.557184314727783,
|
|
"epoch": 1.3547844998022933,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048236903160960677,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.18709568828344345,
|
|
"num_tokens": 31391435.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.542447566986084,
|
|
"epoch": 1.3552787663107948,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000482355334933722,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.18458854258060456,
|
|
"num_tokens": 31403422.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.526493072509766,
|
|
"epoch": 1.3557730328192963,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048234163315686375,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.20021570473909378,
|
|
"num_tokens": 31414940.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.591849422454834,
|
|
"epoch": 1.3562672993277975,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004823279262793692,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.18219470381736755,
|
|
"num_tokens": 31426369.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.585572338104248,
|
|
"epoch": 1.3567615658362988,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048231421430157547,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.18620910942554475,
|
|
"num_tokens": 31438426.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.479246664047241,
|
|
"epoch": 1.3572558323448003,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004823004972238199,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.1875782012939453,
|
|
"num_tokens": 31450230.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.604035377502441,
|
|
"epoch": 1.3577500988533018,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048228677504643996,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.17704587578773498,
|
|
"num_tokens": 31462564.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.575523757934571,
|
|
"epoch": 1.358244365361803,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004822730477697732,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.19584511816501618,
|
|
"num_tokens": 31475053.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.531681394577026,
|
|
"epoch": 1.3587386318703045,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004822593153941573,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1911413162946701,
|
|
"num_tokens": 31487187.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.613844108581543,
|
|
"epoch": 1.3592328983788058,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048224557791993013,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.18950614780187608,
|
|
"num_tokens": 31499288.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.548209619522095,
|
|
"epoch": 1.3597271648873073,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048223183534742953,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.1843956619501114,
|
|
"num_tokens": 31510113.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.552912473678589,
|
|
"epoch": 1.3602214313958085,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048221808767699373,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.18839042335748674,
|
|
"num_tokens": 31520900.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.62318434715271,
|
|
"epoch": 1.36071569790431,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004822043349089607,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18829481601715087,
|
|
"num_tokens": 31533085.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.490102863311767,
|
|
"epoch": 1.3612099644128115,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004821905770436689,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.18156532645225526,
|
|
"num_tokens": 31544287.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.48185133934021,
|
|
"epoch": 1.3617042309213128,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004821768140814568,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.1897735059261322,
|
|
"num_tokens": 31555233.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.5793962478637695,
|
|
"epoch": 1.362198497429814,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004821630460226629,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.1953558847308159,
|
|
"num_tokens": 31565421.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.536884498596192,
|
|
"epoch": 1.3626927639383155,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000482149272867626,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.18806941360235213,
|
|
"num_tokens": 31576787.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.568742799758911,
|
|
"epoch": 1.363187030446817,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048213549461668476,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1840363010764122,
|
|
"num_tokens": 31587563.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.618517875671387,
|
|
"epoch": 1.3636812969553183,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048212171127017835,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.18457017838954926,
|
|
"num_tokens": 31598186.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.58347601890564,
|
|
"epoch": 1.3641755634638197,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004821079228284456,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.18484410643577576,
|
|
"num_tokens": 31609458.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.52047815322876,
|
|
"epoch": 1.364669829972321,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048209412929182586,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.19333418756723403,
|
|
"num_tokens": 31619497.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.555792617797851,
|
|
"epoch": 1.3651640964808225,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004820803306606584,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.1770672768354416,
|
|
"num_tokens": 31630838.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.639689826965332,
|
|
"epoch": 1.3656583629893237,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004820665269352827,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.18517448902130126,
|
|
"num_tokens": 31642234.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.600019550323486,
|
|
"epoch": 1.3661526294978252,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048205271811603827,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.18303383886814117,
|
|
"num_tokens": 31653283.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.560482215881348,
|
|
"epoch": 1.3666468960063267,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004820389042032649,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.19170407801866532,
|
|
"num_tokens": 31663284.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.5168968677520756,
|
|
"epoch": 1.367141162514828,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004820250851973023,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.18881695717573166,
|
|
"num_tokens": 31674379.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.61357946395874,
|
|
"epoch": 1.3676354290233292,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004820112610984906,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.1860516756772995,
|
|
"num_tokens": 31686420.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.46399245262146,
|
|
"epoch": 1.3681296955318307,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048199743190716966,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.19982898086309434,
|
|
"num_tokens": 31696919.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.486889743804932,
|
|
"epoch": 1.3686239620403322,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048198359762367983,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.18307898938655853,
|
|
"num_tokens": 31708878.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.589809560775757,
|
|
"epoch": 1.3691182285488335,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00048196975824836135,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.18672320544719695,
|
|
"num_tokens": 31719348.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.550428104400635,
|
|
"epoch": 1.369612495057335,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004819559137815547,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1889267861843109,
|
|
"num_tokens": 31729349.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.624013471603393,
|
|
"epoch": 1.3701067615658362,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004819420642236005,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.18705124258995057,
|
|
"num_tokens": 31740345.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.592474555969238,
|
|
"epoch": 1.3706010280743377,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004819282095748395,
|
|
"loss": 5.3149,
|
|
"mean_token_accuracy": 0.18576174974441528,
|
|
"num_tokens": 31752231.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.547329664230347,
|
|
"epoch": 1.371095294582839,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004819143498356123,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.18401034027338029,
|
|
"num_tokens": 31764248.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.494870853424072,
|
|
"epoch": 1.3715895610913404,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004819004850062601,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.19540592581033706,
|
|
"num_tokens": 31774173.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.5622578144073485,
|
|
"epoch": 1.372083827599842,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048188661508712376,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.1851779341697693,
|
|
"num_tokens": 31784860.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.549490594863892,
|
|
"epoch": 1.3725780941083432,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004818727400785447,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.18481405526399614,
|
|
"num_tokens": 31797012.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.496869277954102,
|
|
"epoch": 1.3730723606168447,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004818588599808641,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.18949989527463912,
|
|
"num_tokens": 31808216.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.498139905929565,
|
|
"epoch": 1.373566627125346,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048184497479442345,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.1797014743089676,
|
|
"num_tokens": 31820097.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.655687952041626,
|
|
"epoch": 1.3740608936338474,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004818310845195643,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.1744787201285362,
|
|
"num_tokens": 31832252.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.611270761489868,
|
|
"epoch": 1.3745551601423487,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004818171891566284,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.17706188857555388,
|
|
"num_tokens": 31842928.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.555426788330078,
|
|
"epoch": 1.3750494266508502,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004818032887059576,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.18984256237745284,
|
|
"num_tokens": 31854072.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.575338363647461,
|
|
"epoch": 1.3755436931593517,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004817893831678938,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.1851952090859413,
|
|
"num_tokens": 31865163.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.478239917755127,
|
|
"epoch": 1.376037959667853,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048177547254277904,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19826027303934096,
|
|
"num_tokens": 31876583.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.505367183685303,
|
|
"epoch": 1.3765322261763542,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004817615568309557,
|
|
"loss": 5.2679,
|
|
"mean_token_accuracy": 0.19243911057710647,
|
|
"num_tokens": 31886794.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.652082061767578,
|
|
"epoch": 1.3770264926848557,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004817476360327658,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.1845763474702835,
|
|
"num_tokens": 31899980.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.472676229476929,
|
|
"epoch": 1.3775207591933571,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004817337101485521,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.2005974307656288,
|
|
"num_tokens": 31909906.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.418480157852173,
|
|
"epoch": 1.3780150257018584,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048171977917865706,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19873537868261337,
|
|
"num_tokens": 31920499.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.45085129737854,
|
|
"epoch": 1.37850929221036,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048170584312342337,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.1934374213218689,
|
|
"num_tokens": 31931031.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.578192949295044,
|
|
"epoch": 1.3790035587188612,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004816919019831939,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.1903511628508568,
|
|
"num_tokens": 31941887.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.589427709579468,
|
|
"epoch": 1.3794978252273626,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048167795575831154,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.1838187798857689,
|
|
"num_tokens": 31953727.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.58573956489563,
|
|
"epoch": 1.379992091735864,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004816640044491193,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.18646432012319564,
|
|
"num_tokens": 31965418.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.540962076187133,
|
|
"epoch": 1.3804863582443654,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004816500480559607,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.18052270114421845,
|
|
"num_tokens": 31976528.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.560310363769531,
|
|
"epoch": 1.3809806247528669,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048163608657917874,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.1819060832262039,
|
|
"num_tokens": 31987921.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.561914920806885,
|
|
"epoch": 1.3814748912613681,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000481622120019117,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.19500807970762252,
|
|
"num_tokens": 31998824.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.573212432861328,
|
|
"epoch": 1.3819691577698694,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004816081483761191,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.1761224940419197,
|
|
"num_tokens": 32011690.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.569722652435303,
|
|
"epoch": 1.3824634242783709,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004815941716505286,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1885720446705818,
|
|
"num_tokens": 32022946.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.5903980255126955,
|
|
"epoch": 1.3829576907868724,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048158018984268954,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.18407854437828064,
|
|
"num_tokens": 32033683.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.68729829788208,
|
|
"epoch": 1.3834519572953736,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004815662029529457,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.17787885069847106,
|
|
"num_tokens": 32045334.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.530660772323609,
|
|
"epoch": 1.383946223803875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048155221098164123,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18747028857469558,
|
|
"num_tokens": 32056425.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.564030504226684,
|
|
"epoch": 1.3844404903123764,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048153821392912035,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.18638173639774322,
|
|
"num_tokens": 32068053.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.615358495712281,
|
|
"epoch": 1.3849347568208779,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004815242117957273,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.1868830218911171,
|
|
"num_tokens": 32079462.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.460106992721558,
|
|
"epoch": 1.3854290233293791,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048151020458180667,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.19104224145412446,
|
|
"num_tokens": 32090566.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.597770357131958,
|
|
"epoch": 1.3859232898378806,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000481496192287703,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.1850452944636345,
|
|
"num_tokens": 32101535.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.568674850463867,
|
|
"epoch": 1.386417556346382,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004814821749137609,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19037488102912903,
|
|
"num_tokens": 32112450.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.55473313331604,
|
|
"epoch": 1.3869118228548833,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004814681524603252,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.17918507009744644,
|
|
"num_tokens": 32123675.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.616510820388794,
|
|
"epoch": 1.3874060893633846,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000481454124927741,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.18292710781097413,
|
|
"num_tokens": 32135283.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.485527515411377,
|
|
"epoch": 1.387900355871886,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048144009231635326,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.1986176148056984,
|
|
"num_tokens": 32146715.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.473164892196655,
|
|
"epoch": 1.3883946223803876,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004814260546265073,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.18215213268995284,
|
|
"num_tokens": 32158323.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.597801589965821,
|
|
"epoch": 1.3888888888888888,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004814120118585483,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.18366469740867614,
|
|
"num_tokens": 32170453.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.659882593154907,
|
|
"epoch": 1.3893831553973903,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004813979640128218,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.1786791056394577,
|
|
"num_tokens": 32181596.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.569861793518067,
|
|
"epoch": 1.3898774219058916,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004813839110896734,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.185446634888649,
|
|
"num_tokens": 32194603.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.482155704498291,
|
|
"epoch": 1.390371688414393,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048136985308944874,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.18750418722629547,
|
|
"num_tokens": 32206064.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.573109340667725,
|
|
"epoch": 1.3908659549228943,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048135579001249367,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.18112903088331223,
|
|
"num_tokens": 32217254.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.659684038162231,
|
|
"epoch": 1.3913602214313958,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004813417218591542,
|
|
"loss": 5.4529,
|
|
"mean_token_accuracy": 0.1695420816540718,
|
|
"num_tokens": 32228821.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.616552829742432,
|
|
"epoch": 1.3918544879398973,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004813276486297763,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.18476972728967667,
|
|
"num_tokens": 32239476.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.583530282974243,
|
|
"epoch": 1.3923487544483986,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004813135703247062,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.18912833631038667,
|
|
"num_tokens": 32250975.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.573594427108764,
|
|
"epoch": 1.3928430209568998,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048129948694429036,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.19932686239480973,
|
|
"num_tokens": 32261675.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.404256296157837,
|
|
"epoch": 1.3933372874654013,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048128539848887517,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.20076923817396164,
|
|
"num_tokens": 32272523.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.50162262916565,
|
|
"epoch": 1.3938315539739028,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048127130495880703,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.18465988337993622,
|
|
"num_tokens": 32284140.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.551804733276367,
|
|
"epoch": 1.394325820482404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004812572063544329,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.18733243346214296,
|
|
"num_tokens": 32296286.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.559649085998535,
|
|
"epoch": 1.3948200869909055,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048124310267609946,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.18507933467626572,
|
|
"num_tokens": 32307394.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.579262542724609,
|
|
"epoch": 1.3953143534994068,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004812289939241537,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.17738183587789536,
|
|
"num_tokens": 32318788.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.606856107711792,
|
|
"epoch": 1.3958086200079083,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004812148800989427,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18377091735601425,
|
|
"num_tokens": 32332395.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.661629056930542,
|
|
"epoch": 1.3963028865164095,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048120076120081363,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1850421130657196,
|
|
"num_tokens": 32344226.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.633994054794312,
|
|
"epoch": 1.396797153024911,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048118663723011393,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.1815141871571541,
|
|
"num_tokens": 32354677.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.5407774448394775,
|
|
"epoch": 1.3972914195334125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004811725081871909,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.1894712418317795,
|
|
"num_tokens": 32365054.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.462257671356201,
|
|
"epoch": 1.3977856860419138,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004811583740723922,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.2064767897129059,
|
|
"num_tokens": 32376215.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.580702209472657,
|
|
"epoch": 1.3982799525504153,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048114423488606543,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.1849250614643097,
|
|
"num_tokens": 32386880.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.5829915523529055,
|
|
"epoch": 1.3987742190589165,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048113009062855866,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.18869563639163972,
|
|
"num_tokens": 32398227.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.627834939956665,
|
|
"epoch": 1.399268485567418,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004811159413002196,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.18219398111104965,
|
|
"num_tokens": 32410091.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.618755197525024,
|
|
"epoch": 1.3997627520759193,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004811017869013963,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.18500218838453292,
|
|
"num_tokens": 32422710.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.576482486724854,
|
|
"epoch": 1.4002570185844208,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004810876274324372,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.18767495602369308,
|
|
"num_tokens": 32433691.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.5217639923095705,
|
|
"epoch": 1.4007512850929222,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004810734628936905,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.19461503326892854,
|
|
"num_tokens": 32445370.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.506391477584839,
|
|
"epoch": 1.4012455516014235,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048105929328550465,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.1894183024764061,
|
|
"num_tokens": 32456737.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.527261400222779,
|
|
"epoch": 1.4017398181099248,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004810451186082282,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.1799298569560051,
|
|
"num_tokens": 32467957.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.618913030624389,
|
|
"epoch": 1.4022340846184262,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048103093886220984,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1799939900636673,
|
|
"num_tokens": 32481697.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.52026219367981,
|
|
"epoch": 1.4027283511269277,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048101675404779834,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.1989932730793953,
|
|
"num_tokens": 32492828.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.666405582427979,
|
|
"epoch": 1.403222617635429,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004810025641653428,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.17858758717775344,
|
|
"num_tokens": 32505120.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.494580888748169,
|
|
"epoch": 1.4037168841439305,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004809883692151923,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.1917847916483879,
|
|
"num_tokens": 32516837.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.511334848403931,
|
|
"epoch": 1.4042111506524317,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048097416919769595,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1957152560353279,
|
|
"num_tokens": 32526906.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.591095685958862,
|
|
"epoch": 1.4047054171609332,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048095996411320294,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.180920746922493,
|
|
"num_tokens": 32537929.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.556006669998169,
|
|
"epoch": 1.4051996836694345,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048094575396206296,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.18544836342334747,
|
|
"num_tokens": 32549458.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.554550218582153,
|
|
"epoch": 1.405693950177936,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004809315387446255,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.192620712518692,
|
|
"num_tokens": 32560244.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.611189126968384,
|
|
"epoch": 1.4061882166864375,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004809173184612402,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.1824148952960968,
|
|
"num_tokens": 32571337.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.5557976245880125,
|
|
"epoch": 1.4066824831949387,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004809030931122569,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.1870194375514984,
|
|
"num_tokens": 32582325.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.591997575759888,
|
|
"epoch": 1.40717674970344,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048088886269802565,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.18786220550537108,
|
|
"num_tokens": 32592953.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.507330083847046,
|
|
"epoch": 1.4076710162119415,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004808746272188964,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.18943574875593186,
|
|
"num_tokens": 32604190.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.608222389221192,
|
|
"epoch": 1.408165282720443,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048086038667521935,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18823712170124055,
|
|
"num_tokens": 32614467.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.563982534408569,
|
|
"epoch": 1.4086595492289442,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004808461410673449,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.1894093155860901,
|
|
"num_tokens": 32624022.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.50787320137024,
|
|
"epoch": 1.4091538157374457,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004808318903956234,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.18933749347925186,
|
|
"num_tokens": 32634363.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.47831163406372,
|
|
"epoch": 1.409648082245947,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004808176346604055,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.19605227559804916,
|
|
"num_tokens": 32646143.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.541686391830444,
|
|
"epoch": 1.4101423487544484,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004808033738620419,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.18495482504367827,
|
|
"num_tokens": 32658735.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.657311964035034,
|
|
"epoch": 1.4106366152629497,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048078910800088327,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.17824603021144866,
|
|
"num_tokens": 32669337.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.528915977478027,
|
|
"epoch": 1.4111308817714512,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004807748370772807,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.19796449095010757,
|
|
"num_tokens": 32680072.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.564443588256836,
|
|
"epoch": 1.4116251482799527,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048076056109158525,
|
|
"loss": 5.2615,
|
|
"mean_token_accuracy": 0.18784509152173995,
|
|
"num_tokens": 32691142.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.59086971282959,
|
|
"epoch": 1.412119414788454,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004807462800441481,
|
|
"loss": 5.3639,
|
|
"mean_token_accuracy": 0.18151748478412627,
|
|
"num_tokens": 32702482.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.573894214630127,
|
|
"epoch": 1.4126136812969552,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004807319939353204,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18142396807670594,
|
|
"num_tokens": 32714456.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.615094614028931,
|
|
"epoch": 1.4131079478054567,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048071770276545377,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18678772896528245,
|
|
"num_tokens": 32726305.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.473111248016357,
|
|
"epoch": 1.4136022143139582,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048070340653489984,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.19643620252609253,
|
|
"num_tokens": 32736446.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.549442911148072,
|
|
"epoch": 1.4140964808224594,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048068910524401014,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.18239953070878984,
|
|
"num_tokens": 32746798.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.492679691314697,
|
|
"epoch": 1.414590747330961,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048067479889313654,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.19464655369520187,
|
|
"num_tokens": 32758647.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.558327150344849,
|
|
"epoch": 1.4150850138394622,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048066048748263097,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18336590379476547,
|
|
"num_tokens": 32770759.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.531225967407226,
|
|
"epoch": 1.4155792803479637,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048064617101284553,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.1947077050805092,
|
|
"num_tokens": 32783398.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.569667148590088,
|
|
"epoch": 1.416073546856465,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048063184948413237,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.1792918249964714,
|
|
"num_tokens": 32795995.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.609825181961059,
|
|
"epoch": 1.4165678133649664,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048061752289684385,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.18622799962759018,
|
|
"num_tokens": 32808700.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.594605302810669,
|
|
"epoch": 1.4170620798734679,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004806031912513323,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.17162495851516724,
|
|
"num_tokens": 32820815.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.600676584243774,
|
|
"epoch": 1.4175563463819691,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048058885454795036,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1870318830013275,
|
|
"num_tokens": 32832216.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.65184440612793,
|
|
"epoch": 1.4180506128904704,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004805745127870508,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.18112110644578933,
|
|
"num_tokens": 32845118.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.563069486618042,
|
|
"epoch": 1.418544879398972,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004805601659689862,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18804137408733368,
|
|
"num_tokens": 32855662.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.605299663543701,
|
|
"epoch": 1.4190391459074734,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004805458140941097,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.1868645057082176,
|
|
"num_tokens": 32865530.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.5773028373718265,
|
|
"epoch": 1.4195334124159746,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048053145716277424,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18146448582410812,
|
|
"num_tokens": 32877542.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.473843002319336,
|
|
"epoch": 1.4200276789244761,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004805170951753331,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.18693141490221024,
|
|
"num_tokens": 32888197.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.573131895065307,
|
|
"epoch": 1.4205219454329774,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004805027281321395,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.18877836018800737,
|
|
"num_tokens": 32899633.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.564231586456299,
|
|
"epoch": 1.4210162119414789,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004804883560335469,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.19620063453912734,
|
|
"num_tokens": 32910334.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.635857772827149,
|
|
"epoch": 1.4215104784499801,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004804739788799089,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.18857786655426026,
|
|
"num_tokens": 32920071.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.507350778579712,
|
|
"epoch": 1.4220047449584816,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048045959667157914,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.18948892652988433,
|
|
"num_tokens": 32931391.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.581920003890991,
|
|
"epoch": 1.422499011466983,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004804452094089114,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.18723374158143996,
|
|
"num_tokens": 32941831.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.553662967681885,
|
|
"epoch": 1.4229932779754844,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004804308170922597,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.19095309525728227,
|
|
"num_tokens": 32952949.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.628994131088257,
|
|
"epoch": 1.4234875444839858,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004804164197219779,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.18082363307476043,
|
|
"num_tokens": 32964411.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.621307468414306,
|
|
"epoch": 1.423981810992487,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004804020172984204,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.18483766168355942,
|
|
"num_tokens": 32975484.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.534967088699341,
|
|
"epoch": 1.4244760775009886,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048038760982194135,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19126868695020677,
|
|
"num_tokens": 32986691.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.553135633468628,
|
|
"epoch": 1.4249703440094899,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004803731972928954,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.1891745522618294,
|
|
"num_tokens": 32998357.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.597092151641846,
|
|
"epoch": 1.4254646105179913,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048035877971163674,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.1867652952671051,
|
|
"num_tokens": 33009451.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.484658145904541,
|
|
"epoch": 1.4259588770264928,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004803443570785203,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19013091474771499,
|
|
"num_tokens": 33020143.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.499288892745971,
|
|
"epoch": 1.426453143534994,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048032992939390086,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.19542147517204284,
|
|
"num_tokens": 33031448.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.625458812713623,
|
|
"epoch": 1.4269474100434953,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004803154966581333,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.18488842695951463,
|
|
"num_tokens": 33041545.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.55997862815857,
|
|
"epoch": 1.4274416765519968,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048030105887157253,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.18963631689548494,
|
|
"num_tokens": 33051681.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.627289962768555,
|
|
"epoch": 1.4279359430604983,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048028661603457406,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.18297496289014817,
|
|
"num_tokens": 33062735.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.5332865715026855,
|
|
"epoch": 1.4284302095689996,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004802721681474929,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.19902900457382203,
|
|
"num_tokens": 33073975.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.560697460174561,
|
|
"epoch": 1.428924476077501,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048025771521068456,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.1870541453361511,
|
|
"num_tokens": 33086928.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.633601808547974,
|
|
"epoch": 1.4294187425860023,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048024325722450454,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.18528334349393843,
|
|
"num_tokens": 33099073.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.621482276916504,
|
|
"epoch": 1.4299130090945038,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004802287941893087,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.18068507611751555,
|
|
"num_tokens": 33110245.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.566349697113037,
|
|
"epoch": 1.430407275603005,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004802143261054525,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.18283815383911134,
|
|
"num_tokens": 33121659.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.540917873382568,
|
|
"epoch": 1.4309015421115066,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00048019985297329215,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1821035772562027,
|
|
"num_tokens": 33133296.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.579281806945801,
|
|
"epoch": 1.431395808620008,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004801853747931836,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.18496647030115126,
|
|
"num_tokens": 33145069.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.6217607975006105,
|
|
"epoch": 1.4318900751285093,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048017089156548293,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.1836545631289482,
|
|
"num_tokens": 33156089.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.585944318771363,
|
|
"epoch": 1.4323843416370106,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048015640329054655,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.18700124323368073,
|
|
"num_tokens": 33168300.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.546902990341186,
|
|
"epoch": 1.432878608145512,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048014190996873075,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.19913600534200668,
|
|
"num_tokens": 33179072.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.577807283401489,
|
|
"epoch": 1.4333728746540135,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048012741160039223,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.1894232988357544,
|
|
"num_tokens": 33190888.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.535152816772461,
|
|
"epoch": 1.4338671411625148,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004801129081858875,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.18402993977069854,
|
|
"num_tokens": 33202747.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.616452980041504,
|
|
"epoch": 1.4343614076710163,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004800983997255735,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.18142681568861008,
|
|
"num_tokens": 33213917.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.602930068969727,
|
|
"epoch": 1.4348556741795175,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004800838862198069,
|
|
"loss": 5.2698,
|
|
"mean_token_accuracy": 0.18481141626834868,
|
|
"num_tokens": 33223924.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.525443744659424,
|
|
"epoch": 1.435349940688019,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000480069367668945,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.18904316872358323,
|
|
"num_tokens": 33234487.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.538818073272705,
|
|
"epoch": 1.4358442071965203,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048005484407334474,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.19146053045988082,
|
|
"num_tokens": 33245585.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.498763370513916,
|
|
"epoch": 1.4363384737050218,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004800403154333636,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.19642590135335922,
|
|
"num_tokens": 33256545.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.5143757343292235,
|
|
"epoch": 1.4368327402135233,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004800257817493589,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18903917223215103,
|
|
"num_tokens": 33267946.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.54251914024353,
|
|
"epoch": 1.4373270067220245,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048001124302168814,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19021065831184386,
|
|
"num_tokens": 33279099.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.6197246551513675,
|
|
"epoch": 1.4378212732305258,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004799966992507089,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.1829625755548477,
|
|
"num_tokens": 33290544.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.5823205471038815,
|
|
"epoch": 1.4383155397390273,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047998215043677914,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.19457839876413346,
|
|
"num_tokens": 33302317.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.5433385372161865,
|
|
"epoch": 1.4388098062475287,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004799675965802567,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.19108469486236573,
|
|
"num_tokens": 33313553.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.590180826187134,
|
|
"epoch": 1.43930407275603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047995303768149955,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18762049078941345,
|
|
"num_tokens": 33324610.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.51207857131958,
|
|
"epoch": 1.4397983392645315,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004799384737408659,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.18939408361911775,
|
|
"num_tokens": 33335562.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.657593822479248,
|
|
"epoch": 1.4402926057730328,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047992390475871396,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.1770044445991516,
|
|
"num_tokens": 33346778.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.586666488647461,
|
|
"epoch": 1.4407868722815342,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004799093307354022,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.18101177662611007,
|
|
"num_tokens": 33358712.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.5600501537323,
|
|
"epoch": 1.4412811387900355,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004798947516712891,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.1855143278837204,
|
|
"num_tokens": 33369293.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.637475633621216,
|
|
"epoch": 1.441775405298537,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047988016756673335,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.1813728243112564,
|
|
"num_tokens": 33383119.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.640036535263062,
|
|
"epoch": 1.4422696718070385,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004798655784220937,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.18696243911981583,
|
|
"num_tokens": 33395334.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.458930826187133,
|
|
"epoch": 1.4427639383155397,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000479850984237729,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.19842140078544618,
|
|
"num_tokens": 33406676.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.591583728790283,
|
|
"epoch": 1.443258204824041,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004798363850139983,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.18125992268323898,
|
|
"num_tokens": 33419153.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.564644908905029,
|
|
"epoch": 1.4437524713325425,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004798217807512608,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19350000470876694,
|
|
"num_tokens": 33430146.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.608479356765747,
|
|
"epoch": 1.444246737841044,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047980717144987574,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.17655962258577346,
|
|
"num_tokens": 33441484.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.603740787506103,
|
|
"epoch": 1.4447410043495452,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047979255711020236,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.18883455395698548,
|
|
"num_tokens": 33451817.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.560500717163086,
|
|
"epoch": 1.4452352708580467,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004797779377326004,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.18980128318071365,
|
|
"num_tokens": 33463805.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.541805267333984,
|
|
"epoch": 1.445729537366548,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004797633133174295,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.18026009649038316,
|
|
"num_tokens": 33475931.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.596223258972168,
|
|
"epoch": 1.4462238038750495,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004797486838650491,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.18546245247125626,
|
|
"num_tokens": 33487306.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.527856397628784,
|
|
"epoch": 1.4467180703835507,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004797340493758195,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.18578239381313325,
|
|
"num_tokens": 33499049.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.5273681640625,
|
|
"epoch": 1.4472123368920522,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004797194098501004,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.18957515805959702,
|
|
"num_tokens": 33509626.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.58604588508606,
|
|
"epoch": 1.4477066034005537,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004797047652882521,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.18178920149803163,
|
|
"num_tokens": 33521510.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.578613901138306,
|
|
"epoch": 1.448200869909055,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047969011569063487,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.18981773555278778,
|
|
"num_tokens": 33532622.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.500091648101806,
|
|
"epoch": 1.4486951364175564,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004796754610576091,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19658045172691346,
|
|
"num_tokens": 33544196.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.596436309814453,
|
|
"epoch": 1.4491894029260577,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047966080138953505,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18191457092761992,
|
|
"num_tokens": 33554927.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.607356214523316,
|
|
"epoch": 1.4496836694345592,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004796461366867736,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.17914806455373763,
|
|
"num_tokens": 33566412.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.5341369152069095,
|
|
"epoch": 1.4501779359430604,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047963146694968546,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.18858973681926727,
|
|
"num_tokens": 33578010.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.555627298355103,
|
|
"epoch": 1.450672202451562,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004796167921786315,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.18082652240991592,
|
|
"num_tokens": 33589647.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.673175573348999,
|
|
"epoch": 1.4511664689600634,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047960211237397274,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.1768357053399086,
|
|
"num_tokens": 33601292.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.654656934738159,
|
|
"epoch": 1.4516607354685647,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047958742753607015,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18487266600131988,
|
|
"num_tokens": 33612878.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.576922607421875,
|
|
"epoch": 1.452155001977066,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047957273766528524,
|
|
"loss": 5.3048,
|
|
"mean_token_accuracy": 0.1896791473031044,
|
|
"num_tokens": 33625680.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.498727321624756,
|
|
"epoch": 1.4526492684855674,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004795580427619791,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.18795981556177138,
|
|
"num_tokens": 33637066.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.599577713012695,
|
|
"epoch": 1.453143534994069,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047954334282651357,
|
|
"loss": 5.4137,
|
|
"mean_token_accuracy": 0.1780152678489685,
|
|
"num_tokens": 33648213.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.639522647857666,
|
|
"epoch": 1.4536378015025702,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004795286378592499,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.18515968322753906,
|
|
"num_tokens": 33661582.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.562168788909912,
|
|
"epoch": 1.4541320680110716,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004795139278605501,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.19517935961484909,
|
|
"num_tokens": 33673122.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.562953138351441,
|
|
"epoch": 1.454626334519573,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047949921283077594,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.1911136895418167,
|
|
"num_tokens": 33683926.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.526447582244873,
|
|
"epoch": 1.4551206010280744,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004794844927702894,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18930965662002563,
|
|
"num_tokens": 33694529.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.593991136550903,
|
|
"epoch": 1.4556148675365757,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004794697676794526,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18855096101760865,
|
|
"num_tokens": 33704618.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.5640575885772705,
|
|
"epoch": 1.4561091340450771,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004794550375586278,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18387958258390427,
|
|
"num_tokens": 33716354.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.52382984161377,
|
|
"epoch": 1.4566034005535786,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004794403024081774,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.1902504161000252,
|
|
"num_tokens": 33728065.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.584285306930542,
|
|
"epoch": 1.4570976670620799,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004794255622284638,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.18333973437547685,
|
|
"num_tokens": 33740207.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.608087825775146,
|
|
"epoch": 1.4575919335705811,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047941081701984966,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.18143415749073027,
|
|
"num_tokens": 33750768.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.532852363586426,
|
|
"epoch": 1.4580862000790826,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.00047939606678269774,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.1894086182117462,
|
|
"num_tokens": 33762029.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.522656965255737,
|
|
"epoch": 1.4585804665875841,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004793813115173708,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1906030535697937,
|
|
"num_tokens": 33773483.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.591189384460449,
|
|
"epoch": 1.4590747330960854,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000479366551224232,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18499938249588013,
|
|
"num_tokens": 33784404.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.511642646789551,
|
|
"epoch": 1.4595689996045869,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004793517859036443,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.18774395883083345,
|
|
"num_tokens": 33794625.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.536852836608887,
|
|
"epoch": 1.4600632661130881,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004793370155559709,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.18581661432981492,
|
|
"num_tokens": 33805872.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.500100231170654,
|
|
"epoch": 1.4605575326215896,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004793222401815753,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20004004389047622,
|
|
"num_tokens": 33815979.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.562071466445923,
|
|
"epoch": 1.4610517991300909,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004793074597808208,
|
|
"loss": 5.3397,
|
|
"mean_token_accuracy": 0.18641309440135956,
|
|
"num_tokens": 33827571.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.543570041656494,
|
|
"epoch": 1.4615460656385924,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047929267435407115,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.1804566964507103,
|
|
"num_tokens": 33838749.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.581147527694702,
|
|
"epoch": 1.4620403321470938,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047927788390168997,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.18315261453390122,
|
|
"num_tokens": 33849494.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.614911985397339,
|
|
"epoch": 1.462534598655595,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047926308842404126,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.18392074555158616,
|
|
"num_tokens": 33860586.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.516197299957275,
|
|
"epoch": 1.4630288651640964,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004792482879214888,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20478178560733795,
|
|
"num_tokens": 33871261.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.531460285186768,
|
|
"epoch": 1.4635231316725978,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004792334823943968,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.19377671778202057,
|
|
"num_tokens": 33883160.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.588959169387818,
|
|
"epoch": 1.4640173981810993,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004792186718431294,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.19160519689321517,
|
|
"num_tokens": 33894250.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.512599086761474,
|
|
"epoch": 1.4645116646896006,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000479203856268051,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.18476281613111495,
|
|
"num_tokens": 33905076.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.477286005020142,
|
|
"epoch": 1.465005931198102,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004791890356695261,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.18740978240966796,
|
|
"num_tokens": 33916982.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.62805871963501,
|
|
"epoch": 1.4655001977066033,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004791742100479193,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.18320221155881883,
|
|
"num_tokens": 33928306.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.674407815933227,
|
|
"epoch": 1.4659944642151048,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004791593794035952,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18029894977807998,
|
|
"num_tokens": 33940371.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.566388702392578,
|
|
"epoch": 1.466488730723606,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004791445437369187,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.18236166387796401,
|
|
"num_tokens": 33952250.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.574384069442749,
|
|
"epoch": 1.4669829972321076,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004791297030482547,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.18584947884082795,
|
|
"num_tokens": 33963426.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.516686582565308,
|
|
"epoch": 1.467477263740609,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004791148573379684,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1821470558643341,
|
|
"num_tokens": 33974982.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.5599432468414305,
|
|
"epoch": 1.4679715302491103,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047910000660642487,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.19064150005578995,
|
|
"num_tokens": 33986413.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.608616018295288,
|
|
"epoch": 1.4684657967576116,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004790851508539896,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.19308703541755676,
|
|
"num_tokens": 33996821.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.517739772796631,
|
|
"epoch": 1.468960063266113,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004790702900810279,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.18195559382438659,
|
|
"num_tokens": 34008817.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.5564850807189945,
|
|
"epoch": 1.4694543297746145,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047905542428790536,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.19241035878658294,
|
|
"num_tokens": 34020051.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.498719644546509,
|
|
"epoch": 1.4699485962831158,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004790405534749878,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.19930285662412645,
|
|
"num_tokens": 34032764.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.542438936233521,
|
|
"epoch": 1.4704428627916173,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000479025677642641,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.18873116075992585,
|
|
"num_tokens": 34042868.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.552968215942383,
|
|
"epoch": 1.4709371293001186,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004790107967912309,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.18717188388109207,
|
|
"num_tokens": 34054807.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.634930515289307,
|
|
"epoch": 1.47143139580862,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047899591092112343,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.18473067730665207,
|
|
"num_tokens": 34066378.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.615357065200806,
|
|
"epoch": 1.4719256623171213,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000478981020032685,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.17699342221021652,
|
|
"num_tokens": 34078267.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.557473373413086,
|
|
"epoch": 1.4724199288256228,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047896612412628184,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.1794321969151497,
|
|
"num_tokens": 34090356.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.608606147766113,
|
|
"epoch": 1.4729141953341243,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047895122320228026,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.19032384008169173,
|
|
"num_tokens": 34101143.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.545310068130493,
|
|
"epoch": 1.4734084618426255,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047893631726104703,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.1873413622379303,
|
|
"num_tokens": 34112655.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.565098714828491,
|
|
"epoch": 1.4739027283511268,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004789214063029488,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.1873139277100563,
|
|
"num_tokens": 34123825.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.545733880996704,
|
|
"epoch": 1.4743969948596283,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047890649032835233,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.18840881288051606,
|
|
"num_tokens": 34135416.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.561224174499512,
|
|
"epoch": 1.4748912613681298,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004788915693376245,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18459036946296692,
|
|
"num_tokens": 34146797.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.631625986099243,
|
|
"epoch": 1.475385527876631,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047887664333113244,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.1787152260541916,
|
|
"num_tokens": 34158749.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.5761114120483395,
|
|
"epoch": 1.4758797943851325,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004788617123092434,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.192367222905159,
|
|
"num_tokens": 34169694.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.536347818374634,
|
|
"epoch": 1.4763740608936338,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004788467762723245,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.1832881137728691,
|
|
"num_tokens": 34182166.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.580696535110474,
|
|
"epoch": 1.4768683274021353,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047883183522074335,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.19334750771522521,
|
|
"num_tokens": 34193651.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.612848854064941,
|
|
"epoch": 1.4773625939106365,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047881688915486743,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18250785171985626,
|
|
"num_tokens": 34204173.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.511914587020874,
|
|
"epoch": 1.477856860419138,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047880193807506446,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.19631754904985427,
|
|
"num_tokens": 34214872.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.563386154174805,
|
|
"epoch": 1.4783511269276395,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004787869819817021,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.1884036034345627,
|
|
"num_tokens": 34226433.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.54158878326416,
|
|
"epoch": 1.4788453934361407,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047877202087514843,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.1883425697684288,
|
|
"num_tokens": 34238047.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.56583194732666,
|
|
"epoch": 1.4793396599446422,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004787570547557715,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.18675317913293837,
|
|
"num_tokens": 34250445.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.558454370498657,
|
|
"epoch": 1.4798339264531435,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047874208362393925,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.19121613055467607,
|
|
"num_tokens": 34261324.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.5375302791595455,
|
|
"epoch": 1.480328192961645,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047872710748002024,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18409102112054826,
|
|
"num_tokens": 34272074.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.510438871383667,
|
|
"epoch": 1.4808224594701462,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004787121263243827,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.18520420491695405,
|
|
"num_tokens": 34282958.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.586644220352173,
|
|
"epoch": 1.4813167259786477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047869714015739533,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.19317712187767028,
|
|
"num_tokens": 34294999.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.570887327194214,
|
|
"epoch": 1.4818109924871492,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047868214897942675,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.18777282536029816,
|
|
"num_tokens": 34305363.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.5224199295043945,
|
|
"epoch": 1.4823052589956505,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004786671527908456,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.18557692766189576,
|
|
"num_tokens": 34317467.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.657279777526855,
|
|
"epoch": 1.4827995255041517,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000478652151592021,
|
|
"loss": 5.3523,
|
|
"mean_token_accuracy": 0.18103250861167908,
|
|
"num_tokens": 34331058.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.4827995255041517,
|
|
"eval_entropy": 5.428649393248236,
|
|
"eval_loss": 5.362654209136963,
|
|
"eval_mean_token_accuracy": 0.19102040012384253,
|
|
"eval_num_tokens": 34331058.0,
|
|
"eval_runtime": 26.705,
|
|
"eval_samples_per_second": 1217.486,
|
|
"eval_steps_per_second": 152.219,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.5630574226379395,
|
|
"epoch": 1.4832937920126532,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004786371453833217,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.1870290145277977,
|
|
"num_tokens": 34342593.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.529469394683838,
|
|
"epoch": 1.4837880585211547,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047862213416511717,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.18581428229808808,
|
|
"num_tokens": 34353507.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.474502992630005,
|
|
"epoch": 1.484282325029656,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004786071179377766,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.19689220190048218,
|
|
"num_tokens": 34365606.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.567005014419555,
|
|
"epoch": 1.4847765915381574,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004785920967016692,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.18752921223640442,
|
|
"num_tokens": 34375925.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.6123768329620365,
|
|
"epoch": 1.4852708580466587,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047857707045716473,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.18295256644487382,
|
|
"num_tokens": 34387806.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.505084419250489,
|
|
"epoch": 1.4857651245551602,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047856203920463273,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.19526824206113816,
|
|
"num_tokens": 34400367.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.5272284030914305,
|
|
"epoch": 1.4862593910636615,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000478547002944443,
|
|
"loss": 5.2787,
|
|
"mean_token_accuracy": 0.18817630857229234,
|
|
"num_tokens": 34412082.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.568836784362793,
|
|
"epoch": 1.486753657572163,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004785319616769654,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19133568406105042,
|
|
"num_tokens": 34423315.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.558071851730347,
|
|
"epoch": 1.4872479240806644,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047851691540256995,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.1836305156350136,
|
|
"num_tokens": 34433748.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.520220327377319,
|
|
"epoch": 1.4877421905891657,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047850186412162684,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.19150304943323135,
|
|
"num_tokens": 34444425.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.5826630115509035,
|
|
"epoch": 1.488236457097667,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004784868078345063,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18663082718849183,
|
|
"num_tokens": 34456350.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.598330354690551,
|
|
"epoch": 1.4887307236061684,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004784717465415787,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.18225550204515456,
|
|
"num_tokens": 34466606.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.5908308029174805,
|
|
"epoch": 1.48922499011467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047845668024321455,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.18252890706062316,
|
|
"num_tokens": 34478085.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.558799076080322,
|
|
"epoch": 1.4897192566231712,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004784416089397846,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.18630673587322236,
|
|
"num_tokens": 34488437.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.596774101257324,
|
|
"epoch": 1.4902135231316727,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004784265326316594,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.18570556193590165,
|
|
"num_tokens": 34499999.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.60131573677063,
|
|
"epoch": 1.490707789640174,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047841145131921,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18726940155029298,
|
|
"num_tokens": 34510509.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.601349496841431,
|
|
"epoch": 1.4912020561486754,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047839636500280724,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.18524722009897232,
|
|
"num_tokens": 34521192.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.61033182144165,
|
|
"epoch": 1.4916963226571767,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004783812736828225,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18767644762992858,
|
|
"num_tokens": 34532401.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.6044878482818605,
|
|
"epoch": 1.4921905891656781,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047836617735962675,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.18746606558561324,
|
|
"num_tokens": 34544306.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.491836881637573,
|
|
"epoch": 1.4926848556741796,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004783510760335915,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.18964152932167053,
|
|
"num_tokens": 34557122.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.506884384155273,
|
|
"epoch": 1.493179122182681,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004783359697050883,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1929740011692047,
|
|
"num_tokens": 34568302.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.587466526031494,
|
|
"epoch": 1.4936733886911822,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047832085837448864,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.19335301965475082,
|
|
"num_tokens": 34578536.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.538439083099365,
|
|
"epoch": 1.4941676551996836,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047830574204216436,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1883515387773514,
|
|
"num_tokens": 34590333.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.608569192886352,
|
|
"epoch": 1.4946619217081851,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004782906207084873,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.1793975606560707,
|
|
"num_tokens": 34601447.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.588088178634644,
|
|
"epoch": 1.4951561882166864,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004782754943738294,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.18221147507429122,
|
|
"num_tokens": 34613559.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.5317565441131595,
|
|
"epoch": 1.4956504547251879,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004782603630385628,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.18709374517202376,
|
|
"num_tokens": 34624354.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.599626970291138,
|
|
"epoch": 1.4961447212336891,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004782452267030598,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.18020368367433548,
|
|
"num_tokens": 34636093.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.655661582946777,
|
|
"epoch": 1.4966389877421906,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004782300853676926,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19241878986358643,
|
|
"num_tokens": 34647503.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.5464366436004635,
|
|
"epoch": 1.4971332542506919,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047821493903283383,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.18412718921899796,
|
|
"num_tokens": 34660258.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.554385042190551,
|
|
"epoch": 1.4976275207591934,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000478199787698856,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.185629640519619,
|
|
"num_tokens": 34672199.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.560821056365967,
|
|
"epoch": 1.4981217872676948,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047818463136613184,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19207804948091506,
|
|
"num_tokens": 34684419.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.414809799194336,
|
|
"epoch": 1.498616053776196,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047816947003503425,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.2045839786529541,
|
|
"num_tokens": 34695649.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.60502552986145,
|
|
"epoch": 1.4991103202846974,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047815430370593627,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.18858781903982164,
|
|
"num_tokens": 34707019.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.54815411567688,
|
|
"epoch": 1.4996045867931989,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047813913237921077,
|
|
"loss": 5.2224,
|
|
"mean_token_accuracy": 0.18993597626686096,
|
|
"num_tokens": 34717609.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.55745792388916,
|
|
"epoch": 1.5000988533017003,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004781239560552312,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.18290771245956422,
|
|
"num_tokens": 34728607.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.476379871368408,
|
|
"epoch": 1.5005931198102016,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047810877473437077,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.1894824281334877,
|
|
"num_tokens": 34739537.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.557500886917114,
|
|
"epoch": 1.501087386318703,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047809358841700297,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.18850425779819488,
|
|
"num_tokens": 34751814.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.61226897239685,
|
|
"epoch": 1.5015816528272046,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004780783971035014,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19012539088726044,
|
|
"num_tokens": 34762647.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.561236715316772,
|
|
"epoch": 1.5020759193357058,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004780632007942397,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.18544408828020095,
|
|
"num_tokens": 34774157.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.521604013442993,
|
|
"epoch": 1.502570185844207,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004780479994895918,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.18947969526052474,
|
|
"num_tokens": 34785244.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.571971035003662,
|
|
"epoch": 1.5030644523527086,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004780327931899316,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.19107118099927903,
|
|
"num_tokens": 34797090.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.504898929595948,
|
|
"epoch": 1.50355871886121,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047801758189563315,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.18651082068681718,
|
|
"num_tokens": 34808598.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.549701404571533,
|
|
"epoch": 1.5040529853697113,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047800236560707076,
|
|
"loss": 5.3235,
|
|
"mean_token_accuracy": 0.18831779807806015,
|
|
"num_tokens": 34820619.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.545615720748901,
|
|
"epoch": 1.5045472518782126,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047798714432461864,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.1891194000840187,
|
|
"num_tokens": 34832463.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.60429539680481,
|
|
"epoch": 1.505041518386714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004779719180486513,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18763417303562163,
|
|
"num_tokens": 34844255.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.545992517471314,
|
|
"epoch": 1.5055357848952156,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004779566867795433,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.18274773508310319,
|
|
"num_tokens": 34857215.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.524267911911011,
|
|
"epoch": 1.5060300514037168,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047794145051766935,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.19686075299978256,
|
|
"num_tokens": 34868831.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.561470460891724,
|
|
"epoch": 1.5065243179122183,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004779262092634042,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1954202100634575,
|
|
"num_tokens": 34879258.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.551108407974243,
|
|
"epoch": 1.5070185844207198,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047791096301712276,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.1841468021273613,
|
|
"num_tokens": 34891492.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.478701162338257,
|
|
"epoch": 1.507512850929221,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047789571177920024,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18375557363033296,
|
|
"num_tokens": 34901836.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.563991737365723,
|
|
"epoch": 1.5080071174377223,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004778804555500117,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.1879316121339798,
|
|
"num_tokens": 34913892.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.634564447402954,
|
|
"epoch": 1.5085013839462238,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004778651943299324,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.18420514464378357,
|
|
"num_tokens": 34925657.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.593143129348755,
|
|
"epoch": 1.5089956504547253,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000477849928119338,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.1826822742819786,
|
|
"num_tokens": 34937921.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.524355936050415,
|
|
"epoch": 1.5094899169632265,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004778346569186038,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.1891760140657425,
|
|
"num_tokens": 34948742.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.506691408157349,
|
|
"epoch": 1.5099841834717278,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047781938072810555,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.19083022475242614,
|
|
"num_tokens": 34960912.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.613119840621948,
|
|
"epoch": 1.5104784499802293,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047780409954821914,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18563404977321624,
|
|
"num_tokens": 34971188.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.584841060638428,
|
|
"epoch": 1.5109727164887308,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047778881337932037,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.18516241163015365,
|
|
"num_tokens": 34983316.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.641468572616577,
|
|
"epoch": 1.511466982997232,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047777352222178537,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.17472305446863173,
|
|
"num_tokens": 34995698.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.566215324401855,
|
|
"epoch": 1.5119612495057335,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047775822607599023,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.1953329935669899,
|
|
"num_tokens": 35007296.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.638717603683472,
|
|
"epoch": 1.512455516014235,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004777429249423113,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.18256236761808395,
|
|
"num_tokens": 35019126.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.53805627822876,
|
|
"epoch": 1.5129497825227363,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00047772761882112493,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.19288395196199418,
|
|
"num_tokens": 35030213.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.462105703353882,
|
|
"epoch": 1.5134440490312375,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004777123077128077,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18960463255643845,
|
|
"num_tokens": 35043134.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.6216167449951175,
|
|
"epoch": 1.513938315539739,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004776969916177363,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.1844857931137085,
|
|
"num_tokens": 35055484.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.598306369781494,
|
|
"epoch": 1.5144325820482405,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004776816705362874,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.18162624686956405,
|
|
"num_tokens": 35067037.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.490774488449096,
|
|
"epoch": 1.5149268485567418,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004776663444688381,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18556499779224395,
|
|
"num_tokens": 35078340.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.589513874053955,
|
|
"epoch": 1.515421115065243,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004776510134157651,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.18722173422574998,
|
|
"num_tokens": 35090526.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.5688684463500975,
|
|
"epoch": 1.5159153815737447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047763567737744576,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18197028040885926,
|
|
"num_tokens": 35103757.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.516309309005737,
|
|
"epoch": 1.516409648082246,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004776203363542574,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19033866971731186,
|
|
"num_tokens": 35115694.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.551747989654541,
|
|
"epoch": 1.5169039145907472,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004776049903465773,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.19618955105543137,
|
|
"num_tokens": 35126691.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.556742525100708,
|
|
"epoch": 1.5173981810992487,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000477589639354783,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.18847395479679108,
|
|
"num_tokens": 35137851.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.546887397766113,
|
|
"epoch": 1.5178924476077502,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004775742833792521,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18309759646654128,
|
|
"num_tokens": 35148583.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.576987266540527,
|
|
"epoch": 1.5183867141162515,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004775589224203625,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18549445271492004,
|
|
"num_tokens": 35161469.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.495751619338989,
|
|
"epoch": 1.5188809806247527,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047754355647849185,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.19699050933122636,
|
|
"num_tokens": 35172349.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.478640747070313,
|
|
"epoch": 1.5193752471332542,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047752818555401845,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.18791319727897643,
|
|
"num_tokens": 35183118.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.602480125427246,
|
|
"epoch": 1.5198695136417557,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047751280964732014,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1881476029753685,
|
|
"num_tokens": 35195702.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.678789758682251,
|
|
"epoch": 1.520363780150257,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047749742875877535,
|
|
"loss": 5.4165,
|
|
"mean_token_accuracy": 0.17397448569536209,
|
|
"num_tokens": 35207356.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.5697776794433596,
|
|
"epoch": 1.5208580466587585,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004774820428887624,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.1863084092736244,
|
|
"num_tokens": 35219207.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.541266393661499,
|
|
"epoch": 1.52135231316726,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004774666520376597,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.18865794390439988,
|
|
"num_tokens": 35230396.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.558375263214112,
|
|
"epoch": 1.5218465796757612,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004774512562058461,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.18753491938114167,
|
|
"num_tokens": 35242320.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.651818704605103,
|
|
"epoch": 1.5223408461842625,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004774358553937001,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.18144586235284804,
|
|
"num_tokens": 35252926.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.652591943740845,
|
|
"epoch": 1.522835112692764,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004774204496016006,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.1785482347011566,
|
|
"num_tokens": 35263833.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.528440666198731,
|
|
"epoch": 1.5233293792012654,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047740503882992677,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.1803864762187004,
|
|
"num_tokens": 35274951.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.609523105621338,
|
|
"epoch": 1.5238236457097667,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004773896230790575,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.18514057993888855,
|
|
"num_tokens": 35287940.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.547504138946533,
|
|
"epoch": 1.524317912218268,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047737420234937215,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.19384041130542756,
|
|
"num_tokens": 35299321.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.506019401550293,
|
|
"epoch": 1.5248121787267694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047735877664125,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19049740433692933,
|
|
"num_tokens": 35310181.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.573339986801147,
|
|
"epoch": 1.525306445235271,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047734334595507045,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.18469940274953842,
|
|
"num_tokens": 35320435.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.567989110946655,
|
|
"epoch": 1.5258007117437722,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004773279102912134,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.17989310324192048,
|
|
"num_tokens": 35332533.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.516954851150513,
|
|
"epoch": 1.5262949782522737,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004773124696500582,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.20097929686307908,
|
|
"num_tokens": 35344289.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.5695765018463135,
|
|
"epoch": 1.5267892447607752,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004772970240319849,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.190805883705616,
|
|
"num_tokens": 35355679.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.482913494110107,
|
|
"epoch": 1.5272835112692764,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047728157343737346,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.19412298053503035,
|
|
"num_tokens": 35367489.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.512883996963501,
|
|
"epoch": 1.5277777777777777,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047726611786660396,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19173542261123658,
|
|
"num_tokens": 35378349.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.544522905349732,
|
|
"epoch": 1.5282720442862792,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047725065732005654,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.186369626224041,
|
|
"num_tokens": 35388927.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.522233152389527,
|
|
"epoch": 1.5287663107947806,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004772351917981115,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.18986246585845948,
|
|
"num_tokens": 35401859.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.641986751556397,
|
|
"epoch": 1.529260577303282,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004772197213011494,
|
|
"loss": 5.2816,
|
|
"mean_token_accuracy": 0.18406756073236466,
|
|
"num_tokens": 35412735.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.538111639022827,
|
|
"epoch": 1.5297548438117832,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004772042458295509,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.1897275075316429,
|
|
"num_tokens": 35422960.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.611293983459473,
|
|
"epoch": 1.5302491103202847,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047718876538369655,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.18497169613838196,
|
|
"num_tokens": 35435054.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.561801338195801,
|
|
"epoch": 1.5307433768287861,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047717327996396716,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.18365446776151656,
|
|
"num_tokens": 35447388.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.5975236892700195,
|
|
"epoch": 1.5312376433372874,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004771577895707437,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1865108221769333,
|
|
"num_tokens": 35459181.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.503553247451782,
|
|
"epoch": 1.5317319098457889,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004771422942044073,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.18961346745491028,
|
|
"num_tokens": 35469978.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.477680778503418,
|
|
"epoch": 1.5322261763542904,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004771267938653391,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.19740347266197206,
|
|
"num_tokens": 35482196.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.4932035446167,
|
|
"epoch": 1.5327204428627916,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004771112885539204,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.20580088645219802,
|
|
"num_tokens": 35493025.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.513411235809326,
|
|
"epoch": 1.533214709371293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047709577827053257,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.18928309977054597,
|
|
"num_tokens": 35504379.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.552103281021118,
|
|
"epoch": 1.5337089758797944,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047708026301555736,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.19930283725261688,
|
|
"num_tokens": 35515401.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.615586137771606,
|
|
"epoch": 1.5342032423882959,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047706474278937626,
|
|
"loss": 5.311,
|
|
"mean_token_accuracy": 0.18804558217525483,
|
|
"num_tokens": 35527625.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.583318090438842,
|
|
"epoch": 1.5346975088967971,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047704921759237116,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.18548008799552917,
|
|
"num_tokens": 35539484.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.627565622329712,
|
|
"epoch": 1.5351917754052984,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047703368742492403,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.17987337410449983,
|
|
"num_tokens": 35550362.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.5681843757629395,
|
|
"epoch": 1.5356860419137999,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004770181522874167,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.190787410736084,
|
|
"num_tokens": 35561564.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.512441158294678,
|
|
"epoch": 1.5361803084223014,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004770026121802316,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.19414934664964675,
|
|
"num_tokens": 35572216.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.488073205947876,
|
|
"epoch": 1.5366745749308026,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004769870671037509,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.2007207527756691,
|
|
"num_tokens": 35584471.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.519488382339477,
|
|
"epoch": 1.537168841439304,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047697151705835693,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.19247497022151946,
|
|
"num_tokens": 35596551.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.527089309692383,
|
|
"epoch": 1.5376631079478056,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004769559620444324,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19188157618045806,
|
|
"num_tokens": 35607425.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.491629219055175,
|
|
"epoch": 1.5381573744563068,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047694040206235983,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.19301111847162247,
|
|
"num_tokens": 35618900.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.548868036270141,
|
|
"epoch": 1.538651640964808,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000476924837112522,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.19468343406915664,
|
|
"num_tokens": 35630126.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.545919942855835,
|
|
"epoch": 1.5391459074733096,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047690926719530193,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.192589607834816,
|
|
"num_tokens": 35642406.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.4919017314910885,
|
|
"epoch": 1.539640173981811,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047689369231108253,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.18672604709863663,
|
|
"num_tokens": 35654701.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.6244041442871096,
|
|
"epoch": 1.5401344404903123,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000476878112460247,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.1814424455165863,
|
|
"num_tokens": 35665668.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.572934341430664,
|
|
"epoch": 1.5406287069988136,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047686252764317854,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19284992218017577,
|
|
"num_tokens": 35676940.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.572154521942139,
|
|
"epoch": 1.5411229735073153,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047684693786026054,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.17687064856290818,
|
|
"num_tokens": 35687860.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.501327753067017,
|
|
"epoch": 1.5416172400158166,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047683134311187663,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.1954587772488594,
|
|
"num_tokens": 35698349.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.525604391098023,
|
|
"epoch": 1.5421115065243178,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047681574339841044,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.19579585194587706,
|
|
"num_tokens": 35709649.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.512925052642823,
|
|
"epoch": 1.5426057730328193,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047680013872024546,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.19461624771356584,
|
|
"num_tokens": 35720806.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.586317920684815,
|
|
"epoch": 1.5431000395413208,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004767845290777659,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.1907508611679077,
|
|
"num_tokens": 35732044.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.514313220977783,
|
|
"epoch": 1.543594306049822,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004767689144713556,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.1922880545258522,
|
|
"num_tokens": 35743758.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.557594680786133,
|
|
"epoch": 1.5440885725583233,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047675329490139866,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.1860923483967781,
|
|
"num_tokens": 35756184.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.537015676498413,
|
|
"epoch": 1.5445828390668248,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047673767036827947,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.18529835641384124,
|
|
"num_tokens": 35768255.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.536966466903687,
|
|
"epoch": 1.5450771055753263,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004767220408723822,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.18144666403532028,
|
|
"num_tokens": 35779111.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.590515899658203,
|
|
"epoch": 1.5455713720838276,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004767064064140915,
|
|
"loss": 5.3122,
|
|
"mean_token_accuracy": 0.18712117969989778,
|
|
"num_tokens": 35791676.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.512561178207397,
|
|
"epoch": 1.546065638592329,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004766907669937919,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.1961391642689705,
|
|
"num_tokens": 35801868.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.584035873413086,
|
|
"epoch": 1.5465599051008305,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000476675122611868,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.1820852592587471,
|
|
"num_tokens": 35812428.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.597989225387574,
|
|
"epoch": 1.5470541716093318,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000476659473268705,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.19644601196050643,
|
|
"num_tokens": 35823600.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.557652616500855,
|
|
"epoch": 1.547548438117833,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004766438189646876,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.1896715432405472,
|
|
"num_tokens": 35834988.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.565900087356567,
|
|
"epoch": 1.5480427046263345,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047662815970020086,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.19106679856777192,
|
|
"num_tokens": 35846110.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.494934463500977,
|
|
"epoch": 1.548536971134836,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004766124954756302,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19289883524179458,
|
|
"num_tokens": 35858276.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.646693420410156,
|
|
"epoch": 1.5490312376433373,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047659682629136094,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18756202459335328,
|
|
"num_tokens": 35870705.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.54431185722351,
|
|
"epoch": 1.5495255041518385,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004765811521477784,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.18714804351329803,
|
|
"num_tokens": 35882298.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.447721195220947,
|
|
"epoch": 1.55001977066034,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004765654730452682,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.1934949204325676,
|
|
"num_tokens": 35894665.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.546232986450195,
|
|
"epoch": 1.5505140371688415,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004765497889842161,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.19514468610286712,
|
|
"num_tokens": 35905893.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.59613447189331,
|
|
"epoch": 1.5510083036773428,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047653409996500803,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.1947658434510231,
|
|
"num_tokens": 35917883.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.5254072666168215,
|
|
"epoch": 1.5515025701858443,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047651840598802976,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.19460605084896088,
|
|
"num_tokens": 35929863.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.580703830718994,
|
|
"epoch": 1.5519968366943457,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004765027070536674,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.18714593052864076,
|
|
"num_tokens": 35940843.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.515906095504761,
|
|
"epoch": 1.552491103202847,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004764870031623073,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19272675216197968,
|
|
"num_tokens": 35953516.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.5293327331542965,
|
|
"epoch": 1.5529853697113483,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047647129431433566,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.1907994881272316,
|
|
"num_tokens": 35965481.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.588053369522095,
|
|
"epoch": 1.5534796362198497,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004764555805101388,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.1879993960261345,
|
|
"num_tokens": 35976434.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.563168525695801,
|
|
"epoch": 1.5539739027283512,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004764398617501035,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.1909935787320137,
|
|
"num_tokens": 35987644.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.585901212692261,
|
|
"epoch": 1.5544681692368525,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004764241380346163,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.19032102972269058,
|
|
"num_tokens": 35999630.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.635501527786255,
|
|
"epoch": 1.5549624357453538,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004764084093640641,
|
|
"loss": 5.3712,
|
|
"mean_token_accuracy": 0.1866174817085266,
|
|
"num_tokens": 36011889.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.636697387695312,
|
|
"epoch": 1.5554567022538552,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004763926757388338,
|
|
"loss": 5.3351,
|
|
"mean_token_accuracy": 0.1808294415473938,
|
|
"num_tokens": 36024131.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.522370529174805,
|
|
"epoch": 1.5559509687623567,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004763769371593124,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.19459694027900695,
|
|
"num_tokens": 36035759.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.588599157333374,
|
|
"epoch": 1.556445235270858,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004763611936258871,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.18857407420873643,
|
|
"num_tokens": 36047882.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.56195034980774,
|
|
"epoch": 1.5569395017793595,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004763454451389452,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.18682276606559753,
|
|
"num_tokens": 36058268.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.604771137237549,
|
|
"epoch": 1.557433768287861,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047632969169887407,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.18776566684246063,
|
|
"num_tokens": 36070797.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.564238595962524,
|
|
"epoch": 1.5579280347963622,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004763139333060613,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.18756757080554962,
|
|
"num_tokens": 36082858.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.560377168655395,
|
|
"epoch": 1.5584223013048635,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047629816996089464,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.1877347096800804,
|
|
"num_tokens": 36094825.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.608713436126709,
|
|
"epoch": 1.558916567813365,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047628240166376173,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18102313578128815,
|
|
"num_tokens": 36106379.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.515108966827393,
|
|
"epoch": 1.5594108343218664,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047626662841505045,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.19851206988096237,
|
|
"num_tokens": 36117137.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.531961679458618,
|
|
"epoch": 1.5599051008303677,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000476250850215149,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18189078569412231,
|
|
"num_tokens": 36128420.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.558661556243896,
|
|
"epoch": 1.560399367338869,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004762350670644453,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.19435418546199798,
|
|
"num_tokens": 36139017.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.581766510009766,
|
|
"epoch": 1.5608936338473705,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004762192789633278,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18948533535003662,
|
|
"num_tokens": 36151748.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.572039556503296,
|
|
"epoch": 1.561387900355872,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047620348591218475,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.18561292588710784,
|
|
"num_tokens": 36163114.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.568516826629638,
|
|
"epoch": 1.5618821668643732,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004761876879114048,
|
|
"loss": 5.3213,
|
|
"mean_token_accuracy": 0.1860352113842964,
|
|
"num_tokens": 36174601.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.553396129608155,
|
|
"epoch": 1.5623764333728747,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004761718849613765,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.1966896116733551,
|
|
"num_tokens": 36185081.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.562911605834961,
|
|
"epoch": 1.5628706998813762,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004761560770624886,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.18922626078128815,
|
|
"num_tokens": 36196547.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.550323152542115,
|
|
"epoch": 1.5633649663898774,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004761402642151301,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.19610561281442643,
|
|
"num_tokens": 36208115.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.5527716159820555,
|
|
"epoch": 1.5638592328983787,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004761244464196897,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.19227584153413774,
|
|
"num_tokens": 36219571.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.546177053451538,
|
|
"epoch": 1.5643534994068802,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004761086236765569,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.18882315009832382,
|
|
"num_tokens": 36232219.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.554412984848023,
|
|
"epoch": 1.5648477659153817,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004760927959861206,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.18656691759824753,
|
|
"num_tokens": 36243761.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.495314407348633,
|
|
"epoch": 1.565342032423883,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004760769633487704,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.18950630277395247,
|
|
"num_tokens": 36255466.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.535125589370727,
|
|
"epoch": 1.5658362989323842,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047606112576489574,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.18431692123413085,
|
|
"num_tokens": 36267252.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.587519645690918,
|
|
"epoch": 1.566330565440886,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004760452832348862,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.19298448860645295,
|
|
"num_tokens": 36278149.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.669652605056763,
|
|
"epoch": 1.5668248319493872,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047602943575913146,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.19089186042547227,
|
|
"num_tokens": 36290583.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.55829815864563,
|
|
"epoch": 1.5673190984578884,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004760135833380214,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.19085127264261245,
|
|
"num_tokens": 36301508.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.522317218780517,
|
|
"epoch": 1.56781336496639,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000475997725971946,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.1936734363436699,
|
|
"num_tokens": 36312488.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.55488953590393,
|
|
"epoch": 1.5683076314748914,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004759818636612954,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.19084256887435913,
|
|
"num_tokens": 36323263.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.5329734802246096,
|
|
"epoch": 1.5688018979833926,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047596599640645974,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.18156228512525557,
|
|
"num_tokens": 36336095.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.533792877197266,
|
|
"epoch": 1.569296164491894,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047595012420782946,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.18907585442066194,
|
|
"num_tokens": 36346653.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.578935670852661,
|
|
"epoch": 1.5697904310003954,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004759342470657949,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.19406040459871293,
|
|
"num_tokens": 36358190.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.555053567886352,
|
|
"epoch": 1.5702846975088969,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004759183649807467,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1881619781255722,
|
|
"num_tokens": 36369037.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.597461557388305,
|
|
"epoch": 1.5707789640173981,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004759024779530755,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.19184614717960358,
|
|
"num_tokens": 36379881.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.574033308029175,
|
|
"epoch": 1.5712732305258994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047588658598317227,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.19493326246738435,
|
|
"num_tokens": 36390927.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.568516683578491,
|
|
"epoch": 1.571767497034401,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047587068907142783,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.18694723546504974,
|
|
"num_tokens": 36402398.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.469684886932373,
|
|
"epoch": 1.5722617635429024,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004758547872182332,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.18804823011159896,
|
|
"num_tokens": 36413991.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.494017124176025,
|
|
"epoch": 1.5727560300514036,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004758388804239797,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.18898372054100038,
|
|
"num_tokens": 36425807.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.604073715209961,
|
|
"epoch": 1.5732502965599051,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004758229686890586,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.18584917038679122,
|
|
"num_tokens": 36437968.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.633217763900757,
|
|
"epoch": 1.5737445630684066,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047580705201386134,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.18571496456861497,
|
|
"num_tokens": 36449803.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.605480337142945,
|
|
"epoch": 1.5742388295769079,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004757911303987794,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.18034024387598038,
|
|
"num_tokens": 36461849.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.480269813537598,
|
|
"epoch": 1.5747330960854091,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004757752038442045,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.19340770989656447,
|
|
"num_tokens": 36473324.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.591206407546997,
|
|
"epoch": 1.5752273625939106,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004757592723505284,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.18649255931377412,
|
|
"num_tokens": 36483949.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.5207353115081785,
|
|
"epoch": 1.575721629102412,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004757433359181431,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19615457057952881,
|
|
"num_tokens": 36495308.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.456513690948486,
|
|
"epoch": 1.5762158956109134,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047572739454744057,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.18938036561012267,
|
|
"num_tokens": 36506052.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.437809753417969,
|
|
"epoch": 1.5767101621194148,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000475711448238813,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.20404149740934371,
|
|
"num_tokens": 36519175.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.602045679092408,
|
|
"epoch": 1.5772044286279163,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047569549699265275,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.191925285756588,
|
|
"num_tokens": 36529736.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.499224424362183,
|
|
"epoch": 1.5776986951364176,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047567954080935206,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.19023547023534776,
|
|
"num_tokens": 36541715.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.545780992507934,
|
|
"epoch": 1.5781929616449188,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004756635796893036,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.19112806767225266,
|
|
"num_tokens": 36553807.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.562747001647949,
|
|
"epoch": 1.5786872281534203,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004756476136328998,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.1828333094716072,
|
|
"num_tokens": 36566053.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.5470751285552975,
|
|
"epoch": 1.5791814946619218,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047563164264053374,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.19056912064552306,
|
|
"num_tokens": 36577637.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.609174203872681,
|
|
"epoch": 1.579675761170423,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047561566671259803,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.19094742387533187,
|
|
"num_tokens": 36587767.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.493669700622559,
|
|
"epoch": 1.5801700276789243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047559968584948587,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19565580636262894,
|
|
"num_tokens": 36599163.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.545249557495117,
|
|
"epoch": 1.5806642941874258,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004755837000515903,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.1829050987958908,
|
|
"num_tokens": 36611170.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.626910305023193,
|
|
"epoch": 1.5811585606959273,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004755677093193046,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.1805187702178955,
|
|
"num_tokens": 36622907.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.5871734619140625,
|
|
"epoch": 1.5816528272044286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004755517136530221,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.1901850014925003,
|
|
"num_tokens": 36635197.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.5588836669921875,
|
|
"epoch": 1.58214709371293,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047553571305313636,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.19788220524787903,
|
|
"num_tokens": 36646965.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.483852243423462,
|
|
"epoch": 1.5826413602214315,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047551970752004097,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.20215259492397308,
|
|
"num_tokens": 36657344.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.479064273834228,
|
|
"epoch": 1.5831356267299328,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047550369705412964,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.1987358257174492,
|
|
"num_tokens": 36668833.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.534512376785278,
|
|
"epoch": 1.583629893238434,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004754876816557963,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19965051710605622,
|
|
"num_tokens": 36680902.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.517598819732666,
|
|
"epoch": 1.5841241597469355,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047547166132543483,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19467802494764327,
|
|
"num_tokens": 36691312.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.54453182220459,
|
|
"epoch": 1.584618426255437,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047545563606343945,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.19349119067192078,
|
|
"num_tokens": 36701091.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.595710182189942,
|
|
"epoch": 1.5851126927639383,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004754396058702043,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.18974149227142334,
|
|
"num_tokens": 36712524.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.605225086212158,
|
|
"epoch": 1.5856069592724396,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047542357074612375,
|
|
"loss": 5.305,
|
|
"mean_token_accuracy": 0.18619331270456313,
|
|
"num_tokens": 36724181.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.529338788986206,
|
|
"epoch": 1.586101225780941,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047540753069159224,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.19575058966875075,
|
|
"num_tokens": 36734777.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.533871459960937,
|
|
"epoch": 1.5865954922894425,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047539148570700443,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.19174228012561798,
|
|
"num_tokens": 36746437.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.630828380584717,
|
|
"epoch": 1.5870897587979438,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047537543579275496,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.18167472630739212,
|
|
"num_tokens": 36759615.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.572003984451294,
|
|
"epoch": 1.5875840253064453,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004753593809492387,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.18984712064266204,
|
|
"num_tokens": 36770762.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.581334638595581,
|
|
"epoch": 1.5880782918149468,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004753433211768506,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.18708752393722533,
|
|
"num_tokens": 36781410.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.553180789947509,
|
|
"epoch": 1.588572558323448,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047532725647598563,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19079723954200745,
|
|
"num_tokens": 36792737.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.481607437133789,
|
|
"epoch": 1.5890668248319493,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047531118684703916,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20286814123392105,
|
|
"num_tokens": 36804626.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.554210996627807,
|
|
"epoch": 1.5895610913404508,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004752951122904064,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.1827294185757637,
|
|
"num_tokens": 36815964.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.506850337982177,
|
|
"epoch": 1.5900553578489522,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004752790328064828,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.19987799674272538,
|
|
"num_tokens": 36828180.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.519400882720947,
|
|
"epoch": 1.5905496243574535,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047526294839566393,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19394201189279556,
|
|
"num_tokens": 36839589.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.548907947540283,
|
|
"epoch": 1.5910438908659548,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004752468590583454,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1963191494345665,
|
|
"num_tokens": 36850392.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.527910566329956,
|
|
"epoch": 1.5915381573744563,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004752307647949232,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.19409895390272142,
|
|
"num_tokens": 36862334.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.506290483474731,
|
|
"epoch": 1.5920324238829577,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000475214665605793,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19061145484447478,
|
|
"num_tokens": 36874837.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.5083434104919435,
|
|
"epoch": 1.592526690391459,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000475198561491351,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.19539699256420134,
|
|
"num_tokens": 36886375.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.519793939590454,
|
|
"epoch": 1.5930209568999605,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004751824524519934,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.18904990404844285,
|
|
"num_tokens": 36897731.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.541547536849976,
|
|
"epoch": 1.593515223408462,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004751663384881163,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.18028636276721954,
|
|
"num_tokens": 36909647.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.5327942848205565,
|
|
"epoch": 1.5940094899169632,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004751502196001163,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.19388763159513472,
|
|
"num_tokens": 36919960.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.552583265304565,
|
|
"epoch": 1.5945037564254645,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004751340957883898,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.18631939142942427,
|
|
"num_tokens": 36930520.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.608144092559814,
|
|
"epoch": 1.594998022933966,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004751179670533335,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.19139220118522643,
|
|
"num_tokens": 36942627.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.553775978088379,
|
|
"epoch": 1.5954922894424675,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004751018333953442,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.1887057140469551,
|
|
"num_tokens": 36954276.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.47394323348999,
|
|
"epoch": 1.5959865559509687,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004750856948148187,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.1973630055785179,
|
|
"num_tokens": 36965840.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.511866903305053,
|
|
"epoch": 1.59648082245947,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004750695513121541,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.19565611183643342,
|
|
"num_tokens": 36977133.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.612431335449219,
|
|
"epoch": 1.5969750889679717,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004750534028877475,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.19230225086212158,
|
|
"num_tokens": 36989013.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.508110237121582,
|
|
"epoch": 1.597469355476473,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004750372495419962,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.1878071829676628,
|
|
"num_tokens": 37000324.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.549233675003052,
|
|
"epoch": 1.5979636219849742,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004750210912752975,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.19374272376298904,
|
|
"num_tokens": 37010551.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.690651178359985,
|
|
"epoch": 1.5984578884934757,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004750049280880489,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18348969221115113,
|
|
"num_tokens": 37022732.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.592246341705322,
|
|
"epoch": 1.5989521550019772,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047498875998064805,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.1857389599084854,
|
|
"num_tokens": 37033230.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.4814136028289795,
|
|
"epoch": 1.5994464215104784,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004749725869534926,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.19752222597599028,
|
|
"num_tokens": 37043854.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.529146718978882,
|
|
"epoch": 1.5999406880189797,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047495640900698064,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.18964145332574844,
|
|
"num_tokens": 37055208.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.5787622928619385,
|
|
"epoch": 1.6004349545274812,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047494022614150995,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.1830536186695099,
|
|
"num_tokens": 37065938.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.547635316848755,
|
|
"epoch": 1.6009292210359827,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004749240383574786,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.19081999063491822,
|
|
"num_tokens": 37077252.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.499244356155396,
|
|
"epoch": 1.601423487544484,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000474907845655285,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.1939936324954033,
|
|
"num_tokens": 37087443.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.4614733219146725,
|
|
"epoch": 1.6019177540529854,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004748916480353273,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.20688055455684662,
|
|
"num_tokens": 37097621.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.533136415481567,
|
|
"epoch": 1.602412020561487,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047487544549800403,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.18822197169065474,
|
|
"num_tokens": 37110026.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.516726922988892,
|
|
"epoch": 1.6029062870699882,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004748592380437138,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18912703543901443,
|
|
"num_tokens": 37121447.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.562704086303711,
|
|
"epoch": 1.6034005535784894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004748430256728554,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.1904483214020729,
|
|
"num_tokens": 37132245.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.630905246734619,
|
|
"epoch": 1.603894820086991,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047482680838582754,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.1866144523024559,
|
|
"num_tokens": 37144135.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.580252170562744,
|
|
"epoch": 1.6043890865954924,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004748105861830292,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.1843031734228134,
|
|
"num_tokens": 37155716.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.612456655502319,
|
|
"epoch": 1.6048833531039937,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004747943590648594,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.18169937878847123,
|
|
"num_tokens": 37166701.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.612745666503907,
|
|
"epoch": 1.605377619612495,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047477812703171737,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.17591981291770936,
|
|
"num_tokens": 37177655.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.586807155609131,
|
|
"epoch": 1.6058718861209964,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047476189008400246,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.18728739619255066,
|
|
"num_tokens": 37189925.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.526347494125366,
|
|
"epoch": 1.606366152629498,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000474745648222114,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.1888329952955246,
|
|
"num_tokens": 37200756.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.5626109600067135,
|
|
"epoch": 1.6068604191379992,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004747294014464516,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1852453127503395,
|
|
"num_tokens": 37213252.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.5879841327667235,
|
|
"epoch": 1.6073546856465006,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000474713149757415,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18850937038660048,
|
|
"num_tokens": 37223754.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.582654237747192,
|
|
"epoch": 1.6078489521550021,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047469689315540395,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.18429618030786515,
|
|
"num_tokens": 37235930.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.521235418319702,
|
|
"epoch": 1.6083432186635034,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047468063164081826,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.20587607324123383,
|
|
"num_tokens": 37246794.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.495490694046021,
|
|
"epoch": 1.6088374851720046,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004746643652140581,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.1893088549375534,
|
|
"num_tokens": 37257523.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.582438611984253,
|
|
"epoch": 1.6093317516805061,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047464809387552366,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.18898214399814606,
|
|
"num_tokens": 37269505.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.6089905261993405,
|
|
"epoch": 1.6098260181890076,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000474631817625615,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.19451288729906083,
|
|
"num_tokens": 37281139.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.4826301574707035,
|
|
"epoch": 1.6103202846975089,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004746155364647327,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19388942420482635,
|
|
"num_tokens": 37291784.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.496024417877197,
|
|
"epoch": 1.6108145512060101,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047459925039327727,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.1863750621676445,
|
|
"num_tokens": 37302754.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.509329462051392,
|
|
"epoch": 1.6113088177145116,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047458295941164933,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.1947214975953102,
|
|
"num_tokens": 37313478.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.545080852508545,
|
|
"epoch": 1.611803084223013,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004745666635202496,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1865062639117241,
|
|
"num_tokens": 37325223.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.577295303344727,
|
|
"epoch": 1.6122973507315144,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000474550362719479,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.18944137245416642,
|
|
"num_tokens": 37336794.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.674091768264771,
|
|
"epoch": 1.6127916172400159,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047453405700973844,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.17879096418619156,
|
|
"num_tokens": 37349171.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.57783784866333,
|
|
"epoch": 1.6132858837485173,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004745177463914292,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.1777187705039978,
|
|
"num_tokens": 37362201.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.610036420822143,
|
|
"epoch": 1.6137801502570186,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047450143086495244,
|
|
"loss": 5.2961,
|
|
"mean_token_accuracy": 0.18076513558626175,
|
|
"num_tokens": 37373858.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.640679788589478,
|
|
"epoch": 1.6142744167655199,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004744851104307095,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.18363183438777925,
|
|
"num_tokens": 37385973.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.583286619186401,
|
|
"epoch": 1.6147686832740213,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047446878508910194,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.18413402140140533,
|
|
"num_tokens": 37398054.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.587321805953979,
|
|
"epoch": 1.6152629497825228,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047445245484053133,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18629823476076127,
|
|
"num_tokens": 37408656.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.490636348724365,
|
|
"epoch": 1.615757216291024,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004744361196853994,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.19703544974327086,
|
|
"num_tokens": 37420454.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.54899582862854,
|
|
"epoch": 1.6162514827995254,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004744197796241079,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19025007337331773,
|
|
"num_tokens": 37431879.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.560509777069091,
|
|
"epoch": 1.6167457493080268,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004744034346570589,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.1875338539481163,
|
|
"num_tokens": 37443487.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.492399740219116,
|
|
"epoch": 1.6172400158165283,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004743870847846546,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19650127589702607,
|
|
"num_tokens": 37455726.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.599870920181274,
|
|
"epoch": 1.6177342823250296,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004743707300072969,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.18719878196716308,
|
|
"num_tokens": 37466735.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.608331823348999,
|
|
"epoch": 1.618228548833531,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047435437032538843,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.18519935011863708,
|
|
"num_tokens": 37479599.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.510221719741821,
|
|
"epoch": 1.6187228153420326,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047433800573933147,
|
|
"loss": 5.2324,
|
|
"mean_token_accuracy": 0.19093181788921357,
|
|
"num_tokens": 37490896.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.539091682434082,
|
|
"epoch": 1.6192170818505338,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047432163624952874,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.19130464196205138,
|
|
"num_tokens": 37501474.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.5234230041503904,
|
|
"epoch": 1.619711348359035,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004743052618563827,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.19191403985023497,
|
|
"num_tokens": 37513410.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.479239177703858,
|
|
"epoch": 1.6202056148675366,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004742888825602964,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.19815139323472977,
|
|
"num_tokens": 37522612.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.63012547492981,
|
|
"epoch": 1.620699881376038,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004742724983616726,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.18159632235765458,
|
|
"num_tokens": 37534320.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.605421495437622,
|
|
"epoch": 1.6211941478845393,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047425610926091444,
|
|
"loss": 5.2957,
|
|
"mean_token_accuracy": 0.17934496253728865,
|
|
"num_tokens": 37545599.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.566797256469727,
|
|
"epoch": 1.6216884143930406,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004742397152584251,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.1957671523094177,
|
|
"num_tokens": 37558002.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.522682332992554,
|
|
"epoch": 1.6221826809015423,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047422331635460784,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19337865263223647,
|
|
"num_tokens": 37570808.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.565104579925537,
|
|
"epoch": 1.6226769474100435,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047420691254986615,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.19445886909961702,
|
|
"num_tokens": 37581065.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.584222936630249,
|
|
"epoch": 1.6231712139185448,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047419050384460345,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.19489668011665345,
|
|
"num_tokens": 37592472.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.573507261276245,
|
|
"epoch": 1.6236654804270463,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004741740902392235,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18989825993776321,
|
|
"num_tokens": 37604601.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.574497842788697,
|
|
"epoch": 1.6241597469355478,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004741576717341299,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.1923445537686348,
|
|
"num_tokens": 37615978.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.499900579452515,
|
|
"epoch": 1.624654013444049,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004741412483297268,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19305078983306884,
|
|
"num_tokens": 37627532.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.539503526687622,
|
|
"epoch": 1.6251482799525503,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004741248200264181,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.18103116750717163,
|
|
"num_tokens": 37640508.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.529737949371338,
|
|
"epoch": 1.6256425464610518,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004741083868246079,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.18707791715860367,
|
|
"num_tokens": 37652095.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.479440784454345,
|
|
"epoch": 1.6261368129695533,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004740919487247005,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.2011418968439102,
|
|
"num_tokens": 37663481.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.5861427783966064,
|
|
"epoch": 1.6266310794780545,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004740755057271003,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19293910562992095,
|
|
"num_tokens": 37675259.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.5354835987091064,
|
|
"epoch": 1.627125345986556,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047405905783221177,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.19084135293960572,
|
|
"num_tokens": 37686006.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.544863605499268,
|
|
"epoch": 1.6276196124950575,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047404260504043945,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18788450062274933,
|
|
"num_tokens": 37697642.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.5856904029846195,
|
|
"epoch": 1.6281138790035588,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047402614735218824,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.1892191618680954,
|
|
"num_tokens": 37707714.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.537310171127319,
|
|
"epoch": 1.62860814551206,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004740096847678629,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.19107548892498016,
|
|
"num_tokens": 37719562.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.518125343322754,
|
|
"epoch": 1.6291024120205615,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004739932172878685,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.19471408426761627,
|
|
"num_tokens": 37731521.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.553833675384522,
|
|
"epoch": 1.629596678529063,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047397674491261003,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.18721258789300918,
|
|
"num_tokens": 37743015.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.621201753616333,
|
|
"epoch": 1.6300909450375642,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047396026764249285,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18380213677883148,
|
|
"num_tokens": 37754219.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.554624795913696,
|
|
"epoch": 1.6305852115460655,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004739437854779222,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1912817969918251,
|
|
"num_tokens": 37765738.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.370435953140259,
|
|
"epoch": 1.631079478054567,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047392729841930345,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.2123836949467659,
|
|
"num_tokens": 37778647.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.537934494018555,
|
|
"epoch": 1.6315737445630685,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047391080646704237,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.19138409197330475,
|
|
"num_tokens": 37790380.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.5341705799102785,
|
|
"epoch": 1.6320680110715697,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047389430962154464,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18771473914384842,
|
|
"num_tokens": 37802474.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.508397722244263,
|
|
"epoch": 1.6325622775800712,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047387780788321594,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.1813374489545822,
|
|
"num_tokens": 37814154.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.6396654605865475,
|
|
"epoch": 1.6330565440885727,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004738613012524624,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19664339870214462,
|
|
"num_tokens": 37825371.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.571236181259155,
|
|
"epoch": 1.633550810597074,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047384478972968997,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.18834562301635743,
|
|
"num_tokens": 37836475.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.523996353149414,
|
|
"epoch": 1.6340450771055752,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047382827331530483,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18812665939331055,
|
|
"num_tokens": 37848413.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.504469728469848,
|
|
"epoch": 1.6345393436140767,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004738117520097133,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.19595986157655715,
|
|
"num_tokens": 37858174.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.562744140625,
|
|
"epoch": 1.6350336101225782,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000473795225813322,
|
|
"loss": 5.317,
|
|
"mean_token_accuracy": 0.18673986047506333,
|
|
"num_tokens": 37869987.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.523745393753051,
|
|
"epoch": 1.6355278766310795,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047377869472653704,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.20093792378902436,
|
|
"num_tokens": 37882050.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.549457645416259,
|
|
"epoch": 1.6360221431395807,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004737621587497655,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.19112807065248488,
|
|
"num_tokens": 37894537.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.568284940719605,
|
|
"epoch": 1.6365164096480822,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000473745617883414,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.1962245911359787,
|
|
"num_tokens": 37905795.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.533346176147461,
|
|
"epoch": 1.6370106761565837,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047372907212788953,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.19251216799020768,
|
|
"num_tokens": 37918778.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.5463556289672855,
|
|
"epoch": 1.637504942665085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047371252148359897,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.17960706800222398,
|
|
"num_tokens": 37930963.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.577737474441529,
|
|
"epoch": 1.6379992091735864,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004736959659509496,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.18808404505252838,
|
|
"num_tokens": 37943067.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.570840740203858,
|
|
"epoch": 1.638493475682088,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004736794055303487,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.19172247648239135,
|
|
"num_tokens": 37953425.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.475279140472412,
|
|
"epoch": 1.6389877421905892,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047366284022220346,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19293771982192992,
|
|
"num_tokens": 37965801.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.590984535217285,
|
|
"epoch": 1.6394820086990904,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004736462700269216,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.18485313951969146,
|
|
"num_tokens": 37978169.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.563940858840942,
|
|
"epoch": 1.639976275207592,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047362969494491063,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.1960172787308693,
|
|
"num_tokens": 37990154.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.534908771514893,
|
|
"epoch": 1.6404705417160934,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047361311497657845,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.1965550646185875,
|
|
"num_tokens": 38001249.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.523536205291748,
|
|
"epoch": 1.6409648082245947,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004735965301223328,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19780175536870956,
|
|
"num_tokens": 38013453.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.570104455947876,
|
|
"epoch": 1.641459074733096,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047357994038258166,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.17990566194057464,
|
|
"num_tokens": 38024463.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.578190517425537,
|
|
"epoch": 1.6419533412415974,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047356334575773324,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.18958691954612733,
|
|
"num_tokens": 38036131.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.498281002044678,
|
|
"epoch": 1.642447607750099,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004735467462481956,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.19353169798851014,
|
|
"num_tokens": 38047428.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.56439175605774,
|
|
"epoch": 1.6429418742586002,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004735301418543773,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.19813358038663864,
|
|
"num_tokens": 38059864.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.577289485931397,
|
|
"epoch": 1.6434361407671016,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00047351353257668675,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.18560857623815535,
|
|
"num_tokens": 38071356.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.5696617603302006,
|
|
"epoch": 1.6439304072756031,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004734969184155324,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.1826751008629799,
|
|
"num_tokens": 38082124.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.592821359634399,
|
|
"epoch": 1.6444246737841044,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047348029937132306,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.18458859771490096,
|
|
"num_tokens": 38093451.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.559484672546387,
|
|
"epoch": 1.6449189402926057,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047346367544446753,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.18366524577140808,
|
|
"num_tokens": 38105078.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.483122062683106,
|
|
"epoch": 1.6454132068011071,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004734470466353749,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.20375334620475768,
|
|
"num_tokens": 38114953.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.528443479537964,
|
|
"epoch": 1.6459074733096086,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004734304129444542,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.194681516289711,
|
|
"num_tokens": 38126465.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.6039533615112305,
|
|
"epoch": 1.6464017398181099,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004734137743721144,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.18385706692934037,
|
|
"num_tokens": 38139223.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.446664953231812,
|
|
"epoch": 1.6468960063266112,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000473397130918765,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.19423665404319762,
|
|
"num_tokens": 38151676.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.526656818389893,
|
|
"epoch": 1.6473902728351129,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047338048258481545,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1883848249912262,
|
|
"num_tokens": 38162759.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.51065034866333,
|
|
"epoch": 1.6478845393436141,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004733638293706752,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.19271410405635833,
|
|
"num_tokens": 38174820.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.47312297821045,
|
|
"epoch": 1.6483788058521154,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000473347171276754,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.20151613354682923,
|
|
"num_tokens": 38185558.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.548300313949585,
|
|
"epoch": 1.6488730723606169,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004733305083034617,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.1894029751420021,
|
|
"num_tokens": 38198231.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.584406471252441,
|
|
"epoch": 1.6493673388691183,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047331384045120803,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.19167090803384781,
|
|
"num_tokens": 38209539.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.567562532424927,
|
|
"epoch": 1.6498616053776196,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004732971677204031,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.18349882662296296,
|
|
"num_tokens": 38220873.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.528944110870361,
|
|
"epoch": 1.6503558718861209,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047328049011145714,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19708067327737808,
|
|
"num_tokens": 38231186.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.580776023864746,
|
|
"epoch": 1.6508501383946224,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004732638076247804,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.17953802049160003,
|
|
"num_tokens": 38242152.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.590709257125854,
|
|
"epoch": 1.6513444049031238,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047324712026078315,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.18942539542913436,
|
|
"num_tokens": 38254281.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.496087884902954,
|
|
"epoch": 1.651838671411625,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000473230428019876,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.1897260770201683,
|
|
"num_tokens": 38265120.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.565151643753052,
|
|
"epoch": 1.6523329379201266,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047321373090246957,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19440651684999466,
|
|
"num_tokens": 38275509.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.452874422073364,
|
|
"epoch": 1.652827204428628,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047319702890897457,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.20058497786521912,
|
|
"num_tokens": 38285586.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.546641540527344,
|
|
"epoch": 1.6533214709371293,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000473180322039802,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.19075486361980437,
|
|
"num_tokens": 38296091.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.570818042755127,
|
|
"epoch": 1.6538157374456306,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004731636102953627,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.18305505961179733,
|
|
"num_tokens": 38308520.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.569952154159546,
|
|
"epoch": 1.654310003954132,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004731468936760679,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.1857338309288025,
|
|
"num_tokens": 38320584.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.542389917373657,
|
|
"epoch": 1.6548042704626336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004731301721823287,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.19360775202512742,
|
|
"num_tokens": 38332646.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.624086904525757,
|
|
"epoch": 1.6552985369711348,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004731134458145566,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.18812894821166992,
|
|
"num_tokens": 38343382.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.630553770065307,
|
|
"epoch": 1.655792803479636,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047309671457316295,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.1824274942278862,
|
|
"num_tokens": 38354809.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.465882396697998,
|
|
"epoch": 1.6562870699881376,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047307997845855946,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.18770117610692977,
|
|
"num_tokens": 38366524.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.515040349960327,
|
|
"epoch": 1.656781336496639,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004730632374711578,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.19791075140237807,
|
|
"num_tokens": 38377645.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.6369704246521,
|
|
"epoch": 1.6572756030051403,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004730464916113696,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.19123112708330153,
|
|
"num_tokens": 38389633.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.584782314300537,
|
|
"epoch": 1.6577698695136418,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047302974087960704,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.1833358570933342,
|
|
"num_tokens": 38401255.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.548007774353027,
|
|
"epoch": 1.6582641360221433,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004730129852762822,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.18929618299007417,
|
|
"num_tokens": 38413160.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.5257041454315186,
|
|
"epoch": 1.6587584025306445,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047299622480180716,
|
|
"loss": 5.3064,
|
|
"mean_token_accuracy": 0.18268730044364928,
|
|
"num_tokens": 38423789.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.5619128227233885,
|
|
"epoch": 1.6592526690391458,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047297945945659424,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.18928075432777405,
|
|
"num_tokens": 38435031.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.553162574768066,
|
|
"epoch": 1.6597469355476473,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047296268924105594,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19990754425525664,
|
|
"num_tokens": 38445146.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.573150157928467,
|
|
"epoch": 1.6602412020561488,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047294591415560484,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18345189094543457,
|
|
"num_tokens": 38457429.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.550406789779663,
|
|
"epoch": 1.66073546856465,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004729291342006535,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.18880965560674667,
|
|
"num_tokens": 38468218.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.617250442504883,
|
|
"epoch": 1.6612297350731513,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004729123493766147,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.18641462177038193,
|
|
"num_tokens": 38480841.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.496380805969238,
|
|
"epoch": 1.6617240015816528,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004728955596839014,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.19197674244642257,
|
|
"num_tokens": 38493115.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.575050973892212,
|
|
"epoch": 1.6622182680901543,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004728787651229267,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19082382917404175,
|
|
"num_tokens": 38505187.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.581605052947998,
|
|
"epoch": 1.6627125345986555,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047286196569410366,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.18407894372940065,
|
|
"num_tokens": 38518736.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.4902855396270756,
|
|
"epoch": 1.663206801107157,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047284516139784556,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.19477532505989076,
|
|
"num_tokens": 38529703.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.5479179382324215,
|
|
"epoch": 1.6637010676156585,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004728283522345658,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.1884244367480278,
|
|
"num_tokens": 38542200.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.584379625320435,
|
|
"epoch": 1.6641953341241598,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004728115382046779,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.18655404448509216,
|
|
"num_tokens": 38552921.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.552591037750244,
|
|
"epoch": 1.664689600632661,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004727947193085954,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.18871599286794663,
|
|
"num_tokens": 38564837.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.586568450927734,
|
|
"epoch": 1.6651838671411625,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047277789554673217,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1902960240840912,
|
|
"num_tokens": 38575786.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.569282197952271,
|
|
"epoch": 1.665678133649664,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047276106691950204,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.1818220153450966,
|
|
"num_tokens": 38588232.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.555409717559814,
|
|
"epoch": 1.6661724001581653,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047274423342731896,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.18385958820581436,
|
|
"num_tokens": 38600276.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.568722200393677,
|
|
"epoch": 1.6666666666666665,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004727273950705971,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.1912783443927765,
|
|
"num_tokens": 38611879.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.565506887435913,
|
|
"epoch": 1.667160933175168,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047271055184975057,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.17779794484376907,
|
|
"num_tokens": 38623032.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.607215118408203,
|
|
"epoch": 1.6676551996836695,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004726937037651939,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19001731425523757,
|
|
"num_tokens": 38633864.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.4956403255462645,
|
|
"epoch": 1.6681494661921707,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047267685081734133,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.18828164786100388,
|
|
"num_tokens": 38645208.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.521686124801636,
|
|
"epoch": 1.6686437327006722,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004726599930066076,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.1960131675004959,
|
|
"num_tokens": 38655181.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.643523406982422,
|
|
"epoch": 1.6691379992091737,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004726431303334074,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.18706587105989456,
|
|
"num_tokens": 38667381.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.518780088424682,
|
|
"epoch": 1.669632265717675,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047262626279815555,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18865147978067398,
|
|
"num_tokens": 38680479.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.539134883880616,
|
|
"epoch": 1.6701265322261762,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000472609390401267,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.19139347821474076,
|
|
"num_tokens": 38691737.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.554802560806275,
|
|
"epoch": 1.6706207987346777,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004725925131431567,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.19035504758358002,
|
|
"num_tokens": 38703306.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.5550940990447994,
|
|
"epoch": 1.6711150652431792,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047257563102424,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.18883705884218216,
|
|
"num_tokens": 38714683.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.572267770767212,
|
|
"epoch": 1.6716093317516805,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004725587440449321,
|
|
"loss": 5.3343,
|
|
"mean_token_accuracy": 0.17983238399028778,
|
|
"num_tokens": 38727705.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.609952783584594,
|
|
"epoch": 1.6721035982601817,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047254185220564843,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.19120740592479707,
|
|
"num_tokens": 38738687.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.526450967788696,
|
|
"epoch": 1.6725978647686834,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047252495550680453,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.1896759420633316,
|
|
"num_tokens": 38749437.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.454763603210449,
|
|
"epoch": 1.6730921312771847,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004725080539488162,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.21217340528964995,
|
|
"num_tokens": 38761342.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.594578266143799,
|
|
"epoch": 1.673586397785686,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047249114753209896,
|
|
"loss": 5.3008,
|
|
"mean_token_accuracy": 0.18288837671279906,
|
|
"num_tokens": 38773019.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.604700803756714,
|
|
"epoch": 1.6740806642941874,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047247423625706894,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.18540577888488768,
|
|
"num_tokens": 38785291.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.552280044555664,
|
|
"epoch": 1.674574930802689,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000472457320124142,
|
|
"loss": 5.2709,
|
|
"mean_token_accuracy": 0.18948756903409958,
|
|
"num_tokens": 38796926.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.6065233707427975,
|
|
"epoch": 1.6750691973111902,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047244039913373444,
|
|
"loss": 5.2529,
|
|
"mean_token_accuracy": 0.19008801579475404,
|
|
"num_tokens": 38809839.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.6185506820678714,
|
|
"epoch": 1.6755634638196915,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004724234732862624,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.17994152158498763,
|
|
"num_tokens": 38823059.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.477122974395752,
|
|
"epoch": 1.676057730328193,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004724065425821422,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.2034627228975296,
|
|
"num_tokens": 38834275.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.503874588012695,
|
|
"epoch": 1.6765519968366944,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004723896070217905,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.19068557769060135,
|
|
"num_tokens": 38845992.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.549582147598267,
|
|
"epoch": 1.6770462633451957,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004723726666056239,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.19204333275556565,
|
|
"num_tokens": 38857269.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.562768268585205,
|
|
"epoch": 1.677540529853697,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047235572133405904,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.18794002681970595,
|
|
"num_tokens": 38869393.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.63678388595581,
|
|
"epoch": 1.6780347963621987,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047233877120751277,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.1897524580359459,
|
|
"num_tokens": 38881625.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.590556001663208,
|
|
"epoch": 1.6785290628707,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047232181622640216,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.1874576210975647,
|
|
"num_tokens": 38892452.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.514513349533081,
|
|
"epoch": 1.6790233293792012,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004723048563911443,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19993050545454025,
|
|
"num_tokens": 38902415.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.498851299285889,
|
|
"epoch": 1.6795175958877027,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047228789170215623,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19853136241436004,
|
|
"num_tokens": 38912655.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.5069890975952145,
|
|
"epoch": 1.6800118623962041,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047227092215985553,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.1859263598918915,
|
|
"num_tokens": 38923295.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.5683043003082275,
|
|
"epoch": 1.6805061289047054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004722539477646595,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.18930319100618362,
|
|
"num_tokens": 38934879.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.6496264934539795,
|
|
"epoch": 1.6810003954132067,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047223696851698575,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.1793565571308136,
|
|
"num_tokens": 38946574.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.577004528045654,
|
|
"epoch": 1.6814946619217082,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000472219984417252,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.19135456681251525,
|
|
"num_tokens": 38958136.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.595063543319702,
|
|
"epoch": 1.6819889284302096,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004722029954658761,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.19338930547237396,
|
|
"num_tokens": 38969353.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.462925910949707,
|
|
"epoch": 1.682483194938711,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004721860016632758,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19600094854831696,
|
|
"num_tokens": 38979878.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.541908693313599,
|
|
"epoch": 1.6829774614472124,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004721690030098693,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.19270993918180465,
|
|
"num_tokens": 38992847.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.548034429550171,
|
|
"epoch": 1.6834717279557139,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004721519995060748,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18913892209529876,
|
|
"num_tokens": 39003874.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.5396675109863285,
|
|
"epoch": 1.6839659944642151,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047213499115231043,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18825254440307618,
|
|
"num_tokens": 39014327.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.553736209869385,
|
|
"epoch": 1.6844602609727164,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004721179779489948,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18788815438747405,
|
|
"num_tokens": 39024507.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.50848240852356,
|
|
"epoch": 1.6849545274812179,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047210095989654624,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.18589969873428344,
|
|
"num_tokens": 39036184.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.480550098419189,
|
|
"epoch": 1.6854487939897194,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047208393699538356,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19633585810661316,
|
|
"num_tokens": 39047649.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.492911767959595,
|
|
"epoch": 1.6859430604982206,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047206690924592545,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.19265952259302138,
|
|
"num_tokens": 39058167.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.522982263565064,
|
|
"epoch": 1.6864373270067219,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004720498766485907,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.19459711909294128,
|
|
"num_tokens": 39070099.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.543668270111084,
|
|
"epoch": 1.6869315935152234,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047203283920379846,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.19686869978904725,
|
|
"num_tokens": 39080337.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.637980222702026,
|
|
"epoch": 1.6874258600237249,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047201579691196784,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.17710277438163757,
|
|
"num_tokens": 39093455.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.5823023319244385,
|
|
"epoch": 1.6879201265322261,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047199874977351807,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.18475643247365953,
|
|
"num_tokens": 39105424.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.463011741638184,
|
|
"epoch": 1.6884143930407276,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004719816977888685,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.1986666202545166,
|
|
"num_tokens": 39117441.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.532389688491821,
|
|
"epoch": 1.688908659549229,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047196464095843857,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.1870439976453781,
|
|
"num_tokens": 39129853.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.557559537887573,
|
|
"epoch": 1.6894029260577303,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004719475792826479,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.1980454683303833,
|
|
"num_tokens": 39141132.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.4874427795410154,
|
|
"epoch": 1.6898971925662316,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004719305127619162,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.19771636575460433,
|
|
"num_tokens": 39153892.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.560679006576538,
|
|
"epoch": 1.690391459074733,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004719134413966635,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.19835438579320908,
|
|
"num_tokens": 39164410.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.505087518692017,
|
|
"epoch": 1.6908857255832346,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047189636518730945,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.20227185487747193,
|
|
"num_tokens": 39174612.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.539873552322388,
|
|
"epoch": 1.6913799920917358,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047187928413427424,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.1927895337343216,
|
|
"num_tokens": 39187355.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.529417657852173,
|
|
"epoch": 1.691874258600237,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047186219823797815,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.18784212619066237,
|
|
"num_tokens": 39199145.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.625420379638672,
|
|
"epoch": 1.6923685251087386,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047184510749884146,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.19060784280300141,
|
|
"num_tokens": 39210589.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.489500570297241,
|
|
"epoch": 1.69286279161724,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004718280119172846,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.1941944569349289,
|
|
"num_tokens": 39222657.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.486371374130249,
|
|
"epoch": 1.6933570581257413,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047181091149372807,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.20535195171833037,
|
|
"num_tokens": 39233439.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.482947540283203,
|
|
"epoch": 1.6938513246342428,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004717938062285926,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.2016031801700592,
|
|
"num_tokens": 39243787.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.575181293487549,
|
|
"epoch": 1.6943455911427443,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047177669612229894,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.18944211751222612,
|
|
"num_tokens": 39255658.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.543373775482178,
|
|
"epoch": 1.6948398576512456,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047175958117526805,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.18429079949855803,
|
|
"num_tokens": 39269480.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.590872812271118,
|
|
"epoch": 1.6953341241597468,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047174246138792096,
|
|
"loss": 5.2846,
|
|
"mean_token_accuracy": 0.19241732507944107,
|
|
"num_tokens": 39281063.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.582598352432251,
|
|
"epoch": 1.6958283906682483,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047172533676067874,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19050592482089995,
|
|
"num_tokens": 39292188.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.525087547302246,
|
|
"epoch": 1.6963226571767498,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004717082072939628,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.1871927872300148,
|
|
"num_tokens": 39303661.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.5401777744293215,
|
|
"epoch": 1.696816923685251,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004716910729881944,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.18786416798830033,
|
|
"num_tokens": 39315028.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.452537488937378,
|
|
"epoch": 1.6973111901937523,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047167393384379513,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.19621308892965317,
|
|
"num_tokens": 39326629.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.468703031539917,
|
|
"epoch": 1.6978054567022538,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047165678986118653,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.2025471121072769,
|
|
"num_tokens": 39338821.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.523886394500733,
|
|
"epoch": 1.6982997232107553,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004716396410407904,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.19240393936634065,
|
|
"num_tokens": 39350093.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.473460721969604,
|
|
"epoch": 1.6987939897192565,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004716224873830286,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.20054327100515365,
|
|
"num_tokens": 39361120.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.540441417694092,
|
|
"epoch": 1.699288256227758,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047160532888832315,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.1885613366961479,
|
|
"num_tokens": 39373040.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.524891757965088,
|
|
"epoch": 1.6997825227362595,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047158816555709597,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.19589831829071044,
|
|
"num_tokens": 39384576.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.508631467819214,
|
|
"epoch": 1.7002767892447608,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004715709973897696,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.19886304587125778,
|
|
"num_tokens": 39397550.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.578541278839111,
|
|
"epoch": 1.700771055753262,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047155382438676604,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1957048088312149,
|
|
"num_tokens": 39407474.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.501206398010254,
|
|
"epoch": 1.7012653222617635,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047153664654850803,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.18984226882457733,
|
|
"num_tokens": 39420104.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.571781206130981,
|
|
"epoch": 1.701759588770265,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047151946387541795,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.1819096326828003,
|
|
"num_tokens": 39431887.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.529139995574951,
|
|
"epoch": 1.7022538552787663,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004715022763679185,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.19420908838510514,
|
|
"num_tokens": 39442772.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.601952028274536,
|
|
"epoch": 1.7027481217872675,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047148508402643273,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.18805715143680574,
|
|
"num_tokens": 39455067.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.540503931045532,
|
|
"epoch": 1.7032423882957692,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004714678868513834,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.19479119032621384,
|
|
"num_tokens": 39466700.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.592003107070923,
|
|
"epoch": 1.7037366548042705,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004714506848431935,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.19385424256324768,
|
|
"num_tokens": 39477591.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.5479896545410154,
|
|
"epoch": 1.7042309213127718,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047143347800228624,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.18458028882741928,
|
|
"num_tokens": 39488615.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.598716354370117,
|
|
"epoch": 1.7047251878212732,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000471416266329085,
|
|
"loss": 5.2904,
|
|
"mean_token_accuracy": 0.18674174845218658,
|
|
"num_tokens": 39499610.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.592858457565308,
|
|
"epoch": 1.7052194543297747,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004713990498240131,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.19235974848270415,
|
|
"num_tokens": 39511180.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.530462074279785,
|
|
"epoch": 1.705713720838276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047138182848749415,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.1969173178076744,
|
|
"num_tokens": 39523271.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.542901992797852,
|
|
"epoch": 1.7062079873467773,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004713646023199518,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.19262509942054748,
|
|
"num_tokens": 39534334.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.534068584442139,
|
|
"epoch": 1.7067022538552787,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004713473713218097,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.1982777252793312,
|
|
"num_tokens": 39545937.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.583977556228637,
|
|
"epoch": 1.7071965203637802,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004713301354934918,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.18703342080116273,
|
|
"num_tokens": 39558129.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.581902503967285,
|
|
"epoch": 1.7076907868722815,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004713128948354221,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.1898788183927536,
|
|
"num_tokens": 39569649.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.603346538543701,
|
|
"epoch": 1.708185053380783,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004712956493480248,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.19007624983787536,
|
|
"num_tokens": 39581051.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.525624227523804,
|
|
"epoch": 1.7086793198892845,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000471278399031724,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.19163839817047118,
|
|
"num_tokens": 39591225.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.506840419769287,
|
|
"epoch": 1.7091735863977857,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004712611438869442,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.20026247799396515,
|
|
"num_tokens": 39601270.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.467228364944458,
|
|
"epoch": 1.709667852906287,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047124388391410975,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.19573230892419816,
|
|
"num_tokens": 39611574.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.450652408599853,
|
|
"epoch": 1.7101621194147885,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004712266191136453,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.1994699001312256,
|
|
"num_tokens": 39622889.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.551870059967041,
|
|
"epoch": 1.71065638592329,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004712093494859757,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19496834576129912,
|
|
"num_tokens": 39634286.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.551763820648193,
|
|
"epoch": 1.7111506524317912,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004711920750315255,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18508027195930482,
|
|
"num_tokens": 39646653.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.550481081008911,
|
|
"epoch": 1.7116449189402925,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004711747957507199,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19396099746227263,
|
|
"num_tokens": 39658027.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.5774290561676025,
|
|
"epoch": 1.712139185448794,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047115751164398395,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.18690342009067534,
|
|
"num_tokens": 39669912.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.504055166244507,
|
|
"epoch": 1.7126334519572954,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004711402227117427,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.19361567199230195,
|
|
"num_tokens": 39680857.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.501230669021607,
|
|
"epoch": 1.7131277184657967,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047112292895442156,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19767452776432037,
|
|
"num_tokens": 39692301.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.565872287750244,
|
|
"epoch": 1.7136219849742982,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000471105630372446,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.18395307511091233,
|
|
"num_tokens": 39703641.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.557095670700074,
|
|
"epoch": 1.7141162514827997,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047108832696624145,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.2002997264266014,
|
|
"num_tokens": 39714919.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.507198238372803,
|
|
"epoch": 1.714610517991301,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004710710187362336,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.1933806926012039,
|
|
"num_tokens": 39725658.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.502253770828247,
|
|
"epoch": 1.7151047844998022,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047105370568284834,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19967944025993348,
|
|
"num_tokens": 39736899.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.60289831161499,
|
|
"epoch": 1.7155990510083037,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004710363878065115,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.180840602517128,
|
|
"num_tokens": 39747875.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.637871980667114,
|
|
"epoch": 1.7160933175168052,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004710190651076491,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.18920678794384002,
|
|
"num_tokens": 39760253.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.557514333724976,
|
|
"epoch": 1.7165875840253064,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004710017375866872,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.19461606442928314,
|
|
"num_tokens": 39771031.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.448283338546753,
|
|
"epoch": 1.7170818505338077,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047098440524405227,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.19460515528917313,
|
|
"num_tokens": 39780850.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.533964967727661,
|
|
"epoch": 1.7175761170423092,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004709670680801705,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.19853220731019974,
|
|
"num_tokens": 39792975.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.574161052703857,
|
|
"epoch": 1.7180703835508107,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004709497260954685,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19817758202552796,
|
|
"num_tokens": 39803574.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.516184520721436,
|
|
"epoch": 1.718564650059312,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047093237929037284,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.19135793298482895,
|
|
"num_tokens": 39814907.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.523517036437989,
|
|
"epoch": 1.7190589165678134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004709150276653101,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.18839062601327897,
|
|
"num_tokens": 39826344.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.560697174072265,
|
|
"epoch": 1.7195531830763149,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047089767122070756,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19116319417953492,
|
|
"num_tokens": 39838516.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.739330291748047,
|
|
"epoch": 1.7200474495848161,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047088030995699173,
|
|
"loss": 5.4407,
|
|
"mean_token_accuracy": 0.17715674489736558,
|
|
"num_tokens": 39850757.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.660945081710816,
|
|
"epoch": 1.7205417160933174,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004708629438745899,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.18506115227937697,
|
|
"num_tokens": 39861105.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.551349544525147,
|
|
"epoch": 1.721035982601819,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004708455729739293,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18383150398731232,
|
|
"num_tokens": 39873999.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.492051649093628,
|
|
"epoch": 1.7215302491103204,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047082819725543726,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.1881793826818466,
|
|
"num_tokens": 39885768.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.672751379013062,
|
|
"epoch": 1.7220245156188216,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004708108167195411,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.1892711564898491,
|
|
"num_tokens": 39897548.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.544035243988037,
|
|
"epoch": 1.722518782127323,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004707934313666685,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.1983617901802063,
|
|
"num_tokens": 39909192.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.521376371383667,
|
|
"epoch": 1.7230130486358244,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004707760411972471,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19139224290847778,
|
|
"num_tokens": 39921279.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.576279640197754,
|
|
"epoch": 1.7235073151443259,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004707586462117048,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.19021397680044175,
|
|
"num_tokens": 39931638.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.582661104202271,
|
|
"epoch": 1.7240015816528271,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047074124641046934,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.19211679548025132,
|
|
"num_tokens": 39944239.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.6044511795043945,
|
|
"epoch": 1.7244958481613286,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004707238417939689,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.18044055104255677,
|
|
"num_tokens": 39956486.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.440124607086181,
|
|
"epoch": 1.72499011466983,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004707064323626316,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.20219251662492752,
|
|
"num_tokens": 39966271.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.5515525341033936,
|
|
"epoch": 1.7254843811783314,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047068901811688564,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.19078574031591417,
|
|
"num_tokens": 39978810.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.511099195480346,
|
|
"epoch": 1.7259786476868326,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004706715990571595,
|
|
"loss": 5.1874,
|
|
"mean_token_accuracy": 0.1993197351694107,
|
|
"num_tokens": 39989331.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.504051733016968,
|
|
"epoch": 1.726472914195334,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004706541751838817,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.19198761284351348,
|
|
"num_tokens": 39999931.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.5244420051574705,
|
|
"epoch": 1.7269671807038356,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004706367464974808,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.1910328149795532,
|
|
"num_tokens": 40010702.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.53405876159668,
|
|
"epoch": 1.7274614472123369,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047061931299838554,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.19130584001541137,
|
|
"num_tokens": 40022897.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.501959562301636,
|
|
"epoch": 1.7279557137208381,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000470601874687025,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19255649745464326,
|
|
"num_tokens": 40034057.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.5374058246612545,
|
|
"epoch": 1.7284499802293398,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004705844315638279,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.19416226893663407,
|
|
"num_tokens": 40044595.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.5736973762512205,
|
|
"epoch": 1.728944246737841,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004705669836292234,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1911911338567734,
|
|
"num_tokens": 40055175.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.490326642990112,
|
|
"epoch": 1.7294385132463423,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004705495308836408,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.20318637937307357,
|
|
"num_tokens": 40065276.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.502090072631836,
|
|
"epoch": 1.7299327797548438,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004705320733275094,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.18862185180187224,
|
|
"num_tokens": 40077230.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.49861421585083,
|
|
"epoch": 1.7304270462633453,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004705146109612587,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.2042008340358734,
|
|
"num_tokens": 40088058.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.4413799285888675,
|
|
"epoch": 1.7309213127718466,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004704971437853182,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.1941227063536644,
|
|
"num_tokens": 40099618.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.548307275772094,
|
|
"epoch": 1.7314155792803478,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004704796718001176,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.1977142870426178,
|
|
"num_tokens": 40111088.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.602716970443725,
|
|
"epoch": 1.7319098457888493,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047046219500608685,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1917777642607689,
|
|
"num_tokens": 40122191.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.56962366104126,
|
|
"epoch": 1.7324041122973508,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004704447134036557,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.18709876388311386,
|
|
"num_tokens": 40133764.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.481746244430542,
|
|
"epoch": 1.732898378805852,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047042722699325426,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.19956999123096467,
|
|
"num_tokens": 40144502.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.512912273406982,
|
|
"epoch": 1.7333926453143536,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004704097357753128,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19350788742303848,
|
|
"num_tokens": 40155606.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.509117221832275,
|
|
"epoch": 1.733886911822855,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004703922397502614,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.19987072050571442,
|
|
"num_tokens": 40166551.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.63454008102417,
|
|
"epoch": 1.7343811783313563,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047037473891853066,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.1882120281457901,
|
|
"num_tokens": 40178804.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.586340093612671,
|
|
"epoch": 1.7348754448398576,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047035723328055104,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.19054033160209655,
|
|
"num_tokens": 40189861.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.45556149482727,
|
|
"epoch": 1.735369711348359,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004703397228367532,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.1968206509947777,
|
|
"num_tokens": 40202619.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.500414180755615,
|
|
"epoch": 1.7358639778568605,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047032220758756786,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.19133986979722978,
|
|
"num_tokens": 40213509.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.641032934188843,
|
|
"epoch": 1.7363582443653618,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004703046875334259,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.18902143985033035,
|
|
"num_tokens": 40224960.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.537813806533814,
|
|
"epoch": 1.736852510873863,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047028716267475827,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.19109692573547363,
|
|
"num_tokens": 40238516.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.55232081413269,
|
|
"epoch": 1.7373467773823645,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004702696330119963,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18424736708402634,
|
|
"num_tokens": 40249123.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.588963270187378,
|
|
"epoch": 1.737841043890866,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004702520985455709,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.1931760847568512,
|
|
"num_tokens": 40260168.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.596848440170288,
|
|
"epoch": 1.7383353103993673,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047023455927591365,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.1805811807513237,
|
|
"num_tokens": 40273183.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.559323930740357,
|
|
"epoch": 1.7388295769078688,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047021701520345594,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18264115154743193,
|
|
"num_tokens": 40284452.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.52088418006897,
|
|
"epoch": 1.7393238434163703,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047019946632862944,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.19905785471200943,
|
|
"num_tokens": 40295267.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.494823932647705,
|
|
"epoch": 1.7398181099248715,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047018191265186566,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.19732488989830016,
|
|
"num_tokens": 40306766.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.493067598342895,
|
|
"epoch": 1.7403123764333728,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047016435417359667,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.19476093202829362,
|
|
"num_tokens": 40317382.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.548518514633178,
|
|
"epoch": 1.7408066429418743,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047014679089425423,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.1921554520726204,
|
|
"num_tokens": 40328273.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.560882186889648,
|
|
"epoch": 1.7413009094503757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047012922281427046,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.19514698088169097,
|
|
"num_tokens": 40340550.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.654910278320313,
|
|
"epoch": 1.741795175958877,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047011164993407753,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.19010755121707917,
|
|
"num_tokens": 40351752.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.508895969390869,
|
|
"epoch": 1.7422894424673783,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047009407225410776,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.19798146784305573,
|
|
"num_tokens": 40363330.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.427365016937256,
|
|
"epoch": 1.7427837089758798,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004700764897747936,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20725891143083572,
|
|
"num_tokens": 40375674.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.504157257080078,
|
|
"epoch": 1.7432779754843812,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004700589024965674,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.1944149225950241,
|
|
"num_tokens": 40387120.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.5479443073272705,
|
|
"epoch": 1.7437722419928825,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000470041310419862,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.19519811272621154,
|
|
"num_tokens": 40399196.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.511751461029053,
|
|
"epoch": 1.744266508501384,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004700237135451101,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19512049704790116,
|
|
"num_tokens": 40411693.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.41989574432373,
|
|
"epoch": 1.7447607750098855,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004700061118727446,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.20233599990606307,
|
|
"num_tokens": 40422866.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.571409273147583,
|
|
"epoch": 1.7452550415183867,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004699885054031985,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.19675806611776353,
|
|
"num_tokens": 40435028.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.663662433624268,
|
|
"epoch": 1.745749308026888,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000469970894136905,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18389779031276704,
|
|
"num_tokens": 40446802.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.600096082687378,
|
|
"epoch": 1.7462435745353895,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046995327807429715,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.19136440753936768,
|
|
"num_tokens": 40459025.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.5999979972839355,
|
|
"epoch": 1.746737841043891,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046993565721580846,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.1840189963579178,
|
|
"num_tokens": 40471486.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.531054496765137,
|
|
"epoch": 1.7472321075523922,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004699180315618723,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19732726514339446,
|
|
"num_tokens": 40483163.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.5585301399230955,
|
|
"epoch": 1.7477263740608935,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004699004011129224,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.1902832195162773,
|
|
"num_tokens": 40494475.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.487563037872315,
|
|
"epoch": 1.748220640569395,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046988276586939234,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.19188722223043442,
|
|
"num_tokens": 40504557.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.520202112197876,
|
|
"epoch": 1.7487149070778965,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004698651258317161,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.19949487894773482,
|
|
"num_tokens": 40516147.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.489529800415039,
|
|
"epoch": 1.7492091735863977,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004698474810003274,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.20097758620977402,
|
|
"num_tokens": 40527238.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.493621492385865,
|
|
"epoch": 1.7497034400948992,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004698298313756605,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.19975267797708512,
|
|
"num_tokens": 40537470.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.445312786102295,
|
|
"epoch": 1.7501977066034007,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046981217695814953,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1965625673532486,
|
|
"num_tokens": 40549865.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.60402021408081,
|
|
"epoch": 1.750691973111902,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004697945177482287,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18716005384922027,
|
|
"num_tokens": 40561796.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.487012767791748,
|
|
"epoch": 1.7511862396204032,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046977685374633267,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.19334127902984619,
|
|
"num_tokens": 40574597.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.485691213607788,
|
|
"epoch": 1.7516805061289047,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046975918495289576,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.1915511056780815,
|
|
"num_tokens": 40586549.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.535955190658569,
|
|
"epoch": 1.7521747726374062,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004697415113683527,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.19731371402740477,
|
|
"num_tokens": 40597808.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.6004541397094725,
|
|
"epoch": 1.7526690391459074,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046972383299313813,
|
|
"loss": 5.3542,
|
|
"mean_token_accuracy": 0.18784660547971727,
|
|
"num_tokens": 40608636.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.5779698371887205,
|
|
"epoch": 1.7531633056544087,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004697061498276872,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.19797111600637435,
|
|
"num_tokens": 40619099.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.504348516464233,
|
|
"epoch": 1.7536575721629104,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046968846187243473,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1988891288638115,
|
|
"num_tokens": 40630436.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.465347671508789,
|
|
"epoch": 1.7541518386714117,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00046967076912781585,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19597042202949524,
|
|
"num_tokens": 40643078.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.507551765441894,
|
|
"epoch": 1.754646105179913,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046965307159426594,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.198572339117527,
|
|
"num_tokens": 40653368.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.555690908432007,
|
|
"epoch": 1.7551403716884144,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004696353692722202,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.1897468939423561,
|
|
"num_tokens": 40665377.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.593304061889649,
|
|
"epoch": 1.755634638196916,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004696176621621143,
|
|
"loss": 5.326,
|
|
"mean_token_accuracy": 0.185105399787426,
|
|
"num_tokens": 40676599.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.534708166122437,
|
|
"epoch": 1.7561289047054172,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004695999502643836,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.20403447598218918,
|
|
"num_tokens": 40687619.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.458700180053711,
|
|
"epoch": 1.7566231712139184,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046958223357946395,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.194980888068676,
|
|
"num_tokens": 40699410.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.533778953552246,
|
|
"epoch": 1.75711743772242,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046956451210779113,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.18795743137598037,
|
|
"num_tokens": 40711149.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.486410522460938,
|
|
"epoch": 1.7576117042309214,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046954678584980113,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.19942816346883774,
|
|
"num_tokens": 40722997.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.595829200744629,
|
|
"epoch": 1.7581059707394227,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046952905480593014,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.19854436665773392,
|
|
"num_tokens": 40733786.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.568412971496582,
|
|
"epoch": 1.758600237247924,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046951131897661415,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.18643818199634551,
|
|
"num_tokens": 40745925.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.564244985580444,
|
|
"epoch": 1.7590945037564256,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046949357836228946,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.18752457052469254,
|
|
"num_tokens": 40760031.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.560628175735474,
|
|
"epoch": 1.7595887702649269,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046947583296339266,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.1942876935005188,
|
|
"num_tokens": 40771557.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.541092395782471,
|
|
"epoch": 1.7600830367734281,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046945808278036017,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.18695611953735353,
|
|
"num_tokens": 40783557.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.558853244781494,
|
|
"epoch": 1.7605773032819296,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004694403278136287,
|
|
"loss": 5.1261,
|
|
"mean_token_accuracy": 0.20739240646362306,
|
|
"num_tokens": 40794213.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.415123510360718,
|
|
"epoch": 1.7610715697904311,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046942256806363497,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.19938879311084748,
|
|
"num_tokens": 40805753.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.5561565399169925,
|
|
"epoch": 1.7615658362989324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046940480353081587,
|
|
"loss": 5.3242,
|
|
"mean_token_accuracy": 0.1920532077550888,
|
|
"num_tokens": 40818315.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.491773509979248,
|
|
"epoch": 1.7620601028074336,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004693870342156085,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.20364075452089309,
|
|
"num_tokens": 40828740.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.528374862670899,
|
|
"epoch": 1.7625543693159351,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004693692601184499,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19216446131467818,
|
|
"num_tokens": 40841035.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.511745882034302,
|
|
"epoch": 1.7630486358244366,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004693514812397774,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.1932552233338356,
|
|
"num_tokens": 40851857.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.57619833946228,
|
|
"epoch": 1.7635429023329379,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004693336975800283,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.19281331598758697,
|
|
"num_tokens": 40863964.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.530437326431274,
|
|
"epoch": 1.7640371688414394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046931590913964013,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.18968202620744706,
|
|
"num_tokens": 40876076.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.615259647369385,
|
|
"epoch": 1.7645314353499408,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046929811591905034,
|
|
"loss": 5.3271,
|
|
"mean_token_accuracy": 0.18747785985469817,
|
|
"num_tokens": 40887839.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.6102605819702145,
|
|
"epoch": 1.765025701858442,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004692803179186968,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.1910597190260887,
|
|
"num_tokens": 40898978.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.602094936370849,
|
|
"epoch": 1.7655199683669434,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004692625151390173,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.18714176416397094,
|
|
"num_tokens": 40910990.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.452455711364746,
|
|
"epoch": 1.7660142348754448,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004692447075804498,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.19777121990919114,
|
|
"num_tokens": 40922299.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.551053905487061,
|
|
"epoch": 1.7665085013839463,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004692268952434324,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.1922747641801834,
|
|
"num_tokens": 40933181.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.528418064117432,
|
|
"epoch": 1.7670027678924476,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004692090781284032,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.19226523637771606,
|
|
"num_tokens": 40944101.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.560276889801026,
|
|
"epoch": 1.7674970344009489,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004691912562358006,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.1940326452255249,
|
|
"num_tokens": 40956492.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.570573234558106,
|
|
"epoch": 1.7679913009094503,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046917342956606287,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.1849099263548851,
|
|
"num_tokens": 40967477.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.567684936523437,
|
|
"epoch": 1.7684855674179518,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004691555981196287,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.19365704208612441,
|
|
"num_tokens": 40978756.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.518925666809082,
|
|
"epoch": 1.768979833926453,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004691377618969367,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.19688959419727325,
|
|
"num_tokens": 40990583.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.492875432968139,
|
|
"epoch": 1.7694741004349546,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046911992089842565,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.19590175449848174,
|
|
"num_tokens": 41002197.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.544542074203491,
|
|
"epoch": 1.769968366943456,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004691020751245344,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.1915643647313118,
|
|
"num_tokens": 41014038.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.52834038734436,
|
|
"epoch": 1.7704626334519573,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000469084224575702,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.19706303924322127,
|
|
"num_tokens": 41025752.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.515138959884643,
|
|
"epoch": 1.7709568999604586,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004690663692523676,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.19924587607383729,
|
|
"num_tokens": 41035974.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.461003923416138,
|
|
"epoch": 1.77145116646896,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046904850915497037,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.19251419156789779,
|
|
"num_tokens": 41047669.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.621628952026367,
|
|
"epoch": 1.7719454329774615,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004690306442839497,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.18471667021512986,
|
|
"num_tokens": 41059123.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.5092278003692625,
|
|
"epoch": 1.7724396994859628,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004690127746397451,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20072084665298462,
|
|
"num_tokens": 41070382.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.5260578155517575,
|
|
"epoch": 1.772933965994464,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046899490022279613,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19836344569921494,
|
|
"num_tokens": 41081672.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.60119857788086,
|
|
"epoch": 1.7734282325029656,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046897702103354256,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.19552964568138123,
|
|
"num_tokens": 41092448.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.542309761047363,
|
|
"epoch": 1.773922499011467,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00046895913707242423,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.19636811763048173,
|
|
"num_tokens": 41103316.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.492154359817505,
|
|
"epoch": 1.7744167655199683,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004689412483398809,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.19610985070466996,
|
|
"num_tokens": 41114991.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.517730808258056,
|
|
"epoch": 1.7749110320284698,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046892335483635284,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.1942640319466591,
|
|
"num_tokens": 41126693.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.550800132751465,
|
|
"epoch": 1.7754052985369713,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004689054565622801,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.19669530242681504,
|
|
"num_tokens": 41138344.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.516938543319702,
|
|
"epoch": 1.7758995650454725,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004688875535181032,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.19675368219614028,
|
|
"num_tokens": 41148962.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.454982137680053,
|
|
"epoch": 1.7763938315539738,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046886964570426226,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19840387105941773,
|
|
"num_tokens": 41159317.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.548730182647705,
|
|
"epoch": 1.7768880980624753,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004688517331211981,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.19122834205627443,
|
|
"num_tokens": 41170646.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.526239633560181,
|
|
"epoch": 1.7773823645709768,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004688338157693511,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.18494340777397156,
|
|
"num_tokens": 41182868.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.483717060089111,
|
|
"epoch": 1.777876631079478,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046881589364916224,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.19731303602457045,
|
|
"num_tokens": 41194556.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.596875286102295,
|
|
"epoch": 1.7783708975879793,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004687979667610722,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19431340843439102,
|
|
"num_tokens": 41207082.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.533771419525147,
|
|
"epoch": 1.778865164096481,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046878003510552224,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.19183267802000045,
|
|
"num_tokens": 41217436.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.490570020675659,
|
|
"epoch": 1.7793594306049823,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004687620986829533,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.1899787187576294,
|
|
"num_tokens": 41228750.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.7793594306049823,
|
|
"eval_entropy": 5.2891372376848995,
|
|
"eval_loss": 5.295458793640137,
|
|
"eval_mean_token_accuracy": 0.19680195989277383,
|
|
"eval_num_tokens": 41228750.0,
|
|
"eval_runtime": 26.6788,
|
|
"eval_samples_per_second": 1218.685,
|
|
"eval_steps_per_second": 152.368,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.468576240539551,
|
|
"epoch": 1.7798536971134835,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046874415749380673,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.18858144730329512,
|
|
"num_tokens": 41239110.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.544873523712158,
|
|
"epoch": 1.780347963621985,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004687262115385237,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19346197694540024,
|
|
"num_tokens": 41251239.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.597715520858765,
|
|
"epoch": 1.7808422301304865,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000468708260817546,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.1915935680270195,
|
|
"num_tokens": 41263996.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.646156454086304,
|
|
"epoch": 1.7813364966389877,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046869030533131493,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.18421408981084825,
|
|
"num_tokens": 41277210.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.483848619461059,
|
|
"epoch": 1.781830763147489,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004686723450802723,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.1920887678861618,
|
|
"num_tokens": 41288383.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.491811800003052,
|
|
"epoch": 1.7823250296559905,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046865438006486,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.19173911660909654,
|
|
"num_tokens": 41300970.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.5892664909362795,
|
|
"epoch": 1.782819296164492,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046863641028551984,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.18799818754196168,
|
|
"num_tokens": 41312289.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.48663215637207,
|
|
"epoch": 1.7833135626729932,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046861843574269395,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.19241384118795396,
|
|
"num_tokens": 41323562.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.557026147842407,
|
|
"epoch": 1.7838078291814945,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004686004564368245,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.19170820116996765,
|
|
"num_tokens": 41335175.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.53490891456604,
|
|
"epoch": 1.7843020956899962,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004685824723683538,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.20350842475891112,
|
|
"num_tokens": 41346160.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.54312219619751,
|
|
"epoch": 1.7847963621984975,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004685644835377242,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.18347469568252564,
|
|
"num_tokens": 41358619.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.608722400665283,
|
|
"epoch": 1.7852906287069987,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046854648994537835,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.20133571177721024,
|
|
"num_tokens": 41369034.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.5399635314941404,
|
|
"epoch": 1.7857848952155002,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004685284915917588,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.19176696836948395,
|
|
"num_tokens": 41380700.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.557255649566651,
|
|
"epoch": 1.7862791617240017,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046851048847730835,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18895739912986756,
|
|
"num_tokens": 41391297.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.571590089797974,
|
|
"epoch": 1.786773428232503,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046849248060246986,
|
|
"loss": 5.3396,
|
|
"mean_token_accuracy": 0.1860628306865692,
|
|
"num_tokens": 41403418.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.593625068664551,
|
|
"epoch": 1.7872676947410042,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046847446796768633,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.18730613142251967,
|
|
"num_tokens": 41414220.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.519608068466186,
|
|
"epoch": 1.7877619612495057,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004684564505734008,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.19413059651851655,
|
|
"num_tokens": 41425933.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.508856773376465,
|
|
"epoch": 1.7882562277580072,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046843842842005665,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.1924084395170212,
|
|
"num_tokens": 41438413.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.498641729354858,
|
|
"epoch": 1.7887504942665085,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004684204015080971,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.20147126764059067,
|
|
"num_tokens": 41449104.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.594761180877685,
|
|
"epoch": 1.78924476077501,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004684023698379657,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.1823282614350319,
|
|
"num_tokens": 41460766.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.532733631134033,
|
|
"epoch": 1.7897390272835114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004683843334101061,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.1846797451376915,
|
|
"num_tokens": 41471872.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.659728002548218,
|
|
"epoch": 1.7902332937920127,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046836629222496174,
|
|
"loss": 5.2932,
|
|
"mean_token_accuracy": 0.1894953116774559,
|
|
"num_tokens": 41483313.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.477589273452759,
|
|
"epoch": 1.790727560300514,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004683482462829766,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.20473727136850356,
|
|
"num_tokens": 41492935.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.513121175765991,
|
|
"epoch": 1.7912218268090154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004683301955845947,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.19245048761367797,
|
|
"num_tokens": 41504159.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.51608624458313,
|
|
"epoch": 1.791716093317517,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046831214013025996,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.20264342427253723,
|
|
"num_tokens": 41515812.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.455065822601318,
|
|
"epoch": 1.7922103598260182,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004682940799204165,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.20371073484420776,
|
|
"num_tokens": 41527109.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.509970664978027,
|
|
"epoch": 1.7927046263345194,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046827601495550884,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19161777794361115,
|
|
"num_tokens": 41537183.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.490711498260498,
|
|
"epoch": 1.793198892843021,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004682579452359811,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.2000148117542267,
|
|
"num_tokens": 41548170.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.518293714523315,
|
|
"epoch": 1.7936931593515224,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000468239870762278,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.19626033157110215,
|
|
"num_tokens": 41558737.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.486280012130737,
|
|
"epoch": 1.7941874258600237,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000468221791534844,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.20166745483875276,
|
|
"num_tokens": 41570096.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.474480390548706,
|
|
"epoch": 1.7946816923685251,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000468203707554124,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.2005093738436699,
|
|
"num_tokens": 41582670.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.46670355796814,
|
|
"epoch": 1.7951759588770266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004681856188205629,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.1998502716422081,
|
|
"num_tokens": 41594300.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.512265586853028,
|
|
"epoch": 1.795670225385528,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004681675253346055,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.1890109196305275,
|
|
"num_tokens": 41606021.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.511445045471191,
|
|
"epoch": 1.7961644918940292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004681494270966971,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.1928473874926567,
|
|
"num_tokens": 41617338.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.532381772994995,
|
|
"epoch": 1.7966587584025306,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004681313241072828,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.1881639391183853,
|
|
"num_tokens": 41628407.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.485298347473145,
|
|
"epoch": 1.7971530249110321,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046811321636680797,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.18931308537721633,
|
|
"num_tokens": 41639715.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.595309591293335,
|
|
"epoch": 1.7976472914195334,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046809510387571806,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.1878529593348503,
|
|
"num_tokens": 41651078.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.500774145126343,
|
|
"epoch": 1.7981415579280347,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004680769866344586,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.18714529871940613,
|
|
"num_tokens": 41661848.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.549495363235474,
|
|
"epoch": 1.7986358244365361,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004680588646434753,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.19183797687292098,
|
|
"num_tokens": 41673452.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.628052997589111,
|
|
"epoch": 1.7991300909450376,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046804073790321403,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.17916780859231948,
|
|
"num_tokens": 41685312.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.564360952377319,
|
|
"epoch": 1.7996243574535389,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046802260641412065,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19583655148744583,
|
|
"num_tokens": 41696849.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.534795141220092,
|
|
"epoch": 1.8001186239620404,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004680044701766413,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19890225529670716,
|
|
"num_tokens": 41707506.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.5615198612213135,
|
|
"epoch": 1.8006128904705418,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004679863291912219,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1895434319972992,
|
|
"num_tokens": 41718981.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.507856702804565,
|
|
"epoch": 1.8011071569790431,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004679681834583089,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.1928344637155533,
|
|
"num_tokens": 41731638.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.498572826385498,
|
|
"epoch": 1.8016014234875444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046795003297834864,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19970372319221497,
|
|
"num_tokens": 41742820.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.481457853317261,
|
|
"epoch": 1.8020956899960459,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046793187775178764,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.19839363247156144,
|
|
"num_tokens": 41754933.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.5394385814666744,
|
|
"epoch": 1.8025899565045473,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004679137177790725,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.1956421285867691,
|
|
"num_tokens": 41767078.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.558980655670166,
|
|
"epoch": 1.8030842230130486,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004678955530606501,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.1866026073694229,
|
|
"num_tokens": 41778456.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.565158843994141,
|
|
"epoch": 1.8035784895215499,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046787738359696697,
|
|
"loss": 5.2579,
|
|
"mean_token_accuracy": 0.18930499702692033,
|
|
"num_tokens": 41791226.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.505015850067139,
|
|
"epoch": 1.8040727560300513,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004678592093884704,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.2005922183394432,
|
|
"num_tokens": 41803765.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.484988880157471,
|
|
"epoch": 1.8045670225385528,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046784103043560736,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.19253033995628357,
|
|
"num_tokens": 41815983.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.507380867004395,
|
|
"epoch": 1.805061289047054,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046782284673882506,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.2053534522652626,
|
|
"num_tokens": 41826517.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.57950873374939,
|
|
"epoch": 1.8055555555555556,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004678046582985708,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.19327814131975174,
|
|
"num_tokens": 41837064.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.480609035491943,
|
|
"epoch": 1.806049822064057,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000467786465115292,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.2011559098958969,
|
|
"num_tokens": 41849109.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.460634422302246,
|
|
"epoch": 1.8065440885725583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004677682671894364,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.20024803429841995,
|
|
"num_tokens": 41859349.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.464912700653076,
|
|
"epoch": 1.8070383550810596,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046775006452145135,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.2021322175860405,
|
|
"num_tokens": 41870002.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.577898120880127,
|
|
"epoch": 1.807532621589561,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004677318571117849,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.19372325986623765,
|
|
"num_tokens": 41881219.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.499504137039184,
|
|
"epoch": 1.8080268880980626,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046771364496088475,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.19468652606010436,
|
|
"num_tokens": 41893318.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.4859026908874515,
|
|
"epoch": 1.8085211546065638,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046769542806919913,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.196625018119812,
|
|
"num_tokens": 41904816.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.569174528121948,
|
|
"epoch": 1.809015421115065,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004676772064371761,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.1917390301823616,
|
|
"num_tokens": 41916293.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.475543785095215,
|
|
"epoch": 1.8095096876235668,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046765898006526384,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.19994967579841613,
|
|
"num_tokens": 41926654.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.471836948394776,
|
|
"epoch": 1.810003954132068,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046764074895391084,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.2002381756901741,
|
|
"num_tokens": 41937141.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.568009519577027,
|
|
"epoch": 1.8104982206405693,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046762251310356544,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.18842424899339677,
|
|
"num_tokens": 41947793.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.5989879131317135,
|
|
"epoch": 1.8109924871490708,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004676042725146764,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19949828386306762,
|
|
"num_tokens": 41958524.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.553232955932617,
|
|
"epoch": 1.8114867536575723,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046758602718769245,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.18997592031955718,
|
|
"num_tokens": 41969654.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.443448209762574,
|
|
"epoch": 1.8119810201660735,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046756777712306225,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.2016655683517456,
|
|
"num_tokens": 41980881.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.568782043457031,
|
|
"epoch": 1.8124752866745748,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004675495223212349,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.19505283534526824,
|
|
"num_tokens": 41992490.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.482295179367066,
|
|
"epoch": 1.8129695531830763,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004675312627826594,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.20318518877029418,
|
|
"num_tokens": 42001765.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.506588268280029,
|
|
"epoch": 1.8134638196915778,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000467512998507785,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20234201550483705,
|
|
"num_tokens": 42013122.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.594823551177979,
|
|
"epoch": 1.813958086200079,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046749472949706095,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18610976189374923,
|
|
"num_tokens": 42023369.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.590537786483765,
|
|
"epoch": 1.8144523527085805,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004674764557509367,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18453815430402756,
|
|
"num_tokens": 42036054.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.532010889053344,
|
|
"epoch": 1.814946619217082,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004674581772698618,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19566470086574556,
|
|
"num_tokens": 42048782.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.527704334259033,
|
|
"epoch": 1.8154408857255833,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046743989405428584,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18970942497253418,
|
|
"num_tokens": 42059438.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.582079696655273,
|
|
"epoch": 1.8159351522340845,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004674216061046587,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19256236106157304,
|
|
"num_tokens": 42070767.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.544105815887451,
|
|
"epoch": 1.816429418742586,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004674033134214301,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.19910824298858643,
|
|
"num_tokens": 42081782.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.475711917877197,
|
|
"epoch": 1.8169236852510875,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046738501600505016,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.19727294594049455,
|
|
"num_tokens": 42094402.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.587206935882568,
|
|
"epoch": 1.8174179517595888,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000467366713855969,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.1865071102976799,
|
|
"num_tokens": 42106772.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.52301139831543,
|
|
"epoch": 1.81791221826809,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046734840697463685,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.2007423922419548,
|
|
"num_tokens": 42118093.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.515331220626831,
|
|
"epoch": 1.8184064847765915,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046733009536150413,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.18787255585193635,
|
|
"num_tokens": 42130319.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.608082723617554,
|
|
"epoch": 1.818900751285093,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004673117790170211,
|
|
"loss": 5.2311,
|
|
"mean_token_accuracy": 0.18926120549440384,
|
|
"num_tokens": 42140867.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.529702949523926,
|
|
"epoch": 1.8193950177935942,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046729345794163847,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.1950422704219818,
|
|
"num_tokens": 42151425.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.608439779281616,
|
|
"epoch": 1.8198892843020957,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046727513213580703,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.18437281996011734,
|
|
"num_tokens": 42163553.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.537456464767456,
|
|
"epoch": 1.8203835508105972,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004672568015999774,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.18934815227985383,
|
|
"num_tokens": 42174968.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.549863815307617,
|
|
"epoch": 1.8208778173190985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046723846633460074,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.18506048768758773,
|
|
"num_tokens": 42186944.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.578513193130493,
|
|
"epoch": 1.8213720838275997,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046722012634012794,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.19282240122556688,
|
|
"num_tokens": 42198096.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.4974127292633055,
|
|
"epoch": 1.8218663503361012,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046720178161701014,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.19774113297462464,
|
|
"num_tokens": 42208782.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.565509986877442,
|
|
"epoch": 1.8223606168446027,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004671834321656988,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.18936699330806733,
|
|
"num_tokens": 42219925.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.563712787628174,
|
|
"epoch": 1.822854883353104,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046716507798664515,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.19534127712249755,
|
|
"num_tokens": 42231140.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.552528715133667,
|
|
"epoch": 1.8233491498616052,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004671467190803008,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.1932540699839592,
|
|
"num_tokens": 42245025.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.5401942253112795,
|
|
"epoch": 1.8238434163701067,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004671283554471174,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.19315559267997742,
|
|
"num_tokens": 42255776.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.527903604507446,
|
|
"epoch": 1.8243376828786082,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004671099870875465,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18832263946533204,
|
|
"num_tokens": 42268016.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.523198747634888,
|
|
"epoch": 1.8248319493871095,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046709161400204034,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.19354638159275056,
|
|
"num_tokens": 42279521.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.528192949295044,
|
|
"epoch": 1.825326215895611,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046707323619105053,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.20106585323810577,
|
|
"num_tokens": 42290537.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.558225154876709,
|
|
"epoch": 1.8258204824041124,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046705485365502926,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.19552043080329895,
|
|
"num_tokens": 42303119.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.56744647026062,
|
|
"epoch": 1.8263147489126137,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046703646639442893,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.19153828024864197,
|
|
"num_tokens": 42314408.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.460977792739868,
|
|
"epoch": 1.826809015421115,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004670180744097017,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.1969706282019615,
|
|
"num_tokens": 42325848.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.507581758499145,
|
|
"epoch": 1.8273032819296164,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004669996777013,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18842137455940247,
|
|
"num_tokens": 42337737.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.477098369598389,
|
|
"epoch": 1.827797548438118,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046698127626967645,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20090474784374238,
|
|
"num_tokens": 42348418.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.555875587463379,
|
|
"epoch": 1.8282918149466192,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004669628701152837,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.1916119188070297,
|
|
"num_tokens": 42358665.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.577329015731811,
|
|
"epoch": 1.8287860814551204,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004669444592385746,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.20755899846553802,
|
|
"num_tokens": 42369030.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.532495450973511,
|
|
"epoch": 1.829280347963622,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046692604364000203,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.19128282815217973,
|
|
"num_tokens": 42380751.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.490655183792114,
|
|
"epoch": 1.8297746144721234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000466907623320019,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19372829049825668,
|
|
"num_tokens": 42391945.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.559155559539795,
|
|
"epoch": 1.8302688809806247,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046688919827907866,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.19403962641954423,
|
|
"num_tokens": 42403346.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.539839172363282,
|
|
"epoch": 1.8307631474891262,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046687076851763433,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.1869764134287834,
|
|
"num_tokens": 42414895.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.473496150970459,
|
|
"epoch": 1.8312574139976276,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046685233403613927,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.19940180629491805,
|
|
"num_tokens": 42426951.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.519688558578491,
|
|
"epoch": 1.831751680506129,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046683389483504704,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.19238704741001128,
|
|
"num_tokens": 42438313.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.521799802780151,
|
|
"epoch": 1.8322459470146302,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004668154509148112,
|
|
"loss": 5.2069,
|
|
"mean_token_accuracy": 0.1924550488591194,
|
|
"num_tokens": 42448592.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.539303159713745,
|
|
"epoch": 1.8327402135231317,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046679700227588556,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19203598648309708,
|
|
"num_tokens": 42460732.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.601578187942505,
|
|
"epoch": 1.8332344800316331,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046677854891872384,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.19274342358112334,
|
|
"num_tokens": 42472862.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.522445249557495,
|
|
"epoch": 1.8337287465401344,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004667600908437802,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.19672422409057616,
|
|
"num_tokens": 42483227.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.412930631637574,
|
|
"epoch": 1.8342230130486357,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046674162805150843,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.2085564613342285,
|
|
"num_tokens": 42495414.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.491389369964599,
|
|
"epoch": 1.8347172795571374,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046672316054236293,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.19775208532810212,
|
|
"num_tokens": 42507908.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.4667493343353275,
|
|
"epoch": 1.8352115460656386,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046670468831679795,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.2005003124475479,
|
|
"num_tokens": 42519228.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.479134559631348,
|
|
"epoch": 1.83570581257414,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004666862113752679,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.20392893999814987,
|
|
"num_tokens": 42530571.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.515158033370971,
|
|
"epoch": 1.8362000790826414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004666677297182273,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.19350088089704515,
|
|
"num_tokens": 42541781.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.526451492309571,
|
|
"epoch": 1.8366943455911429,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004666492433461308,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.1916348844766617,
|
|
"num_tokens": 42553912.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.413645315170288,
|
|
"epoch": 1.8371886120996441,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004666307522594332,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20849093645811081,
|
|
"num_tokens": 42565812.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.528514719009399,
|
|
"epoch": 1.8376828786081454,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004666122564585893,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.19098139703273773,
|
|
"num_tokens": 42578177.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.541162729263306,
|
|
"epoch": 1.8381771451166469,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046659375594405427,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.19378112852573395,
|
|
"num_tokens": 42590336.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.5639872550964355,
|
|
"epoch": 1.8386714116251484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046657525071628307,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.19415355920791627,
|
|
"num_tokens": 42601438.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.489047622680664,
|
|
"epoch": 1.8391656781336496,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046655674077573104,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.1937595635652542,
|
|
"num_tokens": 42612572.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.574751710891723,
|
|
"epoch": 1.839659944642151,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046653822612285336,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.18954311907291413,
|
|
"num_tokens": 42623138.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.483731508255005,
|
|
"epoch": 1.8401542111506526,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046651970675810574,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.20357498973608018,
|
|
"num_tokens": 42635694.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.601446676254272,
|
|
"epoch": 1.8406484776591538,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004665011826819435,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.19077494293451308,
|
|
"num_tokens": 42648371.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.569435548782349,
|
|
"epoch": 1.841142744167655,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046648265389482245,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.1878170669078827,
|
|
"num_tokens": 42659229.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.472629117965698,
|
|
"epoch": 1.8416370106761566,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004664641203971985,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.19807349145412445,
|
|
"num_tokens": 42669991.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.4637744426727295,
|
|
"epoch": 1.842131277184658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046644558218952745,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.2018835037946701,
|
|
"num_tokens": 42681091.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.542913341522217,
|
|
"epoch": 1.8426255436931593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046642703927226534,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.19262541085481644,
|
|
"num_tokens": 42691928.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.485183143615723,
|
|
"epoch": 1.8431198102016606,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004664084916458684,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.19748211652040482,
|
|
"num_tokens": 42704611.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.544329738616943,
|
|
"epoch": 1.843614076710162,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004663899393107929,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19693227112293243,
|
|
"num_tokens": 42715223.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.468583774566651,
|
|
"epoch": 1.8441083432186636,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004663713822674952,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.19769122302532197,
|
|
"num_tokens": 42728177.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.56872410774231,
|
|
"epoch": 1.8446026097271648,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046635282051643166,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.18926947861909865,
|
|
"num_tokens": 42738469.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.490735673904419,
|
|
"epoch": 1.8450968762356663,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004663342540580593,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.20131054818630217,
|
|
"num_tokens": 42749915.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.590964317321777,
|
|
"epoch": 1.8455911427441678,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004663156828928344,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.186884605884552,
|
|
"num_tokens": 42762679.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.613088083267212,
|
|
"epoch": 1.846085409252669,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004662971070212141,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19018143117427827,
|
|
"num_tokens": 42775351.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.47185959815979,
|
|
"epoch": 1.8465796757611703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046627852644365525,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19244648814201354,
|
|
"num_tokens": 42785435.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.523907804489136,
|
|
"epoch": 1.8470739422696718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046625994116061505,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.1869177043437958,
|
|
"num_tokens": 42795737.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.5867784976959225,
|
|
"epoch": 1.8475682087781733,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004662413511725506,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.19613810777664184,
|
|
"num_tokens": 42806965.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.5968346118927,
|
|
"epoch": 1.8480624752866746,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004662227564799192,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.18881772458553314,
|
|
"num_tokens": 42818346.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.432278728485107,
|
|
"epoch": 1.8485567417951758,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046620415708317834,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.19982812851667403,
|
|
"num_tokens": 42829838.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.585492563247681,
|
|
"epoch": 1.8490510083036773,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004661855529827856,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19135208576917648,
|
|
"num_tokens": 42841212.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.471965408325195,
|
|
"epoch": 1.8495452748121788,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046616694417919854,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20399893820285797,
|
|
"num_tokens": 42853237.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.485932159423828,
|
|
"epoch": 1.85003954132068,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046614833067287504,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.1908968895673752,
|
|
"num_tokens": 42864000.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.506905889511108,
|
|
"epoch": 1.8505338078291815,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046612971246427293,
|
|
"loss": 5.1074,
|
|
"mean_token_accuracy": 0.20181062668561936,
|
|
"num_tokens": 42874491.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.527979707717895,
|
|
"epoch": 1.851028074337683,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046611108955385024,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.1825220838189125,
|
|
"num_tokens": 42885947.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.563817310333252,
|
|
"epoch": 1.8515223408461843,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004660924619420651,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.1914874404668808,
|
|
"num_tokens": 42897907.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.553960180282592,
|
|
"epoch": 1.8520166073546855,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004660738296293758,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.19928926825523377,
|
|
"num_tokens": 42909332.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.578848075866699,
|
|
"epoch": 1.852510873863187,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046605519261624055,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.18840559124946593,
|
|
"num_tokens": 42921877.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.524515962600708,
|
|
"epoch": 1.8530051403716885,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046603655090311796,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.19105300754308702,
|
|
"num_tokens": 42933381.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.542705869674682,
|
|
"epoch": 1.8534994068801898,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004660179044904666,
|
|
"loss": 5.2249,
|
|
"mean_token_accuracy": 0.19202864021062852,
|
|
"num_tokens": 42944756.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.57293930053711,
|
|
"epoch": 1.853993673388691,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046599925337874516,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.19011552333831788,
|
|
"num_tokens": 42955587.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.628411054611206,
|
|
"epoch": 1.8544879398971925,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046598059756841246,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.18678074926137925,
|
|
"num_tokens": 42966150.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.597689914703369,
|
|
"epoch": 1.854982206405694,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004659619370599274,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19081854224205017,
|
|
"num_tokens": 42978626.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.431185245513916,
|
|
"epoch": 1.8554764729141953,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046594327185374906,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.20490580201148986,
|
|
"num_tokens": 42989194.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.430685710906983,
|
|
"epoch": 1.8559707394226967,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046592460195033663,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.20021786838769912,
|
|
"num_tokens": 43000589.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.470165777206421,
|
|
"epoch": 1.8564650059311982,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004659059273501494,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.20191795229911805,
|
|
"num_tokens": 43011417.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.5574767112731935,
|
|
"epoch": 1.8569592724396995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004658872480536467,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.1877949059009552,
|
|
"num_tokens": 43023178.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.527057743072509,
|
|
"epoch": 1.8574535389482008,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046586856406128805,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.18448401391506195,
|
|
"num_tokens": 43035526.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.529011869430542,
|
|
"epoch": 1.8579478054567022,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004658498753735332,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.19690977931022643,
|
|
"num_tokens": 43046681.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.52537899017334,
|
|
"epoch": 1.8584420719652037,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046583118199084177,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.19307512640953065,
|
|
"num_tokens": 43058514.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.552279329299926,
|
|
"epoch": 1.858936338473705,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004658124839136737,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.1853627845644951,
|
|
"num_tokens": 43069588.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.511452102661133,
|
|
"epoch": 1.8594306049822062,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004657937811424889,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.20344630032777786,
|
|
"num_tokens": 43080811.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.598021841049194,
|
|
"epoch": 1.859924871490708,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004657750736777474,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.19239753633737564,
|
|
"num_tokens": 43093506.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.456067943572998,
|
|
"epoch": 1.8604191379992092,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046575636151990955,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1979425698518753,
|
|
"num_tokens": 43105272.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.552865362167358,
|
|
"epoch": 1.8609134045077105,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046573764466943565,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.1937562867999077,
|
|
"num_tokens": 43116070.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.550370550155639,
|
|
"epoch": 1.861407671016212,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046571892312678606,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19283310770988465,
|
|
"num_tokens": 43126347.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.5663737773895265,
|
|
"epoch": 1.8619019375247134,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046570019689242136,
|
|
"loss": 5.2908,
|
|
"mean_token_accuracy": 0.18626917749643326,
|
|
"num_tokens": 43138752.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.60042176246643,
|
|
"epoch": 1.8623962040332147,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004656814659668023,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1827007606625557,
|
|
"num_tokens": 43151283.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.569787788391113,
|
|
"epoch": 1.862890470541716,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046566273035038953,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19521875381469728,
|
|
"num_tokens": 43161643.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.538996267318725,
|
|
"epoch": 1.8633847370502175,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046564399004364403,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19386654794216157,
|
|
"num_tokens": 43171966.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.494546794891358,
|
|
"epoch": 1.863879003558719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046562524504702683,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.1969500035047531,
|
|
"num_tokens": 43183022.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.530912399291992,
|
|
"epoch": 1.8643732700672202,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046560649536099905,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.19580879360437392,
|
|
"num_tokens": 43194927.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.501154279708862,
|
|
"epoch": 1.8648675365757215,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004655877409860218,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.2083970010280609,
|
|
"num_tokens": 43205519.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.467885828018188,
|
|
"epoch": 1.8653618030842232,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046556898192255664,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.18045850992202758,
|
|
"num_tokens": 43217805.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.516713714599609,
|
|
"epoch": 1.8658560695927244,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046555021817106494,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1922693982720375,
|
|
"num_tokens": 43228394.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.587920331954956,
|
|
"epoch": 1.8663503361012257,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046553144973200835,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.19349315017461777,
|
|
"num_tokens": 43240204.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.570528125762939,
|
|
"epoch": 1.8668446026097272,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004655126766058485,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.18732690066099167,
|
|
"num_tokens": 43251103.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.42922887802124,
|
|
"epoch": 1.8673388691182287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046549389879304724,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.1977396547794342,
|
|
"num_tokens": 43263653.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.517672729492188,
|
|
"epoch": 1.86783313562673,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004654751162940665,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.1987312838435173,
|
|
"num_tokens": 43274893.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.508763217926026,
|
|
"epoch": 1.8683274021352312,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004654563291093684,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.19902144372463226,
|
|
"num_tokens": 43287510.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.517113161087036,
|
|
"epoch": 1.8688216686437327,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004654375372394151,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.19231631159782409,
|
|
"num_tokens": 43299735.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.532447338104248,
|
|
"epoch": 1.8693159351522342,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046541874068466876,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.2059502586722374,
|
|
"num_tokens": 43310401.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.490570783615112,
|
|
"epoch": 1.8698102016607354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046539993944559187,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.19156945645809173,
|
|
"num_tokens": 43321300.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.521349716186523,
|
|
"epoch": 1.870304468169237,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000465381133522647,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.1942028895020485,
|
|
"num_tokens": 43332304.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.508532524108887,
|
|
"epoch": 1.8707987346777384,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004653623229162966,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19110133200883866,
|
|
"num_tokens": 43343524.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.539400863647461,
|
|
"epoch": 1.8712930011862396,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046534350762700354,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.18935936242341994,
|
|
"num_tokens": 43353364.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.434255743026734,
|
|
"epoch": 1.871787267694741,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046532468765523075,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.21034334003925323,
|
|
"num_tokens": 43365660.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.607839441299438,
|
|
"epoch": 1.8722815342032424,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046530586300144104,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.19041870385408402,
|
|
"num_tokens": 43376882.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.577685689926147,
|
|
"epoch": 1.8727758007117439,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046528703366609757,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.20087796449661255,
|
|
"num_tokens": 43387872.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.564546346664429,
|
|
"epoch": 1.8732700672202451,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046526819964966363,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.19033182114362718,
|
|
"num_tokens": 43399162.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.562938499450683,
|
|
"epoch": 1.8737643337287464,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004652493609526024,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1930837094783783,
|
|
"num_tokens": 43410163.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.536819648742676,
|
|
"epoch": 1.8742586002372479,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004652305175753774,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.19213214069604873,
|
|
"num_tokens": 43421841.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.500298643112183,
|
|
"epoch": 1.8747528667457494,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004652116695184521,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19933253526687622,
|
|
"num_tokens": 43432301.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.563700819015503,
|
|
"epoch": 1.8752471332542506,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004651928167822903,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.19415659606456756,
|
|
"num_tokens": 43443531.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.433812284469605,
|
|
"epoch": 1.8757413997627521,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004651739593673556,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.20151504129171371,
|
|
"num_tokens": 43455230.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.5328610897064205,
|
|
"epoch": 1.8762356662712536,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004651550972741121,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.19307408034801482,
|
|
"num_tokens": 43466342.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.606976127624511,
|
|
"epoch": 1.8767299327797549,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004651362305030237,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.18711655735969543,
|
|
"num_tokens": 43477962.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.508572673797607,
|
|
"epoch": 1.8772241992882561,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004651173590545545,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.196053209900856,
|
|
"num_tokens": 43489252.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.572917795181274,
|
|
"epoch": 1.8777184657967576,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046509848292916877,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.19838113635778426,
|
|
"num_tokens": 43499199.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.49938645362854,
|
|
"epoch": 1.878212732305259,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046507960212733093,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.19593898057937623,
|
|
"num_tokens": 43509812.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.422563982009888,
|
|
"epoch": 1.8787069988137604,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046506071664950525,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.204907688498497,
|
|
"num_tokens": 43521197.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.508275508880615,
|
|
"epoch": 1.8792012653222616,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046504182649615664,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19999522417783738,
|
|
"num_tokens": 43532826.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.580616760253906,
|
|
"epoch": 1.879695531830763,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046502293166774945,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.18869533985853196,
|
|
"num_tokens": 43544617.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.465098190307617,
|
|
"epoch": 1.8801897983392646,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004650040321647487,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20840506255626678,
|
|
"num_tokens": 43556006.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.511151456832886,
|
|
"epoch": 1.8806840648477658,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004649851279876193,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19512178599834443,
|
|
"num_tokens": 43567112.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.506835794448852,
|
|
"epoch": 1.8811783313562673,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004649662191368263,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.19512265026569367,
|
|
"num_tokens": 43577974.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.469696855545044,
|
|
"epoch": 1.8816725978647688,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004649473056128349,
|
|
"loss": 5.105,
|
|
"mean_token_accuracy": 0.20685658603906631,
|
|
"num_tokens": 43588723.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.488686180114746,
|
|
"epoch": 1.88216686437327,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004649283874161102,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20136795789003373,
|
|
"num_tokens": 43599721.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.555668544769287,
|
|
"epoch": 1.8826611308817713,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004649094645471177,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.191910982131958,
|
|
"num_tokens": 43610517.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.596533346176147,
|
|
"epoch": 1.8831553973902728,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000464890537006323,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.18972000032663344,
|
|
"num_tokens": 43622547.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.579787015914917,
|
|
"epoch": 1.8836496638987743,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004648716047941916,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.19579086303710938,
|
|
"num_tokens": 43633982.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.4942474365234375,
|
|
"epoch": 1.8841439304072756,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004648526679111892,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.19868555217981337,
|
|
"num_tokens": 43644888.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.517919635772705,
|
|
"epoch": 1.8846381969157768,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004648337263577818,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.195791794359684,
|
|
"num_tokens": 43658352.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.445917558670044,
|
|
"epoch": 1.8851324634242785,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046481478013443527,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.203877954185009,
|
|
"num_tokens": 43669127.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.523909282684326,
|
|
"epoch": 1.8856267299327798,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004647958292416157,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.1938689425587654,
|
|
"num_tokens": 43681504.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.437761497497559,
|
|
"epoch": 1.886120996441281,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004647768736797893,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.19982336461544037,
|
|
"num_tokens": 43691396.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.478637981414795,
|
|
"epoch": 1.8866152629497825,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046475791344942227,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.20185624063014984,
|
|
"num_tokens": 43703761.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.463360118865967,
|
|
"epoch": 1.887109529458284,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004647389485509812,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.20048776268959045,
|
|
"num_tokens": 43715041.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.602008819580078,
|
|
"epoch": 1.8876037959667853,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046471997898493256,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.1915571093559265,
|
|
"num_tokens": 43727060.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.555822849273682,
|
|
"epoch": 1.8880980624752866,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000464701004751743,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.18290338814258575,
|
|
"num_tokens": 43738996.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.493233299255371,
|
|
"epoch": 1.888592328983788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004646820258518793,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.19836610853672026,
|
|
"num_tokens": 43749415.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.443238306045532,
|
|
"epoch": 1.8890865954922895,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004646630422858083,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.20100516080856323,
|
|
"num_tokens": 43760289.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.555305624008179,
|
|
"epoch": 1.8895808620007908,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046464405405399707,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19670433402061463,
|
|
"num_tokens": 43771267.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.651031541824341,
|
|
"epoch": 1.890075128509292,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046462506115691274,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.2008487418293953,
|
|
"num_tokens": 43782584.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.54867901802063,
|
|
"epoch": 1.8905693950177938,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046460606359502237,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.18777008801698686,
|
|
"num_tokens": 43792738.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.526866340637207,
|
|
"epoch": 1.891063661526295,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046458706136879354,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.19497581273317338,
|
|
"num_tokens": 43804117.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.567939805984497,
|
|
"epoch": 1.8915579280347963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645680544786935,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.18936678916215896,
|
|
"num_tokens": 43817367.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.517854642868042,
|
|
"epoch": 1.8920521945432978,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046454904292518996,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.19367168396711348,
|
|
"num_tokens": 43829213.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.562341833114624,
|
|
"epoch": 1.8925464610517992,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046453002670875055,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.1972803518176079,
|
|
"num_tokens": 43839939.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.591237545013428,
|
|
"epoch": 1.8930407275603005,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046451100582984304,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.19966364949941634,
|
|
"num_tokens": 43850411.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.472397994995117,
|
|
"epoch": 1.8935349940688018,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004644919802889354,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.1900568813085556,
|
|
"num_tokens": 43861083.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.548755931854248,
|
|
"epoch": 1.8940292605773033,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046447295008649576,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.19522689282894135,
|
|
"num_tokens": 43871712.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.5979931354522705,
|
|
"epoch": 1.8945235270858047,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046445391522299204,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.19141656905412674,
|
|
"num_tokens": 43884617.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.509905624389648,
|
|
"epoch": 1.895017793594306,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046443487569889264,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.19534470289945602,
|
|
"num_tokens": 43895533.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.542101907730102,
|
|
"epoch": 1.8955120601028075,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046441583151466586,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.19244514256715775,
|
|
"num_tokens": 43906616.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.552696657180786,
|
|
"epoch": 1.896006326611309,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004643967826707803,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19116513878107072,
|
|
"num_tokens": 43917389.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.51521635055542,
|
|
"epoch": 1.8965005931198102,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004643777291677045,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19233837872743606,
|
|
"num_tokens": 43929239.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.605667686462402,
|
|
"epoch": 1.8969948596283115,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004643586710059072,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.19229089170694352,
|
|
"num_tokens": 43940267.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.575194692611694,
|
|
"epoch": 1.897489126136813,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046433960818585717,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.1959397614002228,
|
|
"num_tokens": 43951505.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.513193130493164,
|
|
"epoch": 1.8979833926453145,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046432054070802344,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.1976376071572304,
|
|
"num_tokens": 43963669.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.470347547531128,
|
|
"epoch": 1.8984776591538157,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046430146857287497,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.19437871277332305,
|
|
"num_tokens": 43975814.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.493502426147461,
|
|
"epoch": 1.898971925662317,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046428239178088106,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.1962042421102524,
|
|
"num_tokens": 43987305.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.568238973617554,
|
|
"epoch": 1.8994661921708185,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046426331033251096,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.19995055049657823,
|
|
"num_tokens": 43997441.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.561341857910156,
|
|
"epoch": 1.89996045867932,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000464244224228234,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.19534057527780532,
|
|
"num_tokens": 44008718.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.536561346054077,
|
|
"epoch": 1.9004547251878212,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004642251334685199,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.19376037567853927,
|
|
"num_tokens": 44020785.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.480124807357788,
|
|
"epoch": 1.9009489916963227,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046420603805383796,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19878680109977723,
|
|
"num_tokens": 44031360.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.4915674209594725,
|
|
"epoch": 1.9014432582048242,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004641869379846583,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.20085185319185256,
|
|
"num_tokens": 44042510.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.533618068695068,
|
|
"epoch": 1.9019375247133254,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046416783326145065,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.19150640517473222,
|
|
"num_tokens": 44053800.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.465390968322754,
|
|
"epoch": 1.9024317912218267,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004641487238846848,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.19659289419651033,
|
|
"num_tokens": 44066727.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.548568820953369,
|
|
"epoch": 1.9029260577303282,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046412960985483105,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19312512278556823,
|
|
"num_tokens": 44077863.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.483467245101929,
|
|
"epoch": 1.9034203242388297,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004641104911723596,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.20606402158737183,
|
|
"num_tokens": 44088218.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.5975278377532955,
|
|
"epoch": 1.903914590747331,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004640913678377407,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.19312585294246673,
|
|
"num_tokens": 44101236.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.508967733383178,
|
|
"epoch": 1.9044088572558322,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004640722398514448,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.19148492962121963,
|
|
"num_tokens": 44114185.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.467040777206421,
|
|
"epoch": 1.9049031237643337,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046405310721394245,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.19469936788082123,
|
|
"num_tokens": 44126060.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.5012561798095705,
|
|
"epoch": 1.9053973902728352,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004640339699257044,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19494916945695878,
|
|
"num_tokens": 44137709.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.5068464279174805,
|
|
"epoch": 1.9058916567813364,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004640148279872013,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.19337964355945586,
|
|
"num_tokens": 44150042.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.5614903450012205,
|
|
"epoch": 1.906385923289838,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046399568139890413,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19510147124528884,
|
|
"num_tokens": 44162926.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.511294031143189,
|
|
"epoch": 1.9068801897983394,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046397653016128396,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20161001980304719,
|
|
"num_tokens": 44174211.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.597979784011841,
|
|
"epoch": 1.9073744563068407,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004639573742748117,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.18187638223171235,
|
|
"num_tokens": 44187127.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.54038724899292,
|
|
"epoch": 1.907868722815342,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046393821373995884,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.19397292733192445,
|
|
"num_tokens": 44199335.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.465989637374878,
|
|
"epoch": 1.9083629893238434,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046391904855719654,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.20818663537502288,
|
|
"num_tokens": 44209911.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.457798814773559,
|
|
"epoch": 1.908857255832345,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046389987872699637,
|
|
"loss": 5.1082,
|
|
"mean_token_accuracy": 0.20085451602935792,
|
|
"num_tokens": 44221391.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.488866949081421,
|
|
"epoch": 1.9093515223408462,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046388070424982985,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.20372474938631058,
|
|
"num_tokens": 44233138.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.507642793655395,
|
|
"epoch": 1.9098457888493474,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004638615251261687,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.20073955059051513,
|
|
"num_tokens": 44244353.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.527268600463867,
|
|
"epoch": 1.910340055357849,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046384234135648475,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.19410845935344695,
|
|
"num_tokens": 44256369.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.5487102508544925,
|
|
"epoch": 1.9108343218663504,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.00046382315294124987,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.19355581253767012,
|
|
"num_tokens": 44267958.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.523752498626709,
|
|
"epoch": 1.9113285883748516,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004638039598809361,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.19291318506002425,
|
|
"num_tokens": 44279379.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.542164611816406,
|
|
"epoch": 1.9118228548833531,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004637847621760158,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.19453615546226502,
|
|
"num_tokens": 44289655.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.570203018188477,
|
|
"epoch": 1.9123171213918546,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046376555982696093,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.19205742329359055,
|
|
"num_tokens": 44301642.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.547519588470459,
|
|
"epoch": 1.9128113879003559,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000463746352834244,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.19460185915231704,
|
|
"num_tokens": 44313260.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.52597279548645,
|
|
"epoch": 1.9133056544088571,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004637271411983375,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.19090783596038818,
|
|
"num_tokens": 44325095.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.5516805171966555,
|
|
"epoch": 1.9137999209173586,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004637079249197141,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.1951184943318367,
|
|
"num_tokens": 44337381.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.484254693984985,
|
|
"epoch": 1.91429418742586,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046368870399884644,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.20437274426221846,
|
|
"num_tokens": 44348487.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.442330360412598,
|
|
"epoch": 1.9147884539343614,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046366947843620737,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.20342880636453628,
|
|
"num_tokens": 44358645.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.4713856220245365,
|
|
"epoch": 1.9152827204428626,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046365024823226994,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20335001349449158,
|
|
"num_tokens": 44369924.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.508076429367065,
|
|
"epoch": 1.9157769869513643,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004636310133875071,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.19533093869686127,
|
|
"num_tokens": 44381684.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.608884239196778,
|
|
"epoch": 1.9162712534598656,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046361177390239204,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.1906208038330078,
|
|
"num_tokens": 44392780.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.562423324584961,
|
|
"epoch": 1.9167655199683669,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004635925297773981,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.19062730222940444,
|
|
"num_tokens": 44405330.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.579905843734741,
|
|
"epoch": 1.9172597864768683,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004635732810129987,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.19088282734155654,
|
|
"num_tokens": 44416307.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.561633443832397,
|
|
"epoch": 1.9177540529853698,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004635540276096673,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.18919444978237152,
|
|
"num_tokens": 44427481.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.46920108795166,
|
|
"epoch": 1.918248319493871,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046353476956787756,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.19697362035512925,
|
|
"num_tokens": 44439462.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.515630292892456,
|
|
"epoch": 1.9187425860023724,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046351550688810317,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.18510069251060485,
|
|
"num_tokens": 44452206.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.516681051254272,
|
|
"epoch": 1.9192368525108738,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004634962395708182,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1965422585606575,
|
|
"num_tokens": 44463598.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.531288433074951,
|
|
"epoch": 1.9197311190193753,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046347696761649647,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.20077922195196152,
|
|
"num_tokens": 44475606.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.5066019058227536,
|
|
"epoch": 1.9202253855278766,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000463457691025612,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.1923340454697609,
|
|
"num_tokens": 44486948.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.542650032043457,
|
|
"epoch": 1.920719652036378,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046343840979863924,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.1972892850637436,
|
|
"num_tokens": 44497408.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.547056388854981,
|
|
"epoch": 1.9212139185448796,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046341912393605225,
|
|
"loss": 5.1895,
|
|
"mean_token_accuracy": 0.20041434615850448,
|
|
"num_tokens": 44508246.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.4086192607879635,
|
|
"epoch": 1.9217081850533808,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004633998334383256,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.1998931124806404,
|
|
"num_tokens": 44520207.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.498799133300781,
|
|
"epoch": 1.922202451561882,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046338053830593384,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.19634246528148652,
|
|
"num_tokens": 44532290.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.566289377212525,
|
|
"epoch": 1.9226967180703836,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004633612385393516,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1916256695985794,
|
|
"num_tokens": 44544305.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.52549376487732,
|
|
"epoch": 1.923190984578885,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004633419341390537,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18628560304641723,
|
|
"num_tokens": 44556753.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.550348377227783,
|
|
"epoch": 1.9236852510873863,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000463322625105515,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.1923278108239174,
|
|
"num_tokens": 44567891.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.517290258407593,
|
|
"epoch": 1.9241795175958876,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046330331143921045,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20252233296632766,
|
|
"num_tokens": 44579060.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.483224487304687,
|
|
"epoch": 1.924673784104389,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046328399314061525,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.19527488052845002,
|
|
"num_tokens": 44591748.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.470106410980224,
|
|
"epoch": 1.9251680506128905,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004632646702102046,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.20061512887477875,
|
|
"num_tokens": 44603119.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.560625696182251,
|
|
"epoch": 1.9256623171213918,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004632453426484539,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.19015513360500336,
|
|
"num_tokens": 44614391.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.464627695083618,
|
|
"epoch": 1.9261565836298933,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046322601045583863,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.21154876351356505,
|
|
"num_tokens": 44623950.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.408189916610718,
|
|
"epoch": 1.9266508501383948,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004632066736328342,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.20589101910591126,
|
|
"num_tokens": 44635177.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.5244382381439205,
|
|
"epoch": 1.927145116646896,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004631873321799164,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.19371999204158782,
|
|
"num_tokens": 44646956.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.575995635986328,
|
|
"epoch": 1.9276393831553973,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000463167986097561,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19143883287906646,
|
|
"num_tokens": 44658161.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.500201606750489,
|
|
"epoch": 1.9281336496638988,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046314863538624403,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.19434182047843934,
|
|
"num_tokens": 44668823.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.507496547698975,
|
|
"epoch": 1.9286279161724003,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004631292800464414,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.18449480831623077,
|
|
"num_tokens": 44682285.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.59843111038208,
|
|
"epoch": 1.9291221826809015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046310992007862935,
|
|
"loss": 5.2555,
|
|
"mean_token_accuracy": 0.1942831188440323,
|
|
"num_tokens": 44694031.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.529182100296021,
|
|
"epoch": 1.9296164491894028,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000463090555483284,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.18760409504175185,
|
|
"num_tokens": 44705636.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.509855651855469,
|
|
"epoch": 1.9301107156979043,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046307118626088184,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19242329895496368,
|
|
"num_tokens": 44716505.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.465768909454345,
|
|
"epoch": 1.9306049822064058,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004630518124118994,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.1893060639500618,
|
|
"num_tokens": 44729298.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.518139362335205,
|
|
"epoch": 1.931099248714907,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046303243393681307,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19361599087715148,
|
|
"num_tokens": 44740456.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.5427638530731205,
|
|
"epoch": 1.9315935152234085,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046301305083609973,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.19788721054792405,
|
|
"num_tokens": 44752311.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.574045658111572,
|
|
"epoch": 1.93208778173191,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046299366311023624,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.19222961962223054,
|
|
"num_tokens": 44763704.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.47178807258606,
|
|
"epoch": 1.9325820482404112,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004629742707596994,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.2004545360803604,
|
|
"num_tokens": 44775053.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.563348007202149,
|
|
"epoch": 1.9330763147489125,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046295487378496643,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.1857325941324234,
|
|
"num_tokens": 44786734.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.68070068359375,
|
|
"epoch": 1.933570581257414,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00046293547218651427,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.18983806669712067,
|
|
"num_tokens": 44798151.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.636642122268677,
|
|
"epoch": 1.9340648477659155,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004629160659648204,
|
|
"loss": 5.2932,
|
|
"mean_token_accuracy": 0.18740257024765014,
|
|
"num_tokens": 44809354.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.484917545318604,
|
|
"epoch": 1.9345591142744167,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004628966551203622,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19402301013469697,
|
|
"num_tokens": 44820994.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.589383792877197,
|
|
"epoch": 1.935053380782918,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046287723965361704,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.18816012740135193,
|
|
"num_tokens": 44831486.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.572396755218506,
|
|
"epoch": 1.9355476472914195,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004628578195650628,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.19297651797533036,
|
|
"num_tokens": 44844078.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.498125600814819,
|
|
"epoch": 1.936041913799921,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004628383948551769,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.19618012011051178,
|
|
"num_tokens": 44854722.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.498398399353027,
|
|
"epoch": 1.9365361803084222,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004628189655244374,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.19812170863151551,
|
|
"num_tokens": 44866337.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.536134958267212,
|
|
"epoch": 1.9370304468169237,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004627995315733222,
|
|
"loss": 5.2536,
|
|
"mean_token_accuracy": 0.19614814817905427,
|
|
"num_tokens": 44878686.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.574501276016235,
|
|
"epoch": 1.9375247133254252,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046278009300230945,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1925429180264473,
|
|
"num_tokens": 44890339.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.590134048461914,
|
|
"epoch": 1.9380189798339265,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004627606498118772,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.1831576034426689,
|
|
"num_tokens": 44902850.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.49483208656311,
|
|
"epoch": 1.9385132463424277,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004627412020025039,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.19713181704282762,
|
|
"num_tokens": 44914074.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.512724781036377,
|
|
"epoch": 1.9390075128509292,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046272174957466783,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.1924554705619812,
|
|
"num_tokens": 44925665.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.588475704193115,
|
|
"epoch": 1.9395017793594307,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004627022925288476,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.19421699047088622,
|
|
"num_tokens": 44936584.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.541826009750366,
|
|
"epoch": 1.939996045867932,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004626828308655219,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19124154895544052,
|
|
"num_tokens": 44948028.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.486946058273316,
|
|
"epoch": 1.9404903123764332,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046266336458516944,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.20257344394922255,
|
|
"num_tokens": 44959504.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.523728656768799,
|
|
"epoch": 1.940984578884935,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004626438936882691,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.18809611797332765,
|
|
"num_tokens": 44971518.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.479797792434693,
|
|
"epoch": 1.9414788453934362,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046262441817529986,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.19984462559223176,
|
|
"num_tokens": 44982514.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.529291200637817,
|
|
"epoch": 1.9419731119019374,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004626049380467408,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.19876565486192704,
|
|
"num_tokens": 44995198.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.514436817169189,
|
|
"epoch": 1.942467378410439,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046258545330307124,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.19864303469657899,
|
|
"num_tokens": 45008014.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.502376222610474,
|
|
"epoch": 1.9429616449189404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046256596394477037,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.1952040508389473,
|
|
"num_tokens": 45021169.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.4996765613555905,
|
|
"epoch": 1.9434559114274417,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004625464699723177,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.2030446082353592,
|
|
"num_tokens": 45032703.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.4769251346588135,
|
|
"epoch": 1.943950177935943,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004625269713861928,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.20067452043294906,
|
|
"num_tokens": 45044350.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.483365869522094,
|
|
"epoch": 1.9444444444444444,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004625074681868753,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.20440057665109634,
|
|
"num_tokens": 45055431.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.557356071472168,
|
|
"epoch": 1.944938710952946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004624879603748449,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.19615652412176132,
|
|
"num_tokens": 45066801.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.455105495452881,
|
|
"epoch": 1.9454329774614472,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004624684479505817,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.1961444541811943,
|
|
"num_tokens": 45078393.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.511121940612793,
|
|
"epoch": 1.9459272439699487,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004624489309145655,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.19305717200040817,
|
|
"num_tokens": 45090782.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.505396747589112,
|
|
"epoch": 1.9464215104784501,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004624294092672766,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.20324634462594987,
|
|
"num_tokens": 45102079.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.492467212677002,
|
|
"epoch": 1.9469157769869514,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004624098830091951,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.20759920924901962,
|
|
"num_tokens": 45112947.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.503773307800293,
|
|
"epoch": 1.9474100434954527,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046239035214080146,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.19507007598876952,
|
|
"num_tokens": 45124577.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.507853174209595,
|
|
"epoch": 1.9479043100039541,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004623708166625761,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.1931399643421173,
|
|
"num_tokens": 45135380.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.532476329803467,
|
|
"epoch": 1.9483985765124556,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046235127657499945,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19948801398277283,
|
|
"num_tokens": 45146926.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.49687614440918,
|
|
"epoch": 1.9488928430209569,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004623317318785524,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19635287821292877,
|
|
"num_tokens": 45157662.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.447842741012574,
|
|
"epoch": 1.9493871095294582,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004623121825737158,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.20901766121387483,
|
|
"num_tokens": 45170239.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.516043710708618,
|
|
"epoch": 1.9498813760379596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046229262866097034,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.19328995198011398,
|
|
"num_tokens": 45180979.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.473241662979126,
|
|
"epoch": 1.9503756425464611,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004622730701407971,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.19824156165122986,
|
|
"num_tokens": 45191160.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.51560869216919,
|
|
"epoch": 1.9508699090549624,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004622535070136774,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.20164530128240585,
|
|
"num_tokens": 45202865.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.514111423492432,
|
|
"epoch": 1.9513641755634639,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046223393928009233,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.19350674301385878,
|
|
"num_tokens": 45214831.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.616607809066773,
|
|
"epoch": 1.9518584420719653,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046221436694052334,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.1938279777765274,
|
|
"num_tokens": 45226453.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.590557718276978,
|
|
"epoch": 1.9523527085804666,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046219478999545184,
|
|
"loss": 5.252,
|
|
"mean_token_accuracy": 0.1898387625813484,
|
|
"num_tokens": 45237292.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.4391319274902346,
|
|
"epoch": 1.9528469750889679,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004621752084453595,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.20694404393434523,
|
|
"num_tokens": 45248117.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.490885496139526,
|
|
"epoch": 1.9533412415974694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046215562229072796,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.18638332486152648,
|
|
"num_tokens": 45259120.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.514722585678101,
|
|
"epoch": 1.9538355081059708,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046213603153203906,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.200519423186779,
|
|
"num_tokens": 45269554.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.493970537185669,
|
|
"epoch": 1.954329774614472,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004621164361697748,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.19518887996673584,
|
|
"num_tokens": 45281055.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.475023555755615,
|
|
"epoch": 1.9548240411229734,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004620968362044172,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.21210511922836303,
|
|
"num_tokens": 45292430.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.434323024749756,
|
|
"epoch": 1.9553183076314749,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004620772316364483,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.1968799889087677,
|
|
"num_tokens": 45303417.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.503079891204834,
|
|
"epoch": 1.9558125741399763,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004620576224663506,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.18668595105409622,
|
|
"num_tokens": 45315243.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.483978033065796,
|
|
"epoch": 1.9563068406484776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004620380086946063,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.20037011802196503,
|
|
"num_tokens": 45326746.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.53099570274353,
|
|
"epoch": 1.956801107156979,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046201839032169794,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.20297128856182098,
|
|
"num_tokens": 45338199.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.56743016242981,
|
|
"epoch": 1.9572953736654806,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004619987673481082,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.19873281866312026,
|
|
"num_tokens": 45349470.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.467140531539917,
|
|
"epoch": 1.9577896401739818,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046197913977431983,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.192662014067173,
|
|
"num_tokens": 45359735.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.606108570098877,
|
|
"epoch": 1.958283906682483,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046195950760081556,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18429202884435653,
|
|
"num_tokens": 45372960.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.603067398071289,
|
|
"epoch": 1.9587781731909846,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004619398708280784,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.19037337303161622,
|
|
"num_tokens": 45385174.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.472183275222778,
|
|
"epoch": 1.959272439699486,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004619202294565914,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.19888432770967485,
|
|
"num_tokens": 45397013.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.617727041244507,
|
|
"epoch": 1.9597667062079873,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004619005834868378,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.17721214145421982,
|
|
"num_tokens": 45408863.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.492086696624756,
|
|
"epoch": 1.9602609727164886,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004618809329193008,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.19731642603874205,
|
|
"num_tokens": 45420630.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.569605302810669,
|
|
"epoch": 1.96075523922499,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004618612777544639,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.1973314568400383,
|
|
"num_tokens": 45431427.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.531325101852417,
|
|
"epoch": 1.9612495057334915,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046184161799281057,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2045842245221138,
|
|
"num_tokens": 45442649.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.400252437591552,
|
|
"epoch": 1.9617437722419928,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046182195363482444,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.2021012246608734,
|
|
"num_tokens": 45454032.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.507088661193848,
|
|
"epoch": 1.9622380387504943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046180228468098927,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.19498708546161653,
|
|
"num_tokens": 45464706.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.67217321395874,
|
|
"epoch": 1.9627323052589958,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046178261113178894,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.18651085942983628,
|
|
"num_tokens": 45476292.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.466442203521728,
|
|
"epoch": 1.963226571767497,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004617629329877074,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.20189798772335052,
|
|
"num_tokens": 45488189.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.5512552738189695,
|
|
"epoch": 1.9637208382759983,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004617432502492287,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.20093457102775575,
|
|
"num_tokens": 45499825.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.446563959121704,
|
|
"epoch": 1.9642151047844998,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004617235629168371,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20000993758440017,
|
|
"num_tokens": 45511164.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.499841976165771,
|
|
"epoch": 1.9647093712930013,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004617038709910168,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.1924394741654396,
|
|
"num_tokens": 45521506.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.604458332061768,
|
|
"epoch": 1.9652036378015025,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004616841744722524,
|
|
"loss": 5.2822,
|
|
"mean_token_accuracy": 0.1900240257382393,
|
|
"num_tokens": 45531622.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.535613203048706,
|
|
"epoch": 1.9656979043100038,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046166447336102836,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.2034526526927948,
|
|
"num_tokens": 45541565.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.539067602157592,
|
|
"epoch": 1.9661921708185055,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046164476765782927,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.19643321633338928,
|
|
"num_tokens": 45552943.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.526517724990844,
|
|
"epoch": 1.9666864373270068,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046162505736313997,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19842501282691954,
|
|
"num_tokens": 45563914.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.448613548278809,
|
|
"epoch": 1.967180703835508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004616053424774453,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.203948912024498,
|
|
"num_tokens": 45575730.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.585793590545654,
|
|
"epoch": 1.9676749703440095,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046158562300123023,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.1883748173713684,
|
|
"num_tokens": 45588369.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.475204849243164,
|
|
"epoch": 1.968169236852511,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046156589893498,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.206639301776886,
|
|
"num_tokens": 45599235.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.4967423439025875,
|
|
"epoch": 1.9686635033610123,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046154617027917955,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.20643251091241838,
|
|
"num_tokens": 45610066.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.453717184066773,
|
|
"epoch": 1.9691577698695135,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046152643703431447,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19678427129983903,
|
|
"num_tokens": 45621543.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.495439147949218,
|
|
"epoch": 1.969652036378015,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046150669920087004,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.18651559352874755,
|
|
"num_tokens": 45634984.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.583123826980591,
|
|
"epoch": 1.9701463028865165,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004614869567793319,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.19675615131855012,
|
|
"num_tokens": 45646778.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.489727306365967,
|
|
"epoch": 1.9706405693950177,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046146720977018567,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.19970486611127852,
|
|
"num_tokens": 45658103.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.505084228515625,
|
|
"epoch": 1.971134835903519,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004614474581739172,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.1976201578974724,
|
|
"num_tokens": 45669166.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.493601894378662,
|
|
"epoch": 1.9716291024120207,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004614277019910123,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.19180103838443757,
|
|
"num_tokens": 45680667.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.51858172416687,
|
|
"epoch": 1.972123368920522,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004614079412219571,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.1858033761382103,
|
|
"num_tokens": 45692347.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.612951421737671,
|
|
"epoch": 1.9726176354290232,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004613881758672375,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.20128642469644548,
|
|
"num_tokens": 45703972.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.489658546447754,
|
|
"epoch": 1.9731119019375247,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046136840592733995,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.19443113654851912,
|
|
"num_tokens": 45715446.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.492223739624023,
|
|
"epoch": 1.9736061684460262,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046134863140275066,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.2090966671705246,
|
|
"num_tokens": 45727210.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.587111234664917,
|
|
"epoch": 1.9741004349545275,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046132885229395606,
|
|
"loss": 5.1911,
|
|
"mean_token_accuracy": 0.19330028146505357,
|
|
"num_tokens": 45738235.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.507756757736206,
|
|
"epoch": 1.9745947014630287,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004613090686014429,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.20466860234737397,
|
|
"num_tokens": 45750743.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.5562849044799805,
|
|
"epoch": 1.9750889679715302,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046128928032569775,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.1939315602183342,
|
|
"num_tokens": 45761989.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.489864778518677,
|
|
"epoch": 1.9755832344800317,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004612694874672073,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.19157196432352067,
|
|
"num_tokens": 45775046.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.632716846466065,
|
|
"epoch": 1.976077500988533,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004612496900264586,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.19218834340572358,
|
|
"num_tokens": 45786776.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.547646188735962,
|
|
"epoch": 1.9765717674970344,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004612298880039387,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.19744065254926682,
|
|
"num_tokens": 45797675.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.489720106124878,
|
|
"epoch": 1.977066034005536,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004612100814001346,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19318032413721084,
|
|
"num_tokens": 45809897.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.59978494644165,
|
|
"epoch": 1.9775603005140372,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004611902702155336,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.18887944370508195,
|
|
"num_tokens": 45822330.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.551256799697876,
|
|
"epoch": 1.9780545670225385,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004611704544506232,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19460364878177644,
|
|
"num_tokens": 45834705.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.5204408168792725,
|
|
"epoch": 1.97854883353104,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004611506341058906,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.19081057757139205,
|
|
"num_tokens": 45846646.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.49912748336792,
|
|
"epoch": 1.9790431000395414,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046113080918182346,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.19983372688293458,
|
|
"num_tokens": 45857252.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.460262489318848,
|
|
"epoch": 1.9795373665480427,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046111097967890975,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.20248449146747588,
|
|
"num_tokens": 45867780.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.547155952453613,
|
|
"epoch": 1.980031633056544,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004610911455976369,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.18402120918035508,
|
|
"num_tokens": 45878998.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.5322350025177,
|
|
"epoch": 1.9805258995650454,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046107130693849303,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.20368250608444213,
|
|
"num_tokens": 45889685.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.498370218276977,
|
|
"epoch": 1.981020166073547,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004610514637019662,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.20102953165769577,
|
|
"num_tokens": 45900887.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.430790948867798,
|
|
"epoch": 1.9815144325820482,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004610316158885444,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19131952673196792,
|
|
"num_tokens": 45913860.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.558204936981201,
|
|
"epoch": 1.9820086990905497,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004610117634987161,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.1960483595728874,
|
|
"num_tokens": 45924669.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.493277835845947,
|
|
"epoch": 1.9825029655990511,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046099190653296946,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.1928176239132881,
|
|
"num_tokens": 45937013.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.446926021575928,
|
|
"epoch": 1.9829972321075524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004609720449917932,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19652587175369263,
|
|
"num_tokens": 45950063.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.49183988571167,
|
|
"epoch": 1.9834914986160537,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046095217887567565,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.19952152371406556,
|
|
"num_tokens": 45962136.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.528193426132202,
|
|
"epoch": 1.9839857651245552,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004609323081851057,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.19766263514757157,
|
|
"num_tokens": 45974712.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.504102945327759,
|
|
"epoch": 1.9844800316330566,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004609124329205721,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.1997441306710243,
|
|
"num_tokens": 45985670.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.56357970237732,
|
|
"epoch": 1.984974298141558,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004608925530825638,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.18652864098548888,
|
|
"num_tokens": 45997215.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.494392347335816,
|
|
"epoch": 1.9854685646500592,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046087266867156997,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.19543157666921615,
|
|
"num_tokens": 46008479.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.523658084869385,
|
|
"epoch": 1.9859628311585606,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046085277968807955,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.19664957225322724,
|
|
"num_tokens": 46019504.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.481656551361084,
|
|
"epoch": 1.9864570976670621,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004608328861325819,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.19456720352172852,
|
|
"num_tokens": 46030218.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.566786909103394,
|
|
"epoch": 1.9869513641755634,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004608129880055665,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.19572463184595107,
|
|
"num_tokens": 46041767.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.4757753849029545,
|
|
"epoch": 1.9874456306840649,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046079308530752274,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.20440162420272828,
|
|
"num_tokens": 46052792.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.535760164260864,
|
|
"epoch": 1.9879398971925664,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046077317803894024,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.19580111503601075,
|
|
"num_tokens": 46064609.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.502293443679809,
|
|
"epoch": 1.9884341637010676,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046075326620030876,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.19817852079868317,
|
|
"num_tokens": 46075624.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.5212438106536865,
|
|
"epoch": 1.9889284302095689,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046073334979211813,
|
|
"loss": 5.1686,
|
|
"mean_token_accuracy": 0.19768168926239013,
|
|
"num_tokens": 46086455.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.5259734153747555,
|
|
"epoch": 1.9894226967180704,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004607134288148582,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.1926160454750061,
|
|
"num_tokens": 46097362.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.486775302886963,
|
|
"epoch": 1.9899169632265719,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046069350326901915,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.20497328788042068,
|
|
"num_tokens": 46107811.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.585179042816162,
|
|
"epoch": 1.9904112297350731,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004606735731550912,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.17899387180805207,
|
|
"num_tokens": 46120178.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.601426410675049,
|
|
"epoch": 1.9909054962435744,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046065363847356443,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19173710644245148,
|
|
"num_tokens": 46131416.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.538605451583862,
|
|
"epoch": 1.991399762752076,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046063369922492943,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.20433817356824874,
|
|
"num_tokens": 46142195.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.508044862747193,
|
|
"epoch": 1.9918940292605773,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004606137554096766,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.1898285537958145,
|
|
"num_tokens": 46154537.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.566688108444214,
|
|
"epoch": 1.9923882957690786,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004605938070282965,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.1947043389081955,
|
|
"num_tokens": 46166711.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.495877647399903,
|
|
"epoch": 1.99288256227758,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046057385408128013,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.2001448780298233,
|
|
"num_tokens": 46178509.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.479730939865112,
|
|
"epoch": 1.9933768287860816,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000460553896569118,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.19797996133565904,
|
|
"num_tokens": 46188413.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.458347606658935,
|
|
"epoch": 1.9938710952945828,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004605339344923014,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.1922590732574463,
|
|
"num_tokens": 46199708.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.489444971084595,
|
|
"epoch": 1.994365361803084,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046051396785132113,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.19820389449596404,
|
|
"num_tokens": 46210670.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.5551646709442135,
|
|
"epoch": 1.9948596283115856,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004604939966466684,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.1953281581401825,
|
|
"num_tokens": 46220935.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.489569139480591,
|
|
"epoch": 1.995353894820087,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004604740208788347,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.19530354142189027,
|
|
"num_tokens": 46232651.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.536714315414429,
|
|
"epoch": 1.9958481613285883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046045404054831124,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.195644810795784,
|
|
"num_tokens": 46244308.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.600068473815918,
|
|
"epoch": 1.9963424278370896,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046043405565558964,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.18735650479793547,
|
|
"num_tokens": 46256941.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.500215673446656,
|
|
"epoch": 1.9968366943455913,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046041406620116144,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.18821847289800644,
|
|
"num_tokens": 46270557.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.552944040298462,
|
|
"epoch": 1.9973309608540926,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004603940721855185,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.20244454592466354,
|
|
"num_tokens": 46280940.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.511205530166626,
|
|
"epoch": 1.9978252273625938,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004603740736091527,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.19796454757452012,
|
|
"num_tokens": 46292358.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.5436413288116455,
|
|
"epoch": 1.9983194938710953,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004603540704725558,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.19907396882772446,
|
|
"num_tokens": 46303210.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.504530239105224,
|
|
"epoch": 1.9988137603795968,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004603340627762201,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.20324250161647797,
|
|
"num_tokens": 46315152.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.473542356491089,
|
|
"epoch": 1.999308026888098,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046031405052063756,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20562226176261902,
|
|
"num_tokens": 46325776.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.474521160125732,
|
|
"epoch": 1.9998022933965993,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046029403370630086,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.20312228202819824,
|
|
"num_tokens": 46336797.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.533314752578735,
|
|
"epoch": 2.000296559905101,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046027401233370203,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.2005628913640976,
|
|
"num_tokens": 46346327.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.452248907089233,
|
|
"epoch": 2.0007908264136023,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046025398640333373,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.20239225327968596,
|
|
"num_tokens": 46358056.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.440829038619995,
|
|
"epoch": 2.0012850929221035,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046023395591568867,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.20494992136955262,
|
|
"num_tokens": 46369792.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.531151533126831,
|
|
"epoch": 2.001779359430605,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046021392087125957,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.2019851326942444,
|
|
"num_tokens": 46381224.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.561125707626343,
|
|
"epoch": 2.0022736259391065,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004601938812705393,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.19322267770767212,
|
|
"num_tokens": 46393788.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.4832840919494625,
|
|
"epoch": 2.002767892447608,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046017383711402076,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.19516634196043015,
|
|
"num_tokens": 46405742.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.520786333084106,
|
|
"epoch": 2.003262158956109,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004601537884021972,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.20054990500211717,
|
|
"num_tokens": 46417276.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.4488380432128904,
|
|
"epoch": 2.0037564254646103,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004601337351355617,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.21217368990182878,
|
|
"num_tokens": 46427950.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.462737655639648,
|
|
"epoch": 2.004250691973112,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004601136773146075,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.21199732571840285,
|
|
"num_tokens": 46439200.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.558974075317383,
|
|
"epoch": 2.0047449584816133,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004600936149398282,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.19376275241374968,
|
|
"num_tokens": 46451176.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.4821977615356445,
|
|
"epoch": 2.0052392249901145,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046007354801171725,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.2011686772108078,
|
|
"num_tokens": 46462798.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.51851110458374,
|
|
"epoch": 2.0057334914986162,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004600534765307682,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.20007896572351455,
|
|
"num_tokens": 46473914.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.587756824493408,
|
|
"epoch": 2.0062277580071175,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046003340049747513,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.2012421354651451,
|
|
"num_tokens": 46485089.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.541608476638794,
|
|
"epoch": 2.0067220245156188,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004600133199123316,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.2036573737859726,
|
|
"num_tokens": 46497115.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.374216222763062,
|
|
"epoch": 2.00721629102412,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004599932347758316,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21568244993686675,
|
|
"num_tokens": 46508845.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.368466854095459,
|
|
"epoch": 2.0077105575326217,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004599731450884694,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.20415625721216202,
|
|
"num_tokens": 46520105.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.477140951156616,
|
|
"epoch": 2.008204824041123,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004599530508507392,
|
|
"loss": 5.0784,
|
|
"mean_token_accuracy": 0.20133910775184632,
|
|
"num_tokens": 46530701.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.507890748977661,
|
|
"epoch": 2.0086990905496243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004599329520631351,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.19856112599372863,
|
|
"num_tokens": 46542614.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.5043909549713135,
|
|
"epoch": 2.009193357058126,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045991284872615184,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.20848346948623658,
|
|
"num_tokens": 46553624.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.45602126121521,
|
|
"epoch": 2.0096876235666272,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045989274084028375,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19810509234666823,
|
|
"num_tokens": 46565599.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.466525506973267,
|
|
"epoch": 2.0101818900751285,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004598726284060256,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.20549815893173218,
|
|
"num_tokens": 46576730.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.515876388549804,
|
|
"epoch": 2.0106761565836297,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000459852511423872,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.2007232576608658,
|
|
"num_tokens": 46587435.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.439176225662232,
|
|
"epoch": 2.0111704230921315,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004598323898943181,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20668934136629105,
|
|
"num_tokens": 46598431.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.489616537094117,
|
|
"epoch": 2.0116646896006327,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004598122638178586,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.1953104853630066,
|
|
"num_tokens": 46609343.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.5702934741973875,
|
|
"epoch": 2.012158956109134,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045979213319498883,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.2011447072029114,
|
|
"num_tokens": 46621844.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.449167728424072,
|
|
"epoch": 2.0126532226176352,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004597719980262039,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.20054117888212203,
|
|
"num_tokens": 46633278.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.4825520515441895,
|
|
"epoch": 2.013147489126137,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004597518583119991,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.19671673625707625,
|
|
"num_tokens": 46644375.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.541831636428833,
|
|
"epoch": 2.013641755634638,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004597317140528699,
|
|
"loss": 5.1684,
|
|
"mean_token_accuracy": 0.19437800645828246,
|
|
"num_tokens": 46655631.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.445701551437378,
|
|
"epoch": 2.0141360221431395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045971156524931195,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.2124285191297531,
|
|
"num_tokens": 46667095.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.507350921630859,
|
|
"epoch": 2.014630288651641,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004596914119018209,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.19714003354310988,
|
|
"num_tokens": 46678524.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.518720006942749,
|
|
"epoch": 2.0151245551601424,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045967125401089233,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20286975502967836,
|
|
"num_tokens": 46689785.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.495860910415649,
|
|
"epoch": 2.0156188216686437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004596510915770223,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19590726345777512,
|
|
"num_tokens": 46701109.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.4953210830688475,
|
|
"epoch": 2.016113088177145,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004596309246007068,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20461118668317796,
|
|
"num_tokens": 46711381.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.549831485748291,
|
|
"epoch": 2.0166073546856467,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004596107530824419,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.19918929040431976,
|
|
"num_tokens": 46722237.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.436575508117675,
|
|
"epoch": 2.017101621194148,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045959057702272383,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20387003272771836,
|
|
"num_tokens": 46733679.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.564180612564087,
|
|
"epoch": 2.017595887702649,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004595703964220489,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.19382375478744507,
|
|
"num_tokens": 46746207.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.500241994857788,
|
|
"epoch": 2.0180901542111505,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004595502112809137,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.20072818100452422,
|
|
"num_tokens": 46756607.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.490242767333984,
|
|
"epoch": 2.018584420719652,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004595300215998145,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.20125380754470826,
|
|
"num_tokens": 46768383.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.613409090042114,
|
|
"epoch": 2.0190786872281534,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004595098273792482,
|
|
"loss": 5.1585,
|
|
"mean_token_accuracy": 0.193632173538208,
|
|
"num_tokens": 46779511.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.487150096893311,
|
|
"epoch": 2.0195729537366547,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004594896286197116,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.19876699000597,
|
|
"num_tokens": 46791281.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.450695610046386,
|
|
"epoch": 2.0200672202451564,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045946942532170147,
|
|
"loss": 5.1088,
|
|
"mean_token_accuracy": 0.20568579137325288,
|
|
"num_tokens": 46802090.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.480408096313477,
|
|
"epoch": 2.0205614867536577,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004594492174857149,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.19987173676490783,
|
|
"num_tokens": 46814688.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.507055854797363,
|
|
"epoch": 2.021055753262159,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045942900511224886,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20177957266569138,
|
|
"num_tokens": 46826212.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.468183088302612,
|
|
"epoch": 2.02155001977066,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004594087882018008,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.20513266175985337,
|
|
"num_tokens": 46836583.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.481951475143433,
|
|
"epoch": 2.022044286279162,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004593885667548679,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.2002298966050148,
|
|
"num_tokens": 46847973.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.449289274215698,
|
|
"epoch": 2.022538552787663,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045936834077194754,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.198235359787941,
|
|
"num_tokens": 46860113.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.607916641235351,
|
|
"epoch": 2.0230328192961644,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004593481102535375,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.20936962366104125,
|
|
"num_tokens": 46871578.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.486044836044312,
|
|
"epoch": 2.0235270858046657,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045932787520013533,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.20132843554019927,
|
|
"num_tokens": 46883701.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.414364433288574,
|
|
"epoch": 2.0240213523131674,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004593076356122389,
|
|
"loss": 5.0602,
|
|
"mean_token_accuracy": 0.20477647930383683,
|
|
"num_tokens": 46895107.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.43996901512146,
|
|
"epoch": 2.0245156188216686,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000459287391490346,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.2142287239432335,
|
|
"num_tokens": 46906984.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.475747013092041,
|
|
"epoch": 2.02500988533017,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045926714283495466,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.1982148841023445,
|
|
"num_tokens": 46918582.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.522703504562378,
|
|
"epoch": 2.0255041518386716,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045924688964656303,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.2021074652671814,
|
|
"num_tokens": 46930799.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.527202224731445,
|
|
"epoch": 2.025998418347173,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045922663192566926,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.20663172006607056,
|
|
"num_tokens": 46941517.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.4823974609375,
|
|
"epoch": 2.026492684855674,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045920636967277187,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.20146812200546266,
|
|
"num_tokens": 46953160.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.452744197845459,
|
|
"epoch": 2.0269869513641754,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045918610288836915,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.2068669617176056,
|
|
"num_tokens": 46964284.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.527225208282471,
|
|
"epoch": 2.027481217872677,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004591658315729598,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.19729732125997543,
|
|
"num_tokens": 46975402.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.5359409809112545,
|
|
"epoch": 2.0279754843811784,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004591455557270423,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.20234152376651765,
|
|
"num_tokens": 46988629.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.505955600738526,
|
|
"epoch": 2.0284697508896796,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045912527535111567,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.20467866212129593,
|
|
"num_tokens": 47000497.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.467528629302978,
|
|
"epoch": 2.028964017398181,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045910499044567865,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.19712900519371032,
|
|
"num_tokens": 47010841.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.474954891204834,
|
|
"epoch": 2.0294582839066826,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004590847010112303,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.2015874356031418,
|
|
"num_tokens": 47023131.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.5322222232818605,
|
|
"epoch": 2.029952550415184,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045906440704826973,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.20346480906009673,
|
|
"num_tokens": 47034363.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.471569633483886,
|
|
"epoch": 2.030446816923685,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004590441085572962,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.19701913893222808,
|
|
"num_tokens": 47045584.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.540451526641846,
|
|
"epoch": 2.030941083432187,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045902380553880913,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.20306239277124405,
|
|
"num_tokens": 47056245.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.489695072174072,
|
|
"epoch": 2.031435349940688,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004590034979933078,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.20536917001008986,
|
|
"num_tokens": 47067856.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.426219511032104,
|
|
"epoch": 2.0319296164491893,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045898318592129197,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.20924043506383896,
|
|
"num_tokens": 47079316.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.516140270233154,
|
|
"epoch": 2.0324238829576906,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045896286932326115,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19470874071121216,
|
|
"num_tokens": 47090268.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.500525617599488,
|
|
"epoch": 2.0329181494661923,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004589425481997152,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.20211490392684936,
|
|
"num_tokens": 47100980.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.53579626083374,
|
|
"epoch": 2.0334124159746936,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000458922222551154,
|
|
"loss": 5.0621,
|
|
"mean_token_accuracy": 0.20190414637327195,
|
|
"num_tokens": 47112548.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.452711200714111,
|
|
"epoch": 2.033906682483195,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004589018923780777,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.19715598374605178,
|
|
"num_tokens": 47123378.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.456440114974976,
|
|
"epoch": 2.0344009489916965,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004588815576809862,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.1896336629986763,
|
|
"num_tokens": 47135279.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.58902759552002,
|
|
"epoch": 2.034895215500198,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045886121846037996,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.2042861506342888,
|
|
"num_tokens": 47146510.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.483782625198364,
|
|
"epoch": 2.035389482008699,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045884087471675917,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.20798861384391784,
|
|
"num_tokens": 47158275.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.450441217422485,
|
|
"epoch": 2.0358837485172003,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045882052645062433,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.202764093875885,
|
|
"num_tokens": 47170530.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.496099948883057,
|
|
"epoch": 2.036378015025702,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000458800173662476,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19784106612205504,
|
|
"num_tokens": 47182092.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.588519096374512,
|
|
"epoch": 2.0368722815342033,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045877981635281497,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20017841309309006,
|
|
"num_tokens": 47193184.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.540717506408692,
|
|
"epoch": 2.0373665480427046,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045875945452214186,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.19264403134584426,
|
|
"num_tokens": 47205032.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.496053886413574,
|
|
"epoch": 2.037860814551206,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045873908817095773,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.19825955629348754,
|
|
"num_tokens": 47217553.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.548597908020019,
|
|
"epoch": 2.0383550810597075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004587187172997635,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.2002077132463455,
|
|
"num_tokens": 47230625.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.4888935565948485,
|
|
"epoch": 2.038849347568209,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004586983419090603,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20184389799833297,
|
|
"num_tokens": 47240703.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.40282416343689,
|
|
"epoch": 2.03934361407671,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045867796199934943,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.20721320658922196,
|
|
"num_tokens": 47253768.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.509104633331299,
|
|
"epoch": 2.0398378805852118,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004586575775711322,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.19749699532985687,
|
|
"num_tokens": 47264226.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.462013006210327,
|
|
"epoch": 2.040332147093713,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045863718862491,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.20065515786409377,
|
|
"num_tokens": 47276675.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.5171348571777346,
|
|
"epoch": 2.0408264136022143,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045861679516118447,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.1964618071913719,
|
|
"num_tokens": 47288876.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.504780435562134,
|
|
"epoch": 2.0413206801107155,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004585963971804574,
|
|
"loss": 5.0839,
|
|
"mean_token_accuracy": 0.19746282547712327,
|
|
"num_tokens": 47300430.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.484387302398682,
|
|
"epoch": 2.0418149466192173,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004585759946832304,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.19984601587057113,
|
|
"num_tokens": 47310822.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.480873060226441,
|
|
"epoch": 2.0423092131277185,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045855558767000546,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.1969541445374489,
|
|
"num_tokens": 47323042.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.468114519119263,
|
|
"epoch": 2.0428034796362198,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004585351761412846,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.2024805411696434,
|
|
"num_tokens": 47334003.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.5061524391174315,
|
|
"epoch": 2.043297746144721,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004585147600975699,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.1999462589621544,
|
|
"num_tokens": 47346279.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.471137809753418,
|
|
"epoch": 2.0437920126532227,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004584943395393637,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.2020306333899498,
|
|
"num_tokens": 47357655.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.448476696014405,
|
|
"epoch": 2.044286279161724,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045847391446716826,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2014422133564949,
|
|
"num_tokens": 47369494.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.438139247894287,
|
|
"epoch": 2.0447805456702253,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000458453484881486,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.2042825251817703,
|
|
"num_tokens": 47380221.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.429848718643188,
|
|
"epoch": 2.045274812178727,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004584330507828196,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.20642690509557723,
|
|
"num_tokens": 47391119.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.53942904472351,
|
|
"epoch": 2.0457690786872282,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004584126121716717,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20450975149869918,
|
|
"num_tokens": 47401828.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.401464366912842,
|
|
"epoch": 2.0462633451957295,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004583921690485451,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.20538584440946578,
|
|
"num_tokens": 47412921.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.500869178771973,
|
|
"epoch": 2.0467576117042308,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004583717214139427,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.19732307642698288,
|
|
"num_tokens": 47424117.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.484540939331055,
|
|
"epoch": 2.0472518782127325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045835126926836744,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.1989603891968727,
|
|
"num_tokens": 47434457.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.481767702102661,
|
|
"epoch": 2.0477461447212337,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004583308126123225,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.19856842756271362,
|
|
"num_tokens": 47446108.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.453869962692261,
|
|
"epoch": 2.048240411229735,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045831035144631115,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.20707159638404846,
|
|
"num_tokens": 47458735.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.547342920303345,
|
|
"epoch": 2.0487346777382363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045828988577083674,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.20092644691467285,
|
|
"num_tokens": 47471726.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.569121170043945,
|
|
"epoch": 2.049228944246738,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004582694155864027,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.1924632802605629,
|
|
"num_tokens": 47483940.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.429461717605591,
|
|
"epoch": 2.0497232107552392,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045824894089351265,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.20628137588500978,
|
|
"num_tokens": 47494723.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.4928656101226805,
|
|
"epoch": 2.0502174772637405,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004582284616926702,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.19653364270925522,
|
|
"num_tokens": 47506454.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.507935237884522,
|
|
"epoch": 2.050711743772242,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004582079779843791,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.19511387795209884,
|
|
"num_tokens": 47518366.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.454151773452759,
|
|
"epoch": 2.0512060102807435,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004581874897691434,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.1998277023434639,
|
|
"num_tokens": 47530635.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.493227529525757,
|
|
"epoch": 2.0517002767892447,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000458166997047467,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.2000867620110512,
|
|
"num_tokens": 47541158.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.507270574569702,
|
|
"epoch": 2.052194543297746,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045814649981985406,
|
|
"loss": 5.1403,
|
|
"mean_token_accuracy": 0.19455825984477998,
|
|
"num_tokens": 47552392.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.534381866455078,
|
|
"epoch": 2.0526888098062477,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004581259980868088,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.20762900710105897,
|
|
"num_tokens": 47565079.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.557596588134766,
|
|
"epoch": 2.053183076314749,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004581054918488356,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.20199670791625976,
|
|
"num_tokens": 47575529.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.40097279548645,
|
|
"epoch": 2.05367734282325,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045808498110643886,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.20137529522180558,
|
|
"num_tokens": 47587289.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.4694304943084715,
|
|
"epoch": 2.0541716093317515,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045806446586012326,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.2014530748128891,
|
|
"num_tokens": 47599184.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.454950571060181,
|
|
"epoch": 2.054665875840253,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004580439461103933,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.2143726944923401,
|
|
"num_tokens": 47609651.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.521587562561035,
|
|
"epoch": 2.0551601423487544,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004580234218577539,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20023731291294097,
|
|
"num_tokens": 47621138.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.4647656917572025,
|
|
"epoch": 2.0556544088572557,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045800289310270995,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.20646121054887773,
|
|
"num_tokens": 47631492.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.462546682357788,
|
|
"epoch": 2.0561486753657574,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004579823598457664,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.20790420919656755,
|
|
"num_tokens": 47643088.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.420878744125366,
|
|
"epoch": 2.0566429418742587,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045796182208742846,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.2136810839176178,
|
|
"num_tokens": 47653393.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.426799249649048,
|
|
"epoch": 2.05713720838276,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004579412798282013,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.2084339126944542,
|
|
"num_tokens": 47665879.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.394625520706176,
|
|
"epoch": 2.057631474891261,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004579207330685902,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20415761619806289,
|
|
"num_tokens": 47678339.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.504537153244018,
|
|
"epoch": 2.058125741399763,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004579001818091009,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.20559810400009154,
|
|
"num_tokens": 47688867.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.493605422973633,
|
|
"epoch": 2.058620007908264,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004578796260502385,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.19887786209583283,
|
|
"num_tokens": 47700265.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.531893157958985,
|
|
"epoch": 2.0591142744167654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004578590657925091,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.1928228408098221,
|
|
"num_tokens": 47711539.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.541080331802368,
|
|
"epoch": 2.059608540925267,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004578385010364182,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.1977803736925125,
|
|
"num_tokens": 47722433.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.433260774612426,
|
|
"epoch": 2.0601028074337684,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045781793178247194,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.20357330441474913,
|
|
"num_tokens": 47734001.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.423792886734009,
|
|
"epoch": 2.0605970739422697,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004577973580311761,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.21475625932216644,
|
|
"num_tokens": 47744903.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.553942155838013,
|
|
"epoch": 2.061091340450771,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004577767797830369,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.2053961917757988,
|
|
"num_tokens": 47756571.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.434276485443116,
|
|
"epoch": 2.0615856069592726,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045775619703856057,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.20067795664072036,
|
|
"num_tokens": 47767555.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.588631677627563,
|
|
"epoch": 2.062079873467774,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045773560979825347,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.2036454275250435,
|
|
"num_tokens": 47779577.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.486171436309815,
|
|
"epoch": 2.062574139976275,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045771501806262196,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.19999319314956665,
|
|
"num_tokens": 47790898.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.437203025817871,
|
|
"epoch": 2.0630684064847764,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045769442183217273,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.20682502388954163,
|
|
"num_tokens": 47802008.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.497658634185791,
|
|
"epoch": 2.063562672993278,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004576738211074123,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.20705877542495726,
|
|
"num_tokens": 47813544.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.551441621780396,
|
|
"epoch": 2.0640569395017794,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004576532158888476,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.19903288781642914,
|
|
"num_tokens": 47824313.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.47794098854065,
|
|
"epoch": 2.0645512060102806,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004576326061769854,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.2030812069773674,
|
|
"num_tokens": 47836653.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.480556297302246,
|
|
"epoch": 2.065045472518782,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045761199197233285,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.20221483260393142,
|
|
"num_tokens": 47848237.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.492845106124878,
|
|
"epoch": 2.0655397390272836,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045759137327539684,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.19607210159301758,
|
|
"num_tokens": 47859686.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.4147662162780765,
|
|
"epoch": 2.066034005535785,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004575707500866848,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.2019016683101654,
|
|
"num_tokens": 47871730.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.578525400161743,
|
|
"epoch": 2.066528272044286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045755012240670395,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19496129751205443,
|
|
"num_tokens": 47883927.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.465248775482178,
|
|
"epoch": 2.067022538552788,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004575294902359618,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.21650950312614442,
|
|
"num_tokens": 47894885.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.496744966506958,
|
|
"epoch": 2.067516805061289,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045750885357496583,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.196037258207798,
|
|
"num_tokens": 47906183.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.442237091064453,
|
|
"epoch": 2.0680110715697904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004574882124242238,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.1982305347919464,
|
|
"num_tokens": 47918002.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.45166974067688,
|
|
"epoch": 2.0685053380782916,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045746756678424343,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.2067309334874153,
|
|
"num_tokens": 47928300.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.4420191764831545,
|
|
"epoch": 2.0689996045867933,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045744691665553254,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.2010645791888237,
|
|
"num_tokens": 47939591.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.56816930770874,
|
|
"epoch": 2.0694938710952946,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004574262620385993,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.20087568312883378,
|
|
"num_tokens": 47953075.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.562140607833863,
|
|
"epoch": 2.069988137603796,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045740560293395166,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1892802059650421,
|
|
"num_tokens": 47964795.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.407167387008667,
|
|
"epoch": 2.0704824041122976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004573849393420979,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.21493654400110246,
|
|
"num_tokens": 47975175.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.473186206817627,
|
|
"epoch": 2.070976670620799,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004573642712635463,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.20002590566873552,
|
|
"num_tokens": 47986548.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.542366218566895,
|
|
"epoch": 2.0714709371293,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045734359869880535,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.1916937857866287,
|
|
"num_tokens": 47998759.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.46308650970459,
|
|
"epoch": 2.0719652036378013,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004573229216483836,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.2100803956389427,
|
|
"num_tokens": 48010404.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.437503814697266,
|
|
"epoch": 2.072459470146303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004573022401127897,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.20959053486585616,
|
|
"num_tokens": 48019729.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.497600364685058,
|
|
"epoch": 2.0729537366548043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045728155409253236,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.19553096294403077,
|
|
"num_tokens": 48031142.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.495659255981446,
|
|
"epoch": 2.0734480031633056,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004572608635881206,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.20706028640270233,
|
|
"num_tokens": 48043051.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.439391422271728,
|
|
"epoch": 2.073942269671807,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004572401686000633,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.21119371205568313,
|
|
"num_tokens": 48053721.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.340425634384156,
|
|
"epoch": 2.0744365361803085,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045721946912886957,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.21020646244287491,
|
|
"num_tokens": 48065208.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.5476991653442385,
|
|
"epoch": 2.07493080268881,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004571987651750486,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.20099288672208787,
|
|
"num_tokens": 48076416.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.535825872421265,
|
|
"epoch": 2.075425069197311,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004571780567391098,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.19617264717817307,
|
|
"num_tokens": 48087496.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.502159881591797,
|
|
"epoch": 2.0759193357058128,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045715734382156245,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.1978745773434639,
|
|
"num_tokens": 48098920.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.0759193357058128,
|
|
"eval_entropy": 5.275796937942505,
|
|
"eval_loss": 5.2273406982421875,
|
|
"eval_mean_token_accuracy": 0.2033788504965631,
|
|
"eval_num_tokens": 48098920.0,
|
|
"eval_runtime": 26.7025,
|
|
"eval_samples_per_second": 1217.6,
|
|
"eval_steps_per_second": 152.233,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.497160530090332,
|
|
"epoch": 2.076413602214314,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004571366264229162,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.19607924073934554,
|
|
"num_tokens": 48109813.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.544531440734863,
|
|
"epoch": 2.0769078687228153,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004571159045436807,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.20392897576093674,
|
|
"num_tokens": 48120736.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.403412580490112,
|
|
"epoch": 2.0774021352313166,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004570951781843657,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.20758558064699173,
|
|
"num_tokens": 48131631.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.4253761768341064,
|
|
"epoch": 2.0778964017398183,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045707444734548116,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.2054962173104286,
|
|
"num_tokens": 48141662.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.40928168296814,
|
|
"epoch": 2.0783906682483195,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004570537120275369,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.20970614105463029,
|
|
"num_tokens": 48152752.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.5036557674407955,
|
|
"epoch": 2.078884934756821,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000457032972231043,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.2030448153614998,
|
|
"num_tokens": 48163510.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.439107942581177,
|
|
"epoch": 2.079379201265322,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004570122279565098,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.19713331758975983,
|
|
"num_tokens": 48174241.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.471138954162598,
|
|
"epoch": 2.0798734677738238,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045699147920444757,
|
|
"loss": 5.138,
|
|
"mean_token_accuracy": 0.19568201154470444,
|
|
"num_tokens": 48186062.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.498735761642456,
|
|
"epoch": 2.080367734282325,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004569707259753667,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.20976056158542633,
|
|
"num_tokens": 48197108.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.351210308074951,
|
|
"epoch": 2.0808620007908263,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004569499682697778,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.21347033083438874,
|
|
"num_tokens": 48208780.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.461626815795898,
|
|
"epoch": 2.081356267299328,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004569292060881914,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20571133643388748,
|
|
"num_tokens": 48223164.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.489791774749756,
|
|
"epoch": 2.0818505338078293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045690843943111824,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.20784634351730347,
|
|
"num_tokens": 48234402.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.437361335754394,
|
|
"epoch": 2.0823448003163305,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045688766829906936,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.19641065299510957,
|
|
"num_tokens": 48245147.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.515418529510498,
|
|
"epoch": 2.0828390668248318,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004568668926925556,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19398601800203324,
|
|
"num_tokens": 48256787.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.4922160625457765,
|
|
"epoch": 2.0833333333333335,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000456846112612088,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.19705946892499923,
|
|
"num_tokens": 48267648.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.39834508895874,
|
|
"epoch": 2.0838275998418347,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045682532805817796,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.1943109318614006,
|
|
"num_tokens": 48279274.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.513902902603149,
|
|
"epoch": 2.084321866350336,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004568045390313365,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20093391686677933,
|
|
"num_tokens": 48290849.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.508443021774292,
|
|
"epoch": 2.0848161328588377,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045678374553207525,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.1975832164287567,
|
|
"num_tokens": 48301271.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.490620517730713,
|
|
"epoch": 2.085310399367339,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045676294756090565,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.19213752448558807,
|
|
"num_tokens": 48311869.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.505767297744751,
|
|
"epoch": 2.0858046658758402,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004567421451183393,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.205493500828743,
|
|
"num_tokens": 48324907.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.477277851104736,
|
|
"epoch": 2.0862989323843415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000456721338204888,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20937431305646897,
|
|
"num_tokens": 48335887.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.492784404754639,
|
|
"epoch": 2.086793198892843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004567005268210636,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.2031333789229393,
|
|
"num_tokens": 48348190.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.505619478225708,
|
|
"epoch": 2.0872874654013445,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045667971096737805,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.18801287263631822,
|
|
"num_tokens": 48360113.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.530846118927002,
|
|
"epoch": 2.0877817319098457,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004566588906443434,
|
|
"loss": 5.1506,
|
|
"mean_token_accuracy": 0.19893016368150712,
|
|
"num_tokens": 48371463.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.5269303798675535,
|
|
"epoch": 2.088275998418347,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004566380658524719,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.18620703518390655,
|
|
"num_tokens": 48383969.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.432257795333863,
|
|
"epoch": 2.0887702649268487,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004566172365922758,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.20651101022958757,
|
|
"num_tokens": 48395551.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.505698537826538,
|
|
"epoch": 2.08926453143535,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004565964028642675,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.20269762426614762,
|
|
"num_tokens": 48408154.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.369978713989258,
|
|
"epoch": 2.089758797943851,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004565755646689595,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.20789347887039183,
|
|
"num_tokens": 48420060.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.445231246948242,
|
|
"epoch": 2.0902530644523525,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004565547220068644,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.20298174917697906,
|
|
"num_tokens": 48432347.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.58972430229187,
|
|
"epoch": 2.090747330960854,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004565338748784951,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.18681395798921585,
|
|
"num_tokens": 48443177.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.545538854598999,
|
|
"epoch": 2.0912415974693555,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004565130232843642,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19847578406333924,
|
|
"num_tokens": 48453605.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.494526529312134,
|
|
"epoch": 2.0917358639778567,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004564921672249848,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.20262283384799956,
|
|
"num_tokens": 48465364.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.411462211608887,
|
|
"epoch": 2.0922301304863584,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045647130670086996,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.20365285575389863,
|
|
"num_tokens": 48477255.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.46329436302185,
|
|
"epoch": 2.0927243969948597,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004564504417125328,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.20384469479322434,
|
|
"num_tokens": 48487551.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.570232963562011,
|
|
"epoch": 2.093218663503361,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045642957226048667,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.19584483951330184,
|
|
"num_tokens": 48500422.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.442343616485596,
|
|
"epoch": 2.093712930011862,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045640869834524486,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.2058779254555702,
|
|
"num_tokens": 48511588.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.4939830780029295,
|
|
"epoch": 2.094207196520364,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004563878199673209,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.20239321738481522,
|
|
"num_tokens": 48522700.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.560525798797608,
|
|
"epoch": 2.094701463028865,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004563669371272285,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.2008726641535759,
|
|
"num_tokens": 48534253.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.413862657546997,
|
|
"epoch": 2.0951957295373664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045634604982548125,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.20656053423881532,
|
|
"num_tokens": 48545543.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.498996353149414,
|
|
"epoch": 2.095689996045868,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045632515806259306,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.19702216535806655,
|
|
"num_tokens": 48557433.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.497150659561157,
|
|
"epoch": 2.0961842625543694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045630426183907786,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19896326810121537,
|
|
"num_tokens": 48570271.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.447639608383179,
|
|
"epoch": 2.0966785290628707,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004562833611554497,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20392020493745805,
|
|
"num_tokens": 48582376.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.4827710628509525,
|
|
"epoch": 2.097172795571372,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004562624560122227,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.19980849474668502,
|
|
"num_tokens": 48595188.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.448200988769531,
|
|
"epoch": 2.0976670620798736,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004562415464099112,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.20976631790399553,
|
|
"num_tokens": 48606093.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.527675724029541,
|
|
"epoch": 2.098161328588375,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004562206323490295,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.196595698595047,
|
|
"num_tokens": 48618163.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.513439655303955,
|
|
"epoch": 2.098655595096876,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045619971383009216,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.20048485398292543,
|
|
"num_tokens": 48629771.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.5004894733428955,
|
|
"epoch": 2.0991498616053774,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004561787908536138,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.1973576784133911,
|
|
"num_tokens": 48640409.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.427321720123291,
|
|
"epoch": 2.099644128113879,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045615786342010896,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.20440613478422165,
|
|
"num_tokens": 48652223.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.4769083023071286,
|
|
"epoch": 2.1001383946223804,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045613693153009264,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.21186819672584534,
|
|
"num_tokens": 48663667.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.510491561889649,
|
|
"epoch": 2.1006326611308817,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004561159951840797,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.19811929613351822,
|
|
"num_tokens": 48674691.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.445463514328003,
|
|
"epoch": 2.1011269276393834,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004560950543825852,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20026781260967255,
|
|
"num_tokens": 48686888.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.455423641204834,
|
|
"epoch": 2.1016211941478846,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045607410912612426,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.2003601610660553,
|
|
"num_tokens": 48698666.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.518565320968628,
|
|
"epoch": 2.102115460656386,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004560531594152121,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20526330024003983,
|
|
"num_tokens": 48709793.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.378636837005615,
|
|
"epoch": 2.102609727164887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004560322052503642,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.21081382930278778,
|
|
"num_tokens": 48720835.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.539089632034302,
|
|
"epoch": 2.103103993673389,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004560112466320959,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.19392264187335967,
|
|
"num_tokens": 48732990.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.470013999938965,
|
|
"epoch": 2.10359826018189,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045599028356092293,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.206408728659153,
|
|
"num_tokens": 48744985.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.394286108016968,
|
|
"epoch": 2.1040925266903914,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004559693160373608,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.20992245972156526,
|
|
"num_tokens": 48755328.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.460789775848388,
|
|
"epoch": 2.1045867931988926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004559483440619255,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20698548704385758,
|
|
"num_tokens": 48766666.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.548671627044678,
|
|
"epoch": 2.1050810597073943,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045592736763513285,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.1991259604692459,
|
|
"num_tokens": 48779134.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.49554181098938,
|
|
"epoch": 2.1055753262158956,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004559063867574989,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.18977706432342528,
|
|
"num_tokens": 48791338.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.436498975753784,
|
|
"epoch": 2.106069592724397,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045588540142953973,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20877877175807952,
|
|
"num_tokens": 48802711.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.412842273712158,
|
|
"epoch": 2.1065638592328986,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004558644116517717,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.20470788776874543,
|
|
"num_tokens": 48815219.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.423786163330078,
|
|
"epoch": 2.1070581257414,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045584341742471095,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.20343984812498092,
|
|
"num_tokens": 48826075.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.4429051876068115,
|
|
"epoch": 2.107552392249901,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004558224187488742,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.20529575049877166,
|
|
"num_tokens": 48837375.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.49755973815918,
|
|
"epoch": 2.1080466587584024,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045580141562477785,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.19781452417373657,
|
|
"num_tokens": 48849205.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.467577266693115,
|
|
"epoch": 2.108540925266904,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045578040805293864,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.20479799509048463,
|
|
"num_tokens": 48861700.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.514982509613037,
|
|
"epoch": 2.1090351917754053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045575939603387336,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.19361247420310973,
|
|
"num_tokens": 48873510.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.553511333465576,
|
|
"epoch": 2.1095294582839066,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004557383795680988,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.19632184654474258,
|
|
"num_tokens": 48885011.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.482951831817627,
|
|
"epoch": 2.1100237247924083,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045571735865613215,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.2012274369597435,
|
|
"num_tokens": 48895767.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.481770706176758,
|
|
"epoch": 2.1105179913009096,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045569633329849043,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.18783088773488998,
|
|
"num_tokens": 48906616.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.512815856933594,
|
|
"epoch": 2.111012257809411,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004556753034956909,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20441584140062333,
|
|
"num_tokens": 48916841.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.465830850601196,
|
|
"epoch": 2.111506524317912,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004556542692482508,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.20906964242458342,
|
|
"num_tokens": 48928798.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.448719501495361,
|
|
"epoch": 2.112000790826414,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004556332305566877,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.20513275861740113,
|
|
"num_tokens": 48940235.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.48303370475769,
|
|
"epoch": 2.112495057334915,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004556121874215191,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.20409077405929565,
|
|
"num_tokens": 48951718.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.442774629592895,
|
|
"epoch": 2.1129893238434163,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004555911398432627,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.20309423059225082,
|
|
"num_tokens": 48963215.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.570780563354492,
|
|
"epoch": 2.1134835903519176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045557008782243626,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.1966687858104706,
|
|
"num_tokens": 48975761.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.473230934143066,
|
|
"epoch": 2.1139778568604193,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004555490313595575,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.20457555651664733,
|
|
"num_tokens": 48987192.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.411971950531006,
|
|
"epoch": 2.1144721233689205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004555279704551447,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.20943112075328826,
|
|
"num_tokens": 48999503.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.5042869567871096,
|
|
"epoch": 2.114966389877422,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004555069051097158,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.19812714904546738,
|
|
"num_tokens": 49010046.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.473691844940186,
|
|
"epoch": 2.115460656385923,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045548583532378903,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.20428899377584459,
|
|
"num_tokens": 49021028.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.489357376098633,
|
|
"epoch": 2.1159549228944248,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004554647610978827,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.19902999103069305,
|
|
"num_tokens": 49034522.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.549781465530396,
|
|
"epoch": 2.116449189402926,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004554436824325152,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.20216452926397324,
|
|
"num_tokens": 49045034.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.408593273162841,
|
|
"epoch": 2.1169434559114273,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045542259932820515,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.20656188428401948,
|
|
"num_tokens": 49056350.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.515465831756591,
|
|
"epoch": 2.117437722419929,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004554015117854712,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.2019331559538841,
|
|
"num_tokens": 49067362.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.479189205169678,
|
|
"epoch": 2.1179319889284303,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004553804198048321,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.20150836557149887,
|
|
"num_tokens": 49078067.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.430793142318725,
|
|
"epoch": 2.1184262554369315,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045535932338680655,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.20291446894407272,
|
|
"num_tokens": 49090205.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.425461769104004,
|
|
"epoch": 2.118920521945433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004553382225319138,
|
|
"loss": 5.0843,
|
|
"mean_token_accuracy": 0.20857694894075393,
|
|
"num_tokens": 49101134.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.50019006729126,
|
|
"epoch": 2.1194147884539345,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004553171172406728,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.1985215038061142,
|
|
"num_tokens": 49112282.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.453989458084107,
|
|
"epoch": 2.1199090549624358,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004552960075136027,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.20056463927030563,
|
|
"num_tokens": 49123228.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.473192167282105,
|
|
"epoch": 2.120403321470937,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045527489335122284,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.20556581169366836,
|
|
"num_tokens": 49134769.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.38484263420105,
|
|
"epoch": 2.1208975879794387,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045525377475405266,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.21405876725912093,
|
|
"num_tokens": 49146096.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.4314995288848875,
|
|
"epoch": 2.12139185448794,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045523265172261155,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.19596245437860488,
|
|
"num_tokens": 49156829.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.4708497524261475,
|
|
"epoch": 2.1218861209964412,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045521152425741934,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.20439804792404176,
|
|
"num_tokens": 49167364.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.483953952789307,
|
|
"epoch": 2.1223803875049425,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045519039235899573,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.20469803959131241,
|
|
"num_tokens": 49178283.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.540850114822388,
|
|
"epoch": 2.122874654013444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045516925602786043,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.19419609904289245,
|
|
"num_tokens": 49190466.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.498014211654663,
|
|
"epoch": 2.1233689205219455,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004551481152645335,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20404092371463775,
|
|
"num_tokens": 49202601.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.334012269973755,
|
|
"epoch": 2.1238631870304467,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045512697006953504,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.21577212810516358,
|
|
"num_tokens": 49214228.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.383227586746216,
|
|
"epoch": 2.124357453538948,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045510582044338513,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.20126300007104875,
|
|
"num_tokens": 49225495.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.512866115570068,
|
|
"epoch": 2.1248517200474497,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000455084666386604,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.20599897354841232,
|
|
"num_tokens": 49237348.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.466334962844849,
|
|
"epoch": 2.125345986555951,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045506350789971227,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.19609775245189667,
|
|
"num_tokens": 49247691.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.449573993682861,
|
|
"epoch": 2.1258402530644522,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004550423449832302,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.21018802523612976,
|
|
"num_tokens": 49259191.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.471076154708863,
|
|
"epoch": 2.126334519572954,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004550211776376787,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.19971854984760284,
|
|
"num_tokens": 49271760.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.473392486572266,
|
|
"epoch": 2.126828786081455,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045500000586357807,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.19734090715646743,
|
|
"num_tokens": 49283918.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.4627138614654545,
|
|
"epoch": 2.1273230525899565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045497882966144955,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.2085844874382019,
|
|
"num_tokens": 49294313.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.379091596603393,
|
|
"epoch": 2.1278173190984577,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004549576490318138,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.20569958686828613,
|
|
"num_tokens": 49305213.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.4417877197265625,
|
|
"epoch": 2.1283115856069594,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000454936463975192,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.2110251620411873,
|
|
"num_tokens": 49317245.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.544441270828247,
|
|
"epoch": 2.1288058521154607,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004549152744921053,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.19126632511615754,
|
|
"num_tokens": 49328400.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.563454532623291,
|
|
"epoch": 2.129300118623962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004548940805830749,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.19719396829605101,
|
|
"num_tokens": 49341094.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.439585018157959,
|
|
"epoch": 2.129794385132463,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045487288224862224,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20696100145578383,
|
|
"num_tokens": 49352472.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.364221811294556,
|
|
"epoch": 2.130288651640965,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045485167948926876,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.20317644476890565,
|
|
"num_tokens": 49362432.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.3985765933990475,
|
|
"epoch": 2.130782918149466,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000454830472305536,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.20756920874118806,
|
|
"num_tokens": 49373857.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.50927996635437,
|
|
"epoch": 2.1312771846579674,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004548092606979458,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.20115890651941298,
|
|
"num_tokens": 49387545.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.485805606842041,
|
|
"epoch": 2.131771451166469,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045478804466701984,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.20184282958507538,
|
|
"num_tokens": 49398273.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.4722919940948485,
|
|
"epoch": 2.1322657176749704,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045476682421328015,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.1956496551632881,
|
|
"num_tokens": 49408662.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.499329471588135,
|
|
"epoch": 2.1327599841834717,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045474559933724866,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19767630398273467,
|
|
"num_tokens": 49421189.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.541994619369507,
|
|
"epoch": 2.133254250691973,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045472437003944753,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.1993097573518753,
|
|
"num_tokens": 49432878.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.504819440841675,
|
|
"epoch": 2.1337485172004746,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004547031363203991,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19855036437511445,
|
|
"num_tokens": 49444058.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.458438062667847,
|
|
"epoch": 2.134242783708976,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045468189818062554,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.19663193821907043,
|
|
"num_tokens": 49456602.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.479839658737182,
|
|
"epoch": 2.134737050217477,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004546606556206494,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.19677526801824569,
|
|
"num_tokens": 49467287.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.507628536224365,
|
|
"epoch": 2.135231316725979,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004546394086409933,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.20096794366836548,
|
|
"num_tokens": 49478662.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.429534292221069,
|
|
"epoch": 2.13572558323448,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045461815724217984,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.202814319729805,
|
|
"num_tokens": 49489365.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.522376012802124,
|
|
"epoch": 2.1362198497429814,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045459690142473193,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19887436032295228,
|
|
"num_tokens": 49501318.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.557967710494995,
|
|
"epoch": 2.1367141162514827,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004545756411891723,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.19450214207172395,
|
|
"num_tokens": 49512138.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.496899271011353,
|
|
"epoch": 2.1372083827599844,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004545543765360241,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.19863074868917466,
|
|
"num_tokens": 49523325.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.376071929931641,
|
|
"epoch": 2.1377026492684856,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045453310746581036,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.2060544818639755,
|
|
"num_tokens": 49535382.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.433425855636597,
|
|
"epoch": 2.138196915776987,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004545118339790543,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.21011810898780822,
|
|
"num_tokens": 49546151.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.438507318496704,
|
|
"epoch": 2.138691182285488,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004544905560762793,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.20322542935609816,
|
|
"num_tokens": 49558617.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.428427648544312,
|
|
"epoch": 2.13918544879399,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045446927375800876,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.2082756206393242,
|
|
"num_tokens": 49568494.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.4726972579956055,
|
|
"epoch": 2.139679715302491,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045444798702476625,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.20550450980663298,
|
|
"num_tokens": 49579763.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.424627828598022,
|
|
"epoch": 2.1401739818109924,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004544266958770755,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.20894904881715776,
|
|
"num_tokens": 49591631.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.451085186004638,
|
|
"epoch": 2.1406682483194936,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045440540031546004,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.20215726047754287,
|
|
"num_tokens": 49603458.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.426243829727173,
|
|
"epoch": 2.1411625148279954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045438410034044397,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.2064604178071022,
|
|
"num_tokens": 49614076.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.50806679725647,
|
|
"epoch": 2.1416567813364966,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045436279595255125,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.2015524163842201,
|
|
"num_tokens": 49624982.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.441690397262573,
|
|
"epoch": 2.142151047844998,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004543414871523059,
|
|
"loss": 5.0627,
|
|
"mean_token_accuracy": 0.2014481633901596,
|
|
"num_tokens": 49635897.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.419281148910523,
|
|
"epoch": 2.1426453143534996,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004543201739402321,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.206967031955719,
|
|
"num_tokens": 49647023.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.505858707427978,
|
|
"epoch": 2.143139580862001,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045429885631685424,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.19200181365013122,
|
|
"num_tokens": 49658578.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.499928903579712,
|
|
"epoch": 2.143633847370502,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004542775342826967,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20494598746299744,
|
|
"num_tokens": 49670978.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.381011819839477,
|
|
"epoch": 2.1441281138790034,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045425620783828396,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.20801264196634292,
|
|
"num_tokens": 49682553.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.455586576461792,
|
|
"epoch": 2.144622380387505,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004542348769841407,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.2040228173136711,
|
|
"num_tokens": 49694589.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.491195631027222,
|
|
"epoch": 2.1451166468960063,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045421354172079173,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.20186507999897002,
|
|
"num_tokens": 49706530.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.428736066818237,
|
|
"epoch": 2.1456109134045076,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045419220204876175,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.20577556490898133,
|
|
"num_tokens": 49718524.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.511984872817993,
|
|
"epoch": 2.1461051799130093,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045417085796857596,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20351321697235109,
|
|
"num_tokens": 49729555.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.511195135116577,
|
|
"epoch": 2.1465994464215106,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045414950948075906,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.20049637109041213,
|
|
"num_tokens": 49739708.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.50742769241333,
|
|
"epoch": 2.147093712930012,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045412815658583657,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.19940923303365707,
|
|
"num_tokens": 49750997.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.471212482452392,
|
|
"epoch": 2.147587979438513,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004541067992843336,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.21016710847616196,
|
|
"num_tokens": 49761508.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.449388456344605,
|
|
"epoch": 2.148082245947015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045408543757677555,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.20886579751968384,
|
|
"num_tokens": 49772821.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.342594766616822,
|
|
"epoch": 2.148576512455516,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000454064071463688,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.21078437119722365,
|
|
"num_tokens": 49783932.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.434691667556763,
|
|
"epoch": 2.1490707789640173,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004540427009455965,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.20328619480133056,
|
|
"num_tokens": 49795126.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.478298807144165,
|
|
"epoch": 2.1495650454725186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004540213260230267,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.19933412820100785,
|
|
"num_tokens": 49806110.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.555647468566894,
|
|
"epoch": 2.1500593119810203,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004539999466965046,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.19263185411691666,
|
|
"num_tokens": 49818879.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.447303724288941,
|
|
"epoch": 2.1505535784895216,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045397856296655603,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20410825908184052,
|
|
"num_tokens": 49828986.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.457606649398803,
|
|
"epoch": 2.151047844998023,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045395717483370703,
|
|
"loss": 5.1304,
|
|
"mean_token_accuracy": 0.20051389932632446,
|
|
"num_tokens": 49841987.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.500014877319336,
|
|
"epoch": 2.1515421115065245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045393578229848373,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.19530521035194398,
|
|
"num_tokens": 49854151.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.473662805557251,
|
|
"epoch": 2.152036378015026,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045391438536141257,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.20289100110530853,
|
|
"num_tokens": 49866531.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.4246419906616214,
|
|
"epoch": 2.152530644523527,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045389298402301965,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.2051922485232353,
|
|
"num_tokens": 49877737.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.56043119430542,
|
|
"epoch": 2.1530249110320283,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004538715782838316,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.1967581957578659,
|
|
"num_tokens": 49889214.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.508524942398071,
|
|
"epoch": 2.15351917754053,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045385016814437494,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.2086491122841835,
|
|
"num_tokens": 49900293.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.521596765518188,
|
|
"epoch": 2.1540134440490313,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045382875360517645,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.1881273716688156,
|
|
"num_tokens": 49912193.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.500470685958862,
|
|
"epoch": 2.1545077105575325,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004538073346667628,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.20565684586763383,
|
|
"num_tokens": 49922780.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.412070894241333,
|
|
"epoch": 2.155001977066034,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045378591132966105,
|
|
"loss": 5.0408,
|
|
"mean_token_accuracy": 0.20618819445371628,
|
|
"num_tokens": 49934551.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.478486824035644,
|
|
"epoch": 2.1554962435745355,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004537644835943982,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20156006813049315,
|
|
"num_tokens": 49945779.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.384441995620728,
|
|
"epoch": 2.1559905100830368,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004537430514615012,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2104324847459793,
|
|
"num_tokens": 49957127.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.433111381530762,
|
|
"epoch": 2.156484776591538,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045372161493149746,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.20083660930395125,
|
|
"num_tokens": 49968679.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.472336912155152,
|
|
"epoch": 2.1569790431000397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004537001740049142,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.2041481390595436,
|
|
"num_tokens": 49979924.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.507729244232178,
|
|
"epoch": 2.157473309608541,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000453678728682279,
|
|
"loss": 5.1184,
|
|
"mean_token_accuracy": 0.19914151579141617,
|
|
"num_tokens": 49991318.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.327296590805053,
|
|
"epoch": 2.1579675761170423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004536572789641193,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.21249121725559234,
|
|
"num_tokens": 50003096.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.423644304275513,
|
|
"epoch": 2.1584618426255435,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045363582485096295,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.20505326688289643,
|
|
"num_tokens": 50013953.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.451132202148438,
|
|
"epoch": 2.1589561091340452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004536143663433375,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.20263867378234862,
|
|
"num_tokens": 50025696.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.473041725158692,
|
|
"epoch": 2.1594503756425465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045359290344177094,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20563692152500151,
|
|
"num_tokens": 50036880.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.405320358276367,
|
|
"epoch": 2.1599446421510478,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004535714361467913,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.19995920062065126,
|
|
"num_tokens": 50048746.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.394478797912598,
|
|
"epoch": 2.1604389086595495,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004535499644589266,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.21028894186019897,
|
|
"num_tokens": 50060711.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.492297172546387,
|
|
"epoch": 2.1609331751680507,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045352848837870496,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.2077525734901428,
|
|
"num_tokens": 50071878.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.5114038467407225,
|
|
"epoch": 2.161427441676552,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000453507007906655,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.19585060626268386,
|
|
"num_tokens": 50084600.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.381295156478882,
|
|
"epoch": 2.1619217081850532,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004534855230433048,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.21208488047122956,
|
|
"num_tokens": 50095814.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.445086240768433,
|
|
"epoch": 2.162415974693555,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045346403378918314,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.20348407775163652,
|
|
"num_tokens": 50108390.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.443909549713135,
|
|
"epoch": 2.162910241202056,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004534425401448185,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.20195166319608687,
|
|
"num_tokens": 50118939.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.426813077926636,
|
|
"epoch": 2.1634045077105575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004534210421107397,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.20972904413938523,
|
|
"num_tokens": 50129510.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.456368780136108,
|
|
"epoch": 2.1638987742190587,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004533995396874756,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.20585589110851288,
|
|
"num_tokens": 50140611.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.450876092910766,
|
|
"epoch": 2.1643930407275604,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045337803287555525,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.2020418882369995,
|
|
"num_tokens": 50152214.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.565404224395752,
|
|
"epoch": 2.1648873072360617,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004533565216755075,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.19238121509552003,
|
|
"num_tokens": 50164201.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.488421630859375,
|
|
"epoch": 2.165381573744563,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004533350060878615,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.2083245724439621,
|
|
"num_tokens": 50176515.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.4680994033813475,
|
|
"epoch": 2.1658758402530642,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004533134861131469,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.1998581364750862,
|
|
"num_tokens": 50187624.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.300753879547119,
|
|
"epoch": 2.166370106761566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004532919617518929,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21394285559654236,
|
|
"num_tokens": 50199549.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.485292243957519,
|
|
"epoch": 2.166864373270067,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045327043300462887,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.2031971335411072,
|
|
"num_tokens": 50210920.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.451715135574341,
|
|
"epoch": 2.1673586397785685,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004532488998718846,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.2074540913105011,
|
|
"num_tokens": 50221335.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.458260345458984,
|
|
"epoch": 2.16785290628707,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045322736235418973,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.19763005524873734,
|
|
"num_tokens": 50235138.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.4678246021270756,
|
|
"epoch": 2.1683471727955714,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045320582045207405,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20774453431367873,
|
|
"num_tokens": 50246454.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.470566749572754,
|
|
"epoch": 2.1688414393040727,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004531842741660675,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.20096409171819687,
|
|
"num_tokens": 50257591.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.494206857681275,
|
|
"epoch": 2.169335705812574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004531627234967003,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20394384264945983,
|
|
"num_tokens": 50268557.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.512228727340698,
|
|
"epoch": 2.1698299723210757,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004531411684445024,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19990436881780624,
|
|
"num_tokens": 50280617.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.438031005859375,
|
|
"epoch": 2.170324238829577,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045311960901000403,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.20048560500144957,
|
|
"num_tokens": 50292071.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.4563017845153805,
|
|
"epoch": 2.170818505338078,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004530980451937358,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20463332980871202,
|
|
"num_tokens": 50303389.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.457363939285278,
|
|
"epoch": 2.17131277184658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004530764769962279,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.20253465920686722,
|
|
"num_tokens": 50315088.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.439064025878906,
|
|
"epoch": 2.171807038355081,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004530549044180111,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.20380324125289917,
|
|
"num_tokens": 50326177.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.465572786331177,
|
|
"epoch": 2.1723013048635824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045303332745961605,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.20900749117136003,
|
|
"num_tokens": 50337333.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.479910898208618,
|
|
"epoch": 2.1727955713720837,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045301174612157345,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.20635915398597718,
|
|
"num_tokens": 50348406.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.4112812042236325,
|
|
"epoch": 2.1732898378805854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004529901604044143,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.2116081029176712,
|
|
"num_tokens": 50360057.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.46949200630188,
|
|
"epoch": 2.1737841043890866,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004529685703086697,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.20807430446147918,
|
|
"num_tokens": 50370355.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.43659782409668,
|
|
"epoch": 2.174278370897588,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045294697583487056,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.2036882981657982,
|
|
"num_tokens": 50382193.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.458174848556519,
|
|
"epoch": 2.174772637406089,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045292537698354824,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.2019064500927925,
|
|
"num_tokens": 50394383.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.424459934234619,
|
|
"epoch": 2.175266903914591,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000452903773755234,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.21263935118913652,
|
|
"num_tokens": 50405006.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.480849170684815,
|
|
"epoch": 2.175761170423092,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004528821661504594,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.20142632126808166,
|
|
"num_tokens": 50416940.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.454312896728515,
|
|
"epoch": 2.1762554369315934,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004528605541697558,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.2062039852142334,
|
|
"num_tokens": 50428506.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.526965141296387,
|
|
"epoch": 2.176749703440095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045283893781365513,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19642205089330672,
|
|
"num_tokens": 50440421.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.471118402481079,
|
|
"epoch": 2.1772439699485964,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004528173170826889,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.1990600571036339,
|
|
"num_tokens": 50451819.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.577501678466797,
|
|
"epoch": 2.1777382364570976,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004527956919773891,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.19065154790878297,
|
|
"num_tokens": 50464382.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.486111211776733,
|
|
"epoch": 2.178232502965599,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004527740624982877,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20734716653823854,
|
|
"num_tokens": 50474773.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.43578691482544,
|
|
"epoch": 2.1787267694741006,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045275242864591683,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.20489742904901503,
|
|
"num_tokens": 50485626.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.4454625129699705,
|
|
"epoch": 2.179221035982602,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045273079042080854,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.20450943559408188,
|
|
"num_tokens": 50496130.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.440085983276367,
|
|
"epoch": 2.179715302491103,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045270914782349534,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.20665103644132615,
|
|
"num_tokens": 50506578.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.480471515655518,
|
|
"epoch": 2.1802095689996044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045268750085450946,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.19091523289680482,
|
|
"num_tokens": 50517398.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.4409221649169925,
|
|
"epoch": 2.180703835508106,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004526658495143835,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.2173004299402237,
|
|
"num_tokens": 50528577.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.474113988876343,
|
|
"epoch": 2.1811981020166074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004526441938036501,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.21101005971431733,
|
|
"num_tokens": 50539118.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.407461547851563,
|
|
"epoch": 2.1816923685251086,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045262253372284193,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.1975881963968277,
|
|
"num_tokens": 50549934.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.449191761016846,
|
|
"epoch": 2.1821866350336103,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045260086927249193,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.2091893285512924,
|
|
"num_tokens": 50560661.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.481042814254761,
|
|
"epoch": 2.1826809015421116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000452579200453133,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.19765058308839797,
|
|
"num_tokens": 50573304.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.515471935272217,
|
|
"epoch": 2.183175168050613,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004525575272652981,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.18901274353265762,
|
|
"num_tokens": 50584166.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.566880989074707,
|
|
"epoch": 2.183669434559114,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004525358497095206,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.19529741406440734,
|
|
"num_tokens": 50596425.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.441328144073486,
|
|
"epoch": 2.184163701067616,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045251416778633354,
|
|
"loss": 5.0436,
|
|
"mean_token_accuracy": 0.21222379058599472,
|
|
"num_tokens": 50607483.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.40218505859375,
|
|
"epoch": 2.184657967576117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045249248149627046,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.21095477044582367,
|
|
"num_tokens": 50619655.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.479169082641602,
|
|
"epoch": 2.1851522340846183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045247079083986485,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.20085288286209108,
|
|
"num_tokens": 50631323.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.444754409790039,
|
|
"epoch": 2.18564650059312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004524490958176502,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.20833649039268493,
|
|
"num_tokens": 50642931.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.375878238677979,
|
|
"epoch": 2.1861407671016213,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004524273964301603,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.2146366074681282,
|
|
"num_tokens": 50655396.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.350038385391235,
|
|
"epoch": 2.1866350336101226,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045240569267792887,
|
|
"loss": 5.1216,
|
|
"mean_token_accuracy": 0.20548262298107148,
|
|
"num_tokens": 50667264.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.402992534637451,
|
|
"epoch": 2.187129300118624,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045238398456148995,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.20868967324495316,
|
|
"num_tokens": 50679073.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.52568826675415,
|
|
"epoch": 2.1876235666271255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045236227208137744,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.20161896497011184,
|
|
"num_tokens": 50689554.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.482652902603149,
|
|
"epoch": 2.188117833135627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004523405552381256,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.19804674685001372,
|
|
"num_tokens": 50702419.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.4902537822723385,
|
|
"epoch": 2.188612099644128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004523188340322685,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.20533912777900695,
|
|
"num_tokens": 50713016.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.45652208328247,
|
|
"epoch": 2.1891063661526293,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004522971084643406,
|
|
"loss": 5.1321,
|
|
"mean_token_accuracy": 0.1991726502776146,
|
|
"num_tokens": 50723936.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.4537169456481935,
|
|
"epoch": 2.189600632661131,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045227537853487627,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20649251490831375,
|
|
"num_tokens": 50734339.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.5273887634277346,
|
|
"epoch": 2.1900948991696323,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045225364424441016,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.19575559049844743,
|
|
"num_tokens": 50746262.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.486431026458741,
|
|
"epoch": 2.1905891656781336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000452231905593477,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.2060153841972351,
|
|
"num_tokens": 50758218.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.530079030990601,
|
|
"epoch": 2.191083432186635,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004522101625826113,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1975388213992119,
|
|
"num_tokens": 50769263.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.353418827056885,
|
|
"epoch": 2.1915776986951365,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004521884152123482,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.21839907318353652,
|
|
"num_tokens": 50780049.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.421419715881347,
|
|
"epoch": 2.192071965203638,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004521666634832227,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.19770466685295104,
|
|
"num_tokens": 50791817.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.495793581008911,
|
|
"epoch": 2.192566231712139,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004521449073957697,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20371364504098893,
|
|
"num_tokens": 50802669.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.488735246658325,
|
|
"epoch": 2.1930604982206408,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045212314695052447,
|
|
"loss": 5.0765,
|
|
"mean_token_accuracy": 0.2062157467007637,
|
|
"num_tokens": 50813920.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.473265981674194,
|
|
"epoch": 2.193554764729142,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045210138214802227,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.2009732320904732,
|
|
"num_tokens": 50825828.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.4705592632293705,
|
|
"epoch": 2.1940490312376433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045207961298879875,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.19763244837522506,
|
|
"num_tokens": 50837425.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.487411260604858,
|
|
"epoch": 2.1945432977461445,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004520578394733892,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.2052994579076767,
|
|
"num_tokens": 50848720.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.441032552719117,
|
|
"epoch": 2.1950375642546462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045203606160232936,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20376090109348297,
|
|
"num_tokens": 50860304.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.455645370483398,
|
|
"epoch": 2.1955318307631475,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004520142793761549,
|
|
"loss": 5.102,
|
|
"mean_token_accuracy": 0.20044864267110823,
|
|
"num_tokens": 50872099.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.564654445648193,
|
|
"epoch": 2.1960260972716488,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004519924927954017,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.19523929953575134,
|
|
"num_tokens": 50884116.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.456976890563965,
|
|
"epoch": 2.1965203637801505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004519707018606059,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2112756311893463,
|
|
"num_tokens": 50896293.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.376521348953247,
|
|
"epoch": 2.1970146302886517,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045194890657230315,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.21770827621221542,
|
|
"num_tokens": 50908633.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.430121994018554,
|
|
"epoch": 2.197508896797153,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045192710693103,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.2129548966884613,
|
|
"num_tokens": 50919524.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.430606746673584,
|
|
"epoch": 2.1980031633056543,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004519053029373224,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.20280597656965255,
|
|
"num_tokens": 50930157.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.543116712570191,
|
|
"epoch": 2.198497429814156,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000451883494591717,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.19638506025075914,
|
|
"num_tokens": 50942474.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.540287017822266,
|
|
"epoch": 2.1989916963226572,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045186168189475026,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.19577142745256423,
|
|
"num_tokens": 50954847.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.443205308914185,
|
|
"epoch": 2.1994859628311585,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004518398648469586,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.20112030655145646,
|
|
"num_tokens": 50966446.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.405908250808716,
|
|
"epoch": 2.1999802293396598,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045181804344887887,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.2061981439590454,
|
|
"num_tokens": 50977949.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.4577960014343265,
|
|
"epoch": 2.2004744958481615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045179621770104786,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.20345707833766938,
|
|
"num_tokens": 50989297.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.501837491989136,
|
|
"epoch": 2.2009687623566627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045177438760400244,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.20004283040761947,
|
|
"num_tokens": 51001616.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.488684797286988,
|
|
"epoch": 2.201463028865164,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004517525531582797,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.2021377146244049,
|
|
"num_tokens": 51012870.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.433793306350708,
|
|
"epoch": 2.2019572953736652,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045173071436441665,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.2067926585674286,
|
|
"num_tokens": 51025368.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.451766538619995,
|
|
"epoch": 2.202451561882167,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004517088712229507,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.2102508634328842,
|
|
"num_tokens": 51035964.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.485930061340332,
|
|
"epoch": 2.202945828390668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045168702373441904,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.19711207896471022,
|
|
"num_tokens": 51048313.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.444494819641113,
|
|
"epoch": 2.2034400948991695,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045166517189935924,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.21160221695899964,
|
|
"num_tokens": 51060503.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.379508018493652,
|
|
"epoch": 2.203934361407671,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045164331571830875,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.2059958964586258,
|
|
"num_tokens": 51070865.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.466962814331055,
|
|
"epoch": 2.2044286279161724,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045162145519180534,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20033060163259506,
|
|
"num_tokens": 51081158.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.3697117328643795,
|
|
"epoch": 2.2049228944246737,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004515995903203867,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.2164184883236885,
|
|
"num_tokens": 51090661.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.386660766601563,
|
|
"epoch": 2.205417160933175,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004515777211045908,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.2034023731946945,
|
|
"num_tokens": 51101825.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.451193237304688,
|
|
"epoch": 2.2059114274416767,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045155584754495546,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.20262492150068284,
|
|
"num_tokens": 51114546.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.481822681427002,
|
|
"epoch": 2.206405693950178,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004515339696420189,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.20234593898057937,
|
|
"num_tokens": 51124888.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.369677734375,
|
|
"epoch": 2.206899960458679,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004515120873963194,
|
|
"loss": 4.9792,
|
|
"mean_token_accuracy": 0.21450863182544708,
|
|
"num_tokens": 51135892.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.472310638427734,
|
|
"epoch": 2.207394226967181,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004514902008083951,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.19770826250314713,
|
|
"num_tokens": 51147513.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.453230857849121,
|
|
"epoch": 2.207888493475682,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004514683098787845,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.20435138940811157,
|
|
"num_tokens": 51159514.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.469941711425781,
|
|
"epoch": 2.2083827599841834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004514464146080261,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.20124291479587555,
|
|
"num_tokens": 51171245.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.468169832229615,
|
|
"epoch": 2.2088770264926847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045142451499665846,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20534208714962005,
|
|
"num_tokens": 51182763.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.523221397399903,
|
|
"epoch": 2.2093712930011864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045140261104522044,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.19990643858909607,
|
|
"num_tokens": 51193811.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.387230682373047,
|
|
"epoch": 2.2098655595096877,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004513807027542508,
|
|
"loss": 5.0242,
|
|
"mean_token_accuracy": 0.21187486201524736,
|
|
"num_tokens": 51203963.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.415337753295899,
|
|
"epoch": 2.210359826018189,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004513587901242886,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.21227633506059645,
|
|
"num_tokens": 51215128.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.408953905105591,
|
|
"epoch": 2.21085409252669,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045133687315587263,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.2120651423931122,
|
|
"num_tokens": 51226773.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.403735494613647,
|
|
"epoch": 2.211348359035192,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004513149518495424,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20618054419755935,
|
|
"num_tokens": 51238226.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.473879194259643,
|
|
"epoch": 2.211842625543693,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045129302620583683,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.2110820233821869,
|
|
"num_tokens": 51249096.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.508037519454956,
|
|
"epoch": 2.2123368920521944,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045127109622529563,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.21046568155288697,
|
|
"num_tokens": 51259709.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.388283109664917,
|
|
"epoch": 2.212831158560696,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045124916190845797,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.21317354291677476,
|
|
"num_tokens": 51271787.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.470079612731934,
|
|
"epoch": 2.2133254250691974,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045122722325586373,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.2009001389145851,
|
|
"num_tokens": 51284093.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.551580286026001,
|
|
"epoch": 2.2138196915776986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045120528026805235,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.21120179295539857,
|
|
"num_tokens": 51295659.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.462441635131836,
|
|
"epoch": 2.2143139580862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045118333294556377,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.1981760933995247,
|
|
"num_tokens": 51307960.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.360403156280517,
|
|
"epoch": 2.2148082245947016,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004511613812889379,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.2166670575737953,
|
|
"num_tokens": 51319366.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.429664087295532,
|
|
"epoch": 2.215302491103203,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045113942529871473,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.21239563673734665,
|
|
"num_tokens": 51332445.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.394266510009766,
|
|
"epoch": 2.215796757611704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004511174649754343,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.2104736238718033,
|
|
"num_tokens": 51342900.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.407699918746948,
|
|
"epoch": 2.2162910241202054,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000451095500319637,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.20792870968580246,
|
|
"num_tokens": 51354437.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.3780012130737305,
|
|
"epoch": 2.216785290628707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000451073531331863,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21393977254629135,
|
|
"num_tokens": 51364630.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.416752862930298,
|
|
"epoch": 2.2172795571372084,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004510515580126528,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.1966108575463295,
|
|
"num_tokens": 51376547.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.551893949508667,
|
|
"epoch": 2.2177738236457096,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000451029580362547,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.20855042785406114,
|
|
"num_tokens": 51388704.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.600894212722778,
|
|
"epoch": 2.2182680901542113,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004510075983820862,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18894612193107604,
|
|
"num_tokens": 51400884.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.400213050842285,
|
|
"epoch": 2.2187623566627126,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045098561207181114,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2160417541861534,
|
|
"num_tokens": 51412946.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.4361879348754885,
|
|
"epoch": 2.219256623171214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004509636214322628,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19927748292684555,
|
|
"num_tokens": 51425860.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.469024515151977,
|
|
"epoch": 2.219750889679715,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004509416264639821,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.20638439059257507,
|
|
"num_tokens": 51438812.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.505749845504761,
|
|
"epoch": 2.220245156188217,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004509196271675101,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.20011616349220276,
|
|
"num_tokens": 51449881.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.417558765411377,
|
|
"epoch": 2.220739422696718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045089762354338784,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.20899977684020996,
|
|
"num_tokens": 51460403.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.451224756240845,
|
|
"epoch": 2.2212336892052194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045087561559215683,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.19840678423643113,
|
|
"num_tokens": 51471414.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.377906656265258,
|
|
"epoch": 2.221727955713721,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045085360331435835,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.21207940131425856,
|
|
"num_tokens": 51482855.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.531119346618652,
|
|
"epoch": 2.2222222222222223,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000450831586710534,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.20319891422986985,
|
|
"num_tokens": 51495363.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.4503663063049315,
|
|
"epoch": 2.2227164887307236,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045080956578122535,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.2042389154434204,
|
|
"num_tokens": 51506678.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.463925790786743,
|
|
"epoch": 2.223210755239225,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045078754052697406,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.20191659778356552,
|
|
"num_tokens": 51518596.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.522045850753784,
|
|
"epoch": 2.2237050217477266,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045076551094832206,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.1897835522890091,
|
|
"num_tokens": 51531292.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.453851652145386,
|
|
"epoch": 2.224199288256228,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045074347704581114,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.21337843537330628,
|
|
"num_tokens": 51542507.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.4292871952056885,
|
|
"epoch": 2.224693554764729,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045072143881998345,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.20690615922212602,
|
|
"num_tokens": 51553895.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.482722282409668,
|
|
"epoch": 2.2251878212732303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004506993962713812,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.19665465801954268,
|
|
"num_tokens": 51566533.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.452127885818482,
|
|
"epoch": 2.225682087781732,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045067734940054644,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.2034011349081993,
|
|
"num_tokens": 51576308.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.43596830368042,
|
|
"epoch": 2.2261763542902333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045065529820802165,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.20287619084119796,
|
|
"num_tokens": 51589844.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.4372477531433105,
|
|
"epoch": 2.2266706207987346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045063324269434924,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.2062040999531746,
|
|
"num_tokens": 51601685.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.463942146301269,
|
|
"epoch": 2.227164887307236,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004506111828600719,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.21291045397520064,
|
|
"num_tokens": 51613258.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.502474737167359,
|
|
"epoch": 2.2276591538157375,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004505891187057322,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.21133115738630295,
|
|
"num_tokens": 51624088.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.424364423751831,
|
|
"epoch": 2.228153420324239,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004505670502318729,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.20878589004278184,
|
|
"num_tokens": 51636617.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.485426378250122,
|
|
"epoch": 2.22864768683274,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045054497743903687,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.1958390086889267,
|
|
"num_tokens": 51647777.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.479109477996826,
|
|
"epoch": 2.2291419533412418,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004505229003277673,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.19497756212949752,
|
|
"num_tokens": 51660505.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.535318517684937,
|
|
"epoch": 2.229636219849743,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045050081889860713,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.2073805809020996,
|
|
"num_tokens": 51672296.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.439493083953858,
|
|
"epoch": 2.2301304863582443,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045047873315209945,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.21047580242156982,
|
|
"num_tokens": 51684437.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.37967438697815,
|
|
"epoch": 2.2306247528667456,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004504566430887878,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.22455368489027022,
|
|
"num_tokens": 51694919.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.385181093215943,
|
|
"epoch": 2.2311190193752473,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045043454870921553,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.2078988343477249,
|
|
"num_tokens": 51705273.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.4897401332855225,
|
|
"epoch": 2.2316132858837485,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004504124500139261,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20162609815597535,
|
|
"num_tokens": 51717048.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.531285953521729,
|
|
"epoch": 2.23210755239225,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004503903470034632,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.1952867954969406,
|
|
"num_tokens": 51729208.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.39504451751709,
|
|
"epoch": 2.2326018189007515,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045036823967837066,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21744933873414993,
|
|
"num_tokens": 51740393.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.434687852859497,
|
|
"epoch": 2.2330960854092528,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004503461280391921,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20831727236509323,
|
|
"num_tokens": 51751044.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.460771989822388,
|
|
"epoch": 2.233590351917754,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004503240120864716,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20239224433898925,
|
|
"num_tokens": 51761969.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.430784273147583,
|
|
"epoch": 2.2340846184262553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004503018918207532,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.19963111132383346,
|
|
"num_tokens": 51774185.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.463798475265503,
|
|
"epoch": 2.234578884934757,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004502797672425811,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.20784147828817368,
|
|
"num_tokens": 51786155.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.473239994049072,
|
|
"epoch": 2.2350731514432582,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045025763835249957,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.2045741096138954,
|
|
"num_tokens": 51797125.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.530738067626953,
|
|
"epoch": 2.2355674179517595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004502355051510528,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.20333438813686372,
|
|
"num_tokens": 51809046.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.5128583908081055,
|
|
"epoch": 2.2360616844602608,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045021336763878555,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.1940137654542923,
|
|
"num_tokens": 51821857.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.549382734298706,
|
|
"epoch": 2.2365559509687625,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045019122581624224,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.20626272559165953,
|
|
"num_tokens": 51833504.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.362681722640991,
|
|
"epoch": 2.2370502174772637,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045016907968396764,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20376169979572295,
|
|
"num_tokens": 51844166.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.494580602645874,
|
|
"epoch": 2.237544483985765,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004501469292425064,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.2013572096824646,
|
|
"num_tokens": 51855674.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.416225337982178,
|
|
"epoch": 2.2380387504942667,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045012477449240363,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.209158194065094,
|
|
"num_tokens": 51866128.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.442247152328491,
|
|
"epoch": 2.238533017002768,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045010261543420416,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.20557070076465606,
|
|
"num_tokens": 51877036.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.490751314163208,
|
|
"epoch": 2.2390272835112692,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004500804520684532,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.2076960414648056,
|
|
"num_tokens": 51888331.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.512454891204834,
|
|
"epoch": 2.2395215500197705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045005828439569594,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.1975500077009201,
|
|
"num_tokens": 51899843.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.5068785667419435,
|
|
"epoch": 2.240015816528272,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045003611241647783,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.19452141970396042,
|
|
"num_tokens": 51911429.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.459844017028809,
|
|
"epoch": 2.2405100830367735,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045001393613134413,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.20563471615314483,
|
|
"num_tokens": 51923154.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.463518905639648,
|
|
"epoch": 2.2410043495452747,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004499917555408405,
|
|
"loss": 5.104,
|
|
"mean_token_accuracy": 0.20115275382995607,
|
|
"num_tokens": 51935126.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.503543281555176,
|
|
"epoch": 2.241498616053776,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044996957064551244,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.19432093650102616,
|
|
"num_tokens": 51947629.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.465738773345947,
|
|
"epoch": 2.2419928825622777,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004499473814459059,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.20062458366155625,
|
|
"num_tokens": 51957631.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.469844102859497,
|
|
"epoch": 2.242487149070779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044992518794256657,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.19733941107988356,
|
|
"num_tokens": 51969854.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.49449200630188,
|
|
"epoch": 2.24298141557928,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044990299013604045,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.2035774201154709,
|
|
"num_tokens": 51980501.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.5040778636932375,
|
|
"epoch": 2.243475682087782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044988078802687373,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20329577922821046,
|
|
"num_tokens": 51991336.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.505602025985718,
|
|
"epoch": 2.243969948596283,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004498585816156124,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.20199265331029892,
|
|
"num_tokens": 52003215.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.4977131366729735,
|
|
"epoch": 2.2444642151047844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004498363709028029,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.20263072848320007,
|
|
"num_tokens": 52014772.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.455121946334839,
|
|
"epoch": 2.2449584816132857,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044981415588899153,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19981237053871154,
|
|
"num_tokens": 52025808.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.482596302032471,
|
|
"epoch": 2.2454527481217874,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004497919365747248,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.1987760677933693,
|
|
"num_tokens": 52037397.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.459782981872559,
|
|
"epoch": 2.2459470146302887,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044976971296054936,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.21107296794652938,
|
|
"num_tokens": 52048874.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.454881715774536,
|
|
"epoch": 2.24644128113879,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004497474850470118,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19559184163808824,
|
|
"num_tokens": 52061180.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.463914299011231,
|
|
"epoch": 2.2469355476472916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000449725252834659,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20270182937383652,
|
|
"num_tokens": 52073400.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.485079145431518,
|
|
"epoch": 2.247429814155793,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044970301632403796,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.2053244262933731,
|
|
"num_tokens": 52084737.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.422297573089599,
|
|
"epoch": 2.247924080664294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044968077551569554,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.2087634474039078,
|
|
"num_tokens": 52096044.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.504601621627808,
|
|
"epoch": 2.2484183471727954,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000449658530410179,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.20895475745201111,
|
|
"num_tokens": 52108701.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.492856359481811,
|
|
"epoch": 2.248912613681297,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004496362810080354,
|
|
"loss": 5.1072,
|
|
"mean_token_accuracy": 0.204484261572361,
|
|
"num_tokens": 52119797.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.437208938598633,
|
|
"epoch": 2.2494068801897984,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004496140273098123,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19859442561864854,
|
|
"num_tokens": 52132557.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.408165788650512,
|
|
"epoch": 2.2499011466982997,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044959176931605704,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.2084692507982254,
|
|
"num_tokens": 52144058.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.466367292404175,
|
|
"epoch": 2.250395413206801,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044956950702731714,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.20479974448680877,
|
|
"num_tokens": 52155432.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.409068393707275,
|
|
"epoch": 2.2508896797153026,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004495472404441403,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.20423819720745087,
|
|
"num_tokens": 52166925.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.376523017883301,
|
|
"epoch": 2.251383946223804,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004495249695670742,
|
|
"loss": 5.0664,
|
|
"mean_token_accuracy": 0.20269060879945755,
|
|
"num_tokens": 52177452.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.426579380035401,
|
|
"epoch": 2.251878212732305,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004495026943966669,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.20205572098493577,
|
|
"num_tokens": 52189288.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.417010927200318,
|
|
"epoch": 2.2523724792408064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044948041493346615,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.20795025527477265,
|
|
"num_tokens": 52199963.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.393851566314697,
|
|
"epoch": 2.252866745749308,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004494581311780202,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.19874251037836074,
|
|
"num_tokens": 52210727.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.4754065990448,
|
|
"epoch": 2.2533610122578094,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044943584313087705,
|
|
"loss": 5.1091,
|
|
"mean_token_accuracy": 0.20045178085565568,
|
|
"num_tokens": 52222211.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.496287155151367,
|
|
"epoch": 2.2538552787663106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044941355079258517,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.20326752513647078,
|
|
"num_tokens": 52234453.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.412138175964356,
|
|
"epoch": 2.2543495452748123,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004493912541636928,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.20508624613285065,
|
|
"num_tokens": 52246324.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.5012860774993895,
|
|
"epoch": 2.2548438117833136,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004493689532447486,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.2022449791431427,
|
|
"num_tokens": 52258223.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.45849723815918,
|
|
"epoch": 2.255338078291815,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004493466480363011,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.21289248764514923,
|
|
"num_tokens": 52270066.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.542569160461426,
|
|
"epoch": 2.255832344800316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044932433853889903,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.19775531589984893,
|
|
"num_tokens": 52281366.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.4741737842559814,
|
|
"epoch": 2.256326611308818,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004493020247530912,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.2078373610973358,
|
|
"num_tokens": 52292109.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.408083581924439,
|
|
"epoch": 2.256820877817319,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004492797066794264,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.2212707057595253,
|
|
"num_tokens": 52302707.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.418242454528809,
|
|
"epoch": 2.2573151443258204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044925738431845385,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2082698240876198,
|
|
"num_tokens": 52313715.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.466020917892456,
|
|
"epoch": 2.257809410834322,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044923505767072267,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.19809766709804535,
|
|
"num_tokens": 52325612.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.342681980133056,
|
|
"epoch": 2.2583036773428233,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044921272673678197,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.21507082581520082,
|
|
"num_tokens": 52338233.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.407960319519043,
|
|
"epoch": 2.2587979438513246,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004491903915171812,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.2084040954709053,
|
|
"num_tokens": 52348792.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.475236272811889,
|
|
"epoch": 2.259292210359826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044916805201246975,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.2021692380309105,
|
|
"num_tokens": 52359334.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.476551055908203,
|
|
"epoch": 2.2597864768683276,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044914570822319723,
|
|
"loss": 5.1288,
|
|
"mean_token_accuracy": 0.19701761305332183,
|
|
"num_tokens": 52370600.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.488885498046875,
|
|
"epoch": 2.260280743376829,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004491233601499132,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20228964239358901,
|
|
"num_tokens": 52382783.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.404910469055176,
|
|
"epoch": 2.26077500988533,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044910100779316757,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.21688133478164673,
|
|
"num_tokens": 52393372.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.414330291748047,
|
|
"epoch": 2.261269276393832,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004490786511535102,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.20709938257932664,
|
|
"num_tokens": 52405181.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.481075143814087,
|
|
"epoch": 2.261763542902333,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044905629023149084,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20132529735565186,
|
|
"num_tokens": 52417371.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.471041917800903,
|
|
"epoch": 2.2622578094108343,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004490339250276598,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.19947212040424347,
|
|
"num_tokens": 52428712.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.38039493560791,
|
|
"epoch": 2.2627520759193356,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004490115555425672,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.202055487036705,
|
|
"num_tokens": 52439764.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.453199625015259,
|
|
"epoch": 2.263246342427837,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004489891817767634,
|
|
"loss": 5.1157,
|
|
"mean_token_accuracy": 0.19794627875089646,
|
|
"num_tokens": 52451409.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.524020195007324,
|
|
"epoch": 2.2637406089363385,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044896680373079874,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.20266529768705369,
|
|
"num_tokens": 52461471.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.442926454544067,
|
|
"epoch": 2.26423487544484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044894442140522365,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.20157870054244995,
|
|
"num_tokens": 52472693.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.420952033996582,
|
|
"epoch": 2.264729141953341,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004489220348005889,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.20835645049810408,
|
|
"num_tokens": 52483449.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.400354719161987,
|
|
"epoch": 2.265223408461843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000448899643917445,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.20927219092845917,
|
|
"num_tokens": 52494048.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.448080921173096,
|
|
"epoch": 2.265717674970344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004488772487563429,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.19962720870971679,
|
|
"num_tokens": 52506224.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.486981916427612,
|
|
"epoch": 2.2662119414788453,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004488548493178336,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19993958324193956,
|
|
"num_tokens": 52517157.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.462532806396484,
|
|
"epoch": 2.2667062079873466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044883244560246793,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.20119504928588866,
|
|
"num_tokens": 52528826.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.480550718307495,
|
|
"epoch": 2.2672004744958483,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004488100376107972,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.21082860976457596,
|
|
"num_tokens": 52540068.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.411945724487305,
|
|
"epoch": 2.2676947410043495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004487876253433726,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.20766766965389252,
|
|
"num_tokens": 52552611.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.390930652618408,
|
|
"epoch": 2.268189007512851,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004487652088007454,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.20286751687526702,
|
|
"num_tokens": 52564532.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.494980335235596,
|
|
"epoch": 2.2686832740213525,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004487427879834671,
|
|
"loss": 5.1349,
|
|
"mean_token_accuracy": 0.20252057760953904,
|
|
"num_tokens": 52576110.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.469591856002808,
|
|
"epoch": 2.2691775405298538,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044872036289208926,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.2006947159767151,
|
|
"num_tokens": 52586890.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.450709056854248,
|
|
"epoch": 2.269671807038355,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004486979335271635,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.20551495850086213,
|
|
"num_tokens": 52598597.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.424479055404663,
|
|
"epoch": 2.2701660735468563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044867549988924176,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.20583181381225585,
|
|
"num_tokens": 52609361.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.541736221313476,
|
|
"epoch": 2.270660340055358,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044865306197887573,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.20042154639959336,
|
|
"num_tokens": 52620954.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.507930040359497,
|
|
"epoch": 2.2711546065638593,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044863061979661745,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19589168280363084,
|
|
"num_tokens": 52631944.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.5130534172058105,
|
|
"epoch": 2.2716488730723605,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004486081733430189,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.20100173205137253,
|
|
"num_tokens": 52642517.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.488763093948364,
|
|
"epoch": 2.2721431395808622,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044858572261863245,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.20234394073486328,
|
|
"num_tokens": 52653654.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.475712442398072,
|
|
"epoch": 2.2726374060893635,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004485632676240102,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.19945961683988572,
|
|
"num_tokens": 52666068.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.461620759963989,
|
|
"epoch": 2.2731316725978647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004485408083597047,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.20751448720693588,
|
|
"num_tokens": 52677797.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.432921075820923,
|
|
"epoch": 2.273625939106366,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004485183448262684,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.20818679928779601,
|
|
"num_tokens": 52688947.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.419028663635254,
|
|
"epoch": 2.2741202056148677,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004484958770242538,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.19872769564390183,
|
|
"num_tokens": 52700357.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.5372364044189455,
|
|
"epoch": 2.274614472123369,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044847340495421384,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.1951703041791916,
|
|
"num_tokens": 52712602.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.515799236297608,
|
|
"epoch": 2.2751087386318702,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044845092861670114,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.21204862892627716,
|
|
"num_tokens": 52723480.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.403595209121704,
|
|
"epoch": 2.2756030051403715,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004484284480122688,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.199932998418808,
|
|
"num_tokens": 52735418.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.394613742828369,
|
|
"epoch": 2.276097271648873,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044840596314146955,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.20674912482500077,
|
|
"num_tokens": 52746308.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.398219776153565,
|
|
"epoch": 2.2765915381573745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004483834740048568,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.2162153571844101,
|
|
"num_tokens": 52756834.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.4103845119476315,
|
|
"epoch": 2.2770858046658757,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004483609806029837,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.201339653134346,
|
|
"num_tokens": 52768398.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.505957126617432,
|
|
"epoch": 2.277580071174377,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044833848293640354,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.2013295918703079,
|
|
"num_tokens": 52780062.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.440473175048828,
|
|
"epoch": 2.2780743376828787,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044831598100566984,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.20582731813192368,
|
|
"num_tokens": 52791760.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.400449514389038,
|
|
"epoch": 2.27856860419138,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044829347481133613,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.21151357889175415,
|
|
"num_tokens": 52802638.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.3953235149383545,
|
|
"epoch": 2.2790628706998812,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000448270964353956,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.20545130521059035,
|
|
"num_tokens": 52813590.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.414869356155395,
|
|
"epoch": 2.279557137208383,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004482484496340833,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.20907755345106124,
|
|
"num_tokens": 52824177.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.56657304763794,
|
|
"epoch": 2.280051403716884,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004482259306522719,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.19578491598367692,
|
|
"num_tokens": 52834637.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.5099410057067875,
|
|
"epoch": 2.2805456702253855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044820340740907565,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.20289162546396255,
|
|
"num_tokens": 52847893.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.460574054718018,
|
|
"epoch": 2.2810399367338867,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004481808799050488,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.2028070107102394,
|
|
"num_tokens": 52859339.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.4618957996368405,
|
|
"epoch": 2.2815342032423884,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044815834814074544,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.1977651074528694,
|
|
"num_tokens": 52872405.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.368447208404541,
|
|
"epoch": 2.2820284697508897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004481358121167198,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.21394775211811065,
|
|
"num_tokens": 52882187.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.398220014572144,
|
|
"epoch": 2.282522736259391,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044811327183352627,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.2134002313017845,
|
|
"num_tokens": 52894004.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.531612157821655,
|
|
"epoch": 2.2830170027678927,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004480907272917195,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.19640324860811234,
|
|
"num_tokens": 52904749.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.4317731857299805,
|
|
"epoch": 2.283511269276394,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004480681784918539,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.2035178154706955,
|
|
"num_tokens": 52915794.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.435432386398316,
|
|
"epoch": 2.284005535784895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044804562543448436,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.20044576674699782,
|
|
"num_tokens": 52926695.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.440673017501831,
|
|
"epoch": 2.2844998022933964,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004480230681201655,
|
|
"loss": 5.0195,
|
|
"mean_token_accuracy": 0.20987869352102279,
|
|
"num_tokens": 52937824.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.373158693313599,
|
|
"epoch": 2.284994068801898,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044800050654945233,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.20449934899806976,
|
|
"num_tokens": 52949174.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.433677244186401,
|
|
"epoch": 2.2854883353103994,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044797794072289987,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.19790624380111693,
|
|
"num_tokens": 52960675.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.455141496658325,
|
|
"epoch": 2.2859826018189007,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044795537064106335,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.20694676786661148,
|
|
"num_tokens": 52971705.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.463071537017822,
|
|
"epoch": 2.2864768683274024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044793279630449777,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.20225625336170197,
|
|
"num_tokens": 52983025.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.467440938949585,
|
|
"epoch": 2.2869711348359036,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004479102177137586,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.19673410952091216,
|
|
"num_tokens": 52993810.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.428087425231934,
|
|
"epoch": 2.287465401344405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004478876348694012,
|
|
"loss": 5.0709,
|
|
"mean_token_accuracy": 0.19964679330587387,
|
|
"num_tokens": 53005902.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.484973287582397,
|
|
"epoch": 2.287959667852906,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004478650477719812,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.19990008771419526,
|
|
"num_tokens": 53017511.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.362687587738037,
|
|
"epoch": 2.2884539343614074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004478424564220542,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.2180526927113533,
|
|
"num_tokens": 53028514.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.434247398376465,
|
|
"epoch": 2.288948200869909,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044781986082017595,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.20300332605838775,
|
|
"num_tokens": 53039338.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.431693840026855,
|
|
"epoch": 2.2894424673784104,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044779726096690227,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.21098664104938508,
|
|
"num_tokens": 53050877.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.472558832168579,
|
|
"epoch": 2.2899367338869117,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004477746568627892,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.20453207790851594,
|
|
"num_tokens": 53062819.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.444022607803345,
|
|
"epoch": 2.2904310003954134,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044775204850839277,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.20124553591012956,
|
|
"num_tokens": 53073486.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.391992473602295,
|
|
"epoch": 2.2909252669039146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004477294359042692,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.20358388274908065,
|
|
"num_tokens": 53084499.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.441829681396484,
|
|
"epoch": 2.291419533412416,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004477068190509747,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.2020755961537361,
|
|
"num_tokens": 53097181.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.555248260498047,
|
|
"epoch": 2.291913799920917,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044768419794906556,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.20271356403827667,
|
|
"num_tokens": 53108586.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.477429676055908,
|
|
"epoch": 2.292408066429419,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044766157259909853,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20196528881788253,
|
|
"num_tokens": 53119481.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.474532175064087,
|
|
"epoch": 2.29290233293792,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004476389430016299,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.2109207198023796,
|
|
"num_tokens": 53129482.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.353628635406494,
|
|
"epoch": 2.2933965994464214,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044761630915721645,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20724997371435167,
|
|
"num_tokens": 53142311.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.44379448890686,
|
|
"epoch": 2.293890865954923,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004475936710664151,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.20155397057533264,
|
|
"num_tokens": 53153485.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.441036939620972,
|
|
"epoch": 2.2943851324634243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004475710287297826,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.20342763513326645,
|
|
"num_tokens": 53164121.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.457128429412842,
|
|
"epoch": 2.2948793989719256,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004475483821478761,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.20137329399585724,
|
|
"num_tokens": 53174949.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.406279563903809,
|
|
"epoch": 2.295373665480427,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044752573132125263,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.21276717483997346,
|
|
"num_tokens": 53186762.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.43053674697876,
|
|
"epoch": 2.2958679319889286,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004475030762504694,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.20691688507795333,
|
|
"num_tokens": 53198261.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.348531866073609,
|
|
"epoch": 2.29636219849743,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004474804169360836,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.2129147931933403,
|
|
"num_tokens": 53209143.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.55492377281189,
|
|
"epoch": 2.296856465005931,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044745775337865293,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19522450864315033,
|
|
"num_tokens": 53222619.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.447411108016968,
|
|
"epoch": 2.297350731514433,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044743508557873473,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.20778706520795823,
|
|
"num_tokens": 53233829.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.463091897964477,
|
|
"epoch": 2.297844998022934,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044741241353688665,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.20094046741724014,
|
|
"num_tokens": 53244248.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.480132532119751,
|
|
"epoch": 2.2983392645314353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004473897372536665,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.20312254279851913,
|
|
"num_tokens": 53255638.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.434815740585327,
|
|
"epoch": 2.2988335310399366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447367056729632,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.19937446117401122,
|
|
"num_tokens": 53265798.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.4338632106781,
|
|
"epoch": 2.2993277975484383,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004473443719653412,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.20422946959733962,
|
|
"num_tokens": 53278001.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.505098628997803,
|
|
"epoch": 2.2998220640569396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044732168296135217,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20512493550777436,
|
|
"num_tokens": 53289742.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.457031726837158,
|
|
"epoch": 2.300316330565441,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044729898971822296,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.2041373834013939,
|
|
"num_tokens": 53301285.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.406173372268677,
|
|
"epoch": 2.300810597073942,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004472762922365118,
|
|
"loss": 4.9798,
|
|
"mean_token_accuracy": 0.2149757921695709,
|
|
"num_tokens": 53312883.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.460257196426392,
|
|
"epoch": 2.301304863582444,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004472535905167773,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.1978419989347458,
|
|
"num_tokens": 53325215.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.471313238143921,
|
|
"epoch": 2.301799130090945,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004472308845595776,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.1977222219109535,
|
|
"num_tokens": 53337104.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.433367490768433,
|
|
"epoch": 2.3022933965994463,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004472081743654715,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.20247713178396226,
|
|
"num_tokens": 53348097.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.470394897460937,
|
|
"epoch": 2.3027876631079476,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044718545993501754,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.2189238116145134,
|
|
"num_tokens": 53358405.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.4240823745727536,
|
|
"epoch": 2.3032819296164493,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004471627412687745,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.20768845826387405,
|
|
"num_tokens": 53370012.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.458877086639404,
|
|
"epoch": 2.3037761961249505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044714001836730145,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.19704117476940156,
|
|
"num_tokens": 53383214.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.513869047164917,
|
|
"epoch": 2.304270462633452,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044711729123115716,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.19905993491411209,
|
|
"num_tokens": 53395672.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.461809587478638,
|
|
"epoch": 2.3047647291419535,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044709455986090084,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.2026262104511261,
|
|
"num_tokens": 53407577.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.404266262054444,
|
|
"epoch": 2.305258995650455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004470718242570916,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.20679578185081482,
|
|
"num_tokens": 53417772.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.467051792144775,
|
|
"epoch": 2.305753262158956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004470490844202889,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.1978580966591835,
|
|
"num_tokens": 53429675.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.428221559524536,
|
|
"epoch": 2.3062475286674573,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004470263403510519,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.19748691767454146,
|
|
"num_tokens": 53442352.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.536220121383667,
|
|
"epoch": 2.306741795175959,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044700359204994034,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.19028128683567047,
|
|
"num_tokens": 53453710.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.493413877487183,
|
|
"epoch": 2.3072360616844603,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00044698083951751365,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.21122526973485947,
|
|
"num_tokens": 53464764.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.39375901222229,
|
|
"epoch": 2.3077303281929615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004469580827543318,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.21179417818784713,
|
|
"num_tokens": 53476495.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.42393798828125,
|
|
"epoch": 2.3082245947014632,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004469353217609542,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.19645202904939651,
|
|
"num_tokens": 53488613.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.502685260772705,
|
|
"epoch": 2.3087188612099645,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004469125565379411,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.19600758254528045,
|
|
"num_tokens": 53501851.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.482550239562988,
|
|
"epoch": 2.3092131277184658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004468897870858525,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.19893637150526047,
|
|
"num_tokens": 53514325.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.5069272994995115,
|
|
"epoch": 2.309707394226967,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044686701340524836,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.20769056230783461,
|
|
"num_tokens": 53525717.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.431393718719482,
|
|
"epoch": 2.3102016607354687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004468442354966891,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.1995609238743782,
|
|
"num_tokens": 53536488.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.508084297180176,
|
|
"epoch": 2.31069592724397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000446821453360735,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.19119131118059157,
|
|
"num_tokens": 53547230.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.5196634292602536,
|
|
"epoch": 2.3111901937524713,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044679866699794644,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.19612869024276733,
|
|
"num_tokens": 53558673.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.445282316207885,
|
|
"epoch": 2.311684460260973,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004467758764088841,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.21152452677488326,
|
|
"num_tokens": 53570088.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.4456733703613285,
|
|
"epoch": 2.3121787267694742,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004467530815941085,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.20892391949892045,
|
|
"num_tokens": 53582115.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.437289094924926,
|
|
"epoch": 2.3126729932779755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044673028255418047,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.20500196814537047,
|
|
"num_tokens": 53594719.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.321416616439819,
|
|
"epoch": 2.3131672597864767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004467074792896608,
|
|
"loss": 4.9203,
|
|
"mean_token_accuracy": 0.2156531721353531,
|
|
"num_tokens": 53606453.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.4421628475189205,
|
|
"epoch": 2.313661526294978,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044668467180111054,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20909083187580108,
|
|
"num_tokens": 53617038.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.529233121871949,
|
|
"epoch": 2.3141557928034797,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044666186008909077,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.20820472985506058,
|
|
"num_tokens": 53627230.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.504947137832642,
|
|
"epoch": 2.314650059311981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044663904415416245,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.19708001762628555,
|
|
"num_tokens": 53638247.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.477576065063476,
|
|
"epoch": 2.3151443258204822,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004466162239968871,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.20594702512025834,
|
|
"num_tokens": 53648643.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.365424346923828,
|
|
"epoch": 2.315638592328984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004465933996178261,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.21868881285190583,
|
|
"num_tokens": 53659715.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.392257595062256,
|
|
"epoch": 2.316132858837485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044657057101754073,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.2028732568025589,
|
|
"num_tokens": 53671119.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.473867273330688,
|
|
"epoch": 2.3166271253459865,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044654773819659277,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.20930755287408828,
|
|
"num_tokens": 53682145.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.454846668243408,
|
|
"epoch": 2.3171213918544877,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044652490115554386,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.2092534750699997,
|
|
"num_tokens": 53693882.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.446894407272339,
|
|
"epoch": 2.3176156583629894,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004465020598949557,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.1989508256316185,
|
|
"num_tokens": 53706010.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.464134693145752,
|
|
"epoch": 2.3181099248714907,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004464792144153903,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.20111630409955977,
|
|
"num_tokens": 53717657.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.465012741088867,
|
|
"epoch": 2.318604191379992,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004464563647174096,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.20883289873600006,
|
|
"num_tokens": 53729181.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.376503562927246,
|
|
"epoch": 2.3190984578884937,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004464335108015757,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.21281542629003525,
|
|
"num_tokens": 53740864.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.397788381576538,
|
|
"epoch": 2.319592724396995,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004464106526684509,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.20543462336063384,
|
|
"num_tokens": 53751726.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.515195608139038,
|
|
"epoch": 2.320086990905496,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004463877903185974,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.20210451632738113,
|
|
"num_tokens": 53763629.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.438365077972412,
|
|
"epoch": 2.3205812574139975,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004463649237525777,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.21064432263374328,
|
|
"num_tokens": 53774814.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.439261102676392,
|
|
"epoch": 2.321075523922499,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004463420529709543,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.20738704949617387,
|
|
"num_tokens": 53786298.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.4691174030303955,
|
|
"epoch": 2.3215697904310004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044631917797428985,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.20322881639003754,
|
|
"num_tokens": 53798509.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.518418216705323,
|
|
"epoch": 2.3220640569395017,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000446296298763147,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.19981514662504196,
|
|
"num_tokens": 53810689.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.481092071533203,
|
|
"epoch": 2.3225583234480034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004462734153380886,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20127541869878768,
|
|
"num_tokens": 53822432.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.421025180816651,
|
|
"epoch": 2.3230525899565047,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044625052769967766,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.20649343281984328,
|
|
"num_tokens": 53833701.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.396860074996948,
|
|
"epoch": 2.323546856465006,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044622763584847716,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.2123483121395111,
|
|
"num_tokens": 53844413.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.384152603149414,
|
|
"epoch": 2.324041122973507,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044620473978505023,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2095201700925827,
|
|
"num_tokens": 53856392.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.4870799541473385,
|
|
"epoch": 2.324535389482009,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044618183950996017,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.20842831581830978,
|
|
"num_tokens": 53867938.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.356618595123291,
|
|
"epoch": 2.32502965599051,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004461589350237702,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.2134657010436058,
|
|
"num_tokens": 53878153.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.3394067764282225,
|
|
"epoch": 2.3255239224990114,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000446136026327044,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.20810094624757766,
|
|
"num_tokens": 53889090.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.422496318817139,
|
|
"epoch": 2.3260181890075127,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044611311342034494,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.2075164198875427,
|
|
"num_tokens": 53900459.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.480808305740356,
|
|
"epoch": 2.3265124555160144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004460901963042368,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.20831045508384705,
|
|
"num_tokens": 53912815.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.347510099411011,
|
|
"epoch": 2.3270067220245156,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044606727497928324,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.20913825631141664,
|
|
"num_tokens": 53924387.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.501275253295899,
|
|
"epoch": 2.327500988533017,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044604434944604826,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.20446037501096725,
|
|
"num_tokens": 53936147.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.425669145584107,
|
|
"epoch": 2.327995255041518,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004460214197050956,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.2068009316921234,
|
|
"num_tokens": 53948102.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.454986810684204,
|
|
"epoch": 2.32848952155002,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004459984857569896,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.19885686039924622,
|
|
"num_tokens": 53959721.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.456771898269653,
|
|
"epoch": 2.328983788058521,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044597554760229433,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.20892307609319688,
|
|
"num_tokens": 53970302.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.50884222984314,
|
|
"epoch": 2.3294780545670224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000445952605241574,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.2046670526266098,
|
|
"num_tokens": 53982198.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.511990165710449,
|
|
"epoch": 2.329972321075524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044592965867539306,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.19549627602100372,
|
|
"num_tokens": 53994443.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.432645273208618,
|
|
"epoch": 2.3304665875840254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044590670790431604,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.20576945096254348,
|
|
"num_tokens": 54005666.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.40565447807312,
|
|
"epoch": 2.3309608540925266,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004458837529289074,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.20961921513080597,
|
|
"num_tokens": 54016173.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.433719968795776,
|
|
"epoch": 2.331455120601028,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004458607937497321,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.20156891644001007,
|
|
"num_tokens": 54027743.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.534090280532837,
|
|
"epoch": 2.3319493871095296,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004458378303673546,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20178406238555907,
|
|
"num_tokens": 54039804.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.471120405197143,
|
|
"epoch": 2.332443653618031,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004458148627823401,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.20617596209049224,
|
|
"num_tokens": 54050202.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.488564825057983,
|
|
"epoch": 2.332937920126532,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044579189099525334,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.20462463945150375,
|
|
"num_tokens": 54061088.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.354794454574585,
|
|
"epoch": 2.333432186635034,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044576891500665967,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.2095861852169037,
|
|
"num_tokens": 54072524.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.411081266403198,
|
|
"epoch": 2.333926453143535,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004457459348171242,
|
|
"loss": 5.0845,
|
|
"mean_token_accuracy": 0.20432308167219163,
|
|
"num_tokens": 54083265.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.439409875869751,
|
|
"epoch": 2.3344207196520363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044572295042721215,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.21998594850301742,
|
|
"num_tokens": 54093848.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.374304246902466,
|
|
"epoch": 2.3349149861605376,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044569996183748913,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.215274678170681,
|
|
"num_tokens": 54104595.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.324422788619995,
|
|
"epoch": 2.3354092526690393,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044567696904852057,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.21535862237215042,
|
|
"num_tokens": 54115577.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.421136808395386,
|
|
"epoch": 2.3359035191775406,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000445653972060872,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.21123528480529785,
|
|
"num_tokens": 54125579.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.449906730651856,
|
|
"epoch": 2.336397785686042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044563097087510934,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.19832890331745148,
|
|
"num_tokens": 54137895.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.445668411254883,
|
|
"epoch": 2.3368920521945435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044560796549179826,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.2028967946767807,
|
|
"num_tokens": 54149423.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.528980016708374,
|
|
"epoch": 2.337386318703045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004455849559115048,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.20059295147657394,
|
|
"num_tokens": 54160743.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.508137655258179,
|
|
"epoch": 2.337880585211546,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004455619421347949,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.20607281774282454,
|
|
"num_tokens": 54171517.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.412764310836792,
|
|
"epoch": 2.3383748517200473,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044553892416223485,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.2060045063495636,
|
|
"num_tokens": 54182959.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.415164184570313,
|
|
"epoch": 2.3388691182285486,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044551590199439075,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.20404714494943618,
|
|
"num_tokens": 54194577.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.495824670791626,
|
|
"epoch": 2.3393633847370503,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000445492875631829,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.1883851781487465,
|
|
"num_tokens": 54207423.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.458282232284546,
|
|
"epoch": 2.3398576512455516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004454698450751161,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.20829083472490312,
|
|
"num_tokens": 54218776.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.427797651290893,
|
|
"epoch": 2.340351917754053,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004454468103248186,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.20926670134067535,
|
|
"num_tokens": 54229508.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.458190870285034,
|
|
"epoch": 2.3408461842625545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000445423771381503,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.19855430275201796,
|
|
"num_tokens": 54240546.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.433579206466675,
|
|
"epoch": 2.341340450771056,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004454007282457364,
|
|
"loss": 5.0934,
|
|
"mean_token_accuracy": 0.20665213316679001,
|
|
"num_tokens": 54252486.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.5228187084198,
|
|
"epoch": 2.341834717279557,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044537768091808516,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.20252476930618285,
|
|
"num_tokens": 54264240.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.428348445892334,
|
|
"epoch": 2.3423289837880583,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004453546293991168,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.20981816351413726,
|
|
"num_tokens": 54275894.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.4899904251098635,
|
|
"epoch": 2.34282325029656,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000445331573689398,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.2035635754466057,
|
|
"num_tokens": 54287697.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.424953556060791,
|
|
"epoch": 2.3433175168050613,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000445308513789496,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.21604364812374116,
|
|
"num_tokens": 54300327.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.435114955902099,
|
|
"epoch": 2.3438117833135625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044528544969997823,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.1964276671409607,
|
|
"num_tokens": 54311949.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.447161769866943,
|
|
"epoch": 2.3443060498220643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044526238142141196,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.20422642976045607,
|
|
"num_tokens": 54322134.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.5078410625457765,
|
|
"epoch": 2.3448003163305655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044523930895436475,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.19482635259628295,
|
|
"num_tokens": 54334579.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.446677494049072,
|
|
"epoch": 2.3452945828390668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044521623229940407,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.20277819633483887,
|
|
"num_tokens": 54346624.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.384917545318603,
|
|
"epoch": 2.345788849347568,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044519315145709765,
|
|
"loss": 5.0262,
|
|
"mean_token_accuracy": 0.21103499829769135,
|
|
"num_tokens": 54356455.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.547194242477417,
|
|
"epoch": 2.3462831158560697,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004451700664280133,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.1980297327041626,
|
|
"num_tokens": 54368141.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.463581991195679,
|
|
"epoch": 2.346777382364571,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000445146977212719,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.20544976741075516,
|
|
"num_tokens": 54379304.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.434721326828003,
|
|
"epoch": 2.3472716488730723,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004451238838117826,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.21334803998470306,
|
|
"num_tokens": 54391462.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.387145042419434,
|
|
"epoch": 2.347765915381574,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004451007862257723,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.2177960067987442,
|
|
"num_tokens": 54402325.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.3517505645751955,
|
|
"epoch": 2.3482601818900752,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004450776844552562,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.20592666715383529,
|
|
"num_tokens": 54413874.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.415320110321045,
|
|
"epoch": 2.3487544483985765,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004450545785008027,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.20917855054140091,
|
|
"num_tokens": 54426266.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.419110584259033,
|
|
"epoch": 2.3492487149070778,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044503146836298026,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.21217966675758362,
|
|
"num_tokens": 54436682.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.424130487442016,
|
|
"epoch": 2.3497429814155795,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044500835404235727,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.2073086306452751,
|
|
"num_tokens": 54447462.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.52926664352417,
|
|
"epoch": 2.3502372479240807,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004449852355395024,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.21000522375106812,
|
|
"num_tokens": 54460116.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.48525595664978,
|
|
"epoch": 2.350731514432582,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044496211285498434,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.20822741836309433,
|
|
"num_tokens": 54471016.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.413942193984985,
|
|
"epoch": 2.3512257809410833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000444938985989372,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.2124902918934822,
|
|
"num_tokens": 54482410.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.392813348770142,
|
|
"epoch": 2.351720047449585,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044491585494323415,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20398560911417007,
|
|
"num_tokens": 54495555.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.451952314376831,
|
|
"epoch": 2.3522143139580862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044489271971713995,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20816200077533722,
|
|
"num_tokens": 54505658.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.335621738433838,
|
|
"epoch": 2.3527085804665875,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044486958031165856,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.2107233002781868,
|
|
"num_tokens": 54518633.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.526116228103637,
|
|
"epoch": 2.3532028469750887,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044484643672735907,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.1972804605960846,
|
|
"num_tokens": 54531451.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.453356218338013,
|
|
"epoch": 2.3536971134835905,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004448232889648109,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2098526433110237,
|
|
"num_tokens": 54542798.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.429273891448974,
|
|
"epoch": 2.3541913799920917,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004448001370245835,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20332861542701722,
|
|
"num_tokens": 54554551.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.536869144439697,
|
|
"epoch": 2.354685646500593,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044477698090724635,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.2017651081085205,
|
|
"num_tokens": 54564711.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.467349100112915,
|
|
"epoch": 2.3551799130090947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044475382061336913,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.19698564261198043,
|
|
"num_tokens": 54576096.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.464090299606323,
|
|
"epoch": 2.355674179517596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004447306561435215,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.20222220718860626,
|
|
"num_tokens": 54587939.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.49055814743042,
|
|
"epoch": 2.356168446026097,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044470748749827354,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.20679407119750975,
|
|
"num_tokens": 54598470.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.45145173072815,
|
|
"epoch": 2.3566627125345985,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044468431467819505,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.20036374479532243,
|
|
"num_tokens": 54608840.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.420590353012085,
|
|
"epoch": 2.3571569790431,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000444661137683856,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.20552409589290618,
|
|
"num_tokens": 54619319.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.469120454788208,
|
|
"epoch": 2.3576512455516014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004446379565158268,
|
|
"loss": 5.075,
|
|
"mean_token_accuracy": 0.2060706928372383,
|
|
"num_tokens": 54630410.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.503308916091919,
|
|
"epoch": 2.3581455120601027,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004446147711746774,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.19903432875871657,
|
|
"num_tokens": 54642376.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.430089712142944,
|
|
"epoch": 2.3586397785686044,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004445915816609784,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.2043474182486534,
|
|
"num_tokens": 54654378.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.40677227973938,
|
|
"epoch": 2.3591340450771057,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044456838797530006,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.20686686933040618,
|
|
"num_tokens": 54664879.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.416822338104248,
|
|
"epoch": 2.359628311585607,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004445451901182132,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.20767878592014313,
|
|
"num_tokens": 54677251.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.460220003128052,
|
|
"epoch": 2.360122578094108,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004445219880902884,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.2061284750699997,
|
|
"num_tokens": 54688827.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.411448764801025,
|
|
"epoch": 2.36061684460261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004444987818920963,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20011453926563263,
|
|
"num_tokens": 54701046.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.528607749938965,
|
|
"epoch": 2.361111111111111,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004444755715242078,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19635467380285263,
|
|
"num_tokens": 54713254.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.454177379608154,
|
|
"epoch": 2.3616053776196124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044445235698719406,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.20889410078525544,
|
|
"num_tokens": 54723734.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.444929838180542,
|
|
"epoch": 2.362099644128114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000444429138281626,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.19893748462200164,
|
|
"num_tokens": 54735080.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.387450742721557,
|
|
"epoch": 2.3625939106366154,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044440591540807496,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.21425116956233978,
|
|
"num_tokens": 54745164.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.385718822479248,
|
|
"epoch": 2.3630881771451167,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000444382688367112,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.20468474477529525,
|
|
"num_tokens": 54757350.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.420039367675781,
|
|
"epoch": 2.363582443653618,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044435945715930864,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.20815684795379638,
|
|
"num_tokens": 54768290.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.480168676376342,
|
|
"epoch": 2.364076710162119,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004443362217852364,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.20329201519489287,
|
|
"num_tokens": 54779053.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.547258186340332,
|
|
"epoch": 2.364570976670621,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004443129822454668,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.1917516127228737,
|
|
"num_tokens": 54789787.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.523146724700927,
|
|
"epoch": 2.365065243179122,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044428973854057164,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.20396552234888077,
|
|
"num_tokens": 54802036.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.4659035205841064,
|
|
"epoch": 2.3655595096876234,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044426649067112257,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.20439117550849914,
|
|
"num_tokens": 54811765.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.424451780319214,
|
|
"epoch": 2.366053776196125,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004442432386376916,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.21398328095674515,
|
|
"num_tokens": 54823057.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.4576211929321286,
|
|
"epoch": 2.3665480427046264,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044421998244085066,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.20376553535461425,
|
|
"num_tokens": 54834070.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.43367338180542,
|
|
"epoch": 2.3670423092131276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044419672208117204,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.2022787868976593,
|
|
"num_tokens": 54845913.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.4192479133605955,
|
|
"epoch": 2.367536575721629,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004441734575592276,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.20633755922317504,
|
|
"num_tokens": 54856721.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.495712041854858,
|
|
"epoch": 2.3680308422301306,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044415018887559,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.20271584689617156,
|
|
"num_tokens": 54868652.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.431647491455078,
|
|
"epoch": 2.368525108738632,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004441269160308315,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.21604982018470764,
|
|
"num_tokens": 54880753.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.36423625946045,
|
|
"epoch": 2.369019375247133,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00044410363902552466,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.21794374734163285,
|
|
"num_tokens": 54891724.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.441312313079834,
|
|
"epoch": 2.369513641755635,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000444080357860242,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.2050455167889595,
|
|
"num_tokens": 54902516.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.414621114730835,
|
|
"epoch": 2.370007908264136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044405707253555626,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.2071551948785782,
|
|
"num_tokens": 54914392.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.406400871276856,
|
|
"epoch": 2.3705021747726374,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004440337830520404,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.21412672400474547,
|
|
"num_tokens": 54925209.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.4790019512176515,
|
|
"epoch": 2.3709964412811386,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044401048941026725,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.20599905550479888,
|
|
"num_tokens": 54935972.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.341335248947144,
|
|
"epoch": 2.3714907077896403,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004439871916108098,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.21022651344537735,
|
|
"num_tokens": 54945631.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.402506732940674,
|
|
"epoch": 2.3719849742981416,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044396388965424124,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.20064534693956376,
|
|
"num_tokens": 54955734.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.467661809921265,
|
|
"epoch": 2.372479240806643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004439405835411348,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20176356434822082,
|
|
"num_tokens": 54968506.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.372479240806643,
|
|
"eval_entropy": 5.3413844240547546,
|
|
"eval_loss": 5.167645454406738,
|
|
"eval_mean_token_accuracy": 0.20821096962191815,
|
|
"eval_num_tokens": 54968506.0,
|
|
"eval_runtime": 26.6936,
|
|
"eval_samples_per_second": 1218.009,
|
|
"eval_steps_per_second": 152.284,
|
|
"step": 24000
|
|
}
|
|
],
|
|
"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": 8.6032410218496e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|