12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5931198102016607,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.69198923110962,
|
|
"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
|
|
}
|
|
],
|
|
"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": 2.1479895263232e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|