36101 lines
992 KiB
JSON
36101 lines
992 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.07732256203116,
|
|
"eval_steps": 3000,
|
|
"global_step": 18000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691951370239257,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 12.5,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8557,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11955.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691877937316894,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 12.8125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7945,
|
|
"mean_token_accuracy": 0.00010020040208473802,
|
|
"num_tokens": 24473.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.690855121612548,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 10.5625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5617,
|
|
"mean_token_accuracy": 0.02503108715172857,
|
|
"num_tokens": 36716.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.675894641876221,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 6.40625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2237,
|
|
"mean_token_accuracy": 0.045600682869553565,
|
|
"num_tokens": 49747.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.583820247650147,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.9687,
|
|
"mean_token_accuracy": 0.04857061766088009,
|
|
"num_tokens": 61991.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.477548027038575,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.8415,
|
|
"mean_token_accuracy": 0.05598664358258247,
|
|
"num_tokens": 74918.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.462637138366699,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.8059,
|
|
"mean_token_accuracy": 0.054788753390312195,
|
|
"num_tokens": 87833.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.446255970001221,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.7253,
|
|
"mean_token_accuracy": 0.05731462575495243,
|
|
"num_tokens": 101031.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.412657737731934,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.6744,
|
|
"mean_token_accuracy": 0.06321047246456146,
|
|
"num_tokens": 114085.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.344977378845215,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.682,
|
|
"mean_token_accuracy": 0.05514660738408565,
|
|
"num_tokens": 126190.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.360903549194337,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.5899,
|
|
"mean_token_accuracy": 0.07075095213949681,
|
|
"num_tokens": 138933.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.256150436401366,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4931,
|
|
"mean_token_accuracy": 0.07884349599480629,
|
|
"num_tokens": 150542.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.159530735015869,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.4791,
|
|
"mean_token_accuracy": 0.07697005346417427,
|
|
"num_tokens": 163507.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.226024723052978,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.4185,
|
|
"mean_token_accuracy": 0.08218079656362534,
|
|
"num_tokens": 176668.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.084021472930909,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.3547,
|
|
"mean_token_accuracy": 0.08463524356484413,
|
|
"num_tokens": 191413.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.201306247711182,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2867,
|
|
"mean_token_accuracy": 0.08322363793849945,
|
|
"num_tokens": 204176.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.13297176361084,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.2251,
|
|
"mean_token_accuracy": 0.08606483414769173,
|
|
"num_tokens": 216851.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.010610389709473,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.1974,
|
|
"mean_token_accuracy": 0.08009482100605965,
|
|
"num_tokens": 229621.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.165260124206544,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.151,
|
|
"mean_token_accuracy": 0.08369554057717324,
|
|
"num_tokens": 242074.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 9.886237907409669,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.0049,
|
|
"mean_token_accuracy": 0.08854745402932167,
|
|
"num_tokens": 254094.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.991595554351807,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.0197,
|
|
"mean_token_accuracy": 0.08869979456067086,
|
|
"num_tokens": 267560.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.877109718322753,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0088,
|
|
"mean_token_accuracy": 0.08046346381306649,
|
|
"num_tokens": 280717.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.986603260040283,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.956,
|
|
"mean_token_accuracy": 0.08400088958442212,
|
|
"num_tokens": 293856.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.746489906311036,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.7825,
|
|
"mean_token_accuracy": 0.0846656046807766,
|
|
"num_tokens": 305191.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.743055725097657,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.8098,
|
|
"mean_token_accuracy": 0.08250505477190018,
|
|
"num_tokens": 318544.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.622491931915283,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.631,
|
|
"mean_token_accuracy": 0.09809689894318581,
|
|
"num_tokens": 331445.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.531793117523193,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.69,
|
|
"mean_token_accuracy": 0.08484943211078644,
|
|
"num_tokens": 344775.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.43226900100708,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.5877,
|
|
"mean_token_accuracy": 0.08672104477882385,
|
|
"num_tokens": 357804.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.345358848571777,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.5103,
|
|
"mean_token_accuracy": 0.08910816386342049,
|
|
"num_tokens": 369826.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.061049365997315,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.4734,
|
|
"mean_token_accuracy": 0.0947182148694992,
|
|
"num_tokens": 382768.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.184530448913574,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.477,
|
|
"mean_token_accuracy": 0.09176877290010452,
|
|
"num_tokens": 395910.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.0551118850708,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.4796,
|
|
"mean_token_accuracy": 0.08274488113820552,
|
|
"num_tokens": 408140.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.977632331848145,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.3492,
|
|
"mean_token_accuracy": 0.09365171417593957,
|
|
"num_tokens": 420486.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.88683271408081,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.3127,
|
|
"mean_token_accuracy": 0.10231351554393768,
|
|
"num_tokens": 433207.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.718389701843261,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.2991,
|
|
"mean_token_accuracy": 0.09770049974322319,
|
|
"num_tokens": 444880.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.861179733276368,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.3278,
|
|
"mean_token_accuracy": 0.09125575348734856,
|
|
"num_tokens": 456650.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.653267669677735,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.3105,
|
|
"mean_token_accuracy": 0.09449072554707527,
|
|
"num_tokens": 469667.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.639202690124511,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.2226,
|
|
"mean_token_accuracy": 0.10481953471899033,
|
|
"num_tokens": 481952.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.621485424041747,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.2791,
|
|
"mean_token_accuracy": 0.10009086430072785,
|
|
"num_tokens": 494352.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.494072914123535,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.19,
|
|
"mean_token_accuracy": 0.10785712376236915,
|
|
"num_tokens": 506937.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.508214092254638,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.1846,
|
|
"mean_token_accuracy": 0.10090541988611221,
|
|
"num_tokens": 519552.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.504057216644288,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.2334,
|
|
"mean_token_accuracy": 0.09878813922405243,
|
|
"num_tokens": 531359.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.462166213989258,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.2473,
|
|
"mean_token_accuracy": 0.1007633239030838,
|
|
"num_tokens": 544197.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.630421257019043,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.2016,
|
|
"mean_token_accuracy": 0.09566057249903678,
|
|
"num_tokens": 556818.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.372712326049804,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.2354,
|
|
"mean_token_accuracy": 0.10132482126355172,
|
|
"num_tokens": 569363.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.531051921844483,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.2111,
|
|
"mean_token_accuracy": 0.1007345326244831,
|
|
"num_tokens": 581645.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.464646530151366,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.1687,
|
|
"mean_token_accuracy": 0.09699883535504342,
|
|
"num_tokens": 593501.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.380043411254883,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.1632,
|
|
"mean_token_accuracy": 0.10044692009687424,
|
|
"num_tokens": 606328.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.322643375396728,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.0529,
|
|
"mean_token_accuracy": 0.11430942863225937,
|
|
"num_tokens": 619003.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.437573051452636,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.1974,
|
|
"mean_token_accuracy": 0.09745758473873138,
|
|
"num_tokens": 632910.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.345236682891846,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.1263,
|
|
"mean_token_accuracy": 0.1067387342453003,
|
|
"num_tokens": 645959.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.347197151184082,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.1006,
|
|
"mean_token_accuracy": 0.10821648016571998,
|
|
"num_tokens": 658620.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.356802654266357,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.1138,
|
|
"mean_token_accuracy": 0.1112379103899002,
|
|
"num_tokens": 670804.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.397929668426514,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.1186,
|
|
"mean_token_accuracy": 0.1025885134935379,
|
|
"num_tokens": 683656.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.3319091796875,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.093,
|
|
"mean_token_accuracy": 0.10706457123160362,
|
|
"num_tokens": 696629.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.304152488708496,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.113,
|
|
"mean_token_accuracy": 0.10793379172682763,
|
|
"num_tokens": 709053.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.2885817527771,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.0615,
|
|
"mean_token_accuracy": 0.10749010294675827,
|
|
"num_tokens": 721947.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.336502933502198,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.0686,
|
|
"mean_token_accuracy": 0.10405683368444443,
|
|
"num_tokens": 734495.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.229808235168457,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.0824,
|
|
"mean_token_accuracy": 0.1042616605758667,
|
|
"num_tokens": 746965.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.36244821548462,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.0907,
|
|
"mean_token_accuracy": 0.10315949246287345,
|
|
"num_tokens": 760105.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.327516651153564,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.9907,
|
|
"mean_token_accuracy": 0.11302562728524208,
|
|
"num_tokens": 771765.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.284095668792725,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.0752,
|
|
"mean_token_accuracy": 0.10686711072921753,
|
|
"num_tokens": 784895.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.20336627960205,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.0143,
|
|
"mean_token_accuracy": 0.11653341501951217,
|
|
"num_tokens": 797139.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.277932500839233,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.9691,
|
|
"mean_token_accuracy": 0.11882287114858628,
|
|
"num_tokens": 809169.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.219804096221925,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.017,
|
|
"mean_token_accuracy": 0.11045632883906364,
|
|
"num_tokens": 821737.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.202571201324464,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.9302,
|
|
"mean_token_accuracy": 0.1168684981763363,
|
|
"num_tokens": 834365.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.243558883666992,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.9747,
|
|
"mean_token_accuracy": 0.11678506284952164,
|
|
"num_tokens": 846445.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.234999084472657,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.023,
|
|
"mean_token_accuracy": 0.11369575336575508,
|
|
"num_tokens": 858558.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.161874151229858,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.0332,
|
|
"mean_token_accuracy": 0.10968955010175704,
|
|
"num_tokens": 871209.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.284571075439453,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.9815,
|
|
"mean_token_accuracy": 0.11281129494309425,
|
|
"num_tokens": 883270.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.099399852752686,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.9788,
|
|
"mean_token_accuracy": 0.11309987381100654,
|
|
"num_tokens": 895468.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.298340988159179,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.9521,
|
|
"mean_token_accuracy": 0.11634099185466766,
|
|
"num_tokens": 907900.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.028721857070924,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.9507,
|
|
"mean_token_accuracy": 0.11578193232417107,
|
|
"num_tokens": 920036.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.210243511199952,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.9225,
|
|
"mean_token_accuracy": 0.12110625132918358,
|
|
"num_tokens": 932525.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.095637941360474,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.8898,
|
|
"mean_token_accuracy": 0.12433087080717087,
|
|
"num_tokens": 943581.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.17782621383667,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.9898,
|
|
"mean_token_accuracy": 0.11301371231675147,
|
|
"num_tokens": 956270.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.173714351654052,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.9475,
|
|
"mean_token_accuracy": 0.11783768609166145,
|
|
"num_tokens": 967631.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.170480346679687,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.9699,
|
|
"mean_token_accuracy": 0.11223287805914879,
|
|
"num_tokens": 980999.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.166180324554443,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.8761,
|
|
"mean_token_accuracy": 0.11871615797281265,
|
|
"num_tokens": 993404.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.9651154518127445,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.8892,
|
|
"mean_token_accuracy": 0.11921441331505775,
|
|
"num_tokens": 1006009.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.124106407165527,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.9879,
|
|
"mean_token_accuracy": 0.11321467459201813,
|
|
"num_tokens": 1019644.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.151873683929443,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.8907,
|
|
"mean_token_accuracy": 0.12443416640162468,
|
|
"num_tokens": 1032196.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.957633638381958,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.8459,
|
|
"mean_token_accuracy": 0.12779026255011558,
|
|
"num_tokens": 1044211.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.143306255340576,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.8905,
|
|
"mean_token_accuracy": 0.12050737589597701,
|
|
"num_tokens": 1055743.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.111260080337525,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.8987,
|
|
"mean_token_accuracy": 0.11890480741858482,
|
|
"num_tokens": 1068550.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.020257091522216,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.8119,
|
|
"mean_token_accuracy": 0.12798867896199226,
|
|
"num_tokens": 1079878.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.137621879577637,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.8687,
|
|
"mean_token_accuracy": 0.11096916049718857,
|
|
"num_tokens": 1093331.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.066670083999634,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.8257,
|
|
"mean_token_accuracy": 0.12115365341305732,
|
|
"num_tokens": 1105830.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.986959838867188,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.8313,
|
|
"mean_token_accuracy": 0.1250676207244396,
|
|
"num_tokens": 1118071.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.007787656784057,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.8457,
|
|
"mean_token_accuracy": 0.12186303734779358,
|
|
"num_tokens": 1129781.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.014291572570801,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.8951,
|
|
"mean_token_accuracy": 0.11840380728244781,
|
|
"num_tokens": 1142750.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.9940962314605715,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.8294,
|
|
"mean_token_accuracy": 0.12203348949551582,
|
|
"num_tokens": 1154314.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.042590236663818,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.8571,
|
|
"mean_token_accuracy": 0.12293424680829049,
|
|
"num_tokens": 1167199.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.021096801757812,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.8511,
|
|
"mean_token_accuracy": 0.12046421691775322,
|
|
"num_tokens": 1179654.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.927558755874633,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.8023,
|
|
"mean_token_accuracy": 0.1239857017993927,
|
|
"num_tokens": 1190713.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.043779516220093,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8039,
|
|
"mean_token_accuracy": 0.12089489996433259,
|
|
"num_tokens": 1203881.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.005364274978637,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.8446,
|
|
"mean_token_accuracy": 0.1142806276679039,
|
|
"num_tokens": 1215795.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.864235591888428,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.7685,
|
|
"mean_token_accuracy": 0.12962937504053115,
|
|
"num_tokens": 1227773.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.027290201187133,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.7609,
|
|
"mean_token_accuracy": 0.1293689340353012,
|
|
"num_tokens": 1240217.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.006452465057373,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.8361,
|
|
"mean_token_accuracy": 0.1246810033917427,
|
|
"num_tokens": 1253324.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.870799207687378,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.7464,
|
|
"mean_token_accuracy": 0.11857289001345635,
|
|
"num_tokens": 1266007.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.910182189941406,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.7933,
|
|
"mean_token_accuracy": 0.12473395615816116,
|
|
"num_tokens": 1278403.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.910435581207276,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.8167,
|
|
"mean_token_accuracy": 0.1220628336071968,
|
|
"num_tokens": 1290352.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.96209020614624,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.8138,
|
|
"mean_token_accuracy": 0.11629830971360207,
|
|
"num_tokens": 1302304.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.892691946029663,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.7773,
|
|
"mean_token_accuracy": 0.12471387833356858,
|
|
"num_tokens": 1314014.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.03321852684021,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.8184,
|
|
"mean_token_accuracy": 0.12079318463802338,
|
|
"num_tokens": 1326751.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.839642143249511,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.6974,
|
|
"mean_token_accuracy": 0.12328156679868699,
|
|
"num_tokens": 1339070.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.8171533107757565,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.7089,
|
|
"mean_token_accuracy": 0.12542344257235527,
|
|
"num_tokens": 1351345.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.918297529220581,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.7941,
|
|
"mean_token_accuracy": 0.12069407552480697,
|
|
"num_tokens": 1364331.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.783697843551636,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.6797,
|
|
"mean_token_accuracy": 0.13021565973758698,
|
|
"num_tokens": 1377426.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.897759199142456,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.7903,
|
|
"mean_token_accuracy": 0.11785958632826805,
|
|
"num_tokens": 1391553.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.917001342773437,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.7446,
|
|
"mean_token_accuracy": 0.12249603047966957,
|
|
"num_tokens": 1405526.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.944843435287476,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.7697,
|
|
"mean_token_accuracy": 0.12450801730155944,
|
|
"num_tokens": 1417868.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.7399509906768795,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.6914,
|
|
"mean_token_accuracy": 0.12707902863621712,
|
|
"num_tokens": 1429907.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.985376596450806,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.7166,
|
|
"mean_token_accuracy": 0.12132233530282974,
|
|
"num_tokens": 1442552.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.768247318267822,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.7624,
|
|
"mean_token_accuracy": 0.12234465405344963,
|
|
"num_tokens": 1455717.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.9525719165802,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.7642,
|
|
"mean_token_accuracy": 0.1182574063539505,
|
|
"num_tokens": 1468263.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.756762266159058,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.6998,
|
|
"mean_token_accuracy": 0.12650698721408843,
|
|
"num_tokens": 1481632.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.854887342453003,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.648,
|
|
"mean_token_accuracy": 0.1267064943909645,
|
|
"num_tokens": 1495121.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.762281274795532,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7071,
|
|
"mean_token_accuracy": 0.12668090239167212,
|
|
"num_tokens": 1507669.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.738871908187866,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.7326,
|
|
"mean_token_accuracy": 0.11923622786998749,
|
|
"num_tokens": 1520707.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.851386690139771,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.6367,
|
|
"mean_token_accuracy": 0.12671747878193856,
|
|
"num_tokens": 1532974.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.776523685455322,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.6379,
|
|
"mean_token_accuracy": 0.12370964214205742,
|
|
"num_tokens": 1544085.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.664855432510376,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.6676,
|
|
"mean_token_accuracy": 0.13088590577244757,
|
|
"num_tokens": 1556945.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.785807657241821,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.6149,
|
|
"mean_token_accuracy": 0.13267466947436332,
|
|
"num_tokens": 1569570.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.674111986160279,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7054,
|
|
"mean_token_accuracy": 0.12257150337100028,
|
|
"num_tokens": 1582529.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.782325267791748,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6195,
|
|
"mean_token_accuracy": 0.13299935758113862,
|
|
"num_tokens": 1595976.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.767532587051392,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6424,
|
|
"mean_token_accuracy": 0.12903562188148499,
|
|
"num_tokens": 1609093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.731075191497803,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.622,
|
|
"mean_token_accuracy": 0.12647998183965684,
|
|
"num_tokens": 1622233.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.757028245925904,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.6987,
|
|
"mean_token_accuracy": 0.12671734392642975,
|
|
"num_tokens": 1635354.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.748657846450806,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.659,
|
|
"mean_token_accuracy": 0.12423627153038978,
|
|
"num_tokens": 1648223.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.7475920677185055,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.6653,
|
|
"mean_token_accuracy": 0.12359859570860862,
|
|
"num_tokens": 1661652.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.648698377609253,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.5636,
|
|
"mean_token_accuracy": 0.13243083134293557,
|
|
"num_tokens": 1674778.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.787905645370484,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.6459,
|
|
"mean_token_accuracy": 0.12540043219923974,
|
|
"num_tokens": 1686966.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.660491418838501,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.623,
|
|
"mean_token_accuracy": 0.13194708675146102,
|
|
"num_tokens": 1699979.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.710208940505981,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.5421,
|
|
"mean_token_accuracy": 0.1282073549926281,
|
|
"num_tokens": 1712306.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.66764645576477,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6151,
|
|
"mean_token_accuracy": 0.12962080165743828,
|
|
"num_tokens": 1724670.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.820890140533447,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.6844,
|
|
"mean_token_accuracy": 0.12687815874814987,
|
|
"num_tokens": 1736987.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.658799171447754,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.6473,
|
|
"mean_token_accuracy": 0.12734541893005372,
|
|
"num_tokens": 1750587.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.620698738098144,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.6201,
|
|
"mean_token_accuracy": 0.12172205820679664,
|
|
"num_tokens": 1763432.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.6917338371276855,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5204,
|
|
"mean_token_accuracy": 0.13158636018633843,
|
|
"num_tokens": 1777705.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.608352470397949,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.5904,
|
|
"mean_token_accuracy": 0.13091936558485032,
|
|
"num_tokens": 1790673.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.676751232147216,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6165,
|
|
"mean_token_accuracy": 0.12561856135725974,
|
|
"num_tokens": 1803258.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.677963590621948,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.5943,
|
|
"mean_token_accuracy": 0.1276804856956005,
|
|
"num_tokens": 1816534.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.624732446670532,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.5413,
|
|
"mean_token_accuracy": 0.12490850538015366,
|
|
"num_tokens": 1828335.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.605259799957276,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5646,
|
|
"mean_token_accuracy": 0.13269523456692695,
|
|
"num_tokens": 1839327.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.720489597320556,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.6267,
|
|
"mean_token_accuracy": 0.11925766617059708,
|
|
"num_tokens": 1851168.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.6475683689117435,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.6049,
|
|
"mean_token_accuracy": 0.124794951826334,
|
|
"num_tokens": 1863875.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.579368352890015,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5178,
|
|
"mean_token_accuracy": 0.12288314551115036,
|
|
"num_tokens": 1876613.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.694609594345093,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6241,
|
|
"mean_token_accuracy": 0.12489113733172416,
|
|
"num_tokens": 1890311.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.602844142913819,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5948,
|
|
"mean_token_accuracy": 0.12589145004749297,
|
|
"num_tokens": 1902925.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.596966028213501,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5689,
|
|
"mean_token_accuracy": 0.123939748108387,
|
|
"num_tokens": 1915186.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.636845922470092,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.571,
|
|
"mean_token_accuracy": 0.13280307427048682,
|
|
"num_tokens": 1927184.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.59859070777893,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.5462,
|
|
"mean_token_accuracy": 0.134385896474123,
|
|
"num_tokens": 1940275.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.626807355880738,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.5775,
|
|
"mean_token_accuracy": 0.12614732086658478,
|
|
"num_tokens": 1952583.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.596640682220459,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.4969,
|
|
"mean_token_accuracy": 0.12433894649147988,
|
|
"num_tokens": 1965219.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.571691226959229,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.5153,
|
|
"mean_token_accuracy": 0.13145391047000884,
|
|
"num_tokens": 1977193.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.635157775878906,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.4312,
|
|
"mean_token_accuracy": 0.1304060213267803,
|
|
"num_tokens": 1988955.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.514168548583984,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.5695,
|
|
"mean_token_accuracy": 0.12537927627563478,
|
|
"num_tokens": 2001647.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.537772274017334,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.4927,
|
|
"mean_token_accuracy": 0.13620842844247819,
|
|
"num_tokens": 2015185.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.663471412658692,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5901,
|
|
"mean_token_accuracy": 0.1272108480334282,
|
|
"num_tokens": 2027257.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.390483283996582,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.4161,
|
|
"mean_token_accuracy": 0.13912721797823907,
|
|
"num_tokens": 2040716.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.560983800888062,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.55,
|
|
"mean_token_accuracy": 0.12221533954143524,
|
|
"num_tokens": 2053240.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.622315168380737,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5139,
|
|
"mean_token_accuracy": 0.12666195258498192,
|
|
"num_tokens": 2065693.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.4823235988616945,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.4591,
|
|
"mean_token_accuracy": 0.14022310078144073,
|
|
"num_tokens": 2077649.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.467005395889283,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.5063,
|
|
"mean_token_accuracy": 0.12628407776355743,
|
|
"num_tokens": 2090780.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.546123218536377,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.513,
|
|
"mean_token_accuracy": 0.13211931437253951,
|
|
"num_tokens": 2104096.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.543429565429688,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.5109,
|
|
"mean_token_accuracy": 0.12248567417263985,
|
|
"num_tokens": 2117157.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.5339704036712645,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.4826,
|
|
"mean_token_accuracy": 0.12713147699832916,
|
|
"num_tokens": 2129309.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.466995716094971,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.5207,
|
|
"mean_token_accuracy": 0.12562475129961967,
|
|
"num_tokens": 2142344.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.547919607162475,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5488,
|
|
"mean_token_accuracy": 0.12197135463356971,
|
|
"num_tokens": 2155059.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.569330024719238,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5369,
|
|
"mean_token_accuracy": 0.1284255087375641,
|
|
"num_tokens": 2168901.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.4198370456695555,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.3584,
|
|
"mean_token_accuracy": 0.13862554877996444,
|
|
"num_tokens": 2180953.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.476253461837769,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4631,
|
|
"mean_token_accuracy": 0.13572433739900588,
|
|
"num_tokens": 2194097.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.479328727722168,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4058,
|
|
"mean_token_accuracy": 0.13234824016690255,
|
|
"num_tokens": 2206475.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.484198713302613,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.436,
|
|
"mean_token_accuracy": 0.12529727593064308,
|
|
"num_tokens": 2220006.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.488145637512207,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4962,
|
|
"mean_token_accuracy": 0.12320048362016678,
|
|
"num_tokens": 2234082.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.484939479827881,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.4908,
|
|
"mean_token_accuracy": 0.12574098110198975,
|
|
"num_tokens": 2246871.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.439050626754761,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4344,
|
|
"mean_token_accuracy": 0.13258244097232819,
|
|
"num_tokens": 2260172.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.573509597778321,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.4693,
|
|
"mean_token_accuracy": 0.12150668054819107,
|
|
"num_tokens": 2272848.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.414100122451782,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4238,
|
|
"mean_token_accuracy": 0.128422711789608,
|
|
"num_tokens": 2285673.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.493473386764526,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.47,
|
|
"mean_token_accuracy": 0.12711283564567566,
|
|
"num_tokens": 2298459.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.421923589706421,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4389,
|
|
"mean_token_accuracy": 0.1314757324755192,
|
|
"num_tokens": 2311226.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.34346604347229,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.3694,
|
|
"mean_token_accuracy": 0.1267826184630394,
|
|
"num_tokens": 2323481.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.37224383354187,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.4024,
|
|
"mean_token_accuracy": 0.13083600699901582,
|
|
"num_tokens": 2336181.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.499636030197143,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.3534,
|
|
"mean_token_accuracy": 0.13574053421616555,
|
|
"num_tokens": 2348941.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.3138683319091795,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.2945,
|
|
"mean_token_accuracy": 0.1320072427392006,
|
|
"num_tokens": 2361618.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.307975149154663,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.259,
|
|
"mean_token_accuracy": 0.1410675063729286,
|
|
"num_tokens": 2376108.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.366646480560303,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.3883,
|
|
"mean_token_accuracy": 0.13348079323768616,
|
|
"num_tokens": 2387774.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.387966251373291,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.3984,
|
|
"mean_token_accuracy": 0.13679807931184768,
|
|
"num_tokens": 2400816.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.225770616531372,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.3332,
|
|
"mean_token_accuracy": 0.12989477887749673,
|
|
"num_tokens": 2412970.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.398374080657959,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.3348,
|
|
"mean_token_accuracy": 0.13138538971543312,
|
|
"num_tokens": 2424622.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.423074054718017,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.4257,
|
|
"mean_token_accuracy": 0.13353453874588012,
|
|
"num_tokens": 2437293.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.288896751403809,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.3092,
|
|
"mean_token_accuracy": 0.12915137261152268,
|
|
"num_tokens": 2449934.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.371738529205322,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.3638,
|
|
"mean_token_accuracy": 0.1267050661146641,
|
|
"num_tokens": 2463139.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.306709432601929,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4078,
|
|
"mean_token_accuracy": 0.12786821126937867,
|
|
"num_tokens": 2474273.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.4030670642852785,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3521,
|
|
"mean_token_accuracy": 0.13926174938678743,
|
|
"num_tokens": 2486643.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.327881813049316,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3334,
|
|
"mean_token_accuracy": 0.12991991862654687,
|
|
"num_tokens": 2499018.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.229681015014648,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3209,
|
|
"mean_token_accuracy": 0.13620815202593803,
|
|
"num_tokens": 2510463.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.333762550354004,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.3648,
|
|
"mean_token_accuracy": 0.13373479768633842,
|
|
"num_tokens": 2522671.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.2945623874664305,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.3465,
|
|
"mean_token_accuracy": 0.13163619264960288,
|
|
"num_tokens": 2534508.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.360085344314575,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.322,
|
|
"mean_token_accuracy": 0.13855402842164039,
|
|
"num_tokens": 2546804.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.284858369827271,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.3227,
|
|
"mean_token_accuracy": 0.12957534343004226,
|
|
"num_tokens": 2558786.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.372665882110596,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.2956,
|
|
"mean_token_accuracy": 0.13060993254184722,
|
|
"num_tokens": 2570834.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.1804040431976315,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.2577,
|
|
"mean_token_accuracy": 0.13870095685124398,
|
|
"num_tokens": 2583342.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.312113237380982,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.3031,
|
|
"mean_token_accuracy": 0.13401906490325927,
|
|
"num_tokens": 2594878.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.149050855636597,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.2657,
|
|
"mean_token_accuracy": 0.13629036098718644,
|
|
"num_tokens": 2607070.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.316418886184692,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.3088,
|
|
"mean_token_accuracy": 0.13769753351807595,
|
|
"num_tokens": 2620761.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.278573226928711,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.3204,
|
|
"mean_token_accuracy": 0.1292047843337059,
|
|
"num_tokens": 2634161.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.217658758163452,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.2649,
|
|
"mean_token_accuracy": 0.13989781066775323,
|
|
"num_tokens": 2647459.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.200538969039917,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.2675,
|
|
"mean_token_accuracy": 0.13167453035712243,
|
|
"num_tokens": 2660840.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.280622291564941,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.2731,
|
|
"mean_token_accuracy": 0.13342294991016387,
|
|
"num_tokens": 2672673.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.171860647201538,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.289,
|
|
"mean_token_accuracy": 0.13255034536123275,
|
|
"num_tokens": 2685744.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.219749069213867,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.199,
|
|
"mean_token_accuracy": 0.14802319854497908,
|
|
"num_tokens": 2697068.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.331407928466797,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.3567,
|
|
"mean_token_accuracy": 0.12301772236824035,
|
|
"num_tokens": 2710418.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.252064895629883,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.3035,
|
|
"mean_token_accuracy": 0.12562899366021157,
|
|
"num_tokens": 2722440.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.257036256790161,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.2928,
|
|
"mean_token_accuracy": 0.12703390195965766,
|
|
"num_tokens": 2735486.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.245379257202148,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.2958,
|
|
"mean_token_accuracy": 0.12891678139567375,
|
|
"num_tokens": 2747620.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.229975891113281,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.2443,
|
|
"mean_token_accuracy": 0.13310989141464233,
|
|
"num_tokens": 2760987.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.242767477035523,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.2233,
|
|
"mean_token_accuracy": 0.13173784613609313,
|
|
"num_tokens": 2773161.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.143377590179443,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.1702,
|
|
"mean_token_accuracy": 0.1464059606194496,
|
|
"num_tokens": 2786179.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.255331087112427,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.1856,
|
|
"mean_token_accuracy": 0.14088639095425606,
|
|
"num_tokens": 2798859.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.152024507522583,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.2883,
|
|
"mean_token_accuracy": 0.13371546044945717,
|
|
"num_tokens": 2813048.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.280220174789429,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.2463,
|
|
"mean_token_accuracy": 0.13465555906295776,
|
|
"num_tokens": 2826032.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.17284836769104,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.2976,
|
|
"mean_token_accuracy": 0.133281010389328,
|
|
"num_tokens": 2839253.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.185248899459839,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.2206,
|
|
"mean_token_accuracy": 0.1415400303900242,
|
|
"num_tokens": 2852542.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.138202762603759,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.2218,
|
|
"mean_token_accuracy": 0.13877267017960548,
|
|
"num_tokens": 2863967.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.290763425827026,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.3254,
|
|
"mean_token_accuracy": 0.12893034666776657,
|
|
"num_tokens": 2876141.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.014846658706665,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.1565,
|
|
"mean_token_accuracy": 0.13931377455592156,
|
|
"num_tokens": 2888395.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.292420244216919,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.3365,
|
|
"mean_token_accuracy": 0.1309019148349762,
|
|
"num_tokens": 2902399.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.157604312896728,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.0878,
|
|
"mean_token_accuracy": 0.13564511761069298,
|
|
"num_tokens": 2914999.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.144139671325684,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.0883,
|
|
"mean_token_accuracy": 0.14829797372221948,
|
|
"num_tokens": 2928091.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.185041427612305,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.207,
|
|
"mean_token_accuracy": 0.13267041072249414,
|
|
"num_tokens": 2940840.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.118538331985474,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.1349,
|
|
"mean_token_accuracy": 0.13792715817689896,
|
|
"num_tokens": 2952980.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.110788869857788,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.1856,
|
|
"mean_token_accuracy": 0.13442225083708764,
|
|
"num_tokens": 2965437.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.1716221332550045,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.2135,
|
|
"mean_token_accuracy": 0.13230456560850143,
|
|
"num_tokens": 2978077.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.156641292572021,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.2831,
|
|
"mean_token_accuracy": 0.13261316642165183,
|
|
"num_tokens": 2990498.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.198510980606079,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.2269,
|
|
"mean_token_accuracy": 0.13312480375170707,
|
|
"num_tokens": 3002784.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.238051557540894,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.1808,
|
|
"mean_token_accuracy": 0.13066396713256836,
|
|
"num_tokens": 3015689.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.092861557006836,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.1113,
|
|
"mean_token_accuracy": 0.14541881829500197,
|
|
"num_tokens": 3026623.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.083968591690064,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.1675,
|
|
"mean_token_accuracy": 0.14061277359724045,
|
|
"num_tokens": 3039769.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.057619905471801,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.1518,
|
|
"mean_token_accuracy": 0.1339143082499504,
|
|
"num_tokens": 3052044.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.185735702514648,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.1173,
|
|
"mean_token_accuracy": 0.13880359381437302,
|
|
"num_tokens": 3063937.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.0055492401123045,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.0929,
|
|
"mean_token_accuracy": 0.14283955842256546,
|
|
"num_tokens": 3076645.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.1528167724609375,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.1459,
|
|
"mean_token_accuracy": 0.1395370438694954,
|
|
"num_tokens": 3088985.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.103240489959717,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.1467,
|
|
"mean_token_accuracy": 0.13826994374394416,
|
|
"num_tokens": 3101270.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.075673818588257,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.1521,
|
|
"mean_token_accuracy": 0.13071254119277,
|
|
"num_tokens": 3115420.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.155364894866944,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.101,
|
|
"mean_token_accuracy": 0.13510319143533706,
|
|
"num_tokens": 3126176.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.037791395187378,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.134,
|
|
"mean_token_accuracy": 0.14009907394647597,
|
|
"num_tokens": 3139136.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.121502780914307,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.0984,
|
|
"mean_token_accuracy": 0.13803695887327194,
|
|
"num_tokens": 3152036.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.089022874832153,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.124,
|
|
"mean_token_accuracy": 0.1390008471906185,
|
|
"num_tokens": 3164060.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.158830451965332,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.2071,
|
|
"mean_token_accuracy": 0.12887537702918053,
|
|
"num_tokens": 3176410.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.16694221496582,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.2054,
|
|
"mean_token_accuracy": 0.13165885508060454,
|
|
"num_tokens": 3189784.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.0905242443084715,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.126,
|
|
"mean_token_accuracy": 0.1364673689007759,
|
|
"num_tokens": 3202274.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.164013195037842,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.1967,
|
|
"mean_token_accuracy": 0.1339113764464855,
|
|
"num_tokens": 3215593.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.090557193756103,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.0904,
|
|
"mean_token_accuracy": 0.13543560802936555,
|
|
"num_tokens": 3228307.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.0394628047943115,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.063,
|
|
"mean_token_accuracy": 0.137285415828228,
|
|
"num_tokens": 3241676.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.106666898727417,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.1441,
|
|
"mean_token_accuracy": 0.13408377543091773,
|
|
"num_tokens": 3255190.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.084112691879272,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.171,
|
|
"mean_token_accuracy": 0.13335621058940889,
|
|
"num_tokens": 3268236.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.132741975784302,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.1832,
|
|
"mean_token_accuracy": 0.13459478169679642,
|
|
"num_tokens": 3281316.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.08173189163208,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.0801,
|
|
"mean_token_accuracy": 0.1370793603360653,
|
|
"num_tokens": 3293517.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.009785556793213,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.0642,
|
|
"mean_token_accuracy": 0.14415186047554016,
|
|
"num_tokens": 3306814.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.143966817855835,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.1255,
|
|
"mean_token_accuracy": 0.1338451124727726,
|
|
"num_tokens": 3318722.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.947969913482666,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.0902,
|
|
"mean_token_accuracy": 0.13792371451854707,
|
|
"num_tokens": 3331212.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.112496328353882,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 7.065,
|
|
"mean_token_accuracy": 0.14001230895519257,
|
|
"num_tokens": 3343999.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.955641222000122,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.0087,
|
|
"mean_token_accuracy": 0.14088786989450455,
|
|
"num_tokens": 3356281.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.026442623138427,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.0683,
|
|
"mean_token_accuracy": 0.1388309493660927,
|
|
"num_tokens": 3369370.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.115357398986816,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 7.2104,
|
|
"mean_token_accuracy": 0.13239274099469184,
|
|
"num_tokens": 3382400.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.049170970916748,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.0738,
|
|
"mean_token_accuracy": 0.13679501563310623,
|
|
"num_tokens": 3393666.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.102601671218872,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.0784,
|
|
"mean_token_accuracy": 0.13827622160315514,
|
|
"num_tokens": 3405920.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.988848543167114,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 6.9811,
|
|
"mean_token_accuracy": 0.14476096332073213,
|
|
"num_tokens": 3417886.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.066180992126465,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 7.0976,
|
|
"mean_token_accuracy": 0.13426982685923577,
|
|
"num_tokens": 3430626.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.005979776382446,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 6.9849,
|
|
"mean_token_accuracy": 0.13666047602891923,
|
|
"num_tokens": 3443248.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.070165061950684,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.032,
|
|
"mean_token_accuracy": 0.13812974020838736,
|
|
"num_tokens": 3456163.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.949036455154419,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.0586,
|
|
"mean_token_accuracy": 0.1321362428367138,
|
|
"num_tokens": 3468862.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.017643308639526,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 7.0618,
|
|
"mean_token_accuracy": 0.14320022165775298,
|
|
"num_tokens": 3481516.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.152157735824585,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 7.1397,
|
|
"mean_token_accuracy": 0.12845932096242904,
|
|
"num_tokens": 3493063.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.983753442764282,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 6.9992,
|
|
"mean_token_accuracy": 0.13282350823283195,
|
|
"num_tokens": 3505460.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.0605611324310305,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.1184,
|
|
"mean_token_accuracy": 0.13035993799567222,
|
|
"num_tokens": 3519232.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.989923524856567,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 7.0311,
|
|
"mean_token_accuracy": 0.14471797570586203,
|
|
"num_tokens": 3531759.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.006714677810669,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 6.9624,
|
|
"mean_token_accuracy": 0.14889438897371293,
|
|
"num_tokens": 3543457.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.985404443740845,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.1171,
|
|
"mean_token_accuracy": 0.13007233440876007,
|
|
"num_tokens": 3557036.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.086899042129517,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 7.0671,
|
|
"mean_token_accuracy": 0.1431369036436081,
|
|
"num_tokens": 3569415.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.992696142196655,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.0656,
|
|
"mean_token_accuracy": 0.13436094596982,
|
|
"num_tokens": 3581452.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.03533968925476,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.1012,
|
|
"mean_token_accuracy": 0.1372412621974945,
|
|
"num_tokens": 3593482.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.005078983306885,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.0916,
|
|
"mean_token_accuracy": 0.13415241464972497,
|
|
"num_tokens": 3606062.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.060822534561157,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 7.0473,
|
|
"mean_token_accuracy": 0.1380315750837326,
|
|
"num_tokens": 3619210.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.01508846282959,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 7.0976,
|
|
"mean_token_accuracy": 0.13783507272601128,
|
|
"num_tokens": 3631952.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.05513277053833,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 6.9784,
|
|
"mean_token_accuracy": 0.1367719940841198,
|
|
"num_tokens": 3644864.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.986611795425415,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 7.046,
|
|
"mean_token_accuracy": 0.13879042416810988,
|
|
"num_tokens": 3657504.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.017226314544677,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 6.9585,
|
|
"mean_token_accuracy": 0.14265901520848273,
|
|
"num_tokens": 3670304.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.9451819896698,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 6.9718,
|
|
"mean_token_accuracy": 0.13715282902121545,
|
|
"num_tokens": 3681503.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.938751745223999,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 7.0007,
|
|
"mean_token_accuracy": 0.13866478949785233,
|
|
"num_tokens": 3693248.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.016212892532349,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 7.035,
|
|
"mean_token_accuracy": 0.1379549205303192,
|
|
"num_tokens": 3705285.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.883904600143433,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 7.0562,
|
|
"mean_token_accuracy": 0.12795180603861808,
|
|
"num_tokens": 3719025.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.103451251983643,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 7.0306,
|
|
"mean_token_accuracy": 0.13902753069996834,
|
|
"num_tokens": 3732054.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.955500936508178,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.0133,
|
|
"mean_token_accuracy": 0.13680559545755386,
|
|
"num_tokens": 3744080.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.9854591369628904,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.047,
|
|
"mean_token_accuracy": 0.13523856773972512,
|
|
"num_tokens": 3756371.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.104809236526489,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 6.9673,
|
|
"mean_token_accuracy": 0.1353852815926075,
|
|
"num_tokens": 3769307.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.814951086044312,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 6.9706,
|
|
"mean_token_accuracy": 0.14363576769828795,
|
|
"num_tokens": 3782826.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.0104962348937985,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 6.9846,
|
|
"mean_token_accuracy": 0.1368210159242153,
|
|
"num_tokens": 3794566.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.955519914627075,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.0675,
|
|
"mean_token_accuracy": 0.1298111744225025,
|
|
"num_tokens": 3807058.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.028119516372681,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 7.0107,
|
|
"mean_token_accuracy": 0.14360469132661818,
|
|
"num_tokens": 3819836.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.98626184463501,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 7.0598,
|
|
"mean_token_accuracy": 0.1317824549973011,
|
|
"num_tokens": 3832081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.0153602123260494,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 6.9811,
|
|
"mean_token_accuracy": 0.13875427916646005,
|
|
"num_tokens": 3843279.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.946571159362793,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 7.0461,
|
|
"mean_token_accuracy": 0.14072771817445756,
|
|
"num_tokens": 3855479.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.037504243850708,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 7.0258,
|
|
"mean_token_accuracy": 0.1374424070119858,
|
|
"num_tokens": 3868111.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.900399398803711,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 6.9516,
|
|
"mean_token_accuracy": 0.14264189973473548,
|
|
"num_tokens": 3880062.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.105960988998413,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 7.0352,
|
|
"mean_token_accuracy": 0.13576769903302194,
|
|
"num_tokens": 3892293.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.912646913528443,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 6.8992,
|
|
"mean_token_accuracy": 0.1437755271792412,
|
|
"num_tokens": 3904549.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.929834699630737,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 6.953,
|
|
"mean_token_accuracy": 0.14296042323112487,
|
|
"num_tokens": 3916693.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.884093236923218,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.13235038220882417,
|
|
"num_tokens": 3930488.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.985349941253662,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 6.961,
|
|
"mean_token_accuracy": 0.14040945768356322,
|
|
"num_tokens": 3942353.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.977359771728516,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 7.0072,
|
|
"mean_token_accuracy": 0.13477388694882392,
|
|
"num_tokens": 3953868.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.984608507156372,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 7.0248,
|
|
"mean_token_accuracy": 0.13513074964284896,
|
|
"num_tokens": 3965148.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.968512153625488,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 6.9684,
|
|
"mean_token_accuracy": 0.14738112092018127,
|
|
"num_tokens": 3977323.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.937796115875244,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.9445,
|
|
"mean_token_accuracy": 0.1459215387701988,
|
|
"num_tokens": 3990076.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.896608018875122,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.959,
|
|
"mean_token_accuracy": 0.1377126969397068,
|
|
"num_tokens": 4001996.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.98504409790039,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 7.0041,
|
|
"mean_token_accuracy": 0.13642505407333375,
|
|
"num_tokens": 4015095.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.90059175491333,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 6.8935,
|
|
"mean_token_accuracy": 0.1471956580877304,
|
|
"num_tokens": 4028633.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.932298421859741,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.9938,
|
|
"mean_token_accuracy": 0.1394735284149647,
|
|
"num_tokens": 4042265.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.876345634460449,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.954,
|
|
"mean_token_accuracy": 0.1372726485133171,
|
|
"num_tokens": 4054467.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.95422887802124,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 6.951,
|
|
"mean_token_accuracy": 0.1380107432603836,
|
|
"num_tokens": 4068053.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.854258346557617,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 6.9318,
|
|
"mean_token_accuracy": 0.1387524574995041,
|
|
"num_tokens": 4080867.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.933802938461303,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 6.9481,
|
|
"mean_token_accuracy": 0.14056655392050743,
|
|
"num_tokens": 4093228.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.00413064956665,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 6.9716,
|
|
"mean_token_accuracy": 0.14066905975341798,
|
|
"num_tokens": 4104929.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.8644571781158445,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.9945,
|
|
"mean_token_accuracy": 0.14416123032569886,
|
|
"num_tokens": 4119445.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.075875329971313,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.8961,
|
|
"mean_token_accuracy": 0.14873119294643403,
|
|
"num_tokens": 4131558.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.876895570755005,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 7.0549,
|
|
"mean_token_accuracy": 0.12923122197389603,
|
|
"num_tokens": 4144566.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.990751695632935,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.9381,
|
|
"mean_token_accuracy": 0.14834065288305281,
|
|
"num_tokens": 4157295.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.910133790969849,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.9455,
|
|
"mean_token_accuracy": 0.13908031955361366,
|
|
"num_tokens": 4170229.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.951679515838623,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.9645,
|
|
"mean_token_accuracy": 0.13757809549570083,
|
|
"num_tokens": 4182906.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.961617517471313,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9304,
|
|
"mean_token_accuracy": 0.14034477695822717,
|
|
"num_tokens": 4195556.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.911066627502441,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.8961,
|
|
"mean_token_accuracy": 0.1394181601703167,
|
|
"num_tokens": 4207616.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.845373630523682,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.8568,
|
|
"mean_token_accuracy": 0.14717165976762772,
|
|
"num_tokens": 4219299.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.886244630813598,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 7.0009,
|
|
"mean_token_accuracy": 0.13946698978543282,
|
|
"num_tokens": 4232098.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.927741765975952,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.8926,
|
|
"mean_token_accuracy": 0.14187719076871871,
|
|
"num_tokens": 4243879.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.919966363906861,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.9798,
|
|
"mean_token_accuracy": 0.13289057463407516,
|
|
"num_tokens": 4256507.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.115394401550293,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 7.0498,
|
|
"mean_token_accuracy": 0.13213248774409295,
|
|
"num_tokens": 4270763.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.83512053489685,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.9311,
|
|
"mean_token_accuracy": 0.13900210931897164,
|
|
"num_tokens": 4284380.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.999711275100708,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 7.0283,
|
|
"mean_token_accuracy": 0.13723405376076697,
|
|
"num_tokens": 4297812.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.927718687057495,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 7.0,
|
|
"mean_token_accuracy": 0.14325511828064919,
|
|
"num_tokens": 4310374.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.975845861434936,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.966,
|
|
"mean_token_accuracy": 0.1380312144756317,
|
|
"num_tokens": 4322330.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.951593542098999,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.9519,
|
|
"mean_token_accuracy": 0.1390042595565319,
|
|
"num_tokens": 4335204.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.7771580696105955,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.8396,
|
|
"mean_token_accuracy": 0.14716555774211884,
|
|
"num_tokens": 4347339.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.960784196853638,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.8991,
|
|
"mean_token_accuracy": 0.14737813025712967,
|
|
"num_tokens": 4360273.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.812373208999634,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.9116,
|
|
"mean_token_accuracy": 0.14005344808101655,
|
|
"num_tokens": 4373424.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.970333909988403,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.8623,
|
|
"mean_token_accuracy": 0.14696093946695327,
|
|
"num_tokens": 4386125.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.900853633880615,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.9299,
|
|
"mean_token_accuracy": 0.1397725947201252,
|
|
"num_tokens": 4399214.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.842698955535889,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.8108,
|
|
"mean_token_accuracy": 0.14288675636053086,
|
|
"num_tokens": 4411282.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.895815658569336,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.904,
|
|
"mean_token_accuracy": 0.14115357473492623,
|
|
"num_tokens": 4423448.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.8710291385650635,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.8318,
|
|
"mean_token_accuracy": 0.14915311187505723,
|
|
"num_tokens": 4436498.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.864768648147583,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.8424,
|
|
"mean_token_accuracy": 0.14298070967197418,
|
|
"num_tokens": 4448641.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.82587513923645,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8389,
|
|
"mean_token_accuracy": 0.14010173305869103,
|
|
"num_tokens": 4460539.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.890678787231446,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.9094,
|
|
"mean_token_accuracy": 0.1397670365869999,
|
|
"num_tokens": 4472487.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.8611537456512455,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.8784,
|
|
"mean_token_accuracy": 0.14253682196140288,
|
|
"num_tokens": 4485164.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.964418983459472,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.9038,
|
|
"mean_token_accuracy": 0.14524734169244766,
|
|
"num_tokens": 4497708.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.834679794311524,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.9527,
|
|
"mean_token_accuracy": 0.13614820539951325,
|
|
"num_tokens": 4510648.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.901812505722046,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.8605,
|
|
"mean_token_accuracy": 0.14650894105434417,
|
|
"num_tokens": 4522699.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.82709813117981,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.14181671142578126,
|
|
"num_tokens": 4536060.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.863535785675049,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.8218,
|
|
"mean_token_accuracy": 0.14091982021927835,
|
|
"num_tokens": 4549876.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.900723028182983,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.872,
|
|
"mean_token_accuracy": 0.1442640721797943,
|
|
"num_tokens": 4563638.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.806870174407959,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.8087,
|
|
"mean_token_accuracy": 0.14233467727899551,
|
|
"num_tokens": 4575396.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.781218814849853,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.8239,
|
|
"mean_token_accuracy": 0.14259946793317796,
|
|
"num_tokens": 4587261.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.937310457229614,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.1397809252142906,
|
|
"num_tokens": 4600086.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.912576341629029,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.9093,
|
|
"mean_token_accuracy": 0.1342283457517624,
|
|
"num_tokens": 4612320.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.850874280929565,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.8522,
|
|
"mean_token_accuracy": 0.14495468139648438,
|
|
"num_tokens": 4623545.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.87814154624939,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.7709,
|
|
"mean_token_accuracy": 0.15582974776625633,
|
|
"num_tokens": 4637223.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.624226713180542,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.8385,
|
|
"mean_token_accuracy": 0.14391470998525618,
|
|
"num_tokens": 4649748.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.985252904891968,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8723,
|
|
"mean_token_accuracy": 0.14348524510860444,
|
|
"num_tokens": 4662441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.706543636322022,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.8359,
|
|
"mean_token_accuracy": 0.15377265065908433,
|
|
"num_tokens": 4675546.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.046459770202636,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.9101,
|
|
"mean_token_accuracy": 0.1373351812362671,
|
|
"num_tokens": 4687601.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.7164732933044435,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.7657,
|
|
"mean_token_accuracy": 0.15242065340280533,
|
|
"num_tokens": 4699336.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.901521301269531,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.9738,
|
|
"mean_token_accuracy": 0.1383403241634369,
|
|
"num_tokens": 4714312.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.770059871673584,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.6833,
|
|
"mean_token_accuracy": 0.15454858019948006,
|
|
"num_tokens": 4726436.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.858100318908692,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.9327,
|
|
"mean_token_accuracy": 0.13296440094709397,
|
|
"num_tokens": 4739821.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.93988528251648,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.9047,
|
|
"mean_token_accuracy": 0.1361124962568283,
|
|
"num_tokens": 4752701.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.844181823730469,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.9331,
|
|
"mean_token_accuracy": 0.1368408054113388,
|
|
"num_tokens": 4766755.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.866988563537598,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.14372632652521133,
|
|
"num_tokens": 4780201.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.863262557983399,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.8284,
|
|
"mean_token_accuracy": 0.14132185727357865,
|
|
"num_tokens": 4792488.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.798328876495361,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.7934,
|
|
"mean_token_accuracy": 0.14561547935009003,
|
|
"num_tokens": 4805154.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.830894565582275,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.852,
|
|
"mean_token_accuracy": 0.14222206994891168,
|
|
"num_tokens": 4817947.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.834425973892212,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.8408,
|
|
"mean_token_accuracy": 0.14236815497279168,
|
|
"num_tokens": 4830296.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.832809066772461,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.8318,
|
|
"mean_token_accuracy": 0.13888390138745307,
|
|
"num_tokens": 4841210.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.879108953475952,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.9203,
|
|
"mean_token_accuracy": 0.13413121029734612,
|
|
"num_tokens": 4854406.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.848855876922608,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.8873,
|
|
"mean_token_accuracy": 0.1403192825615406,
|
|
"num_tokens": 4868156.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.837898826599121,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.814,
|
|
"mean_token_accuracy": 0.14790826439857482,
|
|
"num_tokens": 4880314.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.8341789722442625,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.8263,
|
|
"mean_token_accuracy": 0.14194524735212327,
|
|
"num_tokens": 4892652.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.928193855285644,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.9246,
|
|
"mean_token_accuracy": 0.13543495833873748,
|
|
"num_tokens": 4905791.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.824593591690063,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8886,
|
|
"mean_token_accuracy": 0.13973383381962776,
|
|
"num_tokens": 4917359.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.9390894889831545,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.8356,
|
|
"mean_token_accuracy": 0.14431015402078629,
|
|
"num_tokens": 4928762.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.8002971649169925,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.8618,
|
|
"mean_token_accuracy": 0.1413520596921444,
|
|
"num_tokens": 4940879.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.9403890609741214,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.8601,
|
|
"mean_token_accuracy": 0.14300046414136885,
|
|
"num_tokens": 4952979.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.7911515712738035,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.15122427493333818,
|
|
"num_tokens": 4965465.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.746047019958496,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.848,
|
|
"mean_token_accuracy": 0.14356525242328644,
|
|
"num_tokens": 4977960.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.9141035079956055,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.8461,
|
|
"mean_token_accuracy": 0.14194221496582032,
|
|
"num_tokens": 4990732.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.763252067565918,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.7825,
|
|
"mean_token_accuracy": 0.14249248653650284,
|
|
"num_tokens": 5002482.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.819217205047607,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.7532,
|
|
"mean_token_accuracy": 0.14924108535051345,
|
|
"num_tokens": 5014932.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.760645580291748,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.8991,
|
|
"mean_token_accuracy": 0.13749758303165435,
|
|
"num_tokens": 5027661.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.762338304519654,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.6503,
|
|
"mean_token_accuracy": 0.1527012199163437,
|
|
"num_tokens": 5040657.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.837014961242676,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.932,
|
|
"mean_token_accuracy": 0.1339501306414604,
|
|
"num_tokens": 5054408.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.857686519622803,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.817,
|
|
"mean_token_accuracy": 0.14147326201200486,
|
|
"num_tokens": 5065499.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.737187385559082,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.7662,
|
|
"mean_token_accuracy": 0.15133574232459068,
|
|
"num_tokens": 5077009.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.883497905731201,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.9356,
|
|
"mean_token_accuracy": 0.1379622347652912,
|
|
"num_tokens": 5089462.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.845494270324707,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.849,
|
|
"mean_token_accuracy": 0.14125331565737725,
|
|
"num_tokens": 5101816.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.83185510635376,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.8147,
|
|
"mean_token_accuracy": 0.13760584592819214,
|
|
"num_tokens": 5115085.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.816512393951416,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.8383,
|
|
"mean_token_accuracy": 0.13956220373511313,
|
|
"num_tokens": 5127705.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.756067323684692,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.8004,
|
|
"mean_token_accuracy": 0.14978178068995476,
|
|
"num_tokens": 5140509.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.873353624343872,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.8414,
|
|
"mean_token_accuracy": 0.13831417188048362,
|
|
"num_tokens": 5153538.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.819164085388183,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7717,
|
|
"mean_token_accuracy": 0.14658078253269197,
|
|
"num_tokens": 5166181.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.798212099075317,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.799,
|
|
"mean_token_accuracy": 0.14503582268953324,
|
|
"num_tokens": 5177209.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.752374887466431,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.8182,
|
|
"mean_token_accuracy": 0.13951095193624496,
|
|
"num_tokens": 5189786.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.845754146575928,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.7955,
|
|
"mean_token_accuracy": 0.14597882628440856,
|
|
"num_tokens": 5202629.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.795567512512207,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.8691,
|
|
"mean_token_accuracy": 0.13765914365649223,
|
|
"num_tokens": 5215339.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.792061185836792,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.7339,
|
|
"mean_token_accuracy": 0.14747889786958696,
|
|
"num_tokens": 5227666.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.6639073371887205,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.7198,
|
|
"mean_token_accuracy": 0.14811492711305618,
|
|
"num_tokens": 5238200.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.769328355789185,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.6725,
|
|
"mean_token_accuracy": 0.14989647567272185,
|
|
"num_tokens": 5250023.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.771991300582886,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.8616,
|
|
"mean_token_accuracy": 0.13556723967194556,
|
|
"num_tokens": 5262634.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.898429107666016,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.8602,
|
|
"mean_token_accuracy": 0.13672183454036713,
|
|
"num_tokens": 5275739.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.76414852142334,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.8172,
|
|
"mean_token_accuracy": 0.14185626655817032,
|
|
"num_tokens": 5289223.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.843665933609008,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.81,
|
|
"mean_token_accuracy": 0.1396335631608963,
|
|
"num_tokens": 5301869.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.808076477050781,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.8278,
|
|
"mean_token_accuracy": 0.13811877146363258,
|
|
"num_tokens": 5314999.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.79498610496521,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.845,
|
|
"mean_token_accuracy": 0.14215158969163894,
|
|
"num_tokens": 5328247.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.880921792984009,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.8275,
|
|
"mean_token_accuracy": 0.13474374860525132,
|
|
"num_tokens": 5341054.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.741239166259765,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.8547,
|
|
"mean_token_accuracy": 0.14400363937020302,
|
|
"num_tokens": 5353857.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.843392419815063,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.13821006268262864,
|
|
"num_tokens": 5366072.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.719191312789917,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7717,
|
|
"mean_token_accuracy": 0.14614173099398614,
|
|
"num_tokens": 5379613.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.86360387802124,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.811,
|
|
"mean_token_accuracy": 0.14077582731842994,
|
|
"num_tokens": 5392394.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.659087896347046,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.7942,
|
|
"mean_token_accuracy": 0.14860865324735642,
|
|
"num_tokens": 5404127.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.989247369766235,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.8993,
|
|
"mean_token_accuracy": 0.13390290439128877,
|
|
"num_tokens": 5417317.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.728624773025513,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7489,
|
|
"mean_token_accuracy": 0.14663361757993698,
|
|
"num_tokens": 5429991.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.749109506607056,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.786,
|
|
"mean_token_accuracy": 0.1380963869392872,
|
|
"num_tokens": 5442661.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.798228549957275,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.8134,
|
|
"mean_token_accuracy": 0.14670575857162477,
|
|
"num_tokens": 5455876.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.707323455810547,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.14578518271446228,
|
|
"num_tokens": 5468151.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.745931768417359,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.15150473788380622,
|
|
"num_tokens": 5481327.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.735119152069092,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.7461,
|
|
"mean_token_accuracy": 0.1452285200357437,
|
|
"num_tokens": 5493794.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.7988443851470945,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.7754,
|
|
"mean_token_accuracy": 0.1396859109401703,
|
|
"num_tokens": 5506831.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.80522894859314,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.6666,
|
|
"mean_token_accuracy": 0.1507306069135666,
|
|
"num_tokens": 5518988.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.527280187606811,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.6262,
|
|
"mean_token_accuracy": 0.14936918169260024,
|
|
"num_tokens": 5530757.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.788536119461059,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.7494,
|
|
"mean_token_accuracy": 0.14626611173152923,
|
|
"num_tokens": 5542819.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.713362503051758,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.14051934331655502,
|
|
"num_tokens": 5555797.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.766080236434936,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.8895,
|
|
"mean_token_accuracy": 0.13041166514158248,
|
|
"num_tokens": 5570086.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.788276147842407,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.6845,
|
|
"mean_token_accuracy": 0.1493205651640892,
|
|
"num_tokens": 5582182.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.735091209411621,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7832,
|
|
"mean_token_accuracy": 0.14482725113630296,
|
|
"num_tokens": 5595395.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.795186614990234,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7803,
|
|
"mean_token_accuracy": 0.14214650616049768,
|
|
"num_tokens": 5608555.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.733956241607666,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.753,
|
|
"mean_token_accuracy": 0.1399676337838173,
|
|
"num_tokens": 5620933.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.807656335830688,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.7964,
|
|
"mean_token_accuracy": 0.14257583171129226,
|
|
"num_tokens": 5634061.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.763797903060913,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.7431,
|
|
"mean_token_accuracy": 0.14566465988755226,
|
|
"num_tokens": 5646617.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.783767938613892,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.8348,
|
|
"mean_token_accuracy": 0.13886496499180795,
|
|
"num_tokens": 5659361.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.7600174903869625,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.6769,
|
|
"mean_token_accuracy": 0.1541120558977127,
|
|
"num_tokens": 5670591.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.7302642345428465,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.7974,
|
|
"mean_token_accuracy": 0.1425503261387348,
|
|
"num_tokens": 5683211.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.790132999420166,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.7847,
|
|
"mean_token_accuracy": 0.14356143027544022,
|
|
"num_tokens": 5695654.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.707987117767334,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.6929,
|
|
"mean_token_accuracy": 0.14759473353624344,
|
|
"num_tokens": 5707776.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.729296684265137,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.7372,
|
|
"mean_token_accuracy": 0.1442895159125328,
|
|
"num_tokens": 5719895.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.8028727054595945,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.7501,
|
|
"mean_token_accuracy": 0.15161172673106194,
|
|
"num_tokens": 5733280.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.734392881393433,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.14286206290125847,
|
|
"num_tokens": 5746563.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.888967847824096,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.8586,
|
|
"mean_token_accuracy": 0.13801560774445534,
|
|
"num_tokens": 5760735.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.7270537376403805,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7564,
|
|
"mean_token_accuracy": 0.13578541129827498,
|
|
"num_tokens": 5774304.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.6204423904418945,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.6497,
|
|
"mean_token_accuracy": 0.15090691298246384,
|
|
"num_tokens": 5786045.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.754159736633301,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.7144,
|
|
"mean_token_accuracy": 0.1462336763739586,
|
|
"num_tokens": 5798126.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.746666812896729,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.15180645808577536,
|
|
"num_tokens": 5809778.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.795130205154419,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.8156,
|
|
"mean_token_accuracy": 0.14033974930644036,
|
|
"num_tokens": 5821902.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.782390499114991,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.7574,
|
|
"mean_token_accuracy": 0.1411186173558235,
|
|
"num_tokens": 5835162.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.764913749694824,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.1470859795808792,
|
|
"num_tokens": 5847708.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.743312931060791,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.7407,
|
|
"mean_token_accuracy": 0.14818446189165116,
|
|
"num_tokens": 5860983.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.69023756980896,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.7176,
|
|
"mean_token_accuracy": 0.1412323720753193,
|
|
"num_tokens": 5873878.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.642313623428345,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.7315,
|
|
"mean_token_accuracy": 0.14647015184164047,
|
|
"num_tokens": 5886577.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.8489755153656,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.7482,
|
|
"mean_token_accuracy": 0.13658007383346557,
|
|
"num_tokens": 5900373.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.667910242080689,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.7465,
|
|
"mean_token_accuracy": 0.14726608991622925,
|
|
"num_tokens": 5913038.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.69633846282959,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.6931,
|
|
"mean_token_accuracy": 0.14734635949134828,
|
|
"num_tokens": 5926096.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.720061302185059,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.7071,
|
|
"mean_token_accuracy": 0.1467483162879944,
|
|
"num_tokens": 5937992.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.702146768569946,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.7227,
|
|
"mean_token_accuracy": 0.15519675761461257,
|
|
"num_tokens": 5949685.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.744102334976196,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.7951,
|
|
"mean_token_accuracy": 0.14176806733012198,
|
|
"num_tokens": 5962751.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.628593158721924,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.5808,
|
|
"mean_token_accuracy": 0.15153488963842393,
|
|
"num_tokens": 5976043.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.740905237197876,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.7368,
|
|
"mean_token_accuracy": 0.1438068449497223,
|
|
"num_tokens": 5988146.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.690333318710327,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.14996936321258544,
|
|
"num_tokens": 6000542.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.7154529094696045,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.7366,
|
|
"mean_token_accuracy": 0.1433037906885147,
|
|
"num_tokens": 6013574.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.607508945465088,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.6318,
|
|
"mean_token_accuracy": 0.14444206804037094,
|
|
"num_tokens": 6025391.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.780825185775757,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.7493,
|
|
"mean_token_accuracy": 0.1451184406876564,
|
|
"num_tokens": 6036595.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.7437080383300785,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.8453,
|
|
"mean_token_accuracy": 0.13703761547803878,
|
|
"num_tokens": 6048852.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.73164849281311,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.15447451919317245,
|
|
"num_tokens": 6061694.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.718098258972168,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.7536,
|
|
"mean_token_accuracy": 0.14859242737293243,
|
|
"num_tokens": 6074244.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.787304067611695,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.7248,
|
|
"mean_token_accuracy": 0.14635652750730516,
|
|
"num_tokens": 6085550.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.705214929580689,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.774,
|
|
"mean_token_accuracy": 0.14355605840682983,
|
|
"num_tokens": 6096749.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.769416809082031,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.6649,
|
|
"mean_token_accuracy": 0.1461700275540352,
|
|
"num_tokens": 6109490.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.711434459686279,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.13653022199869155,
|
|
"num_tokens": 6122656.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.859713554382324,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.724,
|
|
"mean_token_accuracy": 0.1444801300764084,
|
|
"num_tokens": 6135461.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.648364114761352,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.7647,
|
|
"mean_token_accuracy": 0.14585992693901062,
|
|
"num_tokens": 6147698.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.834606456756592,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.7349,
|
|
"mean_token_accuracy": 0.1469629168510437,
|
|
"num_tokens": 6160456.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.665376234054565,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.7258,
|
|
"mean_token_accuracy": 0.14537576138973235,
|
|
"num_tokens": 6173606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.720003461837768,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.7506,
|
|
"mean_token_accuracy": 0.14402114003896713,
|
|
"num_tokens": 6185355.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.787649822235108,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.7692,
|
|
"mean_token_accuracy": 0.14147617369890214,
|
|
"num_tokens": 6198154.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.731502485275269,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.6544,
|
|
"mean_token_accuracy": 0.1494407206773758,
|
|
"num_tokens": 6209901.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.673964262008667,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.7203,
|
|
"mean_token_accuracy": 0.14480748698115348,
|
|
"num_tokens": 6222052.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.75030665397644,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.7232,
|
|
"mean_token_accuracy": 0.15031242072582246,
|
|
"num_tokens": 6235112.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.732296323776245,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7491,
|
|
"mean_token_accuracy": 0.14172388911247252,
|
|
"num_tokens": 6248225.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.760669803619384,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.7068,
|
|
"mean_token_accuracy": 0.14936083406209946,
|
|
"num_tokens": 6259518.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.649824762344361,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.13711516559123993,
|
|
"num_tokens": 6271832.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.7701342582702635,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.14304690212011337,
|
|
"num_tokens": 6284328.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.720312309265137,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6935,
|
|
"mean_token_accuracy": 0.14403096809983254,
|
|
"num_tokens": 6296100.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.617523860931397,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6476,
|
|
"mean_token_accuracy": 0.15421121418476105,
|
|
"num_tokens": 6308262.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.748142957687378,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.13827703297138214,
|
|
"num_tokens": 6319953.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.702780914306641,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.6568,
|
|
"mean_token_accuracy": 0.14931394010782242,
|
|
"num_tokens": 6332953.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.671044635772705,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.7213,
|
|
"mean_token_accuracy": 0.1474708914756775,
|
|
"num_tokens": 6345692.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.7257524013519285,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.696,
|
|
"mean_token_accuracy": 0.1451795779168606,
|
|
"num_tokens": 6358058.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.783554315567017,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.14846932888031006,
|
|
"num_tokens": 6370469.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.787226629257202,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.7985,
|
|
"mean_token_accuracy": 0.1353658489882946,
|
|
"num_tokens": 6384333.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.7711738586425785,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.7377,
|
|
"mean_token_accuracy": 0.14200848788022996,
|
|
"num_tokens": 6397688.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.706867218017578,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.699,
|
|
"mean_token_accuracy": 0.14663641303777694,
|
|
"num_tokens": 6410188.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.719365406036377,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.7169,
|
|
"mean_token_accuracy": 0.14374764263629913,
|
|
"num_tokens": 6423313.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.764793729782104,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.7386,
|
|
"mean_token_accuracy": 0.1467905879020691,
|
|
"num_tokens": 6435853.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.598630714416504,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.6725,
|
|
"mean_token_accuracy": 0.14465839564800262,
|
|
"num_tokens": 6448659.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.732291269302368,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.7292,
|
|
"mean_token_accuracy": 0.14818664789199829,
|
|
"num_tokens": 6460534.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.716020393371582,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6971,
|
|
"mean_token_accuracy": 0.14435341879725455,
|
|
"num_tokens": 6472368.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.693843650817871,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.14448096752166747,
|
|
"num_tokens": 6485430.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.710673141479492,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.6891,
|
|
"mean_token_accuracy": 0.1485920026898384,
|
|
"num_tokens": 6497303.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.699700403213501,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.7567,
|
|
"mean_token_accuracy": 0.15133860260248183,
|
|
"num_tokens": 6510154.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.790226650238037,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.7413,
|
|
"mean_token_accuracy": 0.143829607963562,
|
|
"num_tokens": 6523091.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.75448055267334,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.6531,
|
|
"mean_token_accuracy": 0.14935905635356903,
|
|
"num_tokens": 6536043.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.624383497238159,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.14822530150413513,
|
|
"num_tokens": 6548227.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.759153127670288,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.7117,
|
|
"mean_token_accuracy": 0.14047631323337556,
|
|
"num_tokens": 6560204.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.684758043289184,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.150347737967968,
|
|
"num_tokens": 6573235.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.650673818588257,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.14433368742465974,
|
|
"num_tokens": 6585118.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.750360155105591,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.14643110930919648,
|
|
"num_tokens": 6596690.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.660681819915771,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.15728502422571183,
|
|
"num_tokens": 6609076.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.662906169891357,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.7326,
|
|
"mean_token_accuracy": 0.14466301277279853,
|
|
"num_tokens": 6621352.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.752713441848755,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.1454766198992729,
|
|
"num_tokens": 6633924.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.702887296676636,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.7607,
|
|
"mean_token_accuracy": 0.14415173679590226,
|
|
"num_tokens": 6646490.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.83890929222107,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.14090896472334863,
|
|
"num_tokens": 6660171.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.609751653671265,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.7572,
|
|
"mean_token_accuracy": 0.14278358295559884,
|
|
"num_tokens": 6673505.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.783524751663208,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.7358,
|
|
"mean_token_accuracy": 0.14450631141662598,
|
|
"num_tokens": 6685798.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.639528703689575,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.5888,
|
|
"mean_token_accuracy": 0.14924851357936858,
|
|
"num_tokens": 6699254.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.685869789123535,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.6506,
|
|
"mean_token_accuracy": 0.14859471917152406,
|
|
"num_tokens": 6711088.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.700608539581299,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.7159,
|
|
"mean_token_accuracy": 0.14112428277730943,
|
|
"num_tokens": 6723373.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.637734365463257,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.14265928864479066,
|
|
"num_tokens": 6737984.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.751663398742676,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.6699,
|
|
"mean_token_accuracy": 0.14623800665140152,
|
|
"num_tokens": 6751283.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.637785387039185,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.6511,
|
|
"mean_token_accuracy": 0.1425285041332245,
|
|
"num_tokens": 6765012.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.657239103317261,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.6944,
|
|
"mean_token_accuracy": 0.14595674276351928,
|
|
"num_tokens": 6777708.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.682321071624756,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.6153,
|
|
"mean_token_accuracy": 0.15794552862644196,
|
|
"num_tokens": 6791325.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.583492231369019,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.7509,
|
|
"mean_token_accuracy": 0.1372663803398609,
|
|
"num_tokens": 6805659.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.76855502128601,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.6591,
|
|
"mean_token_accuracy": 0.1441938564181328,
|
|
"num_tokens": 6818110.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.640047025680542,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.6691,
|
|
"mean_token_accuracy": 0.14442232996225357,
|
|
"num_tokens": 6830959.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.750000095367431,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.7234,
|
|
"mean_token_accuracy": 0.14586163461208343,
|
|
"num_tokens": 6843318.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.675041437149048,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.14719301089644432,
|
|
"num_tokens": 6855154.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.5928421974182125,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.685,
|
|
"mean_token_accuracy": 0.14665439277887343,
|
|
"num_tokens": 6867428.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.754723072052002,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.671,
|
|
"mean_token_accuracy": 0.15316719859838485,
|
|
"num_tokens": 6879989.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.6928040981292725,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.14096458703279496,
|
|
"num_tokens": 6893179.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.727335596084595,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.6782,
|
|
"mean_token_accuracy": 0.14420599341392518,
|
|
"num_tokens": 6905647.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.610552978515625,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.6364,
|
|
"mean_token_accuracy": 0.15449649840593338,
|
|
"num_tokens": 6917361.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.71636061668396,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.1424078017473221,
|
|
"num_tokens": 6929515.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.707604217529297,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6391,
|
|
"mean_token_accuracy": 0.14832933098077775,
|
|
"num_tokens": 6942265.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.584933423995972,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.687,
|
|
"mean_token_accuracy": 0.14602783024311067,
|
|
"num_tokens": 6955151.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.765100526809692,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.6589,
|
|
"mean_token_accuracy": 0.14955082535743713,
|
|
"num_tokens": 6968378.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.605684900283814,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.1471999056637287,
|
|
"num_tokens": 6980083.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.687409925460815,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.14363027215003968,
|
|
"num_tokens": 6992981.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.824726104736328,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.14623156040906907,
|
|
"num_tokens": 7006115.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.589347887039184,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.6416,
|
|
"mean_token_accuracy": 0.15562028288841248,
|
|
"num_tokens": 7019176.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.55873851776123,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.5673,
|
|
"mean_token_accuracy": 0.15908343940973282,
|
|
"num_tokens": 7031214.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.615464973449707,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.6403,
|
|
"mean_token_accuracy": 0.14976823478937148,
|
|
"num_tokens": 7044702.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.705451583862304,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.6522,
|
|
"mean_token_accuracy": 0.14741754829883574,
|
|
"num_tokens": 7056489.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.621556758880615,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6752,
|
|
"mean_token_accuracy": 0.14415591955184937,
|
|
"num_tokens": 7068972.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.72447772026062,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.6197,
|
|
"mean_token_accuracy": 0.14744585007429123,
|
|
"num_tokens": 7080894.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.598182201385498,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.6696,
|
|
"mean_token_accuracy": 0.14264965504407884,
|
|
"num_tokens": 7094427.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.590505361557007,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.6003,
|
|
"mean_token_accuracy": 0.15626100897789003,
|
|
"num_tokens": 7105710.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.777636337280273,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.1449590690433979,
|
|
"num_tokens": 7119042.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.564963388442993,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.6343,
|
|
"mean_token_accuracy": 0.14468320608139038,
|
|
"num_tokens": 7132146.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.669665241241455,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.6033,
|
|
"mean_token_accuracy": 0.14561504125595093,
|
|
"num_tokens": 7144805.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.571587038040161,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.5762,
|
|
"mean_token_accuracy": 0.15571997463703155,
|
|
"num_tokens": 7156906.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.654489612579345,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.567,
|
|
"mean_token_accuracy": 0.14885426163673401,
|
|
"num_tokens": 7169451.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.650216817855835,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.7134,
|
|
"mean_token_accuracy": 0.14018807634711267,
|
|
"num_tokens": 7183211.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.727432727813721,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.14724580198526382,
|
|
"num_tokens": 7196062.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.719376134872436,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.7601,
|
|
"mean_token_accuracy": 0.14483619555830957,
|
|
"num_tokens": 7208079.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.697180366516113,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.6972,
|
|
"mean_token_accuracy": 0.14615591317415239,
|
|
"num_tokens": 7221537.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.6564757347106935,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.6652,
|
|
"mean_token_accuracy": 0.14372813254594802,
|
|
"num_tokens": 7234472.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.643028306961059,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.6194,
|
|
"mean_token_accuracy": 0.15096134543418885,
|
|
"num_tokens": 7247818.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.6859259605407715,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.7006,
|
|
"mean_token_accuracy": 0.14851104468107224,
|
|
"num_tokens": 7261351.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.607791996002197,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.568,
|
|
"mean_token_accuracy": 0.1521388918161392,
|
|
"num_tokens": 7274310.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.573197507858277,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.6096,
|
|
"mean_token_accuracy": 0.1469192236661911,
|
|
"num_tokens": 7286560.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.756811904907226,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.6835,
|
|
"mean_token_accuracy": 0.14362717866897584,
|
|
"num_tokens": 7300337.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.617220211029053,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.6485,
|
|
"mean_token_accuracy": 0.1463576778769493,
|
|
"num_tokens": 7313436.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.632095098495483,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.5149,
|
|
"mean_token_accuracy": 0.16170531660318374,
|
|
"num_tokens": 7325766.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.578122663497925,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.614,
|
|
"mean_token_accuracy": 0.1468640923500061,
|
|
"num_tokens": 7337904.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.575803184509278,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.5992,
|
|
"mean_token_accuracy": 0.14721653759479522,
|
|
"num_tokens": 7350448.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.711412048339843,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.14552380070090293,
|
|
"num_tokens": 7363859.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.663523769378662,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.6548,
|
|
"mean_token_accuracy": 0.14727362394332885,
|
|
"num_tokens": 7376963.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.665795135498047,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.6806,
|
|
"mean_token_accuracy": 0.14258197993040084,
|
|
"num_tokens": 7390370.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.65341739654541,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.6101,
|
|
"mean_token_accuracy": 0.14991432875394822,
|
|
"num_tokens": 7402851.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.5872947692871096,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.14421918392181396,
|
|
"num_tokens": 7415428.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.719788837432861,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.6325,
|
|
"mean_token_accuracy": 0.1465821772813797,
|
|
"num_tokens": 7428420.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.657585000991821,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.689,
|
|
"mean_token_accuracy": 0.14700795263051986,
|
|
"num_tokens": 7439626.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.661691093444825,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.14639809280633925,
|
|
"num_tokens": 7452797.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.65012903213501,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.6162,
|
|
"mean_token_accuracy": 0.15301314145326614,
|
|
"num_tokens": 7464311.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.575049352645874,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.6131,
|
|
"mean_token_accuracy": 0.14517637491226196,
|
|
"num_tokens": 7475706.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.673529767990113,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.7028,
|
|
"mean_token_accuracy": 0.1451819732785225,
|
|
"num_tokens": 7489077.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.704615211486816,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.651,
|
|
"mean_token_accuracy": 0.1511762797832489,
|
|
"num_tokens": 7501598.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.562963962554932,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.1568878024816513,
|
|
"num_tokens": 7514776.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.517637109756469,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.6212,
|
|
"mean_token_accuracy": 0.14930416494607926,
|
|
"num_tokens": 7527795.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.645235443115235,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.5076,
|
|
"mean_token_accuracy": 0.15968223363161088,
|
|
"num_tokens": 7541392.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.542176866531372,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.14863153249025346,
|
|
"num_tokens": 7554369.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.647294902801514,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.6432,
|
|
"mean_token_accuracy": 0.1486467257142067,
|
|
"num_tokens": 7567528.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.603502982646388,
|
|
"eval_loss": 6.686180591583252,
|
|
"eval_mean_token_accuracy": 0.14944647604010136,
|
|
"eval_num_tokens": 7567528.0,
|
|
"eval_runtime": 22.9724,
|
|
"eval_samples_per_second": 1224.776,
|
|
"eval_steps_per_second": 153.097,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.667821407318115,
|
|
"epoch": 0.346797461050202,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993924284699165,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.15041287392377853,
|
|
"num_tokens": 7579146.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.5950047969818115,
|
|
"epoch": 0.3473744950952106,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993893942674127,
|
|
"loss": 6.6828,
|
|
"mean_token_accuracy": 0.14685314893722534,
|
|
"num_tokens": 7591902.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.754814577102661,
|
|
"epoch": 0.34795152914021926,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499386352517683,
|
|
"loss": 6.6803,
|
|
"mean_token_accuracy": 0.15172169506549835,
|
|
"num_tokens": 7605565.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.726373863220215,
|
|
"epoch": 0.3485285631852279,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049938330322083,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.15227940529584885,
|
|
"num_tokens": 7618380.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.556258058547973,
|
|
"epoch": 0.3491055972302366,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993802463769558,
|
|
"loss": 6.6459,
|
|
"mean_token_accuracy": 0.14672804325819017,
|
|
"num_tokens": 7632092.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.67885012626648,
|
|
"epoch": 0.34968263127524524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993771819861636,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.14378119856119156,
|
|
"num_tokens": 7644185.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.649367904663086,
|
|
"epoch": 0.3502596653202539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993741100485564,
|
|
"loss": 6.5704,
|
|
"mean_token_accuracy": 0.14890087842941285,
|
|
"num_tokens": 7656635.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.630291414260864,
|
|
"epoch": 0.35083669936526257,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993710305642374,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.14622372686862944,
|
|
"num_tokens": 7669643.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.656918716430664,
|
|
"epoch": 0.3514137334102712,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993679435333102,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.13970368951559067,
|
|
"num_tokens": 7682489.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.555567073822021,
|
|
"epoch": 0.35199076745527985,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993648489558788,
|
|
"loss": 6.5845,
|
|
"mean_token_accuracy": 0.1465017504990101,
|
|
"num_tokens": 7696670.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.7070152282714846,
|
|
"epoch": 0.3525678015002885,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993617468320471,
|
|
"loss": 6.6109,
|
|
"mean_token_accuracy": 0.15563664734363555,
|
|
"num_tokens": 7709054.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.525317859649658,
|
|
"epoch": 0.3531448355452972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993586371619193,
|
|
"loss": 6.6004,
|
|
"mean_token_accuracy": 0.14743918776512147,
|
|
"num_tokens": 7721710.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.660245132446289,
|
|
"epoch": 0.3537218695903058,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993555199456004,
|
|
"loss": 6.6536,
|
|
"mean_token_accuracy": 0.14922718554735184,
|
|
"num_tokens": 7733689.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.594697332382202,
|
|
"epoch": 0.35429890363531447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993523951831949,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.15407218933105468,
|
|
"num_tokens": 7745735.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.747467994689941,
|
|
"epoch": 0.35487593768032316,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993492628748081,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.14074160531163216,
|
|
"num_tokens": 7757352.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.607062578201294,
|
|
"epoch": 0.3554529717253318,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993461230205453,
|
|
"loss": 6.5873,
|
|
"mean_token_accuracy": 0.1461851865053177,
|
|
"num_tokens": 7768363.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.6232137203216555,
|
|
"epoch": 0.35603000577034044,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993429756205121,
|
|
"loss": 6.7003,
|
|
"mean_token_accuracy": 0.14090533256530763,
|
|
"num_tokens": 7781133.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.777905750274658,
|
|
"epoch": 0.3566070398153491,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993398206748142,
|
|
"loss": 6.6873,
|
|
"mean_token_accuracy": 0.14060682207345962,
|
|
"num_tokens": 7794445.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.557980489730835,
|
|
"epoch": 0.3571840738603578,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993366581835581,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.15084142833948136,
|
|
"num_tokens": 7807601.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.540106964111328,
|
|
"epoch": 0.3577611079053664,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993334881468498,
|
|
"loss": 6.5576,
|
|
"mean_token_accuracy": 0.15417141318321229,
|
|
"num_tokens": 7819821.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.614301109313965,
|
|
"epoch": 0.35833814195037506,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993303105647961,
|
|
"loss": 6.5747,
|
|
"mean_token_accuracy": 0.14614431858062743,
|
|
"num_tokens": 7832214.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.612269878387451,
|
|
"epoch": 0.35891517599538375,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993271254375038,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.15465223789215088,
|
|
"num_tokens": 7844566.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.661264038085937,
|
|
"epoch": 0.3594922100403924,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049932393276508,
|
|
"loss": 6.6016,
|
|
"mean_token_accuracy": 0.15167122855782508,
|
|
"num_tokens": 7857965.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.588106966018676,
|
|
"epoch": 0.36006924408540103,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004993207325476323,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.1525164559483528,
|
|
"num_tokens": 7870902.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.747092199325562,
|
|
"epoch": 0.36064627813040967,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993175247852681,
|
|
"loss": 6.6855,
|
|
"mean_token_accuracy": 0.13674851804971694,
|
|
"num_tokens": 7883694.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.653594636917115,
|
|
"epoch": 0.36122331217541837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993143094780954,
|
|
"loss": 6.5716,
|
|
"mean_token_accuracy": 0.15035519748926163,
|
|
"num_tokens": 7896693.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.549767684936524,
|
|
"epoch": 0.361800346220427,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993110866262224,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.14896219372749328,
|
|
"num_tokens": 7910010.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.704126453399658,
|
|
"epoch": 0.36237738026543564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993078562297573,
|
|
"loss": 6.6702,
|
|
"mean_token_accuracy": 0.136037989705801,
|
|
"num_tokens": 7922026.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.580215311050415,
|
|
"epoch": 0.36295441431044434,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993046182888089,
|
|
"loss": 6.6542,
|
|
"mean_token_accuracy": 0.1394454210996628,
|
|
"num_tokens": 7934633.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.594920349121094,
|
|
"epoch": 0.363531448355453,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004993013728034861,
|
|
"loss": 6.5489,
|
|
"mean_token_accuracy": 0.15306085348129272,
|
|
"num_tokens": 7947189.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.6680103778839115,
|
|
"epoch": 0.3641084824004616,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000499298119773898,
|
|
"loss": 6.6236,
|
|
"mean_token_accuracy": 0.14880157262086868,
|
|
"num_tokens": 7961283.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.523037147521973,
|
|
"epoch": 0.36468551644547026,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992948592001541,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.15099794641137124,
|
|
"num_tokens": 7974589.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.691275119781494,
|
|
"epoch": 0.36526255049047895,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499291591082364,
|
|
"loss": 6.6758,
|
|
"mean_token_accuracy": 0.14682248681783677,
|
|
"num_tokens": 7987148.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.697682428359985,
|
|
"epoch": 0.3658395845354876,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992883154206377,
|
|
"loss": 6.6664,
|
|
"mean_token_accuracy": 0.1428602494299412,
|
|
"num_tokens": 8000679.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.5670891284942625,
|
|
"epoch": 0.36641661858049623,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992850322150853,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.15191134065389633,
|
|
"num_tokens": 8014011.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.69585018157959,
|
|
"epoch": 0.36699365262550493,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992817414658172,
|
|
"loss": 6.5802,
|
|
"mean_token_accuracy": 0.14718159288167953,
|
|
"num_tokens": 8026022.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.63649697303772,
|
|
"epoch": 0.36757068667051357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992784431729442,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.14684277549386024,
|
|
"num_tokens": 8040123.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.675275611877441,
|
|
"epoch": 0.3681477207155222,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992751373365771,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.15477651953697205,
|
|
"num_tokens": 8053320.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.5776519775390625,
|
|
"epoch": 0.36872475476053085,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992718239568273,
|
|
"loss": 6.5876,
|
|
"mean_token_accuracy": 0.1540097713470459,
|
|
"num_tokens": 8066682.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.631053400039673,
|
|
"epoch": 0.36930178880553954,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499268503033806,
|
|
"loss": 6.5963,
|
|
"mean_token_accuracy": 0.15034545511007308,
|
|
"num_tokens": 8078887.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.641768169403076,
|
|
"epoch": 0.3698788228505482,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992651745676249,
|
|
"loss": 6.587,
|
|
"mean_token_accuracy": 0.14526487439870833,
|
|
"num_tokens": 8090801.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.607954406738282,
|
|
"epoch": 0.3704558568955568,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992618385583962,
|
|
"loss": 6.6613,
|
|
"mean_token_accuracy": 0.14384082555770875,
|
|
"num_tokens": 8103387.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.5886212348937985,
|
|
"epoch": 0.3710328909405655,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992584950062319,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.1546319343149662,
|
|
"num_tokens": 8115356.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.674334526062012,
|
|
"epoch": 0.37160992498557416,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992551439112446,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.14844774454832077,
|
|
"num_tokens": 8129141.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.7329993724823,
|
|
"epoch": 0.3721869590305828,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992517852735469,
|
|
"loss": 6.659,
|
|
"mean_token_accuracy": 0.15107582956552507,
|
|
"num_tokens": 8142453.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.574329853057861,
|
|
"epoch": 0.37276399307559144,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992484190932517,
|
|
"loss": 6.6139,
|
|
"mean_token_accuracy": 0.14692633971571922,
|
|
"num_tokens": 8154361.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.7408263206481935,
|
|
"epoch": 0.37334102712060013,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992450453704723,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.14180598258972169,
|
|
"num_tokens": 8168354.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.6767510890960695,
|
|
"epoch": 0.3739180611656088,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992416641053223,
|
|
"loss": 6.6188,
|
|
"mean_token_accuracy": 0.15147449523210527,
|
|
"num_tokens": 8180700.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.61651201248169,
|
|
"epoch": 0.3744950952106174,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992382752979153,
|
|
"loss": 6.613,
|
|
"mean_token_accuracy": 0.14319541156291962,
|
|
"num_tokens": 8193987.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.638578748703003,
|
|
"epoch": 0.3750721292556261,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992348789483651,
|
|
"loss": 6.7071,
|
|
"mean_token_accuracy": 0.14582299664616585,
|
|
"num_tokens": 8207150.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.710038661956787,
|
|
"epoch": 0.37564916330063475,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992314750567864,
|
|
"loss": 6.6528,
|
|
"mean_token_accuracy": 0.14282948076725005,
|
|
"num_tokens": 8221050.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.617986631393433,
|
|
"epoch": 0.3762261973456434,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992280636232933,
|
|
"loss": 6.5845,
|
|
"mean_token_accuracy": 0.14726462215185165,
|
|
"num_tokens": 8233641.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.666138219833374,
|
|
"epoch": 0.376803231390652,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992246446480007,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.15233627408742906,
|
|
"num_tokens": 8246717.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.5698161125183105,
|
|
"epoch": 0.3773802654356607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992212181310235,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.14525358229875565,
|
|
"num_tokens": 8258549.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.676126480102539,
|
|
"epoch": 0.37795729948066936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499217784072477,
|
|
"loss": 6.6169,
|
|
"mean_token_accuracy": 0.15047752410173415,
|
|
"num_tokens": 8271580.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.677121210098266,
|
|
"epoch": 0.378534333525678,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992143424724768,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.15735053569078444,
|
|
"num_tokens": 8283866.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.517127513885498,
|
|
"epoch": 0.3791113675706867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992108933311385,
|
|
"loss": 6.5855,
|
|
"mean_token_accuracy": 0.1442652702331543,
|
|
"num_tokens": 8296141.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.704352283477784,
|
|
"epoch": 0.37968840161569534,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992074366485782,
|
|
"loss": 6.5679,
|
|
"mean_token_accuracy": 0.14811346232891082,
|
|
"num_tokens": 8309028.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.6836034774780275,
|
|
"epoch": 0.380265435660704,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499203972424912,
|
|
"loss": 6.557,
|
|
"mean_token_accuracy": 0.14885664880275726,
|
|
"num_tokens": 8321268.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.48089861869812,
|
|
"epoch": 0.3808424697057126,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992005006602567,
|
|
"loss": 6.5689,
|
|
"mean_token_accuracy": 0.15438662618398666,
|
|
"num_tokens": 8333518.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.604173278808593,
|
|
"epoch": 0.3814195037507213,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991970213547289,
|
|
"loss": 6.5919,
|
|
"mean_token_accuracy": 0.15506176948547362,
|
|
"num_tokens": 8345639.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.470817232131958,
|
|
"epoch": 0.38199653779572995,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991935345084457,
|
|
"loss": 6.4928,
|
|
"mean_token_accuracy": 0.15436709225177764,
|
|
"num_tokens": 8358136.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.663488578796387,
|
|
"epoch": 0.3825735718407386,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991900401215243,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.13878891617059708,
|
|
"num_tokens": 8370480.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.650869083404541,
|
|
"epoch": 0.3831506058857473,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991865381940822,
|
|
"loss": 6.565,
|
|
"mean_token_accuracy": 0.1526940122246742,
|
|
"num_tokens": 8382894.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.598002243041992,
|
|
"epoch": 0.3837276399307559,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991830287262374,
|
|
"loss": 6.6647,
|
|
"mean_token_accuracy": 0.14782873764634133,
|
|
"num_tokens": 8395864.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.727650737762451,
|
|
"epoch": 0.38430467397576457,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991795117181077,
|
|
"loss": 6.6743,
|
|
"mean_token_accuracy": 0.14051376208662986,
|
|
"num_tokens": 8408242.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.642122983932495,
|
|
"epoch": 0.3848817080207732,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991759871698113,
|
|
"loss": 6.557,
|
|
"mean_token_accuracy": 0.1540223702788353,
|
|
"num_tokens": 8420677.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.50219759941101,
|
|
"epoch": 0.3854587420657819,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991724550814671,
|
|
"loss": 6.5798,
|
|
"mean_token_accuracy": 0.15331998690962792,
|
|
"num_tokens": 8434505.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.6981383800506595,
|
|
"epoch": 0.38603577611079054,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991689154531937,
|
|
"loss": 6.6211,
|
|
"mean_token_accuracy": 0.1466370016336441,
|
|
"num_tokens": 8447393.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.633738088607788,
|
|
"epoch": 0.3866128101557992,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991653682851102,
|
|
"loss": 6.515,
|
|
"mean_token_accuracy": 0.1519007369875908,
|
|
"num_tokens": 8459659.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.551579332351684,
|
|
"epoch": 0.3871898442008078,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499161813577336,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.1430330380797386,
|
|
"num_tokens": 8473783.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.563436841964721,
|
|
"epoch": 0.3877668782458165,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991582513299903,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.14940204918384553,
|
|
"num_tokens": 8486532.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.553758382797241,
|
|
"epoch": 0.38834391229082516,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991546815431932,
|
|
"loss": 6.6361,
|
|
"mean_token_accuracy": 0.14532858952879907,
|
|
"num_tokens": 8499133.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.683175468444825,
|
|
"epoch": 0.3889209463358338,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499151104217065,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.1406083531677723,
|
|
"num_tokens": 8513391.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.639142322540283,
|
|
"epoch": 0.3894979803808425,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991475193517254,
|
|
"loss": 6.59,
|
|
"mean_token_accuracy": 0.14977881610393523,
|
|
"num_tokens": 8527191.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.645763540267945,
|
|
"epoch": 0.39007501442585113,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991439269472956,
|
|
"loss": 6.646,
|
|
"mean_token_accuracy": 0.1420146033167839,
|
|
"num_tokens": 8541328.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.622199296951294,
|
|
"epoch": 0.39065204847085977,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991403270038961,
|
|
"loss": 6.5389,
|
|
"mean_token_accuracy": 0.14269101321697236,
|
|
"num_tokens": 8553381.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.570790338516235,
|
|
"epoch": 0.3912290825158684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499136719521648,
|
|
"loss": 6.578,
|
|
"mean_token_accuracy": 0.1472961574792862,
|
|
"num_tokens": 8565149.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.591652965545654,
|
|
"epoch": 0.3918061165608771,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004991331045006726,
|
|
"loss": 6.5872,
|
|
"mean_token_accuracy": 0.1539955124258995,
|
|
"num_tokens": 8576767.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.676447868347168,
|
|
"epoch": 0.39238315060588574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991294819410916,
|
|
"loss": 6.6427,
|
|
"mean_token_accuracy": 0.14463468939065932,
|
|
"num_tokens": 8589948.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.538165950775147,
|
|
"epoch": 0.3929601846508944,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004991258518430268,
|
|
"loss": 6.4792,
|
|
"mean_token_accuracy": 0.15250100940465927,
|
|
"num_tokens": 8602233.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.595015525817871,
|
|
"epoch": 0.3935372186959031,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004991222142066003,
|
|
"loss": 6.5569,
|
|
"mean_token_accuracy": 0.14572182223200797,
|
|
"num_tokens": 8614938.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.681994009017944,
|
|
"epoch": 0.3941142527409117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991185690319345,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.1508318766951561,
|
|
"num_tokens": 8628203.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.562502431869507,
|
|
"epoch": 0.39469128678592036,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499114916319152,
|
|
"loss": 6.5623,
|
|
"mean_token_accuracy": 0.15397722721099855,
|
|
"num_tokens": 8640959.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.612614393234253,
|
|
"epoch": 0.395268320830929,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991112560683755,
|
|
"loss": 6.5933,
|
|
"mean_token_accuracy": 0.1472369372844696,
|
|
"num_tokens": 8656995.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.612496614456177,
|
|
"epoch": 0.3958453548759377,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991075882797283,
|
|
"loss": 6.5999,
|
|
"mean_token_accuracy": 0.14946889877319336,
|
|
"num_tokens": 8671476.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.614114093780517,
|
|
"epoch": 0.39642238892094633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991039129533337,
|
|
"loss": 6.6212,
|
|
"mean_token_accuracy": 0.1447447918355465,
|
|
"num_tokens": 8683667.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.663765811920166,
|
|
"epoch": 0.396999422965955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991002300893152,
|
|
"loss": 6.6206,
|
|
"mean_token_accuracy": 0.1453992933034897,
|
|
"num_tokens": 8696564.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.656809711456299,
|
|
"epoch": 0.39757645701096367,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990965396877969,
|
|
"loss": 6.5592,
|
|
"mean_token_accuracy": 0.145858995616436,
|
|
"num_tokens": 8708512.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.593225526809692,
|
|
"epoch": 0.3981534910559723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990928417489027,
|
|
"loss": 6.4353,
|
|
"mean_token_accuracy": 0.16177331209182738,
|
|
"num_tokens": 8721015.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.55296311378479,
|
|
"epoch": 0.39873052510098095,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990891362727572,
|
|
"loss": 6.5552,
|
|
"mean_token_accuracy": 0.1485207624733448,
|
|
"num_tokens": 8732538.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.595230627059936,
|
|
"epoch": 0.3993075591459896,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990854232594848,
|
|
"loss": 6.6106,
|
|
"mean_token_accuracy": 0.141809394210577,
|
|
"num_tokens": 8745093.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.650364685058594,
|
|
"epoch": 0.3998845931909983,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990817027092106,
|
|
"loss": 6.566,
|
|
"mean_token_accuracy": 0.1506790906190872,
|
|
"num_tokens": 8757441.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.536897468566894,
|
|
"epoch": 0.4004616272360069,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990779746220595,
|
|
"loss": 6.5875,
|
|
"mean_token_accuracy": 0.15096076875925063,
|
|
"num_tokens": 8770307.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.628611469268799,
|
|
"epoch": 0.40103866128101556,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990742389981572,
|
|
"loss": 6.5985,
|
|
"mean_token_accuracy": 0.15109818130731584,
|
|
"num_tokens": 8782575.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.702537965774536,
|
|
"epoch": 0.40161569532602426,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499070495837629,
|
|
"loss": 6.645,
|
|
"mean_token_accuracy": 0.14216657131910324,
|
|
"num_tokens": 8794962.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.64976396560669,
|
|
"epoch": 0.4021927293710329,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990667451406012,
|
|
"loss": 6.6286,
|
|
"mean_token_accuracy": 0.1465877667069435,
|
|
"num_tokens": 8807434.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.664065790176392,
|
|
"epoch": 0.40276976341604154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990629869071995,
|
|
"loss": 6.6134,
|
|
"mean_token_accuracy": 0.14227251559495926,
|
|
"num_tokens": 8820748.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.563335418701172,
|
|
"epoch": 0.4033467974610502,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990592211375506,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.15409625843167304,
|
|
"num_tokens": 8833428.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.604947519302368,
|
|
"epoch": 0.4039238315060589,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990554478317811,
|
|
"loss": 6.5739,
|
|
"mean_token_accuracy": 0.14540679156780242,
|
|
"num_tokens": 8845892.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.532162523269653,
|
|
"epoch": 0.4045008655510675,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990516669900179,
|
|
"loss": 6.5188,
|
|
"mean_token_accuracy": 0.15271870493888856,
|
|
"num_tokens": 8857508.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.578783464431763,
|
|
"epoch": 0.40507789959607615,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990478786123882,
|
|
"loss": 6.5523,
|
|
"mean_token_accuracy": 0.14996312260627748,
|
|
"num_tokens": 8868730.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.572446632385254,
|
|
"epoch": 0.40565493364108485,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990440826990193,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.1447156012058258,
|
|
"num_tokens": 8882687.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.566001081466675,
|
|
"epoch": 0.4062319676860935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990402792500392,
|
|
"loss": 6.5601,
|
|
"mean_token_accuracy": 0.15300334095954896,
|
|
"num_tokens": 8894723.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.5859610080719,
|
|
"epoch": 0.4068090017311021,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990364682655754,
|
|
"loss": 6.5359,
|
|
"mean_token_accuracy": 0.15275930017232894,
|
|
"num_tokens": 8906373.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.613490200042724,
|
|
"epoch": 0.40738603577611077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990326497457564,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.1478450857102871,
|
|
"num_tokens": 8918681.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.597956323623658,
|
|
"epoch": 0.40796306982111946,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990288236907104,
|
|
"loss": 6.5754,
|
|
"mean_token_accuracy": 0.1443031385540962,
|
|
"num_tokens": 8930232.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.596869373321534,
|
|
"epoch": 0.4085401038661281,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990249901005661,
|
|
"loss": 6.4973,
|
|
"mean_token_accuracy": 0.1485630303621292,
|
|
"num_tokens": 8942264.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.6454973220825195,
|
|
"epoch": 0.40911713791113674,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004990211489754527,
|
|
"loss": 6.6616,
|
|
"mean_token_accuracy": 0.1454596146941185,
|
|
"num_tokens": 8955679.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.612455701828003,
|
|
"epoch": 0.40969417195614544,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990173003154993,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.15279372185468673,
|
|
"num_tokens": 8968421.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.504389810562134,
|
|
"epoch": 0.4102712060011541,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990134441208351,
|
|
"loss": 6.5535,
|
|
"mean_token_accuracy": 0.1467677101492882,
|
|
"num_tokens": 8981063.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.6303013324737545,
|
|
"epoch": 0.4108482400461627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990095803915901,
|
|
"loss": 6.5088,
|
|
"mean_token_accuracy": 0.1581997647881508,
|
|
"num_tokens": 8993740.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.543606472015381,
|
|
"epoch": 0.41142527409117136,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990057091278942,
|
|
"loss": 6.541,
|
|
"mean_token_accuracy": 0.14845392405986785,
|
|
"num_tokens": 9007135.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.554729413986206,
|
|
"epoch": 0.41200230813618005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990018303298773,
|
|
"loss": 6.5508,
|
|
"mean_token_accuracy": 0.15105100274085997,
|
|
"num_tokens": 9021596.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.514636564254761,
|
|
"epoch": 0.4125793421811887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989979439976703,
|
|
"loss": 6.4981,
|
|
"mean_token_accuracy": 0.1580370619893074,
|
|
"num_tokens": 9033523.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.483329582214355,
|
|
"epoch": 0.41315637622619733,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989940501314037,
|
|
"loss": 6.4665,
|
|
"mean_token_accuracy": 0.15388141348958015,
|
|
"num_tokens": 9045690.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.582033348083496,
|
|
"epoch": 0.413733410271206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989901487312084,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.15002324283123017,
|
|
"num_tokens": 9057672.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.550716686248779,
|
|
"epoch": 0.41431044431621467,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989862397972157,
|
|
"loss": 6.5991,
|
|
"mean_token_accuracy": 0.14664729684591293,
|
|
"num_tokens": 9070004.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.661472129821777,
|
|
"epoch": 0.4148874783612233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989823233295572,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.15296779274940492,
|
|
"num_tokens": 9082453.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.531029796600341,
|
|
"epoch": 0.41546451240623195,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989783993283644,
|
|
"loss": 6.5736,
|
|
"mean_token_accuracy": 0.14416550397872924,
|
|
"num_tokens": 9095839.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.591415214538574,
|
|
"epoch": 0.41604154645124064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989744677937694,
|
|
"loss": 6.5494,
|
|
"mean_token_accuracy": 0.1541710987687111,
|
|
"num_tokens": 9109476.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.541845417022705,
|
|
"epoch": 0.4166185804962493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989705287259046,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.15512136816978456,
|
|
"num_tokens": 9122354.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.513101053237915,
|
|
"epoch": 0.4171956145412579,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989665821249021,
|
|
"loss": 6.4933,
|
|
"mean_token_accuracy": 0.15538508147001268,
|
|
"num_tokens": 9135502.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.614999198913575,
|
|
"epoch": 0.4177726485862666,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498962627990895,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.14729145020246506,
|
|
"num_tokens": 9147654.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.556717014312744,
|
|
"epoch": 0.41834968263127525,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989586663240161,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.14543596506118775,
|
|
"num_tokens": 9161907.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.6760279655456545,
|
|
"epoch": 0.4189267166762839,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989546971243988,
|
|
"loss": 6.5879,
|
|
"mean_token_accuracy": 0.14227512627840042,
|
|
"num_tokens": 9175395.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.621808767318726,
|
|
"epoch": 0.41950375072129253,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989507203921763,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.15439630895853043,
|
|
"num_tokens": 9187688.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.500979614257813,
|
|
"epoch": 0.42008078476630123,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989467361274828,
|
|
"loss": 6.5274,
|
|
"mean_token_accuracy": 0.15244155377149582,
|
|
"num_tokens": 9199773.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.555854415893554,
|
|
"epoch": 0.42065781881130987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004989427443304519,
|
|
"loss": 6.5157,
|
|
"mean_token_accuracy": 0.15048773884773253,
|
|
"num_tokens": 9213997.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.564808464050293,
|
|
"epoch": 0.4212348528563185,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498938745001218,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.14768253713846208,
|
|
"num_tokens": 9227187.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.5995463848114015,
|
|
"epoch": 0.4218118869013272,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989347381399158,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.1467508353292942,
|
|
"num_tokens": 9240860.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.555819511413574,
|
|
"epoch": 0.42238892094633584,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989307237466799,
|
|
"loss": 6.5009,
|
|
"mean_token_accuracy": 0.15100916624069213,
|
|
"num_tokens": 9253771.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.555511999130249,
|
|
"epoch": 0.4229659549913445,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989267018216453,
|
|
"loss": 6.5451,
|
|
"mean_token_accuracy": 0.1484347626566887,
|
|
"num_tokens": 9268380.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.649966144561768,
|
|
"epoch": 0.4235429890363531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989226723649473,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.1520727753639221,
|
|
"num_tokens": 9279911.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.573756361007691,
|
|
"epoch": 0.4241200230813618,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989186353767214,
|
|
"loss": 6.5251,
|
|
"mean_token_accuracy": 0.15676866322755814,
|
|
"num_tokens": 9292105.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.587281703948975,
|
|
"epoch": 0.42469705712637046,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989145908571035,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.1454088181257248,
|
|
"num_tokens": 9305503.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.598947048187256,
|
|
"epoch": 0.4252740911713791,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989105388062295,
|
|
"loss": 6.5304,
|
|
"mean_token_accuracy": 0.14965798407793046,
|
|
"num_tokens": 9317978.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.61584882736206,
|
|
"epoch": 0.4258511252163878,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989064792242358,
|
|
"loss": 6.6039,
|
|
"mean_token_accuracy": 0.14742101579904557,
|
|
"num_tokens": 9332676.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.577369356155396,
|
|
"epoch": 0.42642815926139643,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989024121112589,
|
|
"loss": 6.5021,
|
|
"mean_token_accuracy": 0.150289623439312,
|
|
"num_tokens": 9345594.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.637693548202515,
|
|
"epoch": 0.4270051933064051,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988983374674356,
|
|
"loss": 6.5817,
|
|
"mean_token_accuracy": 0.14303911998867988,
|
|
"num_tokens": 9358303.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.525368690490723,
|
|
"epoch": 0.4275822273514137,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988942552929029,
|
|
"loss": 6.4649,
|
|
"mean_token_accuracy": 0.15538589656352997,
|
|
"num_tokens": 9370953.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.450020742416382,
|
|
"epoch": 0.4281592613964224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988901655877981,
|
|
"loss": 6.5505,
|
|
"mean_token_accuracy": 0.14808087795972824,
|
|
"num_tokens": 9384563.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.571639585494995,
|
|
"epoch": 0.42873629544143105,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988860683522589,
|
|
"loss": 6.4914,
|
|
"mean_token_accuracy": 0.15418324396014213,
|
|
"num_tokens": 9396401.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.549563884735107,
|
|
"epoch": 0.4293133294864397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498881963586423,
|
|
"loss": 6.5066,
|
|
"mean_token_accuracy": 0.15194836109876633,
|
|
"num_tokens": 9408520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.4020223140716555,
|
|
"epoch": 0.4298903635314484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988778512904282,
|
|
"loss": 6.4085,
|
|
"mean_token_accuracy": 0.1552750959992409,
|
|
"num_tokens": 9421431.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.5411797046661375,
|
|
"epoch": 0.430467397576457,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988737314644134,
|
|
"loss": 6.5322,
|
|
"mean_token_accuracy": 0.15222309082746505,
|
|
"num_tokens": 9432566.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.651175785064697,
|
|
"epoch": 0.43104443162146566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988696041085168,
|
|
"loss": 6.6239,
|
|
"mean_token_accuracy": 0.14554398953914643,
|
|
"num_tokens": 9444885.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.622100782394409,
|
|
"epoch": 0.4316214656664743,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004988654692228772,
|
|
"loss": 6.6173,
|
|
"mean_token_accuracy": 0.14461512714624405,
|
|
"num_tokens": 9457823.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.5988099575042725,
|
|
"epoch": 0.432198499711483,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004988613268076335,
|
|
"loss": 6.467,
|
|
"mean_token_accuracy": 0.1583518996834755,
|
|
"num_tokens": 9470799.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.589520645141602,
|
|
"epoch": 0.43277553375649164,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988571768629257,
|
|
"loss": 6.5479,
|
|
"mean_token_accuracy": 0.15336680859327317,
|
|
"num_tokens": 9484175.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.627070426940918,
|
|
"epoch": 0.4333525678015003,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988530193888927,
|
|
"loss": 6.5747,
|
|
"mean_token_accuracy": 0.14501228407025338,
|
|
"num_tokens": 9497809.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.5905872821807865,
|
|
"epoch": 0.4339296018465089,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988488543856747,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.14952886253595352,
|
|
"num_tokens": 9509755.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.532172775268554,
|
|
"epoch": 0.4345066358915176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988446818534115,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.14465863406658172,
|
|
"num_tokens": 9523801.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.547245168685913,
|
|
"epoch": 0.43508366993652625,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004988405017922438,
|
|
"loss": 6.5018,
|
|
"mean_token_accuracy": 0.1546433985233307,
|
|
"num_tokens": 9535846.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.636412525177002,
|
|
"epoch": 0.4356607039815349,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498836314202312,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.14722789376974105,
|
|
"num_tokens": 9548194.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.50278000831604,
|
|
"epoch": 0.4362377380265436,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988321190837568,
|
|
"loss": 6.499,
|
|
"mean_token_accuracy": 0.1481459118425846,
|
|
"num_tokens": 9561069.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.522726202011109,
|
|
"epoch": 0.4368147720715522,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988279164367196,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.15349378883838655,
|
|
"num_tokens": 9573778.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.55922565460205,
|
|
"epoch": 0.43739180611656087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988237062613415,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.1588495686650276,
|
|
"num_tokens": 9586616.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.531683540344238,
|
|
"epoch": 0.4379688401615695,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988194885577644,
|
|
"loss": 6.5371,
|
|
"mean_token_accuracy": 0.15208741575479506,
|
|
"num_tokens": 9597943.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.567034959793091,
|
|
"epoch": 0.4385458742065782,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988152633261299,
|
|
"loss": 6.4738,
|
|
"mean_token_accuracy": 0.15672459453344345,
|
|
"num_tokens": 9609861.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.538378524780273,
|
|
"epoch": 0.43912290825158684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049881103056658,
|
|
"loss": 6.5315,
|
|
"mean_token_accuracy": 0.1557203412055969,
|
|
"num_tokens": 9623307.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.5774413585662845,
|
|
"epoch": 0.4396999422965955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988067902792575,
|
|
"loss": 6.548,
|
|
"mean_token_accuracy": 0.14982074946165086,
|
|
"num_tokens": 9635827.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.617994737625122,
|
|
"epoch": 0.4402769763416042,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988025424643047,
|
|
"loss": 6.5941,
|
|
"mean_token_accuracy": 0.1468472957611084,
|
|
"num_tokens": 9649422.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.6371983051300045,
|
|
"epoch": 0.4408540103866128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987982871218645,
|
|
"loss": 6.5795,
|
|
"mean_token_accuracy": 0.15525637120008468,
|
|
"num_tokens": 9661542.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.573576974868774,
|
|
"epoch": 0.44143104443162146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987940242520802,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.14920065850019454,
|
|
"num_tokens": 9674684.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.644643783569336,
|
|
"epoch": 0.4420080784766301,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498789753855095,
|
|
"loss": 6.5816,
|
|
"mean_token_accuracy": 0.14375625625252725,
|
|
"num_tokens": 9687522.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.556054496765137,
|
|
"epoch": 0.4425851125216388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987854759310526,
|
|
"loss": 6.5199,
|
|
"mean_token_accuracy": 0.15176642686128616,
|
|
"num_tokens": 9699518.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.550537872314453,
|
|
"epoch": 0.44316214656664743,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987811904800968,
|
|
"loss": 6.5914,
|
|
"mean_token_accuracy": 0.15061496943235397,
|
|
"num_tokens": 9711918.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.618970155715942,
|
|
"epoch": 0.44373918061165607,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987768975023719,
|
|
"loss": 6.4637,
|
|
"mean_token_accuracy": 0.1534193515777588,
|
|
"num_tokens": 9725643.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.508399486541748,
|
|
"epoch": 0.44431621465666477,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987725969980222,
|
|
"loss": 6.4791,
|
|
"mean_token_accuracy": 0.15461074262857438,
|
|
"num_tokens": 9738871.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.529386281967163,
|
|
"epoch": 0.4448932487016734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987682889671923,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.15544941425323486,
|
|
"num_tokens": 9751166.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.528097200393677,
|
|
"epoch": 0.44547028274668204,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987639734100272,
|
|
"loss": 6.4395,
|
|
"mean_token_accuracy": 0.1568680375814438,
|
|
"num_tokens": 9765165.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.498267030715942,
|
|
"epoch": 0.4460473167916907,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987596503266721,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.1533951610326767,
|
|
"num_tokens": 9776625.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.5177834033966064,
|
|
"epoch": 0.4466243508366994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987553197172722,
|
|
"loss": 6.4855,
|
|
"mean_token_accuracy": 0.1559309795498848,
|
|
"num_tokens": 9789689.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.627424955368042,
|
|
"epoch": 0.447201384881708,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987509815819732,
|
|
"loss": 6.6022,
|
|
"mean_token_accuracy": 0.14655733555555345,
|
|
"num_tokens": 9801124.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.550175523757934,
|
|
"epoch": 0.44777841892671666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987466359209213,
|
|
"loss": 6.5342,
|
|
"mean_token_accuracy": 0.15006100833415986,
|
|
"num_tokens": 9814264.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.550042581558228,
|
|
"epoch": 0.44835545297172535,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004987422827342622,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.15616977363824844,
|
|
"num_tokens": 9826149.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.557639408111572,
|
|
"epoch": 0.448932487016734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987379220221426,
|
|
"loss": 6.5503,
|
|
"mean_token_accuracy": 0.14510683268308638,
|
|
"num_tokens": 9838485.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.5344490051269535,
|
|
"epoch": 0.44950952106174263,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987335537847092,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.15009704530239104,
|
|
"num_tokens": 9851371.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.512049579620362,
|
|
"epoch": 0.4500865551067513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987291780221088,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.14940400570631027,
|
|
"num_tokens": 9864371.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.560714340209961,
|
|
"epoch": 0.45066358915175997,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987247947344887,
|
|
"loss": 6.5233,
|
|
"mean_token_accuracy": 0.1517380103468895,
|
|
"num_tokens": 9876086.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.528545999526978,
|
|
"epoch": 0.4512406231967686,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987204039219962,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.1479131981730461,
|
|
"num_tokens": 9888850.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.582427883148194,
|
|
"epoch": 0.45181765724177725,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987160055847791,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.15192154794931412,
|
|
"num_tokens": 9901467.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.58316740989685,
|
|
"epoch": 0.45239469128678594,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987115997229852,
|
|
"loss": 6.5235,
|
|
"mean_token_accuracy": 0.1524689018726349,
|
|
"num_tokens": 9914431.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.614464235305786,
|
|
"epoch": 0.4529717253317946,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987071863367629,
|
|
"loss": 6.5604,
|
|
"mean_token_accuracy": 0.15112543925642968,
|
|
"num_tokens": 9926863.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.565920209884643,
|
|
"epoch": 0.4535487593768032,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987027654262604,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.15478066951036454,
|
|
"num_tokens": 9939064.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.430483436584472,
|
|
"epoch": 0.45412579342181186,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986983369916264,
|
|
"loss": 6.4946,
|
|
"mean_token_accuracy": 0.15007816404104232,
|
|
"num_tokens": 9950897.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.655666780471802,
|
|
"epoch": 0.45470282746682056,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986939010330102,
|
|
"loss": 6.5449,
|
|
"mean_token_accuracy": 0.1454168014228344,
|
|
"num_tokens": 9964388.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.409772491455078,
|
|
"epoch": 0.4552798615118292,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986894575505606,
|
|
"loss": 6.382,
|
|
"mean_token_accuracy": 0.16272770017385482,
|
|
"num_tokens": 9977363.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.591909456253052,
|
|
"epoch": 0.45585689555683784,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986850065444272,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.15807752758264543,
|
|
"num_tokens": 9989691.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.590207910537719,
|
|
"epoch": 0.45643392960184653,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986805480147598,
|
|
"loss": 6.4787,
|
|
"mean_token_accuracy": 0.14620172828435898,
|
|
"num_tokens": 10002177.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.495525979995728,
|
|
"epoch": 0.4570109636468552,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004986760819617082,
|
|
"loss": 6.5341,
|
|
"mean_token_accuracy": 0.14582275450229645,
|
|
"num_tokens": 10014844.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.659038019180298,
|
|
"epoch": 0.4575879976918638,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986716083854228,
|
|
"loss": 6.5687,
|
|
"mean_token_accuracy": 0.1485973134636879,
|
|
"num_tokens": 10028351.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.487327241897583,
|
|
"epoch": 0.45816503173687245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986671272860538,
|
|
"loss": 6.4832,
|
|
"mean_token_accuracy": 0.14729729741811753,
|
|
"num_tokens": 10041318.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.540215110778808,
|
|
"epoch": 0.45874206578188115,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986626386637521,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.14569370001554488,
|
|
"num_tokens": 10054985.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.571915769577027,
|
|
"epoch": 0.4593190998268898,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986581425186688,
|
|
"loss": 6.5598,
|
|
"mean_token_accuracy": 0.1512555092573166,
|
|
"num_tokens": 10067528.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.542682886123657,
|
|
"epoch": 0.4598961338718984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986536388509548,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.15116373002529143,
|
|
"num_tokens": 10080210.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.51995530128479,
|
|
"epoch": 0.4604731679169071,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986491276607618,
|
|
"loss": 6.5335,
|
|
"mean_token_accuracy": 0.15148406326770783,
|
|
"num_tokens": 10092040.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.583942508697509,
|
|
"epoch": 0.46105020196191576,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004986446089482416,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.15163778215646745,
|
|
"num_tokens": 10104923.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.4749840259552,
|
|
"epoch": 0.4616272360069244,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986400827135459,
|
|
"loss": 6.4746,
|
|
"mean_token_accuracy": 0.15648574531078338,
|
|
"num_tokens": 10118963.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.527820158004761,
|
|
"epoch": 0.46220427005193304,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986355489568272,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.15958915799856185,
|
|
"num_tokens": 10131457.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.568796968460083,
|
|
"epoch": 0.46278130409694174,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986310076782379,
|
|
"loss": 6.4985,
|
|
"mean_token_accuracy": 0.1522387072443962,
|
|
"num_tokens": 10143796.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.494457387924195,
|
|
"epoch": 0.4633583381419504,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986264588779307,
|
|
"loss": 6.5045,
|
|
"mean_token_accuracy": 0.15380825847387314,
|
|
"num_tokens": 10156723.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.5013172149658205,
|
|
"epoch": 0.463935372186959,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986219025560586,
|
|
"loss": 6.5023,
|
|
"mean_token_accuracy": 0.14863586351275443,
|
|
"num_tokens": 10168701.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.557641696929932,
|
|
"epoch": 0.4645124062319677,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498617338712775,
|
|
"loss": 6.4602,
|
|
"mean_token_accuracy": 0.1560764953494072,
|
|
"num_tokens": 10182308.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.510044240951538,
|
|
"epoch": 0.46508944027697635,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986127673482332,
|
|
"loss": 6.4539,
|
|
"mean_token_accuracy": 0.15890756398439407,
|
|
"num_tokens": 10194237.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.52144136428833,
|
|
"epoch": 0.465666474321985,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986081884625871,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.14942877292633056,
|
|
"num_tokens": 10208570.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.601692390441895,
|
|
"epoch": 0.46624350836699363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986036020559906,
|
|
"loss": 6.4814,
|
|
"mean_token_accuracy": 0.15481637567281722,
|
|
"num_tokens": 10221079.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.356483602523804,
|
|
"epoch": 0.4668205424120023,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498599008128598,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.15378812998533248,
|
|
"num_tokens": 10233473.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.593820810317993,
|
|
"epoch": 0.46739757645701097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985944066805639,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.14852241575717925,
|
|
"num_tokens": 10247840.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.525872278213501,
|
|
"epoch": 0.4679746105020196,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000498589797712043,
|
|
"loss": 6.473,
|
|
"mean_token_accuracy": 0.16045304834842683,
|
|
"num_tokens": 10261471.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.504099178314209,
|
|
"epoch": 0.4685516445470283,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985851812231903,
|
|
"loss": 6.4736,
|
|
"mean_token_accuracy": 0.15337898284196855,
|
|
"num_tokens": 10274386.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.592873764038086,
|
|
"epoch": 0.46912867859203694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985805572141611,
|
|
"loss": 6.5064,
|
|
"mean_token_accuracy": 0.15148324966430665,
|
|
"num_tokens": 10286405.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.614938163757325,
|
|
"epoch": 0.4697057126370456,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985759256851108,
|
|
"loss": 6.5546,
|
|
"mean_token_accuracy": 0.14901065975427627,
|
|
"num_tokens": 10300084.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.57010850906372,
|
|
"epoch": 0.4702827466820542,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985712866361954,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.15720511972904205,
|
|
"num_tokens": 10312558.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.493395519256592,
|
|
"epoch": 0.4708597807270629,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985666400675709,
|
|
"loss": 6.4604,
|
|
"mean_token_accuracy": 0.1560864806175232,
|
|
"num_tokens": 10324185.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.488433313369751,
|
|
"epoch": 0.47143681477207156,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985619859793934,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.1477129116654396,
|
|
"num_tokens": 10338634.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.7163480758667,
|
|
"epoch": 0.4720138488170802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985573243718195,
|
|
"loss": 6.5503,
|
|
"mean_token_accuracy": 0.14475530236959458,
|
|
"num_tokens": 10351272.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.561359500885009,
|
|
"epoch": 0.4725908828620889,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985526552450061,
|
|
"loss": 6.5081,
|
|
"mean_token_accuracy": 0.1437559977173805,
|
|
"num_tokens": 10362894.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.548456525802612,
|
|
"epoch": 0.47316791690709753,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985479785991103,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.14605074226856232,
|
|
"num_tokens": 10376120.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.55332236289978,
|
|
"epoch": 0.47374495095210617,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985432944342892,
|
|
"loss": 6.5026,
|
|
"mean_token_accuracy": 0.153361913561821,
|
|
"num_tokens": 10387986.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.548603773117065,
|
|
"epoch": 0.4743219849971148,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985386027507003,
|
|
"loss": 6.5225,
|
|
"mean_token_accuracy": 0.1517445206642151,
|
|
"num_tokens": 10400920.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.661869049072266,
|
|
"epoch": 0.4748990190421235,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985339035485018,
|
|
"loss": 6.525,
|
|
"mean_token_accuracy": 0.14937230050563813,
|
|
"num_tokens": 10413835.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.533235025405884,
|
|
"epoch": 0.47547605308713214,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985291968278513,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.14905970692634582,
|
|
"num_tokens": 10426959.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.536430978775025,
|
|
"epoch": 0.4760530871321408,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985244825889074,
|
|
"loss": 6.5637,
|
|
"mean_token_accuracy": 0.15390570759773253,
|
|
"num_tokens": 10440319.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.541896820068359,
|
|
"epoch": 0.4766301211771495,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985197608318284,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.15225679874420167,
|
|
"num_tokens": 10453715.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.594496631622315,
|
|
"epoch": 0.4772071552221581,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985150315567735,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.14864421635866165,
|
|
"num_tokens": 10465574.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.506676197052002,
|
|
"epoch": 0.47778418926716676,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004985102947639013,
|
|
"loss": 6.5007,
|
|
"mean_token_accuracy": 0.15153668075799942,
|
|
"num_tokens": 10478105.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.552076911926269,
|
|
"epoch": 0.4783612233121754,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985055504533715,
|
|
"loss": 6.5134,
|
|
"mean_token_accuracy": 0.15088197439908982,
|
|
"num_tokens": 10490723.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.602122354507446,
|
|
"epoch": 0.4789382573571841,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985007986253435,
|
|
"loss": 6.5254,
|
|
"mean_token_accuracy": 0.14911809265613557,
|
|
"num_tokens": 10503155.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.554518699645996,
|
|
"epoch": 0.47951529140219273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984960392799772,
|
|
"loss": 6.5106,
|
|
"mean_token_accuracy": 0.1461018964648247,
|
|
"num_tokens": 10515077.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.592270565032959,
|
|
"epoch": 0.4800923254472014,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984912724174326,
|
|
"loss": 6.4926,
|
|
"mean_token_accuracy": 0.1490560546517372,
|
|
"num_tokens": 10528445.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.542512369155884,
|
|
"epoch": 0.48066935949221,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984864980378701,
|
|
"loss": 6.518,
|
|
"mean_token_accuracy": 0.15329633057117462,
|
|
"num_tokens": 10541877.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.511092805862427,
|
|
"epoch": 0.4812463935372187,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984817161414502,
|
|
"loss": 6.4941,
|
|
"mean_token_accuracy": 0.15064932703971862,
|
|
"num_tokens": 10553527.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.550889539718628,
|
|
"epoch": 0.48182342758222735,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984769267283338,
|
|
"loss": 6.5247,
|
|
"mean_token_accuracy": 0.14874509274959563,
|
|
"num_tokens": 10566492.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.496022319793701,
|
|
"epoch": 0.482400461627236,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004984721297986819,
|
|
"loss": 6.458,
|
|
"mean_token_accuracy": 0.15352972596883774,
|
|
"num_tokens": 10578962.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.561640214920044,
|
|
"epoch": 0.4829774956722447,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984673253526561,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.15236313343048097,
|
|
"num_tokens": 10591254.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.533859395980835,
|
|
"epoch": 0.4835545297172533,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004984625133904176,
|
|
"loss": 6.5014,
|
|
"mean_token_accuracy": 0.15217659398913383,
|
|
"num_tokens": 10604961.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.529065370559692,
|
|
"epoch": 0.48413156376226196,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984576939121286,
|
|
"loss": 6.4615,
|
|
"mean_token_accuracy": 0.15530140995979308,
|
|
"num_tokens": 10617419.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.506486940383911,
|
|
"epoch": 0.4847085978072706,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984528669179511,
|
|
"loss": 6.531,
|
|
"mean_token_accuracy": 0.14775909036397933,
|
|
"num_tokens": 10629721.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.585139322280884,
|
|
"epoch": 0.4852856318522793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984480324080472,
|
|
"loss": 6.5338,
|
|
"mean_token_accuracy": 0.14746304452419282,
|
|
"num_tokens": 10643869.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.593662929534912,
|
|
"epoch": 0.48586266589728794,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049844319038258,
|
|
"loss": 6.5939,
|
|
"mean_token_accuracy": 0.14522895812988282,
|
|
"num_tokens": 10658418.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.564258623123169,
|
|
"epoch": 0.4864396999422966,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984383408417119,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.15308941155672073,
|
|
"num_tokens": 10671105.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.582191467285156,
|
|
"epoch": 0.4870167339873053,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984334837856064,
|
|
"loss": 6.5699,
|
|
"mean_token_accuracy": 0.1451310083270073,
|
|
"num_tokens": 10683862.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.55675687789917,
|
|
"epoch": 0.4875937680323139,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984286192144263,
|
|
"loss": 6.4655,
|
|
"mean_token_accuracy": 0.15599070638418197,
|
|
"num_tokens": 10696559.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.599395895004273,
|
|
"epoch": 0.48817080207732255,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984237471283359,
|
|
"loss": 6.5383,
|
|
"mean_token_accuracy": 0.15275808423757553,
|
|
"num_tokens": 10710227.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.507157993316651,
|
|
"epoch": 0.4887478361223312,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984188675274986,
|
|
"loss": 6.5131,
|
|
"mean_token_accuracy": 0.14976295828819275,
|
|
"num_tokens": 10722761.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.592884159088134,
|
|
"epoch": 0.4893248701673399,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984139804120787,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.1465604603290558,
|
|
"num_tokens": 10734126.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.563351154327393,
|
|
"epoch": 0.4899019042123485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984090857822406,
|
|
"loss": 6.5365,
|
|
"mean_token_accuracy": 0.14797307029366494,
|
|
"num_tokens": 10747570.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.63136625289917,
|
|
"epoch": 0.49047893825735717,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984041836381488,
|
|
"loss": 6.6419,
|
|
"mean_token_accuracy": 0.14504213631153107,
|
|
"num_tokens": 10762975.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.632890224456787,
|
|
"epoch": 0.49105597230236586,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983992739799682,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.15367807745933532,
|
|
"num_tokens": 10774520.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.475261068344116,
|
|
"epoch": 0.4916330063473745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983943568078642,
|
|
"loss": 6.4071,
|
|
"mean_token_accuracy": 0.15381105840206147,
|
|
"num_tokens": 10786250.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.515493011474609,
|
|
"epoch": 0.49221004039238314,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983894321220017,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.14624571949243545,
|
|
"num_tokens": 10799831.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.583249425888061,
|
|
"epoch": 0.4927870744373918,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983844999225468,
|
|
"loss": 6.4694,
|
|
"mean_token_accuracy": 0.15290576964616776,
|
|
"num_tokens": 10812803.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.512081813812256,
|
|
"epoch": 0.4933641084824005,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983795602096651,
|
|
"loss": 6.4783,
|
|
"mean_token_accuracy": 0.15587753057479858,
|
|
"num_tokens": 10825150.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.589651012420655,
|
|
"epoch": 0.4939411425274091,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498374612983523,
|
|
"loss": 6.5828,
|
|
"mean_token_accuracy": 0.14737853184342384,
|
|
"num_tokens": 10838337.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.635598182678223,
|
|
"epoch": 0.49451817657241776,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983696582442866,
|
|
"loss": 6.4461,
|
|
"mean_token_accuracy": 0.16733498871326447,
|
|
"num_tokens": 10852288.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.519201326370239,
|
|
"epoch": 0.49509521061742645,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983646959921227,
|
|
"loss": 6.5311,
|
|
"mean_token_accuracy": 0.14743692576885223,
|
|
"num_tokens": 10864189.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.6310670375823975,
|
|
"epoch": 0.4956722446624351,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004983597262271984,
|
|
"loss": 6.5307,
|
|
"mean_token_accuracy": 0.14658827036619188,
|
|
"num_tokens": 10877410.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.480897855758667,
|
|
"epoch": 0.49624927870744373,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004983547489496804,
|
|
"loss": 6.5108,
|
|
"mean_token_accuracy": 0.14898531660437583,
|
|
"num_tokens": 10889757.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.511052417755127,
|
|
"epoch": 0.49682631275245237,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983497641597365,
|
|
"loss": 6.399,
|
|
"mean_token_accuracy": 0.1597002699971199,
|
|
"num_tokens": 10901636.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.496632814407349,
|
|
"epoch": 0.49740334679746107,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983447718575342,
|
|
"loss": 6.4418,
|
|
"mean_token_accuracy": 0.15892936736345292,
|
|
"num_tokens": 10914063.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.581086921691894,
|
|
"epoch": 0.4979803808424697,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983397720432414,
|
|
"loss": 6.4744,
|
|
"mean_token_accuracy": 0.15386273562908173,
|
|
"num_tokens": 10927730.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.537801122665405,
|
|
"epoch": 0.49855741488747835,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983347647170264,
|
|
"loss": 6.6001,
|
|
"mean_token_accuracy": 0.14655838459730147,
|
|
"num_tokens": 10942440.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.567225456237793,
|
|
"epoch": 0.49913444893248704,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983297498790574,
|
|
"loss": 6.4809,
|
|
"mean_token_accuracy": 0.14959282279014588,
|
|
"num_tokens": 10955801.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.585222673416138,
|
|
"epoch": 0.4997114829774957,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983247275295034,
|
|
"loss": 6.4775,
|
|
"mean_token_accuracy": 0.15232663005590438,
|
|
"num_tokens": 10967918.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.481248474121093,
|
|
"epoch": 0.5002885170225043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983196976685329,
|
|
"loss": 6.4152,
|
|
"mean_token_accuracy": 0.15650064051151275,
|
|
"num_tokens": 10979652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.49305682182312,
|
|
"epoch": 0.500865551067513,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004983146602963155,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.16713591665029526,
|
|
"num_tokens": 10991433.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.41333909034729,
|
|
"epoch": 0.5014425851125216,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004983096154130203,
|
|
"loss": 6.5509,
|
|
"mean_token_accuracy": 0.15196776390075684,
|
|
"num_tokens": 11003976.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.585015773773193,
|
|
"epoch": 0.5020196191575302,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983045630188171,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.1477636769413948,
|
|
"num_tokens": 11018848.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.6534788608551025,
|
|
"epoch": 0.502596653202539,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982995031138759,
|
|
"loss": 6.5037,
|
|
"mean_token_accuracy": 0.1479504019021988,
|
|
"num_tokens": 11030803.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.515288352966309,
|
|
"epoch": 0.5031736872475476,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982944356983666,
|
|
"loss": 6.5648,
|
|
"mean_token_accuracy": 0.14597940295934678,
|
|
"num_tokens": 11044688.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.573613023757934,
|
|
"epoch": 0.5037507212925563,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982893607724602,
|
|
"loss": 6.5372,
|
|
"mean_token_accuracy": 0.1448674187064171,
|
|
"num_tokens": 11057026.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.661010122299194,
|
|
"epoch": 0.5043277553375649,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000498284278336327,
|
|
"loss": 6.5456,
|
|
"mean_token_accuracy": 0.14358318001031875,
|
|
"num_tokens": 11070407.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.476870441436768,
|
|
"epoch": 0.5049047893825735,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004982791883901379,
|
|
"loss": 6.4595,
|
|
"mean_token_accuracy": 0.15498376861214638,
|
|
"num_tokens": 11082655.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.414759540557862,
|
|
"epoch": 0.5054818234275822,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982740909340643,
|
|
"loss": 6.4234,
|
|
"mean_token_accuracy": 0.16286834478378295,
|
|
"num_tokens": 11095948.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.6195331573486325,
|
|
"epoch": 0.5060588574725908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982689859682775,
|
|
"loss": 6.467,
|
|
"mean_token_accuracy": 0.14826145470142366,
|
|
"num_tokens": 11108105.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.554189395904541,
|
|
"epoch": 0.5066358915175996,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982638734929492,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.14397745132446288,
|
|
"num_tokens": 11120322.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.4076619148254395,
|
|
"epoch": 0.5072129255626082,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982587535082515,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.16224624663591386,
|
|
"num_tokens": 11133903.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.466379690170288,
|
|
"epoch": 0.5077899596076169,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982536260143565,
|
|
"loss": 6.3768,
|
|
"mean_token_accuracy": 0.16100105494260789,
|
|
"num_tokens": 11145607.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.51287145614624,
|
|
"epoch": 0.5083669936526255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004982484910114367,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.15186810493469238,
|
|
"num_tokens": 11157332.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.590687894821167,
|
|
"epoch": 0.5089440276976341,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982433484996648,
|
|
"loss": 6.5847,
|
|
"mean_token_accuracy": 0.15006298422813416,
|
|
"num_tokens": 11169404.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.554287099838257,
|
|
"epoch": 0.5095210617426428,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982381984792138,
|
|
"loss": 6.4567,
|
|
"mean_token_accuracy": 0.15406338274478912,
|
|
"num_tokens": 11182506.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.521548748016357,
|
|
"epoch": 0.5100980957876514,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982330409502568,
|
|
"loss": 6.4238,
|
|
"mean_token_accuracy": 0.15082940310239792,
|
|
"num_tokens": 11195507.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.535209894180298,
|
|
"epoch": 0.5106751298326602,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982278759129674,
|
|
"loss": 6.4329,
|
|
"mean_token_accuracy": 0.15719768702983855,
|
|
"num_tokens": 11207219.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.438648223876953,
|
|
"epoch": 0.5112521638776688,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004982227033675194,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.15815673768520355,
|
|
"num_tokens": 11219301.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.460758399963379,
|
|
"epoch": 0.5118291979226774,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982175233140865,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.15656259655952454,
|
|
"num_tokens": 11230957.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.560869407653809,
|
|
"epoch": 0.5124062319676861,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982123357528431,
|
|
"loss": 6.4481,
|
|
"mean_token_accuracy": 0.1526852384209633,
|
|
"num_tokens": 11242813.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.507971668243409,
|
|
"epoch": 0.5129832660126947,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004982071406839636,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.15058354064822196,
|
|
"num_tokens": 11255193.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.388872909545898,
|
|
"epoch": 0.5135603000577034,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982019381076229,
|
|
"loss": 6.4273,
|
|
"mean_token_accuracy": 0.15397539511322975,
|
|
"num_tokens": 11267988.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.536984300613403,
|
|
"epoch": 0.514137334102712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981967280239958,
|
|
"loss": 6.5089,
|
|
"mean_token_accuracy": 0.14631436094641687,
|
|
"num_tokens": 11280456.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.541901874542236,
|
|
"epoch": 0.5147143681477208,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981915104332578,
|
|
"loss": 6.5337,
|
|
"mean_token_accuracy": 0.14940202683210374,
|
|
"num_tokens": 11293304.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.4461493492126465,
|
|
"epoch": 0.5152914021927294,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498186285335584,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.14736132621765136,
|
|
"num_tokens": 11305936.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.674417877197266,
|
|
"epoch": 0.515868436237738,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981810527311505,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.14426559805870057,
|
|
"num_tokens": 11319991.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.577980184555054,
|
|
"epoch": 0.5164454702827467,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000498175812620133,
|
|
"loss": 6.4438,
|
|
"mean_token_accuracy": 0.15654727965593337,
|
|
"num_tokens": 11332572.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.419868278503418,
|
|
"epoch": 0.5170225043277553,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981705650027081,
|
|
"loss": 6.4572,
|
|
"mean_token_accuracy": 0.15874334275722504,
|
|
"num_tokens": 11344435.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.5055430889129635,
|
|
"epoch": 0.517599538372764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000498165309879052,
|
|
"loss": 6.3757,
|
|
"mean_token_accuracy": 0.15824664235115052,
|
|
"num_tokens": 11356078.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.469321823120117,
|
|
"epoch": 0.5181765724177726,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981600472493415,
|
|
"loss": 6.4263,
|
|
"mean_token_accuracy": 0.1546856477856636,
|
|
"num_tokens": 11368933.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.574912452697754,
|
|
"epoch": 0.5187536064627813,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981547771137537,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.1477719157934189,
|
|
"num_tokens": 11380810.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.48729829788208,
|
|
"epoch": 0.51933064050779,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981494994724658,
|
|
"loss": 6.4445,
|
|
"mean_token_accuracy": 0.1526978924870491,
|
|
"num_tokens": 11392447.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.454307603836059,
|
|
"epoch": 0.5199076745527986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981442143256554,
|
|
"loss": 6.4863,
|
|
"mean_token_accuracy": 0.15106553584337234,
|
|
"num_tokens": 11405237.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.603475046157837,
|
|
"epoch": 0.5204847085978073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981389216735001,
|
|
"loss": 6.6036,
|
|
"mean_token_accuracy": 0.14028041437268257,
|
|
"num_tokens": 11418951.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.578861427307129,
|
|
"epoch": 0.5210617426428159,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498133621516178,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.15183505415916443,
|
|
"num_tokens": 11432587.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.549359607696533,
|
|
"epoch": 0.5216387766878245,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981283138538675,
|
|
"loss": 6.5326,
|
|
"mean_token_accuracy": 0.14482680857181549,
|
|
"num_tokens": 11445572.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.562268686294556,
|
|
"epoch": 0.5222158107328332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498122998686747,
|
|
"loss": 6.4821,
|
|
"mean_token_accuracy": 0.14933309257030486,
|
|
"num_tokens": 11457469.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.4967255115509035,
|
|
"epoch": 0.5227928447778419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981176760149951,
|
|
"loss": 6.5183,
|
|
"mean_token_accuracy": 0.15408243611454964,
|
|
"num_tokens": 11470306.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.562189292907715,
|
|
"epoch": 0.5233698788228506,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004981123458387911,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.1558932587504387,
|
|
"num_tokens": 11483839.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.578125905990601,
|
|
"epoch": 0.5239469128678592,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981070081583142,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.14841696321964265,
|
|
"num_tokens": 11495703.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.603797674179077,
|
|
"epoch": 0.5245239469128679,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498101662973744,
|
|
"loss": 6.5831,
|
|
"mean_token_accuracy": 0.14712464138865472,
|
|
"num_tokens": 11508061.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.508516645431518,
|
|
"epoch": 0.5251009809578765,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049809631028526,
|
|
"loss": 6.4236,
|
|
"mean_token_accuracy": 0.15662758201360702,
|
|
"num_tokens": 11520135.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.499169921875,
|
|
"epoch": 0.5256780150028851,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980909500930424,
|
|
"loss": 6.4971,
|
|
"mean_token_accuracy": 0.14866289794445037,
|
|
"num_tokens": 11532255.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.516340065002441,
|
|
"epoch": 0.5262550490478938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980855823972717,
|
|
"loss": 6.4104,
|
|
"mean_token_accuracy": 0.15316666960716246,
|
|
"num_tokens": 11544596.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.5355082035064695,
|
|
"epoch": 0.5268320830929025,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498080207198128,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.1471469670534134,
|
|
"num_tokens": 11556758.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.5845283508300785,
|
|
"epoch": 0.5274091171379112,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980748244957925,
|
|
"loss": 6.5381,
|
|
"mean_token_accuracy": 0.14486694410443307,
|
|
"num_tokens": 11570070.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.519506359100342,
|
|
"epoch": 0.5279861511829198,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004980694342904461,
|
|
"loss": 6.427,
|
|
"mean_token_accuracy": 0.15766648799180985,
|
|
"num_tokens": 11582566.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.420183849334717,
|
|
"epoch": 0.5285631852279284,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980640365822701,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.1610960304737091,
|
|
"num_tokens": 11595238.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.540434312820435,
|
|
"epoch": 0.5291402192729371,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498058631371446,
|
|
"loss": 6.5134,
|
|
"mean_token_accuracy": 0.15686920285224915,
|
|
"num_tokens": 11608646.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.461825847625732,
|
|
"epoch": 0.5297172533179457,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980532186581555,
|
|
"loss": 6.4396,
|
|
"mean_token_accuracy": 0.15351363271474838,
|
|
"num_tokens": 11619610.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.42177448272705,
|
|
"epoch": 0.5302942873629544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498047798442581,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.16407090574502944,
|
|
"num_tokens": 11631691.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.516407203674317,
|
|
"epoch": 0.5308713214079631,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980423707249044,
|
|
"loss": 6.3881,
|
|
"mean_token_accuracy": 0.1592670902609825,
|
|
"num_tokens": 11644330.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.531644344329834,
|
|
"epoch": 0.5314483554529718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980369355053086,
|
|
"loss": 6.5237,
|
|
"mean_token_accuracy": 0.14757917076349258,
|
|
"num_tokens": 11656826.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.451550531387329,
|
|
"epoch": 0.5320253894979804,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004980314927839763,
|
|
"loss": 6.4796,
|
|
"mean_token_accuracy": 0.1471990704536438,
|
|
"num_tokens": 11668669.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.606909942626953,
|
|
"epoch": 0.532602423542989,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004980260425610903,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.14908241629600524,
|
|
"num_tokens": 11681237.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.498003244400024,
|
|
"epoch": 0.5331794575879977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980205848368343,
|
|
"loss": 6.4956,
|
|
"mean_token_accuracy": 0.15172789618372917,
|
|
"num_tokens": 11693953.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.501087999343872,
|
|
"epoch": 0.5337564916330063,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004980151196113917,
|
|
"loss": 6.4413,
|
|
"mean_token_accuracy": 0.1522899702191353,
|
|
"num_tokens": 11705364.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.514171934127807,
|
|
"epoch": 0.534333525678015,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980096468849464,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.15325311124324797,
|
|
"num_tokens": 11717664.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.466876649856568,
|
|
"epoch": 0.5349105597230237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004980041666576823,
|
|
"loss": 6.456,
|
|
"mean_token_accuracy": 0.14555764496326445,
|
|
"num_tokens": 11731143.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.550040197372437,
|
|
"epoch": 0.5354875937680323,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004979986789297837,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.15628498494625093,
|
|
"num_tokens": 11743904.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.330129718780517,
|
|
"epoch": 0.536064627813041,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979931837014355,
|
|
"loss": 6.2898,
|
|
"mean_token_accuracy": 0.15889219790697098,
|
|
"num_tokens": 11756731.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.439878225326538,
|
|
"epoch": 0.5366416618580496,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979876809728223,
|
|
"loss": 6.4106,
|
|
"mean_token_accuracy": 0.1573275938630104,
|
|
"num_tokens": 11768597.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.4509971141815186,
|
|
"epoch": 0.5372186959030583,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004979821707441292,
|
|
"loss": 6.3422,
|
|
"mean_token_accuracy": 0.16196626275777817,
|
|
"num_tokens": 11781464.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.384463500976563,
|
|
"epoch": 0.5377957299480669,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979766530155416,
|
|
"loss": 6.3178,
|
|
"mean_token_accuracy": 0.16592992544174195,
|
|
"num_tokens": 11794215.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.5064746856689455,
|
|
"epoch": 0.5383727639930755,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004979711277872449,
|
|
"loss": 6.5442,
|
|
"mean_token_accuracy": 0.14707691445946694,
|
|
"num_tokens": 11807456.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.544828224182129,
|
|
"epoch": 0.5389497980380843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979655950594252,
|
|
"loss": 6.4476,
|
|
"mean_token_accuracy": 0.15236640498042106,
|
|
"num_tokens": 11819730.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.453517055511474,
|
|
"epoch": 0.5395268320830929,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979600548322684,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.16160822808742523,
|
|
"num_tokens": 11831892.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.519505739212036,
|
|
"epoch": 0.5401038661281016,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497954507105961,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.15195320397615433,
|
|
"num_tokens": 11844114.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.573498392105103,
|
|
"epoch": 0.5406809001731102,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979489518806893,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.1524272158741951,
|
|
"num_tokens": 11855832.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.521721220016479,
|
|
"epoch": 0.5412579342181189,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979433891566405,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.15105092376470566,
|
|
"num_tokens": 11868837.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.530892992019654,
|
|
"epoch": 0.5418349682631275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004979378189340015,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.16228097975254058,
|
|
"num_tokens": 11880608.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.527881860733032,
|
|
"epoch": 0.5424120023081361,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004979322412129597,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.15379999428987504,
|
|
"num_tokens": 11892652.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.513641881942749,
|
|
"epoch": 0.5429890363531449,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979266559937028,
|
|
"loss": 6.3945,
|
|
"mean_token_accuracy": 0.15369104892015456,
|
|
"num_tokens": 11904572.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.591770267486572,
|
|
"epoch": 0.5435660703981535,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979210632764185,
|
|
"loss": 6.5345,
|
|
"mean_token_accuracy": 0.14894211888313294,
|
|
"num_tokens": 11917794.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.52169017791748,
|
|
"epoch": 0.5441431044431622,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004979154630612949,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.15118273198604584,
|
|
"num_tokens": 11930403.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.5592405796051025,
|
|
"epoch": 0.5447201384881708,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979098553485205,
|
|
"loss": 6.5375,
|
|
"mean_token_accuracy": 0.1481676384806633,
|
|
"num_tokens": 11943974.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.52493953704834,
|
|
"epoch": 0.5452971725331794,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979042401382838,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.14051474183797835,
|
|
"num_tokens": 11956887.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.567168235778809,
|
|
"epoch": 0.5458742065781881,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978986174307737,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.16181773245334624,
|
|
"num_tokens": 11969504.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.418928146362305,
|
|
"epoch": 0.5464512406231967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978929872261794,
|
|
"loss": 6.4336,
|
|
"mean_token_accuracy": 0.15474231988191606,
|
|
"num_tokens": 11983432.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.59085521697998,
|
|
"epoch": 0.5470282746682055,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004978873495246901,
|
|
"loss": 6.4298,
|
|
"mean_token_accuracy": 0.16287856549024582,
|
|
"num_tokens": 11995915.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.460890197753907,
|
|
"epoch": 0.5476053087132141,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978817043264955,
|
|
"loss": 6.4353,
|
|
"mean_token_accuracy": 0.15744587630033494,
|
|
"num_tokens": 12008395.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.377586364746094,
|
|
"epoch": 0.5481823427582228,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004978760516317856,
|
|
"loss": 6.3956,
|
|
"mean_token_accuracy": 0.1520675890147686,
|
|
"num_tokens": 12021179.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.540531587600708,
|
|
"epoch": 0.5487593768032314,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004978703914407503,
|
|
"loss": 6.489,
|
|
"mean_token_accuracy": 0.14723778814077376,
|
|
"num_tokens": 12033798.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.561176300048828,
|
|
"epoch": 0.54933641084824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978647237535802,
|
|
"loss": 6.4887,
|
|
"mean_token_accuracy": 0.1505315586924553,
|
|
"num_tokens": 12045720.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.543166399002075,
|
|
"epoch": 0.5499134448932487,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004978590485704657,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.15576629489660263,
|
|
"num_tokens": 12058616.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.486966133117676,
|
|
"epoch": 0.5504904789382573,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978533658915979,
|
|
"loss": 6.5079,
|
|
"mean_token_accuracy": 0.15112854689359664,
|
|
"num_tokens": 12070173.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.481332635879516,
|
|
"epoch": 0.5510675129832661,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004978476757171678,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.16395777463912964,
|
|
"num_tokens": 12083499.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.472747802734375,
|
|
"epoch": 0.5516445470282747,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978419780473668,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.1544622302055359,
|
|
"num_tokens": 12095773.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.4680047035217285,
|
|
"epoch": 0.5522215810732833,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004978362728823865,
|
|
"loss": 6.4666,
|
|
"mean_token_accuracy": 0.15453778207302094,
|
|
"num_tokens": 12107640.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.480125045776367,
|
|
"epoch": 0.552798615118292,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004978305602224189,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.1534944549202919,
|
|
"num_tokens": 12120433.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.440623235702515,
|
|
"epoch": 0.5533756491633006,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978248400676562,
|
|
"loss": 6.3806,
|
|
"mean_token_accuracy": 0.15867497473955156,
|
|
"num_tokens": 12133326.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.586127471923828,
|
|
"epoch": 0.5539526832083093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978191124182905,
|
|
"loss": 6.4862,
|
|
"mean_token_accuracy": 0.149084635078907,
|
|
"num_tokens": 12145119.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.5216453075408936,
|
|
"epoch": 0.5545297172533179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978133772745149,
|
|
"loss": 6.4498,
|
|
"mean_token_accuracy": 0.14746844321489333,
|
|
"num_tokens": 12157414.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.436687326431274,
|
|
"epoch": 0.5551067512983267,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978076346365218,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.15791162550449372,
|
|
"num_tokens": 12170226.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.456769037246704,
|
|
"epoch": 0.5556837853433353,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978018845045047,
|
|
"loss": 6.38,
|
|
"mean_token_accuracy": 0.1574267938733101,
|
|
"num_tokens": 12182804.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.512805700302124,
|
|
"epoch": 0.5562608193883439,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004977961268786568,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.15100056529045106,
|
|
"num_tokens": 12194795.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.4469624042510985,
|
|
"epoch": 0.5568378534333526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977903617591719,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.1635904222726822,
|
|
"num_tokens": 12207880.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.49699854850769,
|
|
"epoch": 0.5574148874783612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977845891462439,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.1520783096551895,
|
|
"num_tokens": 12219434.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.497847318649292,
|
|
"epoch": 0.5579919215233698,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977788090400668,
|
|
"loss": 6.4267,
|
|
"mean_token_accuracy": 0.16363779753446578,
|
|
"num_tokens": 12232775.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.469997453689575,
|
|
"epoch": 0.5585689555683785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977730214408352,
|
|
"loss": 6.4055,
|
|
"mean_token_accuracy": 0.15352552086114885,
|
|
"num_tokens": 12245306.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.411099481582641,
|
|
"epoch": 0.5591459896133872,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004977672263487435,
|
|
"loss": 6.3635,
|
|
"mean_token_accuracy": 0.1560710147023201,
|
|
"num_tokens": 12257553.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.45292592048645,
|
|
"epoch": 0.5597230236583959,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497761423763987,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.15596397668123246,
|
|
"num_tokens": 12269626.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.528067350387573,
|
|
"epoch": 0.5603000577034045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977556136867606,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.15139178037643433,
|
|
"num_tokens": 12282180.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.565957403182983,
|
|
"epoch": 0.5608770917484132,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977497961172598,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.15649604499340058,
|
|
"num_tokens": 12296315.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.459849786758423,
|
|
"epoch": 0.5614541257934218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977439710556802,
|
|
"loss": 6.4183,
|
|
"mean_token_accuracy": 0.14864314943552018,
|
|
"num_tokens": 12308800.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.478931283950805,
|
|
"epoch": 0.5620311598384304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977381385022179,
|
|
"loss": 6.4801,
|
|
"mean_token_accuracy": 0.1533154159784317,
|
|
"num_tokens": 12321717.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.566097736358643,
|
|
"epoch": 0.5626081938834391,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004977322984570688,
|
|
"loss": 6.5094,
|
|
"mean_token_accuracy": 0.1451910525560379,
|
|
"num_tokens": 12335446.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.505554676055908,
|
|
"epoch": 0.5631852279284478,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004977264509204296,
|
|
"loss": 6.4127,
|
|
"mean_token_accuracy": 0.15165958628058435,
|
|
"num_tokens": 12348677.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.485540676116943,
|
|
"epoch": 0.5637622619734565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977205958924967,
|
|
"loss": 6.4415,
|
|
"mean_token_accuracy": 0.1551760196685791,
|
|
"num_tokens": 12360934.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.537460088729858,
|
|
"epoch": 0.5643392960184651,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004977147333734673,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.14865117520093918,
|
|
"num_tokens": 12373538.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.429516363143921,
|
|
"epoch": 0.5649163300634737,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977088633635385,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.1513530433177948,
|
|
"num_tokens": 12385291.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.613570261001587,
|
|
"epoch": 0.5654933641084824,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004977029858629076,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.14706155732274057,
|
|
"num_tokens": 12398324.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.503150606155396,
|
|
"epoch": 0.566070398153491,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976971008717726,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.1525312729179859,
|
|
"num_tokens": 12409807.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.515785837173462,
|
|
"epoch": 0.5666474321984997,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976912083903309,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.14461371153593064,
|
|
"num_tokens": 12422658.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.550714159011841,
|
|
"epoch": 0.5672244662435084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976853084187814,
|
|
"loss": 6.4638,
|
|
"mean_token_accuracy": 0.14637623578310013,
|
|
"num_tokens": 12435912.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.453034782409668,
|
|
"epoch": 0.5678015002885171,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976794009573219,
|
|
"loss": 6.4488,
|
|
"mean_token_accuracy": 0.15766249001026153,
|
|
"num_tokens": 12448382.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.508889102935791,
|
|
"epoch": 0.5683785343335257,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004976734860061515,
|
|
"loss": 6.5688,
|
|
"mean_token_accuracy": 0.15048769414424895,
|
|
"num_tokens": 12461355.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.566471338272095,
|
|
"epoch": 0.5689555683785343,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004976675635654688,
|
|
"loss": 6.4012,
|
|
"mean_token_accuracy": 0.15381542593240738,
|
|
"num_tokens": 12473931.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.4354527473449705,
|
|
"epoch": 0.569532602423543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976616336354733,
|
|
"loss": 6.4381,
|
|
"mean_token_accuracy": 0.15482519343495368,
|
|
"num_tokens": 12486130.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.471525001525879,
|
|
"epoch": 0.5701096364685516,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976556962163645,
|
|
"loss": 6.3731,
|
|
"mean_token_accuracy": 0.156865394115448,
|
|
"num_tokens": 12499336.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.539810228347778,
|
|
"epoch": 0.5706866705135603,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004976497513083419,
|
|
"loss": 6.3757,
|
|
"mean_token_accuracy": 0.15898544192314149,
|
|
"num_tokens": 12512875.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.477344799041748,
|
|
"epoch": 0.571263704558569,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004976437989116055,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.15137718468904496,
|
|
"num_tokens": 12524985.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.505421304702759,
|
|
"epoch": 0.5718407386035776,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004976378390263554,
|
|
"loss": 6.4346,
|
|
"mean_token_accuracy": 0.15926533192396164,
|
|
"num_tokens": 12538244.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.559779691696167,
|
|
"epoch": 0.5724177726485863,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976318716527924,
|
|
"loss": 6.4404,
|
|
"mean_token_accuracy": 0.15664353370666503,
|
|
"num_tokens": 12550769.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.451388883590698,
|
|
"epoch": 0.5729948066935949,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976258967911168,
|
|
"loss": 6.465,
|
|
"mean_token_accuracy": 0.1511801674962044,
|
|
"num_tokens": 12563294.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.450545358657837,
|
|
"epoch": 0.5735718407386036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976199144415298,
|
|
"loss": 6.4484,
|
|
"mean_token_accuracy": 0.14877015054225923,
|
|
"num_tokens": 12575857.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.539900922775269,
|
|
"epoch": 0.5741488747836122,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004976139246042325,
|
|
"loss": 6.4198,
|
|
"mean_token_accuracy": 0.15611875653266907,
|
|
"num_tokens": 12589881.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.510217142105103,
|
|
"epoch": 0.5747259088286208,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004976079272794265,
|
|
"loss": 6.4881,
|
|
"mean_token_accuracy": 0.14711457639932632,
|
|
"num_tokens": 12604100.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.591409635543823,
|
|
"epoch": 0.5753029428736296,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976019224673134,
|
|
"loss": 6.5016,
|
|
"mean_token_accuracy": 0.1494516521692276,
|
|
"num_tokens": 12616643.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.485559701919556,
|
|
"epoch": 0.5758799769186382,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004975959101680953,
|
|
"loss": 6.4145,
|
|
"mean_token_accuracy": 0.15998050570487976,
|
|
"num_tokens": 12627676.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.3982460498809814,
|
|
"epoch": 0.5764570109636469,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004975898903819742,
|
|
"loss": 6.3992,
|
|
"mean_token_accuracy": 0.16120668202638627,
|
|
"num_tokens": 12639352.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.444949531555176,
|
|
"epoch": 0.5770340450086555,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975838631091527,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.15658557564020156,
|
|
"num_tokens": 12652102.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.556867361068726,
|
|
"epoch": 0.5776110790536642,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975778283498336,
|
|
"loss": 6.4777,
|
|
"mean_token_accuracy": 0.1522747591137886,
|
|
"num_tokens": 12665084.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.399194192886353,
|
|
"epoch": 0.5781881130986728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975717861042198,
|
|
"loss": 6.3905,
|
|
"mean_token_accuracy": 0.1488622397184372,
|
|
"num_tokens": 12677512.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.519528579711914,
|
|
"epoch": 0.5787651471436814,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004975657363725146,
|
|
"loss": 6.4929,
|
|
"mean_token_accuracy": 0.14468461647629738,
|
|
"num_tokens": 12690488.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.569351863861084,
|
|
"epoch": 0.5793421811886902,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975596791549213,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.15072959661483765,
|
|
"num_tokens": 12703830.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.528122615814209,
|
|
"epoch": 0.5799192152336988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004975536144516437,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.15344501584768294,
|
|
"num_tokens": 12716020.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.51330943107605,
|
|
"epoch": 0.5804962492787075,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000497547542262886,
|
|
"loss": 6.518,
|
|
"mean_token_accuracy": 0.14512748420238494,
|
|
"num_tokens": 12728989.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.550060606002807,
|
|
"epoch": 0.5810732833237161,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004975414625888521,
|
|
"loss": 6.3809,
|
|
"mean_token_accuracy": 0.15464969575405121,
|
|
"num_tokens": 12741090.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.5245343208312985,
|
|
"epoch": 0.5816503173687247,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004975353754297468,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.15102563947439193,
|
|
"num_tokens": 12754176.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.372476387023926,
|
|
"epoch": 0.5822273514137334,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004975292807857745,
|
|
"loss": 6.406,
|
|
"mean_token_accuracy": 0.1529885560274124,
|
|
"num_tokens": 12766149.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.4757085800170895,
|
|
"epoch": 0.582804385458742,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975231786571406,
|
|
"loss": 6.4473,
|
|
"mean_token_accuracy": 0.15353928953409196,
|
|
"num_tokens": 12778337.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.508154201507568,
|
|
"epoch": 0.5833814195037508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975170690440499,
|
|
"loss": 6.3845,
|
|
"mean_token_accuracy": 0.15635424107313156,
|
|
"num_tokens": 12790146.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.451329183578491,
|
|
"epoch": 0.5839584535487594,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975109519467083,
|
|
"loss": 6.3748,
|
|
"mean_token_accuracy": 0.1544017016887665,
|
|
"num_tokens": 12802821.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.4523937702178955,
|
|
"epoch": 0.584535487593768,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004975048273653212,
|
|
"loss": 6.5114,
|
|
"mean_token_accuracy": 0.15367977023124696,
|
|
"num_tokens": 12814409.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.532897138595581,
|
|
"epoch": 0.5851125216387767,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974986953000948,
|
|
"loss": 6.4037,
|
|
"mean_token_accuracy": 0.14837779253721237,
|
|
"num_tokens": 12827398.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.420920324325562,
|
|
"epoch": 0.5856895556837853,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974925557512354,
|
|
"loss": 6.3946,
|
|
"mean_token_accuracy": 0.15595378279685973,
|
|
"num_tokens": 12840378.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.459633493423462,
|
|
"epoch": 0.586266589728794,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004974864087189493,
|
|
"loss": 6.4854,
|
|
"mean_token_accuracy": 0.15719999819993974,
|
|
"num_tokens": 12853493.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.489672040939331,
|
|
"epoch": 0.5868436237738026,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004974802542034434,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.16045349091291428,
|
|
"num_tokens": 12865052.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.51693902015686,
|
|
"epoch": 0.5874206578188114,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004974740922049246,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.14741032123565673,
|
|
"num_tokens": 12878095.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.476896572113037,
|
|
"epoch": 0.58799769186382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974679227236004,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.162299744784832,
|
|
"num_tokens": 12890855.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.500436401367187,
|
|
"epoch": 0.5885747259088286,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974617457596779,
|
|
"loss": 6.4031,
|
|
"mean_token_accuracy": 0.1562817022204399,
|
|
"num_tokens": 12903833.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.537255668640137,
|
|
"epoch": 0.5891517599538373,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974555613133652,
|
|
"loss": 6.5106,
|
|
"mean_token_accuracy": 0.1479603409767151,
|
|
"num_tokens": 12917579.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.4827710628509525,
|
|
"epoch": 0.5897287939988459,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004974493693848702,
|
|
"loss": 6.479,
|
|
"mean_token_accuracy": 0.15590202063322067,
|
|
"num_tokens": 12929718.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.338919973373413,
|
|
"epoch": 0.5903058280438546,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974431699744011,
|
|
"loss": 6.3377,
|
|
"mean_token_accuracy": 0.16054340749979018,
|
|
"num_tokens": 12943031.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.465764427185059,
|
|
"epoch": 0.5908828620888632,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974369630821665,
|
|
"loss": 6.4345,
|
|
"mean_token_accuracy": 0.16000231057405473,
|
|
"num_tokens": 12954843.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.479459381103515,
|
|
"epoch": 0.5914598961338718,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974307487083752,
|
|
"loss": 6.4406,
|
|
"mean_token_accuracy": 0.15593716353178025,
|
|
"num_tokens": 12966915.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.507039642333984,
|
|
"epoch": 0.5920369301788806,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974245268532361,
|
|
"loss": 6.4844,
|
|
"mean_token_accuracy": 0.14569110572338104,
|
|
"num_tokens": 12979941.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.544470405578613,
|
|
"epoch": 0.5926139642238892,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004974182975169585,
|
|
"loss": 6.3857,
|
|
"mean_token_accuracy": 0.15324565023183823,
|
|
"num_tokens": 12992836.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.545553588867188,
|
|
"epoch": 0.5931909982688979,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497412060699752,
|
|
"loss": 6.4179,
|
|
"mean_token_accuracy": 0.1531425304710865,
|
|
"num_tokens": 13005246.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.393571567535401,
|
|
"epoch": 0.5937680323139065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004974058164018263,
|
|
"loss": 6.3902,
|
|
"mean_token_accuracy": 0.15206687152385712,
|
|
"num_tokens": 13016842.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.4142437934875485,
|
|
"epoch": 0.5943450663589152,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973995646233914,
|
|
"loss": 6.3766,
|
|
"mean_token_accuracy": 0.15784988552331924,
|
|
"num_tokens": 13028388.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.508879947662353,
|
|
"epoch": 0.5949221004039238,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973933053646576,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.1518938884139061,
|
|
"num_tokens": 13041895.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.523378658294678,
|
|
"epoch": 0.5954991344489324,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973870386258355,
|
|
"loss": 6.4875,
|
|
"mean_token_accuracy": 0.1547953560948372,
|
|
"num_tokens": 13055984.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.517923307418823,
|
|
"epoch": 0.5960761684939412,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004973807644071357,
|
|
"loss": 6.4272,
|
|
"mean_token_accuracy": 0.15377702489495276,
|
|
"num_tokens": 13068735.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.57601752281189,
|
|
"epoch": 0.5966532025389498,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973744827087695,
|
|
"loss": 6.5136,
|
|
"mean_token_accuracy": 0.1491558223962784,
|
|
"num_tokens": 13081564.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.510840225219726,
|
|
"epoch": 0.5972302365839585,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497368193530948,
|
|
"loss": 6.43,
|
|
"mean_token_accuracy": 0.1526069462299347,
|
|
"num_tokens": 13094146.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.429110145568847,
|
|
"epoch": 0.5978072706289671,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004973618968738828,
|
|
"loss": 6.3644,
|
|
"mean_token_accuracy": 0.15681997686624527,
|
|
"num_tokens": 13106753.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.384876012802124,
|
|
"epoch": 0.5983843046739757,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973555927377856,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.16190443187952042,
|
|
"num_tokens": 13118645.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.50286865234375,
|
|
"epoch": 0.5989613387189844,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973492811228685,
|
|
"loss": 6.4626,
|
|
"mean_token_accuracy": 0.14891703352332114,
|
|
"num_tokens": 13132250.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.502938985824585,
|
|
"epoch": 0.599538372763993,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973429620293438,
|
|
"loss": 6.4612,
|
|
"mean_token_accuracy": 0.14949870407581328,
|
|
"num_tokens": 13145069.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.515492725372314,
|
|
"epoch": 0.6001154068090018,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973366354574239,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.15858462899923326,
|
|
"num_tokens": 13158244.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.51719102859497,
|
|
"epoch": 0.6006924408540104,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973303014073219,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.14795382171869279,
|
|
"num_tokens": 13171810.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.426719427108765,
|
|
"epoch": 0.601269474899019,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973239598792504,
|
|
"loss": 6.3122,
|
|
"mean_token_accuracy": 0.15710260570049286,
|
|
"num_tokens": 13184448.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.503760433197021,
|
|
"epoch": 0.6018465089440277,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973176108734232,
|
|
"loss": 6.4881,
|
|
"mean_token_accuracy": 0.1439894437789917,
|
|
"num_tokens": 13198350.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.521775341033935,
|
|
"epoch": 0.6024235429890363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973112543900535,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.15527199506759642,
|
|
"num_tokens": 13210660.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.409607553482056,
|
|
"epoch": 0.603000577034045,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004973048904293551,
|
|
"loss": 6.3827,
|
|
"mean_token_accuracy": 0.16117679625749587,
|
|
"num_tokens": 13222991.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.459820032119751,
|
|
"epoch": 0.6035776110790536,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004972985189915422,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.14954399913549424,
|
|
"num_tokens": 13237693.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.474009656906128,
|
|
"epoch": 0.6041546451240624,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000497292140076829,
|
|
"loss": 6.4548,
|
|
"mean_token_accuracy": 0.15322939604520797,
|
|
"num_tokens": 13249843.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.510292482376099,
|
|
"epoch": 0.604731679169071,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972857536854301,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.15622295439243317,
|
|
"num_tokens": 13262185.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.454311656951904,
|
|
"epoch": 0.6053087132140796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972793598175603,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.1478947676718235,
|
|
"num_tokens": 13275344.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.513757181167603,
|
|
"epoch": 0.6058857472590883,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972729584734347,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.1522686466574669,
|
|
"num_tokens": 13287741.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.494974374771118,
|
|
"epoch": 0.6064627813040969,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972665496532685,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.15595458894968034,
|
|
"num_tokens": 13299918.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.378756904602051,
|
|
"epoch": 0.6070398153491056,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004972601333572774,
|
|
"loss": 6.3684,
|
|
"mean_token_accuracy": 0.15408076345920563,
|
|
"num_tokens": 13312765.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.469124364852905,
|
|
"epoch": 0.6076168493941142,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972537095856769,
|
|
"loss": 6.3743,
|
|
"mean_token_accuracy": 0.1507202297449112,
|
|
"num_tokens": 13325324.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.516126489639282,
|
|
"epoch": 0.608193883439123,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004972472783386834,
|
|
"loss": 6.4594,
|
|
"mean_token_accuracy": 0.14877294152975082,
|
|
"num_tokens": 13337578.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.530485391616821,
|
|
"epoch": 0.6087709174841316,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004972408396165132,
|
|
"loss": 6.423,
|
|
"mean_token_accuracy": 0.15622132271528244,
|
|
"num_tokens": 13349218.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.458002948760987,
|
|
"epoch": 0.6093479515291402,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972343934193826,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.1541997194290161,
|
|
"num_tokens": 13362221.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.478120613098144,
|
|
"epoch": 0.6099249855741489,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972279397475086,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.15952515602111816,
|
|
"num_tokens": 13374147.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.396870422363281,
|
|
"epoch": 0.6105020196191575,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972214786011083,
|
|
"loss": 6.3315,
|
|
"mean_token_accuracy": 0.15817706137895585,
|
|
"num_tokens": 13386077.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.551906967163086,
|
|
"epoch": 0.6110790536641661,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497215009980399,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.15904004573822023,
|
|
"num_tokens": 13398442.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.448291397094726,
|
|
"epoch": 0.6116560877091748,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000497208533885598,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.1560212790966034,
|
|
"num_tokens": 13411249.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.414372968673706,
|
|
"epoch": 0.6122331217541835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972020503169235,
|
|
"loss": 6.4052,
|
|
"mean_token_accuracy": 0.16007892787456512,
|
|
"num_tokens": 13424518.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.490907001495361,
|
|
"epoch": 0.6128101557991922,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004971955592745934,
|
|
"loss": 6.418,
|
|
"mean_token_accuracy": 0.14899912327528,
|
|
"num_tokens": 13438530.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.42531452178955,
|
|
"epoch": 0.6133871898442008,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497189060758826,
|
|
"loss": 6.3676,
|
|
"mean_token_accuracy": 0.16263744086027146,
|
|
"num_tokens": 13451154.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.432960033416748,
|
|
"epoch": 0.6139642238892095,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049718255476984,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.161380535364151,
|
|
"num_tokens": 13461938.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.436057424545288,
|
|
"epoch": 0.6145412579342181,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971760413078539,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.15706276893615723,
|
|
"num_tokens": 13474423.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.489777135848999,
|
|
"epoch": 0.6151182919792267,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971695203730872,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.16456449776887894,
|
|
"num_tokens": 13486882.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.458373928070069,
|
|
"epoch": 0.6156953260242354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497162991965759,
|
|
"loss": 6.3343,
|
|
"mean_token_accuracy": 0.15441225916147233,
|
|
"num_tokens": 13499692.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.4966339588165285,
|
|
"epoch": 0.6162723600692441,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004971564560860889,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.15078266859054565,
|
|
"num_tokens": 13512995.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.369403266906739,
|
|
"epoch": 0.6168493941142528,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971499127342968,
|
|
"loss": 6.3278,
|
|
"mean_token_accuracy": 0.16098241358995438,
|
|
"num_tokens": 13525804.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.437539720535279,
|
|
"epoch": 0.6174264281592614,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004971433619106027,
|
|
"loss": 6.4364,
|
|
"mean_token_accuracy": 0.1512218251824379,
|
|
"num_tokens": 13537807.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.584434080123901,
|
|
"epoch": 0.61800346220427,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497136803615227,
|
|
"loss": 6.4724,
|
|
"mean_token_accuracy": 0.14654513746500014,
|
|
"num_tokens": 13550765.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.452790403366089,
|
|
"epoch": 0.6185804962492787,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004971302378483902,
|
|
"loss": 6.4246,
|
|
"mean_token_accuracy": 0.1566222384572029,
|
|
"num_tokens": 13565084.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.529478931427002,
|
|
"epoch": 0.6191575302942873,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004971236646103132,
|
|
"loss": 6.4197,
|
|
"mean_token_accuracy": 0.15318245440721512,
|
|
"num_tokens": 13578851.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.477718639373779,
|
|
"epoch": 0.619734564339296,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971170839012171,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.16245864033699037,
|
|
"num_tokens": 13589984.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.382431983947754,
|
|
"epoch": 0.6203115983843047,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004971104957213233,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.15082724690437316,
|
|
"num_tokens": 13602899.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.47854175567627,
|
|
"epoch": 0.6208886324293134,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004971039000708531,
|
|
"loss": 6.5548,
|
|
"mean_token_accuracy": 0.1424169920384884,
|
|
"num_tokens": 13617672.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.5490500926971436,
|
|
"epoch": 0.621465666474322,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004970972969500286,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.15098279267549514,
|
|
"num_tokens": 13630029.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.42647614479065,
|
|
"epoch": 0.6220427005193306,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497090686359072,
|
|
"loss": 6.3839,
|
|
"mean_token_accuracy": 0.15539321005344392,
|
|
"num_tokens": 13643091.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.385086917877198,
|
|
"epoch": 0.6226197345643393,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004970840682982054,
|
|
"loss": 6.2634,
|
|
"mean_token_accuracy": 0.16022852510213853,
|
|
"num_tokens": 13654790.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.455251741409302,
|
|
"epoch": 0.6231967686093479,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004970774427676514,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.1599068224430084,
|
|
"num_tokens": 13667425.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.516546249389648,
|
|
"epoch": 0.6237738026543566,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497070809767633,
|
|
"loss": 6.4386,
|
|
"mean_token_accuracy": 0.15648358017206193,
|
|
"num_tokens": 13680199.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.4648191928863525,
|
|
"epoch": 0.6243508366993653,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970641692983731,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.15207870900630951,
|
|
"num_tokens": 13693613.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.374730634689331,
|
|
"epoch": 0.624927870744374,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970575213600954,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.15325464606285094,
|
|
"num_tokens": 13706809.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.499360609054565,
|
|
"epoch": 0.6255049047893826,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004970508659530231,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.15512218326330185,
|
|
"num_tokens": 13718976.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.463284254074097,
|
|
"epoch": 0.6260819388343912,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970442030773802,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.15274603366851808,
|
|
"num_tokens": 13731037.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.401796483993531,
|
|
"epoch": 0.6266589728793999,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004970375327333909,
|
|
"loss": 6.412,
|
|
"mean_token_accuracy": 0.1536305785179138,
|
|
"num_tokens": 13743816.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.407013082504273,
|
|
"epoch": 0.6272360069244085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004970308549212796,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.15897883772850036,
|
|
"num_tokens": 13757165.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.470421314239502,
|
|
"epoch": 0.6278130409694171,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004970241696412705,
|
|
"loss": 6.3747,
|
|
"mean_token_accuracy": 0.15822548270225525,
|
|
"num_tokens": 13769982.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.47586350440979,
|
|
"epoch": 0.6283900750144259,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497017476893589,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.16209243834018708,
|
|
"num_tokens": 13782922.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.44397201538086,
|
|
"epoch": 0.6289671090594345,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004970107766784598,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.15553117990493776,
|
|
"num_tokens": 13795683.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.577775239944458,
|
|
"epoch": 0.6295441431044432,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004970040689961084,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.15517319813370706,
|
|
"num_tokens": 13808332.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.529779148101807,
|
|
"epoch": 0.6301211771494518,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004969973538467605,
|
|
"loss": 6.4313,
|
|
"mean_token_accuracy": 0.1575072228908539,
|
|
"num_tokens": 13820949.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.391829109191894,
|
|
"epoch": 0.6306982111944605,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004969906312306419,
|
|
"loss": 6.4199,
|
|
"mean_token_accuracy": 0.15567118525505066,
|
|
"num_tokens": 13833623.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.449386215209961,
|
|
"epoch": 0.6312752452394691,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004969839011479786,
|
|
"loss": 6.3437,
|
|
"mean_token_accuracy": 0.16317939907312393,
|
|
"num_tokens": 13844368.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.489554214477539,
|
|
"epoch": 0.6318522792844777,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.000496977163598997,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.16044973731040954,
|
|
"num_tokens": 13857261.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.304276037216186,
|
|
"epoch": 0.6324293133294865,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969704185839239,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.15524207204580306,
|
|
"num_tokens": 13869438.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.527767086029053,
|
|
"epoch": 0.6330063473744951,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004969636661029859,
|
|
"loss": 6.4693,
|
|
"mean_token_accuracy": 0.14667147621512414,
|
|
"num_tokens": 13883353.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.453281211853027,
|
|
"epoch": 0.6335833814195038,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969569061564103,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.16208689510822297,
|
|
"num_tokens": 13896950.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.5273314952850345,
|
|
"epoch": 0.6341604154645124,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004969501387444245,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.15331158488988877,
|
|
"num_tokens": 13910447.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.448615264892578,
|
|
"epoch": 0.634737449509521,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004969433638672559,
|
|
"loss": 6.4131,
|
|
"mean_token_accuracy": 0.1641377866268158,
|
|
"num_tokens": 13922894.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.470922517776489,
|
|
"epoch": 0.6353144835545297,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969365815251325,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.15074554085731506,
|
|
"num_tokens": 13936558.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.49364275932312,
|
|
"epoch": 0.6358915175995383,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969297917182825,
|
|
"loss": 6.3486,
|
|
"mean_token_accuracy": 0.15768291652202607,
|
|
"num_tokens": 13949005.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.509783792495727,
|
|
"epoch": 0.6364685516445471,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969229944469342,
|
|
"loss": 6.4245,
|
|
"mean_token_accuracy": 0.14853326678276063,
|
|
"num_tokens": 13962285.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.48953537940979,
|
|
"epoch": 0.6370455856895557,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969161897113162,
|
|
"loss": 6.4058,
|
|
"mean_token_accuracy": 0.15401887595653535,
|
|
"num_tokens": 13976037.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.460662126541138,
|
|
"epoch": 0.6376226197345644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969093775116574,
|
|
"loss": 6.3599,
|
|
"mean_token_accuracy": 0.15469125062227249,
|
|
"num_tokens": 13989028.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.354991722106933,
|
|
"epoch": 0.638199653779573,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004969025578481869,
|
|
"loss": 6.3485,
|
|
"mean_token_accuracy": 0.15838611572980882,
|
|
"num_tokens": 14001814.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.5595146179199215,
|
|
"epoch": 0.6387766878245816,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000496895730721134,
|
|
"loss": 6.4544,
|
|
"mean_token_accuracy": 0.14454537704586984,
|
|
"num_tokens": 14014305.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.438262844085694,
|
|
"epoch": 0.6393537218695903,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004968888961307286,
|
|
"loss": 6.3267,
|
|
"mean_token_accuracy": 0.16070610731840135,
|
|
"num_tokens": 14027475.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.447474813461303,
|
|
"epoch": 0.6399307559145989,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004968820540772003,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.15843632072210312,
|
|
"num_tokens": 14041031.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.407632684707641,
|
|
"epoch": 0.6405077899596077,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968752045607794,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.15532173216342926,
|
|
"num_tokens": 14054138.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.498112392425537,
|
|
"epoch": 0.6410848240046163,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004968683475816961,
|
|
"loss": 6.3824,
|
|
"mean_token_accuracy": 0.15433506965637206,
|
|
"num_tokens": 14066708.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.413477897644043,
|
|
"epoch": 0.641661858049625,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004968614831401811,
|
|
"loss": 6.4372,
|
|
"mean_token_accuracy": 0.14834733828902244,
|
|
"num_tokens": 14080251.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.533289051055908,
|
|
"epoch": 0.6422388920946336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004968546112364654,
|
|
"loss": 6.4059,
|
|
"mean_token_accuracy": 0.15228572264313697,
|
|
"num_tokens": 14092622.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.488448190689087,
|
|
"epoch": 0.6428159261396422,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049684773187078,
|
|
"loss": 6.4901,
|
|
"mean_token_accuracy": 0.14898357838392257,
|
|
"num_tokens": 14107033.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.364928388595581,
|
|
"epoch": 0.6433929601846509,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968408450433565,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.15701743066310883,
|
|
"num_tokens": 14119264.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.429807901382446,
|
|
"epoch": 0.6439699942296595,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004968339507544263,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.1542530760169029,
|
|
"num_tokens": 14131360.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.443619251251221,
|
|
"epoch": 0.6445470282746683,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004968270490042212,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.1619213879108429,
|
|
"num_tokens": 14143236.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.433837938308716,
|
|
"epoch": 0.6451240623196769,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004968201397929737,
|
|
"loss": 6.4,
|
|
"mean_token_accuracy": 0.1572832927107811,
|
|
"num_tokens": 14156470.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.525268507003784,
|
|
"epoch": 0.6457010963646855,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004968132231209158,
|
|
"loss": 6.4646,
|
|
"mean_token_accuracy": 0.1507378861308098,
|
|
"num_tokens": 14169359.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.43701810836792,
|
|
"epoch": 0.6462781304096942,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968062989882803,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.15128603354096412,
|
|
"num_tokens": 14181980.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.559728527069092,
|
|
"epoch": 0.6468551644547028,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004967993673953003,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.15603036880493165,
|
|
"num_tokens": 14195456.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.483079195022583,
|
|
"epoch": 0.6474321984997115,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967924283422087,
|
|
"loss": 6.3258,
|
|
"mean_token_accuracy": 0.16091519445180893,
|
|
"num_tokens": 14208269.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.397562265396118,
|
|
"epoch": 0.6480092325447201,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000496785481829239,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.15433711111545562,
|
|
"num_tokens": 14221474.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.533019590377807,
|
|
"epoch": 0.6485862665897288,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967785278566245,
|
|
"loss": 6.4061,
|
|
"mean_token_accuracy": 0.1547924056649208,
|
|
"num_tokens": 14234185.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.418440961837769,
|
|
"epoch": 0.6491633006347375,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004967715664245997,
|
|
"loss": 6.3589,
|
|
"mean_token_accuracy": 0.1545765370130539,
|
|
"num_tokens": 14246853.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.416825199127198,
|
|
"epoch": 0.6497403346797461,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967645975333983,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.15569017976522445,
|
|
"num_tokens": 14260047.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.428913116455078,
|
|
"epoch": 0.6503173687247548,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004967576211832548,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.16324738264083863,
|
|
"num_tokens": 14273478.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.456370687484741,
|
|
"epoch": 0.6508944027697634,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967506373744039,
|
|
"loss": 6.401,
|
|
"mean_token_accuracy": 0.15274422019720077,
|
|
"num_tokens": 14286085.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.430538129806519,
|
|
"epoch": 0.651471436814772,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004967436461070805,
|
|
"loss": 6.3692,
|
|
"mean_token_accuracy": 0.1592407152056694,
|
|
"num_tokens": 14299472.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.490675067901611,
|
|
"epoch": 0.6520484708597807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004967366473815196,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.15632698833942413,
|
|
"num_tokens": 14312624.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.445674705505371,
|
|
"epoch": 0.6526255049047894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004967296411979568,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.16287260502576828,
|
|
"num_tokens": 14325418.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.4445984840393065,
|
|
"epoch": 0.6532025389497981,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004967226275566275,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.1629082068800926,
|
|
"num_tokens": 14337360.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.445386791229248,
|
|
"epoch": 0.6537795729948067,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000496715606457768,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.15481363832950593,
|
|
"num_tokens": 14349119.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.4672932624816895,
|
|
"epoch": 0.6543566070398154,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967085779016142,
|
|
"loss": 6.3848,
|
|
"mean_token_accuracy": 0.16024565547704697,
|
|
"num_tokens": 14361760.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.423304557800293,
|
|
"epoch": 0.654933641084824,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967015418884022,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.15302406400442123,
|
|
"num_tokens": 14374725.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.4012918949127195,
|
|
"epoch": 0.6555106751298326,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004966944984183692,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.155929097533226,
|
|
"num_tokens": 14387267.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.516444730758667,
|
|
"epoch": 0.6560877091748413,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004966874474917518,
|
|
"loss": 6.3887,
|
|
"mean_token_accuracy": 0.156803160905838,
|
|
"num_tokens": 14400531.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.489614677429199,
|
|
"epoch": 0.65666474321985,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004966803891087873,
|
|
"loss": 6.4069,
|
|
"mean_token_accuracy": 0.1479627177119255,
|
|
"num_tokens": 14412507.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.422414636611938,
|
|
"epoch": 0.6572417772648587,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000496673323269713,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.1557417944073677,
|
|
"num_tokens": 14424934.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.513529872894287,
|
|
"epoch": 0.6578188113098673,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966662499747666,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.14428578540682793,
|
|
"num_tokens": 14438875.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.384660053253174,
|
|
"epoch": 0.6583958453548759,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004966591692241859,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.1601344585418701,
|
|
"num_tokens": 14451089.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.498195934295654,
|
|
"epoch": 0.6589728793998846,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004966520810182092,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.15660066306591033,
|
|
"num_tokens": 14463557.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.441149425506592,
|
|
"epoch": 0.6595499134448932,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004966449853570749,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.15349343568086624,
|
|
"num_tokens": 14475865.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.5019457817077635,
|
|
"epoch": 0.6601269474899019,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966378822410215,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.1521094784140587,
|
|
"num_tokens": 14487534.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.501988220214844,
|
|
"epoch": 0.6607039815349106,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004966307716702881,
|
|
"loss": 6.3778,
|
|
"mean_token_accuracy": 0.15803005397319794,
|
|
"num_tokens": 14500006.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.485233545303345,
|
|
"epoch": 0.6612810155799193,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966236536451138,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.1492684841156006,
|
|
"num_tokens": 14512844.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.489582204818726,
|
|
"epoch": 0.6618580496249279,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496616528165738,
|
|
"loss": 6.4387,
|
|
"mean_token_accuracy": 0.14985530823469162,
|
|
"num_tokens": 14525555.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.457883834838867,
|
|
"epoch": 0.6624350836699365,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966093952324003,
|
|
"loss": 6.4158,
|
|
"mean_token_accuracy": 0.14997079819440842,
|
|
"num_tokens": 14537861.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.472036552429199,
|
|
"epoch": 0.6630121177149452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004966022548453406,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.1547412559390068,
|
|
"num_tokens": 14550116.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.530148077011108,
|
|
"epoch": 0.6635891517599538,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004965951070047993,
|
|
"loss": 6.3645,
|
|
"mean_token_accuracy": 0.1600572571158409,
|
|
"num_tokens": 14561841.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.504292011260986,
|
|
"epoch": 0.6641661858049625,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965879517110166,
|
|
"loss": 6.4188,
|
|
"mean_token_accuracy": 0.15461863577365875,
|
|
"num_tokens": 14574889.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.3978352546691895,
|
|
"epoch": 0.6647432198499712,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004965807889642333,
|
|
"loss": 6.4055,
|
|
"mean_token_accuracy": 0.16118682324886321,
|
|
"num_tokens": 14587032.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.445254135131836,
|
|
"epoch": 0.6653202538949798,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00049657361876469,
|
|
"loss": 6.3496,
|
|
"mean_token_accuracy": 0.15695588439702987,
|
|
"num_tokens": 14599654.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.441715860366822,
|
|
"epoch": 0.6658972879399885,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004965664411126282,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.1609531193971634,
|
|
"num_tokens": 14611740.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.444937467575073,
|
|
"epoch": 0.6664743219849971,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004965592560082894,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.15895504653453826,
|
|
"num_tokens": 14625038.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.482732677459717,
|
|
"epoch": 0.6670513560300058,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004965520634519149,
|
|
"loss": 6.4483,
|
|
"mean_token_accuracy": 0.1515585035085678,
|
|
"num_tokens": 14638318.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.4918629169464115,
|
|
"epoch": 0.6676283900750144,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004965448634437468,
|
|
"loss": 6.4173,
|
|
"mean_token_accuracy": 0.15017091631889343,
|
|
"num_tokens": 14651519.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.548173141479492,
|
|
"epoch": 0.668205424120023,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004965376559840272,
|
|
"loss": 6.3733,
|
|
"mean_token_accuracy": 0.15527796149253845,
|
|
"num_tokens": 14662994.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.433021783828735,
|
|
"epoch": 0.6687824581650318,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004965304410729986,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.15886851251125336,
|
|
"num_tokens": 14675488.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.427807283401489,
|
|
"epoch": 0.6693594922100404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004965232187109037,
|
|
"loss": 6.2822,
|
|
"mean_token_accuracy": 0.1672770693898201,
|
|
"num_tokens": 14688512.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.499064922332764,
|
|
"epoch": 0.6699365262550491,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004965159888979854,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.15719753950834275,
|
|
"num_tokens": 14700740.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.412437057495117,
|
|
"epoch": 0.6705135603000577,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004965087516344869,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.1540493041276932,
|
|
"num_tokens": 14713769.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.440626096725464,
|
|
"epoch": 0.6710905943450663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965015069206515,
|
|
"loss": 6.2844,
|
|
"mean_token_accuracy": 0.16277436017990113,
|
|
"num_tokens": 14725710.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.488617420196533,
|
|
"epoch": 0.671667628390075,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496494254756723,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.16651962399482728,
|
|
"num_tokens": 14738504.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.411191701889038,
|
|
"epoch": 0.6722446624350836,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964869951429451,
|
|
"loss": 6.3907,
|
|
"mean_token_accuracy": 0.1528874784708023,
|
|
"num_tokens": 14750344.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.4745879650115965,
|
|
"epoch": 0.6728216964800924,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964797280795622,
|
|
"loss": 6.4371,
|
|
"mean_token_accuracy": 0.15475648939609526,
|
|
"num_tokens": 14764316.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.491079187393188,
|
|
"epoch": 0.673398730525101,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004964724535668188,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.154931178689003,
|
|
"num_tokens": 14776404.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.527394390106201,
|
|
"epoch": 0.6739757645701097,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964651716049593,
|
|
"loss": 6.4032,
|
|
"mean_token_accuracy": 0.15441878139972687,
|
|
"num_tokens": 14788843.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.389228677749633,
|
|
"epoch": 0.6745527986151183,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964578821942288,
|
|
"loss": 6.3468,
|
|
"mean_token_accuracy": 0.15969842821359634,
|
|
"num_tokens": 14802662.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.394847726821899,
|
|
"epoch": 0.6751298326601269,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004964505853348724,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.14911102056503295,
|
|
"num_tokens": 14814354.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.425918245315552,
|
|
"epoch": 0.6757068667051356,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004964432810271356,
|
|
"loss": 6.2954,
|
|
"mean_token_accuracy": 0.16615222096443177,
|
|
"num_tokens": 14826404.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.446470594406128,
|
|
"epoch": 0.6762839007501442,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004964359692712641,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.15671302229166031,
|
|
"num_tokens": 14840046.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.457760667800903,
|
|
"epoch": 0.676860934795153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964286500675037,
|
|
"loss": 6.3953,
|
|
"mean_token_accuracy": 0.1482774406671524,
|
|
"num_tokens": 14853566.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.436824560165405,
|
|
"epoch": 0.6774379688401616,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964213234161007,
|
|
"loss": 6.3278,
|
|
"mean_token_accuracy": 0.15916989594697953,
|
|
"num_tokens": 14866538.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.392537069320679,
|
|
"epoch": 0.6780150028851702,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964139893173014,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.16514576077461243,
|
|
"num_tokens": 14879237.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.483046245574951,
|
|
"epoch": 0.6785920369301789,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964066477713525,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.15573488026857377,
|
|
"num_tokens": 14891295.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.415683555603027,
|
|
"epoch": 0.6791690709751875,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004963992987785011,
|
|
"loss": 6.3904,
|
|
"mean_token_accuracy": 0.1575924351811409,
|
|
"num_tokens": 14902927.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.421587514877319,
|
|
"epoch": 0.6797461050201962,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963919423389942,
|
|
"loss": 6.375,
|
|
"mean_token_accuracy": 0.15122182816267013,
|
|
"num_tokens": 14915203.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.392851495742798,
|
|
"epoch": 0.6803231390652048,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963845784530794,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.16648308783769608,
|
|
"num_tokens": 14927428.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.382313442230225,
|
|
"epoch": 0.6809001731102136,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000496377207121004,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.1617804765701294,
|
|
"num_tokens": 14939979.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.505252695083618,
|
|
"epoch": 0.6814772071552222,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004963698283430164,
|
|
"loss": 6.3816,
|
|
"mean_token_accuracy": 0.15156475305557252,
|
|
"num_tokens": 14952292.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.482873964309692,
|
|
"epoch": 0.6820542412002308,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963624421193646,
|
|
"loss": 6.386,
|
|
"mean_token_accuracy": 0.1532788097858429,
|
|
"num_tokens": 14964942.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.450105810165406,
|
|
"epoch": 0.6826312752452395,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496355048450297,
|
|
"loss": 6.4974,
|
|
"mean_token_accuracy": 0.14616498947143555,
|
|
"num_tokens": 14979196.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.507519197463989,
|
|
"epoch": 0.6832083092902481,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004963476473360623,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.1571754828095436,
|
|
"num_tokens": 14991162.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.466042995452881,
|
|
"epoch": 0.6837853433352568,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963402387769094,
|
|
"loss": 6.3804,
|
|
"mean_token_accuracy": 0.1588766470551491,
|
|
"num_tokens": 15003207.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.41431040763855,
|
|
"epoch": 0.6843623773802654,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004963328227730876,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.14741162210702896,
|
|
"num_tokens": 15016633.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.442387247085572,
|
|
"epoch": 0.684939411425274,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004963253993248461,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.1599098488688469,
|
|
"num_tokens": 15029256.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.425724887847901,
|
|
"epoch": 0.6855164454702828,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004963179684324349,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.15923123359680175,
|
|
"num_tokens": 15041162.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.402348136901855,
|
|
"epoch": 0.6860934795152914,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963105300961036,
|
|
"loss": 6.3577,
|
|
"mean_token_accuracy": 0.16127298772335052,
|
|
"num_tokens": 15054122.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.403144645690918,
|
|
"epoch": 0.6866705135603001,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963030843161026,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.15635056793689728,
|
|
"num_tokens": 15066123.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.3505641460418705,
|
|
"epoch": 0.6872475476053087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004962956310926823,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.16309783309698106,
|
|
"num_tokens": 15078192.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.487194633483886,
|
|
"epoch": 0.6878245816503173,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962881704260934,
|
|
"loss": 6.3194,
|
|
"mean_token_accuracy": 0.16090887039899826,
|
|
"num_tokens": 15090227.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.460311222076416,
|
|
"epoch": 0.688401615695326,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004962807023165868,
|
|
"loss": 6.4389,
|
|
"mean_token_accuracy": 0.159395045787096,
|
|
"num_tokens": 15104093.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.396960067749023,
|
|
"epoch": 0.6889786497403346,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004962732267644138,
|
|
"loss": 6.329,
|
|
"mean_token_accuracy": 0.15944764763116837,
|
|
"num_tokens": 15118064.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.463270425796509,
|
|
"epoch": 0.6895556837853434,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004962657437698254,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.1626880243420601,
|
|
"num_tokens": 15131686.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.419650077819824,
|
|
"epoch": 0.690132717830352,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004962582533330739,
|
|
"loss": 6.4456,
|
|
"mean_token_accuracy": 0.1501251846551895,
|
|
"num_tokens": 15143920.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.49657621383667,
|
|
"epoch": 0.6907097518753607,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962507554544109,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.15870121121406555,
|
|
"num_tokens": 15156989.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.5632383823394775,
|
|
"epoch": 0.6912867859203693,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004962432501340886,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.14517625272274018,
|
|
"num_tokens": 15169068.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.417279434204102,
|
|
"epoch": 0.6918638199653779,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004962357373723596,
|
|
"loss": 6.4305,
|
|
"mean_token_accuracy": 0.1551764652132988,
|
|
"num_tokens": 15182081.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.562622547149658,
|
|
"epoch": 0.6924408540103866,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004962282171694763,
|
|
"loss": 6.4065,
|
|
"mean_token_accuracy": 0.1580890581011772,
|
|
"num_tokens": 15194474.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6924408540103866,
|
|
"eval_entropy": 6.400503651743963,
|
|
"eval_loss": 6.432427883148193,
|
|
"eval_mean_token_accuracy": 0.15697687899999432,
|
|
"eval_num_tokens": 15194474.0,
|
|
"eval_runtime": 22.6959,
|
|
"eval_samples_per_second": 1239.697,
|
|
"eval_steps_per_second": 154.962,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.498694944381714,
|
|
"epoch": 0.6930178880553952,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962206895256919,
|
|
"loss": 6.368,
|
|
"mean_token_accuracy": 0.15929650962352754,
|
|
"num_tokens": 15206371.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.367174577713013,
|
|
"epoch": 0.693594922100404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962131544412595,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.15386435389518738,
|
|
"num_tokens": 15218913.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.497800350189209,
|
|
"epoch": 0.6941719561454126,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004962056119164325,
|
|
"loss": 6.3709,
|
|
"mean_token_accuracy": 0.16197654753923416,
|
|
"num_tokens": 15231647.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.4635841846466064,
|
|
"epoch": 0.6947489901904212,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004961980619514646,
|
|
"loss": 6.3708,
|
|
"mean_token_accuracy": 0.15795217901468278,
|
|
"num_tokens": 15243764.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.443425607681275,
|
|
"epoch": 0.6953260242354299,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004961905045466098,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.14838726967573165,
|
|
"num_tokens": 15256165.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.429970169067383,
|
|
"epoch": 0.6959030582804385,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004961829397021222,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.16175810992717743,
|
|
"num_tokens": 15269169.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.467025279998779,
|
|
"epoch": 0.6964800923254472,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004961753674182564,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.1544795885682106,
|
|
"num_tokens": 15281530.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.419221019744873,
|
|
"epoch": 0.6970571263704558,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004961677876952669,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.15590357780456543,
|
|
"num_tokens": 15295578.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.406968784332276,
|
|
"epoch": 0.6976341604154646,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004961602005334087,
|
|
"loss": 6.397,
|
|
"mean_token_accuracy": 0.15791086107492447,
|
|
"num_tokens": 15308258.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.478301000595093,
|
|
"epoch": 0.6982111944604732,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000496152605932937,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.15565335899591445,
|
|
"num_tokens": 15320370.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.512187814712524,
|
|
"epoch": 0.6987882285054818,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004961450038941074,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.1576465040445328,
|
|
"num_tokens": 15332350.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.39268012046814,
|
|
"epoch": 0.6993652625504905,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004961373944171754,
|
|
"loss": 6.3002,
|
|
"mean_token_accuracy": 0.16454465687274933,
|
|
"num_tokens": 15343424.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.427528715133667,
|
|
"epoch": 0.6999422965954991,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004961297775023968,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.1592035174369812,
|
|
"num_tokens": 15356126.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.345870637893677,
|
|
"epoch": 0.7005193306405078,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000496122153150028,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.16224194318056107,
|
|
"num_tokens": 15369253.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.557456541061401,
|
|
"epoch": 0.7010963646855164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961145213603255,
|
|
"loss": 6.4026,
|
|
"mean_token_accuracy": 0.152187579870224,
|
|
"num_tokens": 15382679.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.414884233474732,
|
|
"epoch": 0.7016733987305251,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000496106882133546,
|
|
"loss": 6.3941,
|
|
"mean_token_accuracy": 0.15569975972175598,
|
|
"num_tokens": 15396052.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.4202300071716305,
|
|
"epoch": 0.7022504327755338,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004960992354699463,
|
|
"loss": 6.444,
|
|
"mean_token_accuracy": 0.15025331526994706,
|
|
"num_tokens": 15409249.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.48999605178833,
|
|
"epoch": 0.7028274668205424,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960915813697836,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.15329759567975998,
|
|
"num_tokens": 15421060.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.440291547775269,
|
|
"epoch": 0.7034045008655511,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004960839198333154,
|
|
"loss": 6.3987,
|
|
"mean_token_accuracy": 0.15348696261644362,
|
|
"num_tokens": 15433083.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.496385335922241,
|
|
"epoch": 0.7039815349105597,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004960762508607994,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.16515322625637055,
|
|
"num_tokens": 15446664.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.437723684310913,
|
|
"epoch": 0.7045585689555683,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004960685744524934,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.15098819732666016,
|
|
"num_tokens": 15458609.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.418120431900024,
|
|
"epoch": 0.705135603000577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004960608906086558,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.15668573081493378,
|
|
"num_tokens": 15470091.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.441114664077759,
|
|
"epoch": 0.7057126370455857,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496053199329545,
|
|
"loss": 6.3913,
|
|
"mean_token_accuracy": 0.15550165474414826,
|
|
"num_tokens": 15483557.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.462738084793091,
|
|
"epoch": 0.7062896710905944,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960455006154196,
|
|
"loss": 6.3639,
|
|
"mean_token_accuracy": 0.15281105488538743,
|
|
"num_tokens": 15497437.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.461950254440308,
|
|
"epoch": 0.706866705135603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004960377944665386,
|
|
"loss": 6.3832,
|
|
"mean_token_accuracy": 0.15458154678344727,
|
|
"num_tokens": 15509942.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.415175914764404,
|
|
"epoch": 0.7074437391806117,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004960300808831611,
|
|
"loss": 6.3258,
|
|
"mean_token_accuracy": 0.1606331631541252,
|
|
"num_tokens": 15522866.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.437211227416992,
|
|
"epoch": 0.7080207732256203,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004960223598655467,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.15498406440019608,
|
|
"num_tokens": 15534731.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.390599346160888,
|
|
"epoch": 0.7085978072706289,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000496014631413955,
|
|
"loss": 6.3549,
|
|
"mean_token_accuracy": 0.15641144812107086,
|
|
"num_tokens": 15546401.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.464565753936768,
|
|
"epoch": 0.7091748413156376,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960068955286459,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.1545490711927414,
|
|
"num_tokens": 15559532.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.450887155532837,
|
|
"epoch": 0.7097518753606463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004959991522098797,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.1544230192899704,
|
|
"num_tokens": 15572426.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.5202630996704105,
|
|
"epoch": 0.710328909405655,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004959914014579168,
|
|
"loss": 6.3851,
|
|
"mean_token_accuracy": 0.15095667839050292,
|
|
"num_tokens": 15584422.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.4888464450836185,
|
|
"epoch": 0.7109059434506636,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004959836432730178,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.1545424059033394,
|
|
"num_tokens": 15595538.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.371583795547485,
|
|
"epoch": 0.7114829774956722,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004959758776554438,
|
|
"loss": 6.3184,
|
|
"mean_token_accuracy": 0.15887101888656616,
|
|
"num_tokens": 15608315.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.514468574523926,
|
|
"epoch": 0.7120600115406809,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000495968104605456,
|
|
"loss": 6.4199,
|
|
"mean_token_accuracy": 0.15411719381809236,
|
|
"num_tokens": 15620181.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.394854784011841,
|
|
"epoch": 0.7126370455856895,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004959603241233157,
|
|
"loss": 6.2669,
|
|
"mean_token_accuracy": 0.16061466783285142,
|
|
"num_tokens": 15632100.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.404596328735352,
|
|
"epoch": 0.7132140796306982,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004959525362092846,
|
|
"loss": 6.2783,
|
|
"mean_token_accuracy": 0.1624158054590225,
|
|
"num_tokens": 15644185.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.3875651359558105,
|
|
"epoch": 0.7137911136757069,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004959447408636247,
|
|
"loss": 6.3236,
|
|
"mean_token_accuracy": 0.16416954696178437,
|
|
"num_tokens": 15657761.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.419309377670288,
|
|
"epoch": 0.7143681477207156,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004959369380865983,
|
|
"loss": 6.3595,
|
|
"mean_token_accuracy": 0.15183151364326478,
|
|
"num_tokens": 15671135.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.441372919082641,
|
|
"epoch": 0.7149451817657242,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004959291278784676,
|
|
"loss": 6.3455,
|
|
"mean_token_accuracy": 0.15111906975507736,
|
|
"num_tokens": 15683286.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.3563837051391605,
|
|
"epoch": 0.7155222158107328,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959213102394954,
|
|
"loss": 6.2707,
|
|
"mean_token_accuracy": 0.167560413479805,
|
|
"num_tokens": 15697535.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.3913243293762205,
|
|
"epoch": 0.7160992498557415,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004959134851699449,
|
|
"loss": 6.3598,
|
|
"mean_token_accuracy": 0.15648961514234544,
|
|
"num_tokens": 15708748.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.477129936218262,
|
|
"epoch": 0.7166762839007501,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959056526700788,
|
|
"loss": 6.3456,
|
|
"mean_token_accuracy": 0.15493126660585405,
|
|
"num_tokens": 15721720.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.409880685806274,
|
|
"epoch": 0.7172533179457588,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004958978127401609,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.15915343463420867,
|
|
"num_tokens": 15734854.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.413718938827515,
|
|
"epoch": 0.7178303519907675,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004958899653804548,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.1601460188627243,
|
|
"num_tokens": 15747575.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.381495141983033,
|
|
"epoch": 0.7184073860357761,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004958821105912246,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.16180343478918074,
|
|
"num_tokens": 15760917.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.55801100730896,
|
|
"epoch": 0.7189844200807848,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000495874248372734,
|
|
"loss": 6.4266,
|
|
"mean_token_accuracy": 0.14924235120415688,
|
|
"num_tokens": 15774045.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.491186237335205,
|
|
"epoch": 0.7195614541257934,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000495866378725248,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.15854604691267013,
|
|
"num_tokens": 15786006.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.407785272598266,
|
|
"epoch": 0.7201384881708021,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495858501649031,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.15561899542808533,
|
|
"num_tokens": 15798078.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.3833420753479,
|
|
"epoch": 0.7207155222158107,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000495850617144348,
|
|
"loss": 6.3406,
|
|
"mean_token_accuracy": 0.15743837952613832,
|
|
"num_tokens": 15810281.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.432937860488892,
|
|
"epoch": 0.7212925562608193,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958427252114643,
|
|
"loss": 6.4155,
|
|
"mean_token_accuracy": 0.1525063246488571,
|
|
"num_tokens": 15822593.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.489366436004639,
|
|
"epoch": 0.7218695903058281,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000495834825850645,
|
|
"loss": 6.3534,
|
|
"mean_token_accuracy": 0.15766695141792297,
|
|
"num_tokens": 15835181.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.476584815979004,
|
|
"epoch": 0.7224466243508367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004958269190621562,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.1545557916164398,
|
|
"num_tokens": 15847679.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.45306282043457,
|
|
"epoch": 0.7230236583958454,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004958190048462637,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.15713143199682236,
|
|
"num_tokens": 15860209.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.485035228729248,
|
|
"epoch": 0.723600692440854,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004958110832032336,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.1563394472002983,
|
|
"num_tokens": 15873165.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.390137529373169,
|
|
"epoch": 0.7241777264858626,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958031541333322,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.15398206412792206,
|
|
"num_tokens": 15885201.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.590787267684936,
|
|
"epoch": 0.7247547605308713,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004957952176368267,
|
|
"loss": 6.4638,
|
|
"mean_token_accuracy": 0.1497330904006958,
|
|
"num_tokens": 15899071.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.381853342056274,
|
|
"epoch": 0.7253317945758799,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004957872737139836,
|
|
"loss": 6.3386,
|
|
"mean_token_accuracy": 0.15825416520237923,
|
|
"num_tokens": 15912274.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.435012531280518,
|
|
"epoch": 0.7259088286208887,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957793223650702,
|
|
"loss": 6.3326,
|
|
"mean_token_accuracy": 0.16138885617256166,
|
|
"num_tokens": 15925302.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.3799999237060545,
|
|
"epoch": 0.7264858626658973,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000495771363590354,
|
|
"loss": 6.392,
|
|
"mean_token_accuracy": 0.1516269102692604,
|
|
"num_tokens": 15938226.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.394499444961548,
|
|
"epoch": 0.727062896710906,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004957633973901027,
|
|
"loss": 6.384,
|
|
"mean_token_accuracy": 0.15402197688817978,
|
|
"num_tokens": 15951136.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.564555644989014,
|
|
"epoch": 0.7276399307559146,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004957554237645841,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.15522871762514115,
|
|
"num_tokens": 15962820.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.393157958984375,
|
|
"epoch": 0.7282169648009232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004957474427140665,
|
|
"loss": 6.3002,
|
|
"mean_token_accuracy": 0.1554463192820549,
|
|
"num_tokens": 15974871.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.330068969726563,
|
|
"epoch": 0.7287939988459319,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004957394542388182,
|
|
"loss": 6.2902,
|
|
"mean_token_accuracy": 0.1576317049562931,
|
|
"num_tokens": 15986916.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.503025722503662,
|
|
"epoch": 0.7293710328909405,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957314583391082,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.1535441353917122,
|
|
"num_tokens": 15999735.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.462880992889405,
|
|
"epoch": 0.7299480669359493,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957234550152052,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.15937893241643905,
|
|
"num_tokens": 16013137.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.423413181304932,
|
|
"epoch": 0.7305251009809579,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957154442673784,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.15815951824188232,
|
|
"num_tokens": 16026750.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.467150354385376,
|
|
"epoch": 0.7311021350259665,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004957074260958972,
|
|
"loss": 6.44,
|
|
"mean_token_accuracy": 0.1503904193639755,
|
|
"num_tokens": 16039028.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.422294855117798,
|
|
"epoch": 0.7316791690709752,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004956994005010315,
|
|
"loss": 6.3013,
|
|
"mean_token_accuracy": 0.16040119528770447,
|
|
"num_tokens": 16051349.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.459820508956909,
|
|
"epoch": 0.7322562031159838,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000495691367483051,
|
|
"loss": 6.3379,
|
|
"mean_token_accuracy": 0.15461637526750566,
|
|
"num_tokens": 16064015.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.490715360641479,
|
|
"epoch": 0.7328332371609925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004956833270422259,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.15606531947851182,
|
|
"num_tokens": 16075571.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.381386137008667,
|
|
"epoch": 0.7334102712060011,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004956752791788269,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.16088762283325195,
|
|
"num_tokens": 16088176.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.450045108795166,
|
|
"epoch": 0.7339873052510099,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004956672238931244,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.15093077719211578,
|
|
"num_tokens": 16099933.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.377976322174073,
|
|
"epoch": 0.7345643392960185,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004956591611853894,
|
|
"loss": 6.2235,
|
|
"mean_token_accuracy": 0.16211253106594087,
|
|
"num_tokens": 16113200.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.424292087554932,
|
|
"epoch": 0.7351413733410271,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004956510910558931,
|
|
"loss": 6.3801,
|
|
"mean_token_accuracy": 0.16113436222076416,
|
|
"num_tokens": 16125532.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.452923822402954,
|
|
"epoch": 0.7357184073860358,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004956430135049071,
|
|
"loss": 6.3211,
|
|
"mean_token_accuracy": 0.15369930267333984,
|
|
"num_tokens": 16137197.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.468174600601197,
|
|
"epoch": 0.7362954414310444,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004956349285327028,
|
|
"loss": 6.387,
|
|
"mean_token_accuracy": 0.16085880845785142,
|
|
"num_tokens": 16150481.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.512467575073242,
|
|
"epoch": 0.7368724754760531,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004956268361395523,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.16043339669704437,
|
|
"num_tokens": 16162395.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.474280881881714,
|
|
"epoch": 0.7374495095210617,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004956187363257278,
|
|
"loss": 6.3575,
|
|
"mean_token_accuracy": 0.15275195389986038,
|
|
"num_tokens": 16174550.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.465876197814941,
|
|
"epoch": 0.7380265435660704,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004956106290915017,
|
|
"loss": 6.3673,
|
|
"mean_token_accuracy": 0.1536040261387825,
|
|
"num_tokens": 16187571.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.422832822799682,
|
|
"epoch": 0.7386035776110791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004956025144371467,
|
|
"loss": 6.3985,
|
|
"mean_token_accuracy": 0.15287847071886063,
|
|
"num_tokens": 16199684.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.385442638397217,
|
|
"epoch": 0.7391806116560877,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004955943923629356,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.1548342451453209,
|
|
"num_tokens": 16211935.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.44033145904541,
|
|
"epoch": 0.7397576457010964,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004955862628691417,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.1508117288351059,
|
|
"num_tokens": 16224346.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.487747716903686,
|
|
"epoch": 0.740334679746105,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004955781259560386,
|
|
"loss": 6.3897,
|
|
"mean_token_accuracy": 0.14921767711639405,
|
|
"num_tokens": 16238137.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.391067790985107,
|
|
"epoch": 0.7409117137911136,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004955699816238995,
|
|
"loss": 6.3537,
|
|
"mean_token_accuracy": 0.15329435765743255,
|
|
"num_tokens": 16250777.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.545683860778809,
|
|
"epoch": 0.7414887478361223,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004955618298729988,
|
|
"loss": 6.365,
|
|
"mean_token_accuracy": 0.15731996297836304,
|
|
"num_tokens": 16262440.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.4182055473327635,
|
|
"epoch": 0.742065781881131,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955536707036105,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.15865564495325088,
|
|
"num_tokens": 16275227.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.390710258483887,
|
|
"epoch": 0.7426428159261397,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495545504116009,
|
|
"loss": 6.3697,
|
|
"mean_token_accuracy": 0.16148028522729874,
|
|
"num_tokens": 16287246.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.4247143268585205,
|
|
"epoch": 0.7432198499711483,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004955373301104691,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.16333142668008804,
|
|
"num_tokens": 16298779.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.32188081741333,
|
|
"epoch": 0.743796884016157,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004955291486872657,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.16090297400951387,
|
|
"num_tokens": 16310965.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.425542116165161,
|
|
"epoch": 0.7443739180611656,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004955209598466738,
|
|
"loss": 6.2903,
|
|
"mean_token_accuracy": 0.15480603873729706,
|
|
"num_tokens": 16324025.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.422914981842041,
|
|
"epoch": 0.7449509521061742,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000495512763588969,
|
|
"loss": 6.3311,
|
|
"mean_token_accuracy": 0.15080109387636184,
|
|
"num_tokens": 16336152.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.359565687179566,
|
|
"epoch": 0.7455279861511829,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004955045599144269,
|
|
"loss": 6.3426,
|
|
"mean_token_accuracy": 0.15447487831115722,
|
|
"num_tokens": 16349118.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.373418140411377,
|
|
"epoch": 0.7461050201961916,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004954963488233235,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.15982365757226943,
|
|
"num_tokens": 16362986.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.465278196334839,
|
|
"epoch": 0.7466820542412003,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000495488130315935,
|
|
"loss": 6.4488,
|
|
"mean_token_accuracy": 0.14422052949666977,
|
|
"num_tokens": 16376384.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.436511468887329,
|
|
"epoch": 0.7472590882862089,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004954799043925377,
|
|
"loss": 6.2663,
|
|
"mean_token_accuracy": 0.15960704237222673,
|
|
"num_tokens": 16388137.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.442381572723389,
|
|
"epoch": 0.7478361223312175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004954716710534082,
|
|
"loss": 6.3868,
|
|
"mean_token_accuracy": 0.15023239105939865,
|
|
"num_tokens": 16400037.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.4429028034210205,
|
|
"epoch": 0.7484131563762262,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004954634302988237,
|
|
"loss": 6.3091,
|
|
"mean_token_accuracy": 0.15836434438824654,
|
|
"num_tokens": 16412065.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.423034954071045,
|
|
"epoch": 0.7489901904212348,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954551821290612,
|
|
"loss": 6.3568,
|
|
"mean_token_accuracy": 0.15571586638689042,
|
|
"num_tokens": 16424345.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.433213615417481,
|
|
"epoch": 0.7495672244662435,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004954469265443981,
|
|
"loss": 6.4097,
|
|
"mean_token_accuracy": 0.1566193573176861,
|
|
"num_tokens": 16436423.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.387920618057251,
|
|
"epoch": 0.7501442585112522,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004954386635451123,
|
|
"loss": 6.3036,
|
|
"mean_token_accuracy": 0.15891094803810119,
|
|
"num_tokens": 16449496.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.435271167755127,
|
|
"epoch": 0.7507212925562609,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004954303931314814,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.15708634853363038,
|
|
"num_tokens": 16462193.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.427425193786621,
|
|
"epoch": 0.7512983266012695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004954221153037837,
|
|
"loss": 6.3555,
|
|
"mean_token_accuracy": 0.15513187199831008,
|
|
"num_tokens": 16474470.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.497897005081176,
|
|
"epoch": 0.7518753606462781,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004954138300622978,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.15803459137678147,
|
|
"num_tokens": 16487231.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.431686544418335,
|
|
"epoch": 0.7524523946912868,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495405537407302,
|
|
"loss": 6.4133,
|
|
"mean_token_accuracy": 0.1513650543987751,
|
|
"num_tokens": 16500822.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.419403791427612,
|
|
"epoch": 0.7530294287362954,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004953972373390755,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.1541321247816086,
|
|
"num_tokens": 16514529.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.402029132843017,
|
|
"epoch": 0.753606462781304,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004953889298578975,
|
|
"loss": 6.3215,
|
|
"mean_token_accuracy": 0.151659794151783,
|
|
"num_tokens": 16527281.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.446967220306396,
|
|
"epoch": 0.7541834968263128,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004953806149640473,
|
|
"loss": 6.3285,
|
|
"mean_token_accuracy": 0.15949189513921738,
|
|
"num_tokens": 16539763.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.376011753082276,
|
|
"epoch": 0.7547605308713214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953722926578045,
|
|
"loss": 6.3066,
|
|
"mean_token_accuracy": 0.16653935611248016,
|
|
"num_tokens": 16552197.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.45217113494873,
|
|
"epoch": 0.7553375649163301,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004953639629394492,
|
|
"loss": 6.3595,
|
|
"mean_token_accuracy": 0.15816257297992706,
|
|
"num_tokens": 16563988.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.346515941619873,
|
|
"epoch": 0.7559145989613387,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953556258092613,
|
|
"loss": 6.354,
|
|
"mean_token_accuracy": 0.152614526450634,
|
|
"num_tokens": 16576982.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.500877237319946,
|
|
"epoch": 0.7564916330063474,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953472812675216,
|
|
"loss": 6.3918,
|
|
"mean_token_accuracy": 0.15306739658117294,
|
|
"num_tokens": 16590268.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.4272643566131595,
|
|
"epoch": 0.757068667051356,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004953389293145104,
|
|
"loss": 6.2367,
|
|
"mean_token_accuracy": 0.16499679684638976,
|
|
"num_tokens": 16602599.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.439320850372314,
|
|
"epoch": 0.7576457010963646,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004953305699505088,
|
|
"loss": 6.336,
|
|
"mean_token_accuracy": 0.15458009764552116,
|
|
"num_tokens": 16614278.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.435625171661377,
|
|
"epoch": 0.7582227351413734,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004953222031757979,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.15230781883001326,
|
|
"num_tokens": 16626810.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.333204841613769,
|
|
"epoch": 0.758799769186382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004953138289906592,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.15872435569763182,
|
|
"num_tokens": 16639134.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.464828538894653,
|
|
"epoch": 0.7593768032313907,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004953054473953742,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.15388649702072144,
|
|
"num_tokens": 16652724.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.3356160640716555,
|
|
"epoch": 0.7599538372763993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004952970583902251,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.15653215497732162,
|
|
"num_tokens": 16666045.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.404564905166626,
|
|
"epoch": 0.760530871321408,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004952886619754937,
|
|
"loss": 6.4156,
|
|
"mean_token_accuracy": 0.14934709966182708,
|
|
"num_tokens": 16678422.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.406267356872559,
|
|
"epoch": 0.7611079053664166,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004952802581514625,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.15902172029018402,
|
|
"num_tokens": 16690243.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.393883800506591,
|
|
"epoch": 0.7616849394114252,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004952718469184144,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.16410621106624604,
|
|
"num_tokens": 16702418.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.468479824066162,
|
|
"epoch": 0.762261973456434,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004952634282766322,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.15294192880392074,
|
|
"num_tokens": 16713974.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.432626152038575,
|
|
"epoch": 0.7628390075014426,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004952550022263988,
|
|
"loss": 6.2699,
|
|
"mean_token_accuracy": 0.1547722727060318,
|
|
"num_tokens": 16726518.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.352759170532226,
|
|
"epoch": 0.7634160415464513,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952465687679979,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.1620583415031433,
|
|
"num_tokens": 16738701.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.434079885482788,
|
|
"epoch": 0.7639930755914599,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000495238127901713,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.14946923404932022,
|
|
"num_tokens": 16751251.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.453442096710205,
|
|
"epoch": 0.7645701096364685,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004952296796278282,
|
|
"loss": 6.3561,
|
|
"mean_token_accuracy": 0.15859053581953048,
|
|
"num_tokens": 16764233.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.302823925018311,
|
|
"epoch": 0.7651471436814772,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952212239466274,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.16784807592630385,
|
|
"num_tokens": 16778408.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.466341161727906,
|
|
"epoch": 0.7657241777264858,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004952127608583953,
|
|
"loss": 6.3576,
|
|
"mean_token_accuracy": 0.1531306877732277,
|
|
"num_tokens": 16789863.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.465719747543335,
|
|
"epoch": 0.7663012117714946,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004952042903634162,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.16282862573862075,
|
|
"num_tokens": 16804448.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.363318300247192,
|
|
"epoch": 0.7668782458165032,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004951958124619752,
|
|
"loss": 6.3713,
|
|
"mean_token_accuracy": 0.15907371491193772,
|
|
"num_tokens": 16817922.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.424112319946289,
|
|
"epoch": 0.7674552798615119,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951873271543573,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.16005789488554,
|
|
"num_tokens": 16830322.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.532310724258423,
|
|
"epoch": 0.7680323139065205,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004951788344408483,
|
|
"loss": 6.3789,
|
|
"mean_token_accuracy": 0.1579961434006691,
|
|
"num_tokens": 16843489.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.482181167602539,
|
|
"epoch": 0.7686093479515291,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004951703343217335,
|
|
"loss": 6.3652,
|
|
"mean_token_accuracy": 0.1490263119339943,
|
|
"num_tokens": 16855256.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.410966539382935,
|
|
"epoch": 0.7691863819965378,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004951618267972987,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.15816780030727387,
|
|
"num_tokens": 16869927.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.371284675598145,
|
|
"epoch": 0.7697634160415464,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951533118678304,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.16636443585157396,
|
|
"num_tokens": 16882095.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.5100563049316404,
|
|
"epoch": 0.7703404500865552,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004951447895336147,
|
|
"loss": 6.4317,
|
|
"mean_token_accuracy": 0.15491466969251633,
|
|
"num_tokens": 16893338.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.3982367515563965,
|
|
"epoch": 0.7709174841315638,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004951362597949384,
|
|
"loss": 6.3991,
|
|
"mean_token_accuracy": 0.15819637775421141,
|
|
"num_tokens": 16907138.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.452460479736328,
|
|
"epoch": 0.7714945181765724,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004951277226520883,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.15423502773046494,
|
|
"num_tokens": 16919756.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.4641800880432125,
|
|
"epoch": 0.7720715522215811,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004951191781053517,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.16414030492305756,
|
|
"num_tokens": 16932059.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.405013608932495,
|
|
"epoch": 0.7726485862665897,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004951106261550157,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.15656148940324782,
|
|
"num_tokens": 16944777.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.428842639923095,
|
|
"epoch": 0.7732256203115984,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004951020668013683,
|
|
"loss": 6.3287,
|
|
"mean_token_accuracy": 0.15988122075796127,
|
|
"num_tokens": 16957111.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.433229970932007,
|
|
"epoch": 0.773802654356607,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004950935000446972,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.14823095202445985,
|
|
"num_tokens": 16968663.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.4144176006317135,
|
|
"epoch": 0.7743796884016156,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950849258852905,
|
|
"loss": 6.3352,
|
|
"mean_token_accuracy": 0.1517917647957802,
|
|
"num_tokens": 16980668.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.46686315536499,
|
|
"epoch": 0.7749567224466244,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004950763443234366,
|
|
"loss": 6.362,
|
|
"mean_token_accuracy": 0.16094649136066436,
|
|
"num_tokens": 16993537.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.4711127281188965,
|
|
"epoch": 0.775533756491633,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004950677553594243,
|
|
"loss": 6.3256,
|
|
"mean_token_accuracy": 0.15494734719395636,
|
|
"num_tokens": 17006268.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.444059276580811,
|
|
"epoch": 0.7761107905366417,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004950591589935422,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.15666031688451768,
|
|
"num_tokens": 17018643.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.418145561218262,
|
|
"epoch": 0.7766878245816503,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004950505552260798,
|
|
"loss": 6.3034,
|
|
"mean_token_accuracy": 0.16328714042901993,
|
|
"num_tokens": 17030670.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.476660203933716,
|
|
"epoch": 0.777264858626659,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004950419440573261,
|
|
"loss": 6.3197,
|
|
"mean_token_accuracy": 0.15912694185972215,
|
|
"num_tokens": 17042617.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.406995248794556,
|
|
"epoch": 0.7778418926716676,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000495033325487571,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.15629192739725112,
|
|
"num_tokens": 17055217.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.397409391403198,
|
|
"epoch": 0.7784189267166762,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004950246995171042,
|
|
"loss": 6.2153,
|
|
"mean_token_accuracy": 0.1760856807231903,
|
|
"num_tokens": 17068614.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.403274583816528,
|
|
"epoch": 0.778995960761685,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000495016066146216,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.1673291563987732,
|
|
"num_tokens": 17079892.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.386370849609375,
|
|
"epoch": 0.7795729948066936,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004950074253751968,
|
|
"loss": 6.351,
|
|
"mean_token_accuracy": 0.15970607101917267,
|
|
"num_tokens": 17092113.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.390835618972778,
|
|
"epoch": 0.7801500288517023,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000494998777204337,
|
|
"loss": 6.3212,
|
|
"mean_token_accuracy": 0.1628754422068596,
|
|
"num_tokens": 17103387.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.480059051513672,
|
|
"epoch": 0.7807270628967109,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004949901216339276,
|
|
"loss": 6.3738,
|
|
"mean_token_accuracy": 0.15862331688404083,
|
|
"num_tokens": 17116008.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.376413249969483,
|
|
"epoch": 0.7813040969417195,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004949814586642598,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.16962072998285294,
|
|
"num_tokens": 17129224.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.316375637054444,
|
|
"epoch": 0.7818811309867282,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000494972788295625,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.15894538313150405,
|
|
"num_tokens": 17141357.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.3543017387390135,
|
|
"epoch": 0.7824581650317368,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004949641105283144,
|
|
"loss": 6.2748,
|
|
"mean_token_accuracy": 0.15785481184720992,
|
|
"num_tokens": 17153672.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.419472122192383,
|
|
"epoch": 0.7830351990767456,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004949554253626205,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.1508081555366516,
|
|
"num_tokens": 17168429.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.4885454177856445,
|
|
"epoch": 0.7836122331217542,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949467327988351,
|
|
"loss": 6.3155,
|
|
"mean_token_accuracy": 0.15907162874937059,
|
|
"num_tokens": 17181000.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.396276998519897,
|
|
"epoch": 0.7841892671667628,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004949380328372505,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.15487978011369705,
|
|
"num_tokens": 17193984.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.482124853134155,
|
|
"epoch": 0.7847663012117715,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004949293254781595,
|
|
"loss": 6.327,
|
|
"mean_token_accuracy": 0.15890616029500962,
|
|
"num_tokens": 17207289.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.413140916824341,
|
|
"epoch": 0.7853433352567801,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004949206107218547,
|
|
"loss": 6.3719,
|
|
"mean_token_accuracy": 0.15868546366691588,
|
|
"num_tokens": 17220785.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.459430408477783,
|
|
"epoch": 0.7859203693017888,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004949118885686296,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.1554628610610962,
|
|
"num_tokens": 17233475.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.440314626693725,
|
|
"epoch": 0.7864974033467974,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004949031590187774,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.1579444646835327,
|
|
"num_tokens": 17246652.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.4201226234436035,
|
|
"epoch": 0.7870744373918062,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004948944220725915,
|
|
"loss": 6.3246,
|
|
"mean_token_accuracy": 0.158696049451828,
|
|
"num_tokens": 17259966.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.3556853294372555,
|
|
"epoch": 0.7876514714368148,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000494885677730366,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.16671997755765916,
|
|
"num_tokens": 17272556.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.431224250793457,
|
|
"epoch": 0.7882285054818234,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000494876925992395,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.15880678445100785,
|
|
"num_tokens": 17285960.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.45187816619873,
|
|
"epoch": 0.7888055395268321,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004948681668589728,
|
|
"loss": 6.4111,
|
|
"mean_token_accuracy": 0.14944198802113534,
|
|
"num_tokens": 17299743.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.4086791515350345,
|
|
"epoch": 0.7893825735718407,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494859400330394,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.15799426585435866,
|
|
"num_tokens": 17312317.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.4271081447601315,
|
|
"epoch": 0.7899596076168494,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004948506264069535,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.15904499739408492,
|
|
"num_tokens": 17326204.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.375916767120361,
|
|
"epoch": 0.790536641661858,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004948418450889464,
|
|
"loss": 6.2957,
|
|
"mean_token_accuracy": 0.1635165348649025,
|
|
"num_tokens": 17338362.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.390348434448242,
|
|
"epoch": 0.7911136757068667,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000494833056376668,
|
|
"loss": 6.3198,
|
|
"mean_token_accuracy": 0.16242424845695497,
|
|
"num_tokens": 17350713.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.476944398880005,
|
|
"epoch": 0.7916907097518754,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004948242602704139,
|
|
"loss": 6.3484,
|
|
"mean_token_accuracy": 0.14923545345664024,
|
|
"num_tokens": 17364055.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.442521095275879,
|
|
"epoch": 0.792267743796884,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004948154567704801,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.161513988673687,
|
|
"num_tokens": 17377940.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.425199937820435,
|
|
"epoch": 0.7928447778418927,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004948066458771625,
|
|
"loss": 6.3176,
|
|
"mean_token_accuracy": 0.15831714868545532,
|
|
"num_tokens": 17390348.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.433390998840332,
|
|
"epoch": 0.7934218118869013,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004947978275907577,
|
|
"loss": 6.319,
|
|
"mean_token_accuracy": 0.15604161992669105,
|
|
"num_tokens": 17403406.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.44692759513855,
|
|
"epoch": 0.79399884593191,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000494789001911562,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.15025489330291747,
|
|
"num_tokens": 17415306.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.500966596603393,
|
|
"epoch": 0.7945758799769186,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004947801688398725,
|
|
"loss": 6.3779,
|
|
"mean_token_accuracy": 0.15381309092044831,
|
|
"num_tokens": 17427901.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.417627954483033,
|
|
"epoch": 0.7951529140219273,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004947713283759862,
|
|
"loss": 6.3172,
|
|
"mean_token_accuracy": 0.15818158090114592,
|
|
"num_tokens": 17439812.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.404314374923706,
|
|
"epoch": 0.795729948066936,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004947624805202003,
|
|
"loss": 6.432,
|
|
"mean_token_accuracy": 0.15916587486863137,
|
|
"num_tokens": 17453317.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.379020404815674,
|
|
"epoch": 0.7963069821119446,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004947536252728126,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.15128010660409927,
|
|
"num_tokens": 17465563.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.4297808647155765,
|
|
"epoch": 0.7968840161569533,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004947447626341209,
|
|
"loss": 6.366,
|
|
"mean_token_accuracy": 0.15720113217830659,
|
|
"num_tokens": 17477672.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.426624536514282,
|
|
"epoch": 0.7974610502019619,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004947358926044232,
|
|
"loss": 6.3237,
|
|
"mean_token_accuracy": 0.15934155583381654,
|
|
"num_tokens": 17489061.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.392905282974243,
|
|
"epoch": 0.7980380842469705,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004947270151840179,
|
|
"loss": 6.371,
|
|
"mean_token_accuracy": 0.15421160608530043,
|
|
"num_tokens": 17501734.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.442747926712036,
|
|
"epoch": 0.7986151182919792,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004947181303732038,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.15750008672475815,
|
|
"num_tokens": 17514387.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.403343772888183,
|
|
"epoch": 0.7991921523369879,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004947092381722793,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.1647616818547249,
|
|
"num_tokens": 17526483.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.44573745727539,
|
|
"epoch": 0.7997691863819966,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004947003385815438,
|
|
"loss": 6.307,
|
|
"mean_token_accuracy": 0.16297112554311752,
|
|
"num_tokens": 17539809.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.416499471664428,
|
|
"epoch": 0.8003462204270052,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004946914316012964,
|
|
"loss": 6.3167,
|
|
"mean_token_accuracy": 0.15640088468790053,
|
|
"num_tokens": 17552973.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.429599618911743,
|
|
"epoch": 0.8009232544720138,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000494682517231837,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.16080797612667083,
|
|
"num_tokens": 17567803.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.481288766860962,
|
|
"epoch": 0.8015002885170225,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004946735954734652,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.156865856051445,
|
|
"num_tokens": 17579718.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.400873327255249,
|
|
"epoch": 0.8020773225620311,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004946646663264811,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.15859004408121108,
|
|
"num_tokens": 17592384.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.439334154129028,
|
|
"epoch": 0.8026543566070398,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004946557297911852,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.16009974032640456,
|
|
"num_tokens": 17604292.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.35125412940979,
|
|
"epoch": 0.8032313906520485,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004946467858678777,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.16352516561746597,
|
|
"num_tokens": 17616638.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.439220523834228,
|
|
"epoch": 0.8038084246970572,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004946378345568597,
|
|
"loss": 6.3572,
|
|
"mean_token_accuracy": 0.14690545722842216,
|
|
"num_tokens": 17630672.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.457352066040039,
|
|
"epoch": 0.8043854587420658,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004946288758584324,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.15353938937187195,
|
|
"num_tokens": 17644215.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.430181646347046,
|
|
"epoch": 0.8049624927870744,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004946199097728968,
|
|
"loss": 6.4047,
|
|
"mean_token_accuracy": 0.15424128770828247,
|
|
"num_tokens": 17655982.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.427625846862793,
|
|
"epoch": 0.8055395268320831,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004946109363005548,
|
|
"loss": 6.3272,
|
|
"mean_token_accuracy": 0.15317181050777434,
|
|
"num_tokens": 17668059.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.449534893035889,
|
|
"epoch": 0.8061165608770917,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000494601955441708,
|
|
"loss": 6.3512,
|
|
"mean_token_accuracy": 0.1613871321082115,
|
|
"num_tokens": 17680924.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.417742967605591,
|
|
"epoch": 0.8066935949221004,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004945929671966585,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.15113742798566818,
|
|
"num_tokens": 17693381.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.323920249938965,
|
|
"epoch": 0.8072706289671091,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004945839715657085,
|
|
"loss": 6.2573,
|
|
"mean_token_accuracy": 0.1607775092124939,
|
|
"num_tokens": 17705900.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.417225408554077,
|
|
"epoch": 0.8078476630121177,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004945749685491607,
|
|
"loss": 6.2688,
|
|
"mean_token_accuracy": 0.16660031527280808,
|
|
"num_tokens": 17719139.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.399656534194946,
|
|
"epoch": 0.8084246970571264,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004945659581473181,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.1602562978863716,
|
|
"num_tokens": 17734312.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.474909067153931,
|
|
"epoch": 0.809001731102135,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004945569403604833,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.1548770174384117,
|
|
"num_tokens": 17746137.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.39998688697815,
|
|
"epoch": 0.8095787651471437,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004945479151889601,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.1639669805765152,
|
|
"num_tokens": 17758879.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.332425308227539,
|
|
"epoch": 0.8101557991921523,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004945388826330517,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.16598912477493286,
|
|
"num_tokens": 17770820.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.469837856292725,
|
|
"epoch": 0.8107328332371609,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004945298426930621,
|
|
"loss": 6.3626,
|
|
"mean_token_accuracy": 0.15875112563371657,
|
|
"num_tokens": 17783495.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.473739576339722,
|
|
"epoch": 0.8113098672821697,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004945207953692952,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.15288871824741362,
|
|
"num_tokens": 17795780.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.462626647949219,
|
|
"epoch": 0.8118869013271783,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004945117406620556,
|
|
"loss": 6.3471,
|
|
"mean_token_accuracy": 0.15740556567907332,
|
|
"num_tokens": 17809684.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.404884290695191,
|
|
"epoch": 0.812463935372187,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004945026785716474,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.15713463425636293,
|
|
"num_tokens": 17822719.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.485169458389282,
|
|
"epoch": 0.8130409694171956,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004944936090983757,
|
|
"loss": 6.3756,
|
|
"mean_token_accuracy": 0.15452174842357635,
|
|
"num_tokens": 17834883.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.423402452468872,
|
|
"epoch": 0.8136180034622043,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004944845322425455,
|
|
"loss": 6.3131,
|
|
"mean_token_accuracy": 0.16450032442808152,
|
|
"num_tokens": 17847009.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.4183858871459964,
|
|
"epoch": 0.8141950375072129,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004944754480044621,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.15603942126035691,
|
|
"num_tokens": 17859106.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.444196557998657,
|
|
"epoch": 0.8147720715522215,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004944663563844311,
|
|
"loss": 6.3201,
|
|
"mean_token_accuracy": 0.15441031754016876,
|
|
"num_tokens": 17871418.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.40857720375061,
|
|
"epoch": 0.8153491055972303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004944572573827581,
|
|
"loss": 6.2908,
|
|
"mean_token_accuracy": 0.1583213210105896,
|
|
"num_tokens": 17884219.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.3658651351928714,
|
|
"epoch": 0.8159261396422389,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004944481509997494,
|
|
"loss": 6.3028,
|
|
"mean_token_accuracy": 0.15765465348958968,
|
|
"num_tokens": 17896206.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.43848180770874,
|
|
"epoch": 0.8165031736872476,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000494439037235711,
|
|
"loss": 6.3986,
|
|
"mean_token_accuracy": 0.15387010723352432,
|
|
"num_tokens": 17909488.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.43320894241333,
|
|
"epoch": 0.8170802077322562,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004944299160909495,
|
|
"loss": 6.346,
|
|
"mean_token_accuracy": 0.15420840233564376,
|
|
"num_tokens": 17922851.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.46990966796875,
|
|
"epoch": 0.8176572417772648,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000494420787565772,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.16781508177518845,
|
|
"num_tokens": 17934586.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.410624599456787,
|
|
"epoch": 0.8182342758222735,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004944116516604852,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.15871597677469254,
|
|
"num_tokens": 17947637.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.419895935058594,
|
|
"epoch": 0.8188113098672821,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004944025083753965,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.15860212296247483,
|
|
"num_tokens": 17959601.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.42613205909729,
|
|
"epoch": 0.8193883439122909,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004943933577108133,
|
|
"loss": 6.3047,
|
|
"mean_token_accuracy": 0.1616590827703476,
|
|
"num_tokens": 17972568.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.461557245254516,
|
|
"epoch": 0.8199653779572995,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004943841996670436,
|
|
"loss": 6.3088,
|
|
"mean_token_accuracy": 0.1592638984322548,
|
|
"num_tokens": 17984665.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.465728902816773,
|
|
"epoch": 0.8205424120023082,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004943750342443953,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.1517217919230461,
|
|
"num_tokens": 17997140.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.459466886520386,
|
|
"epoch": 0.8211194460473168,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004943658614431767,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.15835410803556443,
|
|
"num_tokens": 18009361.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.377575302124024,
|
|
"epoch": 0.8216964800923254,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004943566812636963,
|
|
"loss": 6.2799,
|
|
"mean_token_accuracy": 0.15527833849191666,
|
|
"num_tokens": 18021233.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.3838001728057865,
|
|
"epoch": 0.8222735141373341,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.000494347493706263,
|
|
"loss": 6.1757,
|
|
"mean_token_accuracy": 0.1724259674549103,
|
|
"num_tokens": 18034086.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.393672943115234,
|
|
"epoch": 0.8228505481823427,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004943382987711856,
|
|
"loss": 6.2819,
|
|
"mean_token_accuracy": 0.16438249498605728,
|
|
"num_tokens": 18046604.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.414757633209229,
|
|
"epoch": 0.8234275822273515,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004943290964587734,
|
|
"loss": 6.3044,
|
|
"mean_token_accuracy": 0.16008765250444412,
|
|
"num_tokens": 18059185.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.397540616989136,
|
|
"epoch": 0.8240046162723601,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004943198867693361,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.16008234918117523,
|
|
"num_tokens": 18071707.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.433577537536621,
|
|
"epoch": 0.8245816503173687,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 0.0004943106697031833,
|
|
"loss": 6.4092,
|
|
"mean_token_accuracy": 0.15259905457496642,
|
|
"num_tokens": 18084657.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.472084045410156,
|
|
"epoch": 0.8251586843623774,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004943014452606251,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.1545234352350235,
|
|
"num_tokens": 18097084.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.420034742355346,
|
|
"epoch": 0.825735718407386,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004942922134419717,
|
|
"loss": 6.283,
|
|
"mean_token_accuracy": 0.15995100438594817,
|
|
"num_tokens": 18109306.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.360563182830811,
|
|
"epoch": 0.8263127524523947,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004942829742475336,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.15680315494537353,
|
|
"num_tokens": 18120300.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.409770345687866,
|
|
"epoch": 0.8268897864974033,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004942737276776217,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.1568691462278366,
|
|
"num_tokens": 18132251.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.3930370807647705,
|
|
"epoch": 0.827466820542412,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004942644737325468,
|
|
"loss": 6.2378,
|
|
"mean_token_accuracy": 0.16396623849868774,
|
|
"num_tokens": 18146198.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.412364673614502,
|
|
"epoch": 0.8280438545874207,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004942552124126202,
|
|
"loss": 6.3532,
|
|
"mean_token_accuracy": 0.15747751146554947,
|
|
"num_tokens": 18159493.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.372334575653076,
|
|
"epoch": 0.8286208886324293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004942459437181535,
|
|
"loss": 6.2454,
|
|
"mean_token_accuracy": 0.16117880791425704,
|
|
"num_tokens": 18172120.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.417788648605347,
|
|
"epoch": 0.829197922677438,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004942366676494584,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.15891496539115907,
|
|
"num_tokens": 18184704.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.5040661811828615,
|
|
"epoch": 0.8297749567224466,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004942273842068469,
|
|
"loss": 6.378,
|
|
"mean_token_accuracy": 0.1573457822203636,
|
|
"num_tokens": 18196770.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.42578158378601,
|
|
"epoch": 0.8303519907674553,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004942180933906311,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.1560923770070076,
|
|
"num_tokens": 18209987.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.427188396453857,
|
|
"epoch": 0.8309290248124639,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004942087952011237,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.15685783326625824,
|
|
"num_tokens": 18224864.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.477103185653687,
|
|
"epoch": 0.8315060588574726,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004941994896386374,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.1615700140595436,
|
|
"num_tokens": 18237270.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.358955335617066,
|
|
"epoch": 0.8320830929024813,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004941901767034851,
|
|
"loss": 6.3402,
|
|
"mean_token_accuracy": 0.15311284065246583,
|
|
"num_tokens": 18251227.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.375926876068116,
|
|
"epoch": 0.8326601269474899,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004941808563959802,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.1678831934928894,
|
|
"num_tokens": 18264762.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.457195186614991,
|
|
"epoch": 0.8332371609924986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004941715287164359,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.15596022307872773,
|
|
"num_tokens": 18276836.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.384139442443848,
|
|
"epoch": 0.8338141950375072,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004941621936651661,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.16242541372776031,
|
|
"num_tokens": 18290362.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.4580583572387695,
|
|
"epoch": 0.8343912290825158,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004941528512424849,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.1578863427042961,
|
|
"num_tokens": 18303924.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.370277833938599,
|
|
"epoch": 0.8349682631275245,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004941435014487064,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.16379570066928864,
|
|
"num_tokens": 18316490.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.417813491821289,
|
|
"epoch": 0.8355452971725332,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000494134144284145,
|
|
"loss": 6.2853,
|
|
"mean_token_accuracy": 0.15361817181110382,
|
|
"num_tokens": 18328819.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.363092947006225,
|
|
"epoch": 0.8361223312175419,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004941247797491156,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.16033381819725037,
|
|
"num_tokens": 18341872.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.436460399627686,
|
|
"epoch": 0.8366993652625505,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004941154078439329,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.15880754142999648,
|
|
"num_tokens": 18354644.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.445900964736938,
|
|
"epoch": 0.8372763993075591,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004941060285689126,
|
|
"loss": 6.3164,
|
|
"mean_token_accuracy": 0.1531373918056488,
|
|
"num_tokens": 18367581.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.410998773574829,
|
|
"epoch": 0.8378534333525678,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004940966419243695,
|
|
"loss": 6.2879,
|
|
"mean_token_accuracy": 0.16572379171848298,
|
|
"num_tokens": 18381123.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.344087362289429,
|
|
"epoch": 0.8384304673975764,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049408724791062,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.1606621190905571,
|
|
"num_tokens": 18395711.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.464009857177734,
|
|
"epoch": 0.8390075014425851,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004940778465279797,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.14919317811727523,
|
|
"num_tokens": 18409434.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.4164632797241214,
|
|
"epoch": 0.8395845354875938,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940684377767647,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.15381991267204284,
|
|
"num_tokens": 18423138.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.401902055740356,
|
|
"epoch": 0.8401615695326025,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004940590216572916,
|
|
"loss": 6.3188,
|
|
"mean_token_accuracy": 0.15444015413522721,
|
|
"num_tokens": 18435655.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.337902498245239,
|
|
"epoch": 0.8407386035776111,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004940495981698772,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.16857851296663284,
|
|
"num_tokens": 18448344.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.393205165863037,
|
|
"epoch": 0.8413156376226197,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004940401673148384,
|
|
"loss": 6.2057,
|
|
"mean_token_accuracy": 0.16652216762304306,
|
|
"num_tokens": 18460409.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.415207719802856,
|
|
"epoch": 0.8418926716676284,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004940307290924923,
|
|
"loss": 6.3247,
|
|
"mean_token_accuracy": 0.15722924172878266,
|
|
"num_tokens": 18473650.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.35351300239563,
|
|
"epoch": 0.842469705712637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004940212835031565,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.16438708156347276,
|
|
"num_tokens": 18487108.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.432998180389404,
|
|
"epoch": 0.8430467397576457,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004940118305471486,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.15940231084823608,
|
|
"num_tokens": 18500377.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.433759593963623,
|
|
"epoch": 0.8436237738026544,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004940023702247866,
|
|
"loss": 6.3466,
|
|
"mean_token_accuracy": 0.1481998160481453,
|
|
"num_tokens": 18513257.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.464117813110351,
|
|
"epoch": 0.844200807847663,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004939929025363886,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.15689841657876968,
|
|
"num_tokens": 18525438.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.4316305160522464,
|
|
"epoch": 0.8447778418926717,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004939834274822731,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.16183712780475618,
|
|
"num_tokens": 18537937.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.469800138473511,
|
|
"epoch": 0.8453548759376803,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004939739450627588,
|
|
"loss": 6.3821,
|
|
"mean_token_accuracy": 0.15115718245506288,
|
|
"num_tokens": 18551629.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.4402059555053714,
|
|
"epoch": 0.845931909982689,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004939644552781647,
|
|
"loss": 6.3297,
|
|
"mean_token_accuracy": 0.15563774853944778,
|
|
"num_tokens": 18564549.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.371536636352539,
|
|
"epoch": 0.8465089440276976,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004939549581288099,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.16682110875844955,
|
|
"num_tokens": 18576536.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.324753952026367,
|
|
"epoch": 0.8470859780727062,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004939454536150138,
|
|
"loss": 6.2766,
|
|
"mean_token_accuracy": 0.16521506160497665,
|
|
"num_tokens": 18588655.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.4212664604187015,
|
|
"epoch": 0.847663012117715,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000493935941737096,
|
|
"loss": 6.251,
|
|
"mean_token_accuracy": 0.16551081836223602,
|
|
"num_tokens": 18602152.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.347581577301026,
|
|
"epoch": 0.8482400461627236,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004939264224953768,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.1667644664645195,
|
|
"num_tokens": 18615391.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.302462100982666,
|
|
"epoch": 0.8488170802077323,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000493916895890176,
|
|
"loss": 6.3328,
|
|
"mean_token_accuracy": 0.15009007528424262,
|
|
"num_tokens": 18629987.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.5011743068695065,
|
|
"epoch": 0.8493941142527409,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000493907361921814,
|
|
"loss": 6.38,
|
|
"mean_token_accuracy": 0.15558104068040848,
|
|
"num_tokens": 18643064.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.517504692077637,
|
|
"epoch": 0.8499711482977496,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004938978205906118,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.15750785619020463,
|
|
"num_tokens": 18654950.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.375610494613648,
|
|
"epoch": 0.8505481823427582,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004938882718968901,
|
|
"loss": 6.2809,
|
|
"mean_token_accuracy": 0.15807467252016066,
|
|
"num_tokens": 18666318.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.356922674179077,
|
|
"epoch": 0.8511252163877668,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004938787158409702,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.16371146887540816,
|
|
"num_tokens": 18677357.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.3947381496429445,
|
|
"epoch": 0.8517022504327756,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004938691524231733,
|
|
"loss": 6.2723,
|
|
"mean_token_accuracy": 0.16164294630289078,
|
|
"num_tokens": 18689563.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.312204122543335,
|
|
"epoch": 0.8522792844777842,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004938595816438212,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.1561274692416191,
|
|
"num_tokens": 18701442.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.441098594665528,
|
|
"epoch": 0.8528563185227929,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004938500035032358,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.15520687401294708,
|
|
"num_tokens": 18714942.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.293469429016113,
|
|
"epoch": 0.8534333525678015,
|
|
"grad_norm": 3.25,
|
|
"learning_rate": 0.0004938404180017392,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.16100662648677827,
|
|
"num_tokens": 18727752.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.428264188766479,
|
|
"epoch": 0.8540103866128101,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004938308251396539,
|
|
"loss": 6.3428,
|
|
"mean_token_accuracy": 0.1571537360548973,
|
|
"num_tokens": 18741719.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.4747106552124025,
|
|
"epoch": 0.8545874206578188,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004938212249173024,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.14972534030675888,
|
|
"num_tokens": 18754472.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.4440333366394045,
|
|
"epoch": 0.8551644547028274,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004938116173350078,
|
|
"loss": 6.3288,
|
|
"mean_token_accuracy": 0.15726516842842103,
|
|
"num_tokens": 18766691.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.412831592559814,
|
|
"epoch": 0.8557414887478362,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004938020023930932,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.15810909271240234,
|
|
"num_tokens": 18780083.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.457475090026856,
|
|
"epoch": 0.8563185227928448,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004937923800918817,
|
|
"loss": 6.359,
|
|
"mean_token_accuracy": 0.15542669594287872,
|
|
"num_tokens": 18792559.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.3452540874481205,
|
|
"epoch": 0.8568955568378535,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004937827504316974,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.16970468163490296,
|
|
"num_tokens": 18805089.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.240821170806885,
|
|
"epoch": 0.8574725908828621,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004937731134128639,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.15851088762283325,
|
|
"num_tokens": 18818476.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.44542875289917,
|
|
"epoch": 0.8580496249278707,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004937634690357054,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.15640219449996948,
|
|
"num_tokens": 18830785.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.495653343200684,
|
|
"epoch": 0.8586266589728794,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004937538173005462,
|
|
"loss": 6.3712,
|
|
"mean_token_accuracy": 0.1560351386666298,
|
|
"num_tokens": 18844029.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.422978258132934,
|
|
"epoch": 0.859203693017888,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004937441582077111,
|
|
"loss": 6.3346,
|
|
"mean_token_accuracy": 0.15770572125911714,
|
|
"num_tokens": 18857468.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.425333786010742,
|
|
"epoch": 0.8597807270628968,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004937344917575249,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.15311031341552733,
|
|
"num_tokens": 18870487.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.4155045509338375,
|
|
"epoch": 0.8603577611079054,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004937248179503127,
|
|
"loss": 6.3045,
|
|
"mean_token_accuracy": 0.1591097131371498,
|
|
"num_tokens": 18883273.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.372232294082641,
|
|
"epoch": 0.860934795152914,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004937151367863998,
|
|
"loss": 6.2792,
|
|
"mean_token_accuracy": 0.1714622050523758,
|
|
"num_tokens": 18895863.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.392306852340698,
|
|
"epoch": 0.8615118291979227,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000493705448266112,
|
|
"loss": 6.3424,
|
|
"mean_token_accuracy": 0.1597261071205139,
|
|
"num_tokens": 18909406.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.38096022605896,
|
|
"epoch": 0.8620888632429313,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004936957523897752,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.16298051476478576,
|
|
"num_tokens": 18922794.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.395741033554077,
|
|
"epoch": 0.86266589728794,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004936860491577153,
|
|
"loss": 6.2997,
|
|
"mean_token_accuracy": 0.1635509356856346,
|
|
"num_tokens": 18936511.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.436820840835571,
|
|
"epoch": 0.8632429313329486,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004936763385702588,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.15443028509616852,
|
|
"num_tokens": 18948164.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.445798921585083,
|
|
"epoch": 0.8638199653779572,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004936666206277322,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.1542191758751869,
|
|
"num_tokens": 18960608.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.390499258041382,
|
|
"epoch": 0.864396999422966,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004936568953304624,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.17056952118873597,
|
|
"num_tokens": 18972266.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.33178129196167,
|
|
"epoch": 0.8649740334679746,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004936471626787766,
|
|
"loss": 6.2737,
|
|
"mean_token_accuracy": 0.15900991410017012,
|
|
"num_tokens": 18984518.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.370002889633179,
|
|
"epoch": 0.8655510675129833,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004936374226730022,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.1658060982823372,
|
|
"num_tokens": 18998611.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.413336277008057,
|
|
"epoch": 0.8661281015579919,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004936276753134666,
|
|
"loss": 6.2949,
|
|
"mean_token_accuracy": 0.15621051490306853,
|
|
"num_tokens": 19012117.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.277068948745727,
|
|
"epoch": 0.8667051356030006,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004936179206004976,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.16537234038114548,
|
|
"num_tokens": 19024075.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.416962480545044,
|
|
"epoch": 0.8672821696480092,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004936081585344236,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.15432593673467637,
|
|
"num_tokens": 19037350.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.509782838821411,
|
|
"epoch": 0.8678592036930178,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004935983891155727,
|
|
"loss": 6.3553,
|
|
"mean_token_accuracy": 0.15507148206233978,
|
|
"num_tokens": 19049438.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.379511880874634,
|
|
"epoch": 0.8684362377380266,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004935886123442737,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.15508285611867906,
|
|
"num_tokens": 19061689.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.466004753112793,
|
|
"epoch": 0.8690132717830352,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004935788282208551,
|
|
"loss": 6.3727,
|
|
"mean_token_accuracy": 0.15051396191120148,
|
|
"num_tokens": 19075606.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.3925048351287845,
|
|
"epoch": 0.8695903058280439,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004935690367456464,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.15860063582658768,
|
|
"num_tokens": 19088248.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.416834545135498,
|
|
"epoch": 0.8701673398730525,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004935592379189766,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1581605017185211,
|
|
"num_tokens": 19102480.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.363423204421997,
|
|
"epoch": 0.8707443739180611,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935494317411754,
|
|
"loss": 6.2578,
|
|
"mean_token_accuracy": 0.16764952838420868,
|
|
"num_tokens": 19114454.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.3521568298339846,
|
|
"epoch": 0.8713214079630698,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004935396182125726,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.16149284839630126,
|
|
"num_tokens": 19126709.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.3308103561401365,
|
|
"epoch": 0.8718984420080784,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935297973334983,
|
|
"loss": 6.2911,
|
|
"mean_token_accuracy": 0.1629858657717705,
|
|
"num_tokens": 19138831.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.431607007980347,
|
|
"epoch": 0.8724754760530872,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004935199691042828,
|
|
"loss": 6.1944,
|
|
"mean_token_accuracy": 0.1633341908454895,
|
|
"num_tokens": 19151555.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.300298261642456,
|
|
"epoch": 0.8730525100980958,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004935101335252568,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.16245049238204956,
|
|
"num_tokens": 19164557.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.392845678329468,
|
|
"epoch": 0.8736295441431045,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004935002905967509,
|
|
"loss": 6.3803,
|
|
"mean_token_accuracy": 0.15307363122701645,
|
|
"num_tokens": 19177081.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.405813980102539,
|
|
"epoch": 0.8742065781881131,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004934904403190963,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.15920666754245758,
|
|
"num_tokens": 19190209.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.415853786468506,
|
|
"epoch": 0.8747836122331217,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004934805826926242,
|
|
"loss": 6.2746,
|
|
"mean_token_accuracy": 0.1588641032576561,
|
|
"num_tokens": 19202262.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.336044120788574,
|
|
"epoch": 0.8753606462781304,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004934707177176663,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.15697792172431946,
|
|
"num_tokens": 19214752.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.4314311981201175,
|
|
"epoch": 0.875937680323139,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004934608453945543,
|
|
"loss": 6.3528,
|
|
"mean_token_accuracy": 0.1546017959713936,
|
|
"num_tokens": 19227320.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.463335561752319,
|
|
"epoch": 0.8765147143681478,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934509657236203,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.15523393899202348,
|
|
"num_tokens": 19239571.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.394824266433716,
|
|
"epoch": 0.8770917484131564,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004934410787051965,
|
|
"loss": 6.2782,
|
|
"mean_token_accuracy": 0.16422777026891708,
|
|
"num_tokens": 19252242.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.398877048492432,
|
|
"epoch": 0.877668782458165,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004934311843396157,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.16020542681217192,
|
|
"num_tokens": 19265501.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.389577150344849,
|
|
"epoch": 0.8782458165031737,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934212826272104,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.1710354968905449,
|
|
"num_tokens": 19278152.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.268189096450806,
|
|
"epoch": 0.8788228505481823,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004934113735683137,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.15756093189120293,
|
|
"num_tokens": 19290555.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.378724002838135,
|
|
"epoch": 0.879399884593191,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000493401457163259,
|
|
"loss": 6.252,
|
|
"mean_token_accuracy": 0.16543366014957428,
|
|
"num_tokens": 19302866.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.493717765808105,
|
|
"epoch": 0.8799769186381996,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004933915334123798,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.15103889033198356,
|
|
"num_tokens": 19315577.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.472537183761597,
|
|
"epoch": 0.8805539526832084,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004933816023160099,
|
|
"loss": 6.3288,
|
|
"mean_token_accuracy": 0.15646580904722213,
|
|
"num_tokens": 19328593.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.432592248916626,
|
|
"epoch": 0.881130986728217,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004933716638744832,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.1658412992954254,
|
|
"num_tokens": 19341669.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.324086666107178,
|
|
"epoch": 0.8817080207732256,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000493361718088134,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.15649446547031404,
|
|
"num_tokens": 19354268.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.411100578308106,
|
|
"epoch": 0.8822850548182343,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000493351764957297,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.15419866889715195,
|
|
"num_tokens": 19367676.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.486693906784057,
|
|
"epoch": 0.8828620888632429,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004933418044823068,
|
|
"loss": 6.3086,
|
|
"mean_token_accuracy": 0.16112906634807586,
|
|
"num_tokens": 19380726.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.410530614852905,
|
|
"epoch": 0.8834391229082516,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004933318366634984,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.15761423408985137,
|
|
"num_tokens": 19392917.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.391311740875244,
|
|
"epoch": 0.8840161569532602,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004933218615012072,
|
|
"loss": 6.3448,
|
|
"mean_token_accuracy": 0.1594384342432022,
|
|
"num_tokens": 19406026.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.393275213241577,
|
|
"epoch": 0.8845931909982689,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004933118789957687,
|
|
"loss": 6.2815,
|
|
"mean_token_accuracy": 0.1612059071660042,
|
|
"num_tokens": 19418612.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.414052724838257,
|
|
"epoch": 0.8851702250432776,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004933018891475186,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.1564637005329132,
|
|
"num_tokens": 19430746.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.396469593048096,
|
|
"epoch": 0.8857472590882862,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004932918919567927,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.1536492109298706,
|
|
"num_tokens": 19443043.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.478463459014892,
|
|
"epoch": 0.8863242931332949,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004932818874239275,
|
|
"loss": 6.3276,
|
|
"mean_token_accuracy": 0.15937264189124106,
|
|
"num_tokens": 19456463.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.444648313522339,
|
|
"epoch": 0.8869013271783035,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004932718755492595,
|
|
"loss": 6.305,
|
|
"mean_token_accuracy": 0.15255717635154725,
|
|
"num_tokens": 19468108.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.367991638183594,
|
|
"epoch": 0.8874783612233121,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004932618563331254,
|
|
"loss": 6.3265,
|
|
"mean_token_accuracy": 0.15850533843040465,
|
|
"num_tokens": 19480741.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.35459451675415,
|
|
"epoch": 0.8880553952683208,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004932518297758622,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.1637923687696457,
|
|
"num_tokens": 19492996.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.439085531234741,
|
|
"epoch": 0.8886324293133295,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004932417958778071,
|
|
"loss": 6.2594,
|
|
"mean_token_accuracy": 0.16098986119031905,
|
|
"num_tokens": 19505513.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.417087125778198,
|
|
"epoch": 0.8892094633583382,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004932317546392976,
|
|
"loss": 6.3979,
|
|
"mean_token_accuracy": 0.15393300205469132,
|
|
"num_tokens": 19518244.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.320071363449097,
|
|
"epoch": 0.8897864974033468,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004932217060606714,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.1595987156033516,
|
|
"num_tokens": 19530987.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.3398231029510494,
|
|
"epoch": 0.8903635314483554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004932116501422665,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.1674814835190773,
|
|
"num_tokens": 19543546.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.446526670455933,
|
|
"epoch": 0.8909405654933641,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004932015868844211,
|
|
"loss": 6.2946,
|
|
"mean_token_accuracy": 0.1571994751691818,
|
|
"num_tokens": 19556867.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.37026309967041,
|
|
"epoch": 0.8915175995383727,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004931915162874738,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.15851514786481857,
|
|
"num_tokens": 19569738.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.363567304611206,
|
|
"epoch": 0.8920946335833814,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004931814383517632,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.15662410855293274,
|
|
"num_tokens": 19581701.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.377171468734741,
|
|
"epoch": 0.8926716676283901,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004931713530776284,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.16711300909519194,
|
|
"num_tokens": 19593698.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.349302959442139,
|
|
"epoch": 0.8932487016733988,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004931612604654083,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.15497682094573975,
|
|
"num_tokens": 19605323.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.404062414169312,
|
|
"epoch": 0.8938257357184074,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004931511605154428,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.1544952780008316,
|
|
"num_tokens": 19616577.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.473753356933594,
|
|
"epoch": 0.894402769763416,
|
|
"grad_norm": 3.046875,
|
|
"learning_rate": 0.0004931410532280711,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.15787958949804307,
|
|
"num_tokens": 19629177.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.344061231613159,
|
|
"epoch": 0.8949798038084247,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004931309386036337,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.15972928553819657,
|
|
"num_tokens": 19642170.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.308340644836425,
|
|
"epoch": 0.8955568378534333,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004931208166424704,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.16119810193777084,
|
|
"num_tokens": 19655648.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.403913593292236,
|
|
"epoch": 0.896133871898442,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004931106873449219,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.16124669313430787,
|
|
"num_tokens": 19667941.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.437334489822388,
|
|
"epoch": 0.8967109059434507,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004931005507113285,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.1630260318517685,
|
|
"num_tokens": 19680523.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.261597490310669,
|
|
"epoch": 0.8972879399884593,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004930904067420317,
|
|
"loss": 6.276,
|
|
"mean_token_accuracy": 0.16263071596622466,
|
|
"num_tokens": 19692984.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.432254409790039,
|
|
"epoch": 0.897864974033468,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004930802554373723,
|
|
"loss": 6.2354,
|
|
"mean_token_accuracy": 0.16485002189874648,
|
|
"num_tokens": 19705926.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.449591398239136,
|
|
"epoch": 0.8984420080784766,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004930700967976918,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.16124334186315536,
|
|
"num_tokens": 19717322.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.39738130569458,
|
|
"epoch": 0.8990190421234853,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000493059930823332,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.14967879951000213,
|
|
"num_tokens": 19730577.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.44396858215332,
|
|
"epoch": 0.8995960761684939,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004930497575146346,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.15643653869628907,
|
|
"num_tokens": 19744054.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.342684650421143,
|
|
"epoch": 0.9001731102135025,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004930395768719421,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.1550717294216156,
|
|
"num_tokens": 19755898.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.396816730499268,
|
|
"epoch": 0.9007501442585113,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004930293888955966,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.15300133675336838,
|
|
"num_tokens": 19769599.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.453741598129272,
|
|
"epoch": 0.9013271783035199,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000493019193585941,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.14918754994869232,
|
|
"num_tokens": 19783442.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.4418963432312015,
|
|
"epoch": 0.9019042123485286,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000493008990943318,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.15801341980695724,
|
|
"num_tokens": 19796039.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.478892612457275,
|
|
"epoch": 0.9024812463935372,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004929987809680709,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.16183366179466246,
|
|
"num_tokens": 19808695.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.390950679779053,
|
|
"epoch": 0.9030582804385459,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004929885636605432,
|
|
"loss": 6.2872,
|
|
"mean_token_accuracy": 0.15758599042892457,
|
|
"num_tokens": 19821173.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.370595455169678,
|
|
"epoch": 0.9036353144835545,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004929783390210784,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.15149060785770416,
|
|
"num_tokens": 19833804.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.405590677261353,
|
|
"epoch": 0.9042123485285631,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004929681070500204,
|
|
"loss": 6.2947,
|
|
"mean_token_accuracy": 0.1585235998034477,
|
|
"num_tokens": 19845690.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.453483057022095,
|
|
"epoch": 0.9047893825735719,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004929578677477135,
|
|
"loss": 6.3082,
|
|
"mean_token_accuracy": 0.1503335326910019,
|
|
"num_tokens": 19859463.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.3136523246765135,
|
|
"epoch": 0.9053664166185805,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004929476211145019,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.16918923556804658,
|
|
"num_tokens": 19872168.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.331404352188111,
|
|
"epoch": 0.9059434506635892,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004929373671507303,
|
|
"loss": 6.2647,
|
|
"mean_token_accuracy": 0.16442092657089233,
|
|
"num_tokens": 19884927.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.3881467342376705,
|
|
"epoch": 0.9065204847085978,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004929271058567436,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.16083337366580963,
|
|
"num_tokens": 19897105.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.376621198654175,
|
|
"epoch": 0.9070975187536064,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000492916837232887,
|
|
"loss": 6.2943,
|
|
"mean_token_accuracy": 0.1583924874663353,
|
|
"num_tokens": 19909973.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.371397638320923,
|
|
"epoch": 0.9076745527986151,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004929065612795058,
|
|
"loss": 6.2893,
|
|
"mean_token_accuracy": 0.1654267877340317,
|
|
"num_tokens": 19923674.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.401323223114014,
|
|
"epoch": 0.9082515868436237,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004928962779969456,
|
|
"loss": 6.3279,
|
|
"mean_token_accuracy": 0.1563215509057045,
|
|
"num_tokens": 19935742.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.431182050704956,
|
|
"epoch": 0.9088286208886325,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004928859873855524,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.15487526804208757,
|
|
"num_tokens": 19947945.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.463040542602539,
|
|
"epoch": 0.9094056549336411,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004928756894456723,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.16083851903676988,
|
|
"num_tokens": 19961275.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.431319952011108,
|
|
"epoch": 0.9099826889786498,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004928653841776515,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.15611430555582045,
|
|
"num_tokens": 19973634.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.450580596923828,
|
|
"epoch": 0.9105597230236584,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004928550715818368,
|
|
"loss": 6.3138,
|
|
"mean_token_accuracy": 0.15701612830162048,
|
|
"num_tokens": 19985920.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.391114807128906,
|
|
"epoch": 0.911136757068667,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004928447516585749,
|
|
"loss": 6.3351,
|
|
"mean_token_accuracy": 0.15266132205724717,
|
|
"num_tokens": 19999081.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.3048357486724855,
|
|
"epoch": 0.9117137911136757,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000492834424408213,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.16531692892313005,
|
|
"num_tokens": 20012801.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.479332065582275,
|
|
"epoch": 0.9122908251586843,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004928240898310984,
|
|
"loss": 6.3693,
|
|
"mean_token_accuracy": 0.15050050467252732,
|
|
"num_tokens": 20024618.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.47349362373352,
|
|
"epoch": 0.9128678592036931,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004928137479275789,
|
|
"loss": 6.3076,
|
|
"mean_token_accuracy": 0.16095187067985534,
|
|
"num_tokens": 20038587.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.414200925827027,
|
|
"epoch": 0.9134448932487017,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000492803398698002,
|
|
"loss": 6.3259,
|
|
"mean_token_accuracy": 0.15401843264698983,
|
|
"num_tokens": 20051811.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.4483012676239015,
|
|
"epoch": 0.9140219272937103,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004927930421427161,
|
|
"loss": 6.3042,
|
|
"mean_token_accuracy": 0.15708602219820023,
|
|
"num_tokens": 20064463.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.372395849227905,
|
|
"epoch": 0.914598961338719,
|
|
"grad_norm": 5.53125,
|
|
"learning_rate": 0.0004927826782620694,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.1550089493393898,
|
|
"num_tokens": 20076614.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.468643712997436,
|
|
"epoch": 0.9151759953837276,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004927723070564104,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.15085637867450713,
|
|
"num_tokens": 20090395.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.419011640548706,
|
|
"epoch": 0.9157530294287363,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004927619285260881,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.15481395423412322,
|
|
"num_tokens": 20102736.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.410750818252564,
|
|
"epoch": 0.9163300634737449,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004927515426714515,
|
|
"loss": 6.321,
|
|
"mean_token_accuracy": 0.15636474043130874,
|
|
"num_tokens": 20116516.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.385376882553101,
|
|
"epoch": 0.9169070975187537,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00049274114949285,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.16122057735919954,
|
|
"num_tokens": 20128742.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.438413190841675,
|
|
"epoch": 0.9174841315637623,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000492730748990633,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.1578374445438385,
|
|
"num_tokens": 20140590.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.3685081005096436,
|
|
"epoch": 0.9180611656087709,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004927203411651504,
|
|
"loss": 6.2941,
|
|
"mean_token_accuracy": 0.15343682318925858,
|
|
"num_tokens": 20153748.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.46742205619812,
|
|
"epoch": 0.9186381996537796,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004927099260167523,
|
|
"loss": 6.2976,
|
|
"mean_token_accuracy": 0.1620119497179985,
|
|
"num_tokens": 20167094.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.400900650024414,
|
|
"epoch": 0.9192152336987882,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004926995035457889,
|
|
"loss": 6.2755,
|
|
"mean_token_accuracy": 0.15437212586402893,
|
|
"num_tokens": 20180716.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.422587203979492,
|
|
"epoch": 0.9197922677437969,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000492689073752611,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.158352267742157,
|
|
"num_tokens": 20192214.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.322636461257934,
|
|
"epoch": 0.9203693017888055,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004926786366375691,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.159789976477623,
|
|
"num_tokens": 20204789.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.395492315292358,
|
|
"epoch": 0.9209463358338142,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004926681922010145,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.15341563820838927,
|
|
"num_tokens": 20217318.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.503517580032349,
|
|
"epoch": 0.9215233698788229,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004926577404432982,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.15594429075717925,
|
|
"num_tokens": 20229757.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.401009654998779,
|
|
"epoch": 0.9221004039238315,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004926472813647721,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.1593426927924156,
|
|
"num_tokens": 20242042.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.317966318130493,
|
|
"epoch": 0.9226774379688402,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004926368149657876,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.16747417151927949,
|
|
"num_tokens": 20255188.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.4740152835845945,
|
|
"epoch": 0.9232544720138488,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004926263412466972,
|
|
"loss": 6.2961,
|
|
"mean_token_accuracy": 0.16103923618793486,
|
|
"num_tokens": 20267359.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.388199758529663,
|
|
"epoch": 0.9238315060588574,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004926158602078527,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.15565205961465836,
|
|
"num_tokens": 20280023.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.334804201126099,
|
|
"epoch": 0.9244085401038661,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004926053718496069,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.15743525475263595,
|
|
"num_tokens": 20293043.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.403419828414917,
|
|
"epoch": 0.9249855741488748,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004925948761723126,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.15326788574457167,
|
|
"num_tokens": 20304929.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.409779071807861,
|
|
"epoch": 0.9255626081938835,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004925843731763226,
|
|
"loss": 6.242,
|
|
"mean_token_accuracy": 0.15896770507097244,
|
|
"num_tokens": 20317024.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.434144783020019,
|
|
"epoch": 0.9261396422388921,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004925738628619904,
|
|
"loss": 6.3182,
|
|
"mean_token_accuracy": 0.1545105457305908,
|
|
"num_tokens": 20329909.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.324703788757324,
|
|
"epoch": 0.9267166762839008,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004925633452296693,
|
|
"loss": 6.28,
|
|
"mean_token_accuracy": 0.15805017352104186,
|
|
"num_tokens": 20344224.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.506214904785156,
|
|
"epoch": 0.9272937103289094,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004925528202797131,
|
|
"loss": 6.3046,
|
|
"mean_token_accuracy": 0.15081962794065476,
|
|
"num_tokens": 20357393.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.424812507629395,
|
|
"epoch": 0.927870744373918,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004925422880124761,
|
|
"loss": 6.3061,
|
|
"mean_token_accuracy": 0.16021231263875962,
|
|
"num_tokens": 20369551.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.379309225082397,
|
|
"epoch": 0.9284477784189267,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004925317484283121,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.14904050678014755,
|
|
"num_tokens": 20382639.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.429602766036988,
|
|
"epoch": 0.9290248124639354,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004925212015275758,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.16726955473423005,
|
|
"num_tokens": 20394751.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.39623794555664,
|
|
"epoch": 0.9296018465089441,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000492510647310622,
|
|
"loss": 6.2848,
|
|
"mean_token_accuracy": 0.1595268651843071,
|
|
"num_tokens": 20408235.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.398084878921509,
|
|
"epoch": 0.9301788805539527,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004925000857778055,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.15427375137805938,
|
|
"num_tokens": 20423063.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.427191162109375,
|
|
"epoch": 0.9307559145989613,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004924895169294818,
|
|
"loss": 6.2369,
|
|
"mean_token_accuracy": 0.1577201783657074,
|
|
"num_tokens": 20436225.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.4034092903137205,
|
|
"epoch": 0.93133294864397,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004924789407660062,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.1600277066230774,
|
|
"num_tokens": 20447957.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.381423425674439,
|
|
"epoch": 0.9319099826889786,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004924683572877345,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.16029435247182847,
|
|
"num_tokens": 20459836.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.533320760726928,
|
|
"epoch": 0.9324870167339873,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004924577664950225,
|
|
"loss": 6.3824,
|
|
"mean_token_accuracy": 0.15089137703180314,
|
|
"num_tokens": 20471907.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.440421152114868,
|
|
"epoch": 0.933064050778996,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004924471683882266,
|
|
"loss": 6.3825,
|
|
"mean_token_accuracy": 0.15363826006650924,
|
|
"num_tokens": 20485166.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.420388221740723,
|
|
"epoch": 0.9336410848240047,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004924365629677031,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.16712835282087327,
|
|
"num_tokens": 20498973.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.355935859680176,
|
|
"epoch": 0.9342181188690133,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000492425950233809,
|
|
"loss": 6.2747,
|
|
"mean_token_accuracy": 0.16278841942548752,
|
|
"num_tokens": 20511615.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.3108885288238525,
|
|
"epoch": 0.9347951529140219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492415330186901,
|
|
"loss": 6.2678,
|
|
"mean_token_accuracy": 0.15716547816991805,
|
|
"num_tokens": 20523615.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.421422386169434,
|
|
"epoch": 0.9353721869590306,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004924047028273364,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.15872604250907899,
|
|
"num_tokens": 20537048.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.393527889251709,
|
|
"epoch": 0.9359492210040392,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004923940681554725,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.1614370346069336,
|
|
"num_tokens": 20551041.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.415983819961548,
|
|
"epoch": 0.9365262550490479,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004923834261716672,
|
|
"loss": 6.3455,
|
|
"mean_token_accuracy": 0.15478847175836563,
|
|
"num_tokens": 20563123.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.448668527603149,
|
|
"epoch": 0.9371032890940566,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004923727768762782,
|
|
"loss": 6.2795,
|
|
"mean_token_accuracy": 0.16725585907697677,
|
|
"num_tokens": 20577487.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.402075386047363,
|
|
"epoch": 0.9376803231390652,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000492362120269664,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.1627908691763878,
|
|
"num_tokens": 20590125.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.418191576004029,
|
|
"epoch": 0.9382573571840739,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004923514563521827,
|
|
"loss": 6.3141,
|
|
"mean_token_accuracy": 0.15729555934667588,
|
|
"num_tokens": 20603035.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.403626775741577,
|
|
"epoch": 0.9388343912290825,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004923407851241933,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.15334731638431548,
|
|
"num_tokens": 20615280.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.4232524871826175,
|
|
"epoch": 0.9394114252740912,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004923301065860545,
|
|
"loss": 6.2766,
|
|
"mean_token_accuracy": 0.15411915630102158,
|
|
"num_tokens": 20627800.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.412774085998535,
|
|
"epoch": 0.9399884593190998,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004923194207381254,
|
|
"loss": 6.2985,
|
|
"mean_token_accuracy": 0.15818233788013458,
|
|
"num_tokens": 20639264.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.378032875061035,
|
|
"epoch": 0.9405654933641084,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004923087275807656,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.1706040620803833,
|
|
"num_tokens": 20652155.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.391241407394409,
|
|
"epoch": 0.9411425274091172,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004922980271143347,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.15853582173585892,
|
|
"num_tokens": 20665642.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.422382640838623,
|
|
"epoch": 0.9417195614541258,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004922873193391927,
|
|
"loss": 6.2504,
|
|
"mean_token_accuracy": 0.16132109612226486,
|
|
"num_tokens": 20678685.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.333035278320312,
|
|
"epoch": 0.9422965954991345,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004922766042556994,
|
|
"loss": 6.21,
|
|
"mean_token_accuracy": 0.15850515216588973,
|
|
"num_tokens": 20690714.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.418743991851807,
|
|
"epoch": 0.9428736295441431,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004922658818642156,
|
|
"loss": 6.3091,
|
|
"mean_token_accuracy": 0.1515625908970833,
|
|
"num_tokens": 20703316.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.327837753295898,
|
|
"epoch": 0.9434506635891518,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004922551521651018,
|
|
"loss": 6.204,
|
|
"mean_token_accuracy": 0.1694895327091217,
|
|
"num_tokens": 20716144.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.418542194366455,
|
|
"epoch": 0.9440276976341604,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004922444151587189,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.15802036374807357,
|
|
"num_tokens": 20728089.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.298161745071411,
|
|
"epoch": 0.944604731679169,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004922336708454279,
|
|
"loss": 6.2609,
|
|
"mean_token_accuracy": 0.16404679417610168,
|
|
"num_tokens": 20741684.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.420363283157348,
|
|
"epoch": 0.9451817657241778,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004922229192255903,
|
|
"loss": 6.3386,
|
|
"mean_token_accuracy": 0.15321814119815827,
|
|
"num_tokens": 20754840.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.379177618026733,
|
|
"epoch": 0.9457587997691864,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004922121602995678,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.16860224455595016,
|
|
"num_tokens": 20767528.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.300572204589844,
|
|
"epoch": 0.9463358338141951,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004922013940677221,
|
|
"loss": 6.2703,
|
|
"mean_token_accuracy": 0.16143476068973542,
|
|
"num_tokens": 20778886.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.394140338897705,
|
|
"epoch": 0.9469128678592037,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004921906205304155,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.1543475106358528,
|
|
"num_tokens": 20792928.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.387519454956054,
|
|
"epoch": 0.9474899019042123,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004921798396880101,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.1540800616145134,
|
|
"num_tokens": 20805766.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.3942780017852785,
|
|
"epoch": 0.948066935949221,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004921690515408688,
|
|
"loss": 6.273,
|
|
"mean_token_accuracy": 0.1582356408238411,
|
|
"num_tokens": 20819008.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.369224262237549,
|
|
"epoch": 0.9486439699942296,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004921582560893543,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1553818851709366,
|
|
"num_tokens": 20832706.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.4350669384002686,
|
|
"epoch": 0.9492210040392384,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004921474533338297,
|
|
"loss": 6.2547,
|
|
"mean_token_accuracy": 0.16016023606061935,
|
|
"num_tokens": 20844568.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.399309062957764,
|
|
"epoch": 0.949798038084247,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004921366432746585,
|
|
"loss": 6.2834,
|
|
"mean_token_accuracy": 0.1573599874973297,
|
|
"num_tokens": 20856157.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.362299489974975,
|
|
"epoch": 0.9503750721292556,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000492125825912204,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.16097963899374007,
|
|
"num_tokens": 20868039.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.463052082061767,
|
|
"epoch": 0.9509521061742643,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004921150012468302,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.15774607434868812,
|
|
"num_tokens": 20880190.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.41200098991394,
|
|
"epoch": 0.9515291402192729,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004921041692789013,
|
|
"loss": 6.2571,
|
|
"mean_token_accuracy": 0.16535381972789764,
|
|
"num_tokens": 20892996.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.455173110961914,
|
|
"epoch": 0.9521061742642816,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004920933300087813,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.15742640495300292,
|
|
"num_tokens": 20906080.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.430334520339966,
|
|
"epoch": 0.9526832083092902,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004920824834368353,
|
|
"loss": 6.3609,
|
|
"mean_token_accuracy": 0.15268936306238173,
|
|
"num_tokens": 20917944.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.340414762496948,
|
|
"epoch": 0.953260242354299,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004920716295634275,
|
|
"loss": 6.2397,
|
|
"mean_token_accuracy": 0.17364375591278075,
|
|
"num_tokens": 20929046.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.455630874633789,
|
|
"epoch": 0.9538372763993076,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004920607683889235,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.1561593271791935,
|
|
"num_tokens": 20941643.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.538067293167114,
|
|
"epoch": 0.9544143104443162,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004920498999136882,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.1545989155769348,
|
|
"num_tokens": 20954620.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.4215727806091305,
|
|
"epoch": 0.9549913444893249,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004920390241380874,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.15070486068725586,
|
|
"num_tokens": 20968033.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.422377824783325,
|
|
"epoch": 0.9555683785343335,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004920281410624868,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.16499000191688537,
|
|
"num_tokens": 20980586.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.349878549575806,
|
|
"epoch": 0.9561454125793422,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004920172506872525,
|
|
"loss": 6.2084,
|
|
"mean_token_accuracy": 0.16240258812904357,
|
|
"num_tokens": 20992346.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.268904733657837,
|
|
"epoch": 0.9567224466243508,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004920063530127508,
|
|
"loss": 6.1527,
|
|
"mean_token_accuracy": 0.17184782773256302,
|
|
"num_tokens": 21004399.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.457413578033448,
|
|
"epoch": 0.9572994806693594,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004919954480393482,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.1487828180193901,
|
|
"num_tokens": 21017066.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.539893627166748,
|
|
"epoch": 0.9578765147143682,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004919845357674114,
|
|
"loss": 6.4393,
|
|
"mean_token_accuracy": 0.14757169634103776,
|
|
"num_tokens": 21031664.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.500674772262573,
|
|
"epoch": 0.9584535487593768,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919736161973076,
|
|
"loss": 6.272,
|
|
"mean_token_accuracy": 0.1634308248758316,
|
|
"num_tokens": 21043980.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.353540134429932,
|
|
"epoch": 0.9590305828043855,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000491962689329404,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.15528810173273086,
|
|
"num_tokens": 21056916.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.502210283279419,
|
|
"epoch": 0.9596076168493941,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004919517551640681,
|
|
"loss": 6.3659,
|
|
"mean_token_accuracy": 0.1515677571296692,
|
|
"num_tokens": 21070027.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.526283597946167,
|
|
"epoch": 0.9601846508944027,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004919408137016677,
|
|
"loss": 6.3125,
|
|
"mean_token_accuracy": 0.15769415199756623,
|
|
"num_tokens": 21082596.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.284257698059082,
|
|
"epoch": 0.9607616849394114,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004919298649425708,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.16701944917440414,
|
|
"num_tokens": 21098160.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.364248371124267,
|
|
"epoch": 0.96133871898442,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004919189088871456,
|
|
"loss": 6.251,
|
|
"mean_token_accuracy": 0.15590550601482392,
|
|
"num_tokens": 21111562.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.41587643623352,
|
|
"epoch": 0.9619157530294288,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004919079455357608,
|
|
"loss": 6.2395,
|
|
"mean_token_accuracy": 0.1601430892944336,
|
|
"num_tokens": 21123177.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.406910991668701,
|
|
"epoch": 0.9624927870744374,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004918969748887847,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.15528492927551268,
|
|
"num_tokens": 21135390.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.391875457763672,
|
|
"epoch": 0.9630698211194461,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004918859969465868,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.16090984791517257,
|
|
"num_tokens": 21148718.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.409095191955567,
|
|
"epoch": 0.9636468551644547,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004918750117095361,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.15558131486177446,
|
|
"num_tokens": 21161057.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.4546857357025145,
|
|
"epoch": 0.9642238892094633,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004918640191780021,
|
|
"loss": 6.2665,
|
|
"mean_token_accuracy": 0.15689287930727006,
|
|
"num_tokens": 21175048.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.404264736175537,
|
|
"epoch": 0.964800923254472,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004918530193523546,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.16269493997097015,
|
|
"num_tokens": 21187995.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.339152526855469,
|
|
"epoch": 0.9653779572994806,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004918420122329634,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.16081032305955886,
|
|
"num_tokens": 21200685.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.348997116088867,
|
|
"epoch": 0.9659549913444894,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004918309978201989,
|
|
"loss": 6.1992,
|
|
"mean_token_accuracy": 0.1665423795580864,
|
|
"num_tokens": 21212709.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.451622152328492,
|
|
"epoch": 0.966532025389498,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004918199761144315,
|
|
"loss": 6.3389,
|
|
"mean_token_accuracy": 0.15161336064338685,
|
|
"num_tokens": 21224846.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.403325319290161,
|
|
"epoch": 0.9671090594345066,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004918089471160318,
|
|
"loss": 6.3308,
|
|
"mean_token_accuracy": 0.16391047835350037,
|
|
"num_tokens": 21238490.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.386717939376831,
|
|
"epoch": 0.9676860934795153,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004917979108253709,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.16050710380077363,
|
|
"num_tokens": 21250064.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.421000051498413,
|
|
"epoch": 0.9682631275245239,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049178686724282,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.15899699330329894,
|
|
"num_tokens": 21262777.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.395197439193725,
|
|
"epoch": 0.9688401615695326,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004917758163687506,
|
|
"loss": 6.2687,
|
|
"mean_token_accuracy": 0.16623124480247498,
|
|
"num_tokens": 21274837.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.374613809585571,
|
|
"epoch": 0.9694171956145412,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004917647582035341,
|
|
"loss": 6.3607,
|
|
"mean_token_accuracy": 0.15184668079018593,
|
|
"num_tokens": 21287683.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.376201486587524,
|
|
"epoch": 0.96999422965955,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004917536927475428,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.16200344264507294,
|
|
"num_tokens": 21300053.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.440302991867066,
|
|
"epoch": 0.9705712637045586,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004917426200011486,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.1626146748661995,
|
|
"num_tokens": 21312143.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.382162284851074,
|
|
"epoch": 0.9711482977495672,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000491731539964724,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.1642318233847618,
|
|
"num_tokens": 21324530.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.407947683334351,
|
|
"epoch": 0.9717253317945759,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004917204526386418,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.16119913905858993,
|
|
"num_tokens": 21337766.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.442886304855347,
|
|
"epoch": 0.9723023658395845,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004917093580232748,
|
|
"loss": 6.2729,
|
|
"mean_token_accuracy": 0.16371907740831376,
|
|
"num_tokens": 21350304.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.390522384643555,
|
|
"epoch": 0.9728793998845932,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004916982561189962,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.15955062806606293,
|
|
"num_tokens": 21362030.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.373282623291016,
|
|
"epoch": 0.9734564339296018,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004916871469261794,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.1568213276565075,
|
|
"num_tokens": 21374279.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.364431238174438,
|
|
"epoch": 0.9740334679746105,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000491676030445198,
|
|
"loss": 6.3004,
|
|
"mean_token_accuracy": 0.16820743083953857,
|
|
"num_tokens": 21388220.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.4249077320098875,
|
|
"epoch": 0.9746105020196192,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004916649066764259,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.16421249657869338,
|
|
"num_tokens": 21400770.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.374565935134887,
|
|
"epoch": 0.9751875360646278,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004916537756202375,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.16066452264785766,
|
|
"num_tokens": 21413078.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.362772464752197,
|
|
"epoch": 0.9757645701096365,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004916426372770069,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.15732649713754654,
|
|
"num_tokens": 21427285.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.42603907585144,
|
|
"epoch": 0.9763416041546451,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004916314916471087,
|
|
"loss": 6.3029,
|
|
"mean_token_accuracy": 0.15744611397385597,
|
|
"num_tokens": 21440659.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.410357141494751,
|
|
"epoch": 0.9769186381996537,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004916203387309179,
|
|
"loss": 6.246,
|
|
"mean_token_accuracy": 0.152059967815876,
|
|
"num_tokens": 21452301.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.278444290161133,
|
|
"epoch": 0.9774956722446624,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004916091785288096,
|
|
"loss": 6.1978,
|
|
"mean_token_accuracy": 0.16501330584287643,
|
|
"num_tokens": 21466716.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.429250001907349,
|
|
"epoch": 0.9780727062896711,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004915980110411593,
|
|
"loss": 6.29,
|
|
"mean_token_accuracy": 0.15631196796894073,
|
|
"num_tokens": 21479314.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.427707147598267,
|
|
"epoch": 0.9786497403346798,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004915868362683425,
|
|
"loss": 6.2077,
|
|
"mean_token_accuracy": 0.16927620470523835,
|
|
"num_tokens": 21491968.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.281297016143799,
|
|
"epoch": 0.9792267743796884,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004915756542107349,
|
|
"loss": 6.298,
|
|
"mean_token_accuracy": 0.15860208868980408,
|
|
"num_tokens": 21505744.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.404678392410278,
|
|
"epoch": 0.979803808424697,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004915644648687127,
|
|
"loss": 6.3305,
|
|
"mean_token_accuracy": 0.15427371114492416,
|
|
"num_tokens": 21520981.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.421433591842652,
|
|
"epoch": 0.9803808424697057,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004915532682426524,
|
|
"loss": 6.2965,
|
|
"mean_token_accuracy": 0.15904518067836762,
|
|
"num_tokens": 21533712.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.336588764190674,
|
|
"epoch": 0.9809578765147143,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004915420643329306,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.16007357686758042,
|
|
"num_tokens": 21546875.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.358702325820923,
|
|
"epoch": 0.981534910559723,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000491530853139924,
|
|
"loss": 6.2287,
|
|
"mean_token_accuracy": 0.16115213334560394,
|
|
"num_tokens": 21559154.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.469691753387451,
|
|
"epoch": 0.9821119446047317,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004915196346640095,
|
|
"loss": 6.3238,
|
|
"mean_token_accuracy": 0.15400136709213258,
|
|
"num_tokens": 21573164.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.439447975158691,
|
|
"epoch": 0.9826889786497404,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004915084089055648,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.14860097840428352,
|
|
"num_tokens": 21585449.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.328643274307251,
|
|
"epoch": 0.983266012694749,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004914971758649673,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.16568298786878585,
|
|
"num_tokens": 21598120.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.421794176101685,
|
|
"epoch": 0.9838430467397576,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004914859355425948,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.15581102222204207,
|
|
"num_tokens": 21609912.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.466002559661865,
|
|
"epoch": 0.9844200807847663,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004914746879388255,
|
|
"loss": 6.2581,
|
|
"mean_token_accuracy": 0.16066803485155107,
|
|
"num_tokens": 21623242.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.35989294052124,
|
|
"epoch": 0.9849971148297749,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004914634330540373,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.16082993894815445,
|
|
"num_tokens": 21635527.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.380307149887085,
|
|
"epoch": 0.9855741488747836,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004914521708886093,
|
|
"loss": 6.2392,
|
|
"mean_token_accuracy": 0.16111573278903962,
|
|
"num_tokens": 21648994.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.379744577407837,
|
|
"epoch": 0.9861511829197923,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004914409014429201,
|
|
"loss": 6.2758,
|
|
"mean_token_accuracy": 0.15881554186344146,
|
|
"num_tokens": 21661512.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.381563758850097,
|
|
"epoch": 0.986728216964801,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004914296247173486,
|
|
"loss": 6.3171,
|
|
"mean_token_accuracy": 0.15678785592317582,
|
|
"num_tokens": 21674900.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.508550548553467,
|
|
"epoch": 0.9873052510098096,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004914183407122741,
|
|
"loss": 6.5073,
|
|
"mean_token_accuracy": 0.1529560297727585,
|
|
"num_tokens": 21688451.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.460909605026245,
|
|
"epoch": 0.9878822850548182,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004914070494280763,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.15463425517082213,
|
|
"num_tokens": 21700350.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.382816743850708,
|
|
"epoch": 0.9884593190998269,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004913957508651349,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.16228749752044677,
|
|
"num_tokens": 21713211.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.36720757484436,
|
|
"epoch": 0.9890363531448355,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004913844450238299,
|
|
"loss": 6.2327,
|
|
"mean_token_accuracy": 0.16315484046936035,
|
|
"num_tokens": 21726105.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.412167978286743,
|
|
"epoch": 0.9896133871898442,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004913731319045416,
|
|
"loss": 6.2817,
|
|
"mean_token_accuracy": 0.16310435831546782,
|
|
"num_tokens": 21738075.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.411454057693481,
|
|
"epoch": 0.9901904212348529,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004913618115076505,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.16109486371278764,
|
|
"num_tokens": 21750614.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.256771802902222,
|
|
"epoch": 0.9907674552798615,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004913504838335372,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.1610737442970276,
|
|
"num_tokens": 21763670.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.344682216644287,
|
|
"epoch": 0.9913444893248702,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004913391488825829,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.16902547478675842,
|
|
"num_tokens": 21776623.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.429253101348877,
|
|
"epoch": 0.9919215233698788,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004913278066551689,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.1598364844918251,
|
|
"num_tokens": 21787903.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.308300876617432,
|
|
"epoch": 0.9924985574148875,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004913164571516765,
|
|
"loss": 6.1519,
|
|
"mean_token_accuracy": 0.1660546824336052,
|
|
"num_tokens": 21800409.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.34729495048523,
|
|
"epoch": 0.9930755914598961,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004913051003724876,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.15751274973154067,
|
|
"num_tokens": 21812741.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.407994890213013,
|
|
"epoch": 0.9936526255049047,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004912937363179839,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.16249522119760512,
|
|
"num_tokens": 21826180.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.504053926467895,
|
|
"epoch": 0.9942296595499135,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000491282364988548,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.15898843556642533,
|
|
"num_tokens": 21838961.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.395296335220337,
|
|
"epoch": 0.9948066935949221,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004912709863845621,
|
|
"loss": 6.2812,
|
|
"mean_token_accuracy": 0.16122212558984755,
|
|
"num_tokens": 21850942.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.361412048339844,
|
|
"epoch": 0.9953837276399308,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000491259600506409,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.16818103045225144,
|
|
"num_tokens": 21862666.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.396421813964844,
|
|
"epoch": 0.9959607616849394,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004912482073544716,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.16952535808086394,
|
|
"num_tokens": 21874866.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.403103637695312,
|
|
"epoch": 0.996537795729948,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004912368069291333,
|
|
"loss": 6.3302,
|
|
"mean_token_accuracy": 0.1602864071726799,
|
|
"num_tokens": 21887886.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.4391790390014645,
|
|
"epoch": 0.9971148297749567,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004912253992307773,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.15628421008586885,
|
|
"num_tokens": 21901096.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.439533281326294,
|
|
"epoch": 0.9976918638199653,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004912139842597875,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.16195413023233413,
|
|
"num_tokens": 21914018.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.36651029586792,
|
|
"epoch": 0.9982688978649741,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004912025620165477,
|
|
"loss": 6.2606,
|
|
"mean_token_accuracy": 0.16470131576061248,
|
|
"num_tokens": 21925488.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.478236961364746,
|
|
"epoch": 0.9988459319099827,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004911911325014421,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.14617064893245696,
|
|
"num_tokens": 21938268.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.4387367248535154,
|
|
"epoch": 0.9994229659549914,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004911796957148552,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.16030535250902175,
|
|
"num_tokens": 21951219.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.430270862579346,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004911682516571715,
|
|
"loss": 6.2959,
|
|
"mean_token_accuracy": 0.15840745270252227,
|
|
"num_tokens": 21963117.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.426940965652466,
|
|
"epoch": 1.0005770340450086,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004911568003287761,
|
|
"loss": 6.2376,
|
|
"mean_token_accuracy": 0.1605121448636055,
|
|
"num_tokens": 21974187.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.415137052536011,
|
|
"epoch": 1.0011540680900173,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004911453417300541,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.16247110962867736,
|
|
"num_tokens": 21987393.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.38947024345398,
|
|
"epoch": 1.001731102135026,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004911338758613909,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.16808023154735566,
|
|
"num_tokens": 21998638.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.340237426757812,
|
|
"epoch": 1.0023081361800346,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004911224027231722,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.16497329473495484,
|
|
"num_tokens": 22012231.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.314101123809815,
|
|
"epoch": 1.0028851702250432,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004911109223157838,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.1724448785185814,
|
|
"num_tokens": 22024929.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.372276830673218,
|
|
"epoch": 1.0034622042700518,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004910994346396118,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.16675959825515746,
|
|
"num_tokens": 22037873.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.307498407363892,
|
|
"epoch": 1.0040392383150605,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004910879396950427,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.16449054181575776,
|
|
"num_tokens": 22049572.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.38808240890503,
|
|
"epoch": 1.0046162723600693,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000491076437482463,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.15654898583889007,
|
|
"num_tokens": 22063290.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 6.271512460708618,
|
|
"epoch": 1.005193306405078,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004910649280022599,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.1705736681818962,
|
|
"num_tokens": 22076387.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.347558546066284,
|
|
"epoch": 1.0057703404500866,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004910534112548201,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.16337237358093262,
|
|
"num_tokens": 22088780.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.276888036727906,
|
|
"epoch": 1.0063473744950953,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004910418872405312,
|
|
"loss": 6.0633,
|
|
"mean_token_accuracy": 0.1731952100992203,
|
|
"num_tokens": 22102150.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.3603862762451175,
|
|
"epoch": 1.006924408540104,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004910303559597806,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.16267468482255937,
|
|
"num_tokens": 22115250.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.325836277008056,
|
|
"epoch": 1.0075014425851125,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004910188174129564,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.1561719983816147,
|
|
"num_tokens": 22129015.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.2975523471832275,
|
|
"epoch": 1.0080784766301212,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004910072716004466,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.16403840184211732,
|
|
"num_tokens": 22141716.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.385508728027344,
|
|
"epoch": 1.0086555106751298,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004909957185226394,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.1517787382006645,
|
|
"num_tokens": 22153568.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.447339200973511,
|
|
"epoch": 1.0092325447201385,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004909841581799236,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.1596845343708992,
|
|
"num_tokens": 22165443.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.389078998565674,
|
|
"epoch": 1.009809578765147,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004909725905726879,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.1615777239203453,
|
|
"num_tokens": 22179068.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.350357580184936,
|
|
"epoch": 1.0103866128101557,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004909610157013214,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.15202371701598166,
|
|
"num_tokens": 22191597.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.410714101791382,
|
|
"epoch": 1.0109636468551644,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004909494335662134,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.16322282552719117,
|
|
"num_tokens": 22203724.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.303729724884033,
|
|
"epoch": 1.011540680900173,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004909378441677535,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.16659850329160691,
|
|
"num_tokens": 22216100.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.359002780914307,
|
|
"epoch": 1.0121177149451817,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004909262475063314,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.15876885056495665,
|
|
"num_tokens": 22228162.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.332960414886474,
|
|
"epoch": 1.0126947489901905,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004909146435823373,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.16825098544359207,
|
|
"num_tokens": 22239756.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.333130693435669,
|
|
"epoch": 1.0132717830351992,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004909030323961613,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.15986109226942063,
|
|
"num_tokens": 22252781.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.3398871421813965,
|
|
"epoch": 1.0138488170802078,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004908914139481942,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.15804215222597123,
|
|
"num_tokens": 22265171.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.337258434295654,
|
|
"epoch": 1.0144258511252164,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004908797882388265,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.16364909410476686,
|
|
"num_tokens": 22278121.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.275689315795899,
|
|
"epoch": 1.015002885170225,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004908681552684495,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.166185662150383,
|
|
"num_tokens": 22290074.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.295356369018554,
|
|
"epoch": 1.0155799192152337,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004908565150374542,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.16460571438074112,
|
|
"num_tokens": 22303088.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.413890361785889,
|
|
"epoch": 1.0161569532602424,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004908448675462323,
|
|
"loss": 6.2355,
|
|
"mean_token_accuracy": 0.1506106361746788,
|
|
"num_tokens": 22317693.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.359114170074463,
|
|
"epoch": 1.016733987305251,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004908332127951756,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.1655200481414795,
|
|
"num_tokens": 22330876.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.337749481201172,
|
|
"epoch": 1.0173110213502596,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004908215507846757,
|
|
"loss": 6.1308,
|
|
"mean_token_accuracy": 0.1639953449368477,
|
|
"num_tokens": 22342620.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.328289365768432,
|
|
"epoch": 1.0178880553952683,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004908098815151254,
|
|
"loss": 6.1631,
|
|
"mean_token_accuracy": 0.1632054179906845,
|
|
"num_tokens": 22353733.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.461244201660156,
|
|
"epoch": 1.018465089440277,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004907982049869168,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.15410459488630296,
|
|
"num_tokens": 22366857.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.299141931533813,
|
|
"epoch": 1.0190421234852856,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004907865212004428,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.16742806285619735,
|
|
"num_tokens": 22377658.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.279093837738037,
|
|
"epoch": 1.0196191575302942,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004907748301560963,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.15780699700117112,
|
|
"num_tokens": 22390060.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.34080319404602,
|
|
"epoch": 1.0201961915753028,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004907631318542707,
|
|
"loss": 6.1819,
|
|
"mean_token_accuracy": 0.1587137073278427,
|
|
"num_tokens": 22402903.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.349684619903565,
|
|
"epoch": 1.0207732256203117,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004907514262953594,
|
|
"loss": 6.1471,
|
|
"mean_token_accuracy": 0.16755905002355576,
|
|
"num_tokens": 22416036.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.399058294296265,
|
|
"epoch": 1.0213502596653203,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004907397134797559,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.16025111079216003,
|
|
"num_tokens": 22428000.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.285398197174072,
|
|
"epoch": 1.021927293710329,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004907279934078543,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.16548313647508622,
|
|
"num_tokens": 22440029.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.307600975036621,
|
|
"epoch": 1.0225043277553376,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004907162660800488,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.1566235363483429,
|
|
"num_tokens": 22452906.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.368782329559326,
|
|
"epoch": 1.0230813618003463,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004907045314967338,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.17112531810998916,
|
|
"num_tokens": 22465853.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.359477853775024,
|
|
"epoch": 1.023658395845355,
|
|
"grad_norm": 4.71875,
|
|
"learning_rate": 0.0004906927896583041,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.1638613685965538,
|
|
"num_tokens": 22478583.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.2635619163513185,
|
|
"epoch": 1.0242354298903635,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004906810405651546,
|
|
"loss": 6.185,
|
|
"mean_token_accuracy": 0.16508891731500625,
|
|
"num_tokens": 22491665.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.332400894165039,
|
|
"epoch": 1.0248124639353722,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004906692842176803,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.16148089468479157,
|
|
"num_tokens": 22504015.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.441442584991455,
|
|
"epoch": 1.0253894979803808,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004906575206162769,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.15498681217432023,
|
|
"num_tokens": 22516385.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.370885753631592,
|
|
"epoch": 1.0259665320253895,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004906457497613399,
|
|
"loss": 6.1514,
|
|
"mean_token_accuracy": 0.16406670212745667,
|
|
"num_tokens": 22527988.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.2743278503417965,
|
|
"epoch": 1.026543566070398,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004906339716532651,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.16317007690668106,
|
|
"num_tokens": 22540613.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.298226737976075,
|
|
"epoch": 1.0271206001154067,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004906221862924488,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.16695300936698915,
|
|
"num_tokens": 22552137.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.369357299804688,
|
|
"epoch": 1.0276976341604154,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004906103936792875,
|
|
"loss": 6.2491,
|
|
"mean_token_accuracy": 0.15076114386320114,
|
|
"num_tokens": 22564677.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.419727420806884,
|
|
"epoch": 1.028274668205424,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004905985938141777,
|
|
"loss": 6.1798,
|
|
"mean_token_accuracy": 0.1652047887444496,
|
|
"num_tokens": 22578236.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.350459432601928,
|
|
"epoch": 1.0288517022504329,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004905867866975163,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.16516325920820235,
|
|
"num_tokens": 22592533.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.358260679244995,
|
|
"epoch": 1.0294287362954415,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004905749723297003,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.15685783475637435,
|
|
"num_tokens": 22606062.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.399117088317871,
|
|
"epoch": 1.0300057703404502,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004905631507111271,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.15823203176259995,
|
|
"num_tokens": 22619342.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.342332744598389,
|
|
"epoch": 1.0305828043854588,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004905513218421946,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.16186433136463166,
|
|
"num_tokens": 22632003.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.3654186725616455,
|
|
"epoch": 1.0311598384304674,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004905394857233004,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.16698863506317138,
|
|
"num_tokens": 22644179.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.423052978515625,
|
|
"epoch": 1.031736872475476,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004905276423548426,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.16120436564087867,
|
|
"num_tokens": 22657544.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.401259517669677,
|
|
"epoch": 1.0323139065204847,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004905157917372197,
|
|
"loss": 6.2665,
|
|
"mean_token_accuracy": 0.15423907488584518,
|
|
"num_tokens": 22670789.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.326565361022949,
|
|
"epoch": 1.0328909405654934,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004905039338708302,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.15901732444763184,
|
|
"num_tokens": 22682491.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.43274712562561,
|
|
"epoch": 1.033467974610502,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004904920687560728,
|
|
"loss": 6.2071,
|
|
"mean_token_accuracy": 0.16146688759326935,
|
|
"num_tokens": 22695235.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.322785186767578,
|
|
"epoch": 1.0340450086555106,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004904801963933469,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.16150673478841782,
|
|
"num_tokens": 22707222.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.356104993820191,
|
|
"epoch": 1.0346220427005193,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004904683167830515,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.1534208372235298,
|
|
"num_tokens": 22718820.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.398207187652588,
|
|
"epoch": 1.035199076745528,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004904564299255862,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.16409973949193954,
|
|
"num_tokens": 22731265.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.334744119644165,
|
|
"epoch": 1.0357761107905366,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004904445358213511,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.1598776698112488,
|
|
"num_tokens": 22744222.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.229028511047363,
|
|
"epoch": 1.0363531448355452,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004904326344707461,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.1658041372895241,
|
|
"num_tokens": 22756190.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.297280120849609,
|
|
"epoch": 1.036930178880554,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004904207258741712,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.1679148942232132,
|
|
"num_tokens": 22767943.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.369158220291138,
|
|
"epoch": 1.0375072129255627,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004904088100320274,
|
|
"loss": 6.1554,
|
|
"mean_token_accuracy": 0.1659896582365036,
|
|
"num_tokens": 22780972.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.400546598434448,
|
|
"epoch": 1.0380842469705713,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004903968869447151,
|
|
"loss": 6.2692,
|
|
"mean_token_accuracy": 0.1603499099612236,
|
|
"num_tokens": 22792584.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.354660606384277,
|
|
"epoch": 1.03866128101558,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004903849566126356,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.16254472136497497,
|
|
"num_tokens": 22807385.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.03866128101558,
|
|
"eval_entropy": 6.251975536007484,
|
|
"eval_loss": 6.3294453620910645,
|
|
"eval_mean_token_accuracy": 0.16032058560999918,
|
|
"eval_num_tokens": 22807385.0,
|
|
"eval_runtime": 22.7515,
|
|
"eval_samples_per_second": 1236.663,
|
|
"eval_steps_per_second": 154.583,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 6.375589609146118,
|
|
"epoch": 1.0392383150605886,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004903730190361902,
|
|
"loss": 6.2186,
|
|
"mean_token_accuracy": 0.1562452420592308,
|
|
"num_tokens": 22820655.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 6.387510585784912,
|
|
"epoch": 1.0398153491055973,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00049036107421578,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.16923735439777374,
|
|
"num_tokens": 22833043.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 6.322872257232666,
|
|
"epoch": 1.040392383150606,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004903491221518073,
|
|
"loss": 6.2247,
|
|
"mean_token_accuracy": 0.16158089339733123,
|
|
"num_tokens": 22844414.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 6.334288787841797,
|
|
"epoch": 1.0409694171956145,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004903371628446737,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.16435754895210267,
|
|
"num_tokens": 22855966.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 6.290288877487183,
|
|
"epoch": 1.0415464512406232,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004903251962947817,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.16436477303504943,
|
|
"num_tokens": 22869300.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 6.392134428024292,
|
|
"epoch": 1.0421234852856318,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004903132225025335,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.1661277323961258,
|
|
"num_tokens": 22881040.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 6.345999336242675,
|
|
"epoch": 1.0427005193306405,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004903012414683322,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.1675960272550583,
|
|
"num_tokens": 22892367.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 6.356339693069458,
|
|
"epoch": 1.043277553375649,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004902892531925805,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1567448541522026,
|
|
"num_tokens": 22904737.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 6.377230978012085,
|
|
"epoch": 1.0438545874206577,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004902772576756818,
|
|
"loss": 6.2375,
|
|
"mean_token_accuracy": 0.15742040425539017,
|
|
"num_tokens": 22917775.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 6.351797676086425,
|
|
"epoch": 1.0444316214656664,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004902652549180394,
|
|
"loss": 6.2575,
|
|
"mean_token_accuracy": 0.15253747701644899,
|
|
"num_tokens": 22930496.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 6.380230855941773,
|
|
"epoch": 1.0450086555106752,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004902532449200571,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.15602196007966995,
|
|
"num_tokens": 22943787.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 6.360061550140381,
|
|
"epoch": 1.0455856895556839,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004902412276821386,
|
|
"loss": 6.1759,
|
|
"mean_token_accuracy": 0.16011980623006822,
|
|
"num_tokens": 22956399.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 6.331561517715454,
|
|
"epoch": 1.0461627236006925,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004902292032046887,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.15832901746034622,
|
|
"num_tokens": 22969993.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 6.431485795974732,
|
|
"epoch": 1.0467397576457012,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004902171714881112,
|
|
"loss": 6.2884,
|
|
"mean_token_accuracy": 0.15681524723768234,
|
|
"num_tokens": 22983807.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 6.39180817604065,
|
|
"epoch": 1.0473167916907098,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004902051325328112,
|
|
"loss": 6.235,
|
|
"mean_token_accuracy": 0.1634105086326599,
|
|
"num_tokens": 22996238.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 6.372631359100342,
|
|
"epoch": 1.0478938257357184,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004901930863391934,
|
|
"loss": 6.2263,
|
|
"mean_token_accuracy": 0.1627142459154129,
|
|
"num_tokens": 23009084.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 6.471501731872559,
|
|
"epoch": 1.048470859780727,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000490181032907663,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.15503096878528594,
|
|
"num_tokens": 23022799.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 6.345464706420898,
|
|
"epoch": 1.0490478938257357,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004901689722386255,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.1631155714392662,
|
|
"num_tokens": 23035566.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 6.2709979057312015,
|
|
"epoch": 1.0496249278707444,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004901569043324864,
|
|
"loss": 6.1007,
|
|
"mean_token_accuracy": 0.17416824996471406,
|
|
"num_tokens": 23050156.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 6.332347631454468,
|
|
"epoch": 1.050201961915753,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004901448291896518,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.16119893938302993,
|
|
"num_tokens": 23063121.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 6.363145351409912,
|
|
"epoch": 1.0507789959607616,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004901327468105277,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.1751132309436798,
|
|
"num_tokens": 23075236.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 6.300115585327148,
|
|
"epoch": 1.0513560300057703,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004901206571955205,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.16072097718715667,
|
|
"num_tokens": 23089091.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 6.385873746871948,
|
|
"epoch": 1.051933064050779,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004901085603450369,
|
|
"loss": 6.2176,
|
|
"mean_token_accuracy": 0.15178074762225152,
|
|
"num_tokens": 23101642.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 6.3707091331481935,
|
|
"epoch": 1.0525100980957875,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004900964562594838,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.16434525996446608,
|
|
"num_tokens": 23113427.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 6.324672508239746,
|
|
"epoch": 1.0530871321407964,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000490084344939268,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.16822165101766587,
|
|
"num_tokens": 23125857.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 6.295746231079102,
|
|
"epoch": 1.053664166185805,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004900722263847973,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.16180892288684845,
|
|
"num_tokens": 23138541.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 6.283871793746949,
|
|
"epoch": 1.0542412002308137,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004900601005964791,
|
|
"loss": 6.1741,
|
|
"mean_token_accuracy": 0.1658548966050148,
|
|
"num_tokens": 23151155.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 6.381706619262696,
|
|
"epoch": 1.0548182342758223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004900479675747212,
|
|
"loss": 6.179,
|
|
"mean_token_accuracy": 0.15879111289978026,
|
|
"num_tokens": 23165478.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 6.3661736965179445,
|
|
"epoch": 1.055395268320831,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004900358273199316,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.15336017161607743,
|
|
"num_tokens": 23178120.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 6.3876782894134525,
|
|
"epoch": 1.0559723023658396,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000490023679832519,
|
|
"loss": 6.2258,
|
|
"mean_token_accuracy": 0.15789849311113358,
|
|
"num_tokens": 23191275.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 6.295345401763916,
|
|
"epoch": 1.0565493364108482,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004900115251128916,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.15735087543725967,
|
|
"num_tokens": 23204518.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 6.415962743759155,
|
|
"epoch": 1.057126370455857,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004899993631614583,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.15383946001529694,
|
|
"num_tokens": 23217488.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 6.418709421157837,
|
|
"epoch": 1.0577034045008655,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004899871939786283,
|
|
"loss": 6.2066,
|
|
"mean_token_accuracy": 0.16239057183265687,
|
|
"num_tokens": 23230101.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 6.295369005203247,
|
|
"epoch": 1.0582804385458742,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004899750175648107,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.15164581537246705,
|
|
"num_tokens": 23243747.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 6.400159597396851,
|
|
"epoch": 1.0588574725908828,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004899628339204154,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.1617654398083687,
|
|
"num_tokens": 23256593.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 6.389183235168457,
|
|
"epoch": 1.0594345066358914,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004899506430458518,
|
|
"loss": 6.2726,
|
|
"mean_token_accuracy": 0.15196809992194177,
|
|
"num_tokens": 23269359.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 6.304968214035034,
|
|
"epoch": 1.0600115406809,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004899384449415302,
|
|
"loss": 6.1119,
|
|
"mean_token_accuracy": 0.16750582456588745,
|
|
"num_tokens": 23283462.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 6.301669359207153,
|
|
"epoch": 1.0605885747259087,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004899262396078606,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.16235196888446807,
|
|
"num_tokens": 23295920.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 6.443309926986695,
|
|
"epoch": 1.0611656087709176,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004899140270452539,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.16026893705129625,
|
|
"num_tokens": 23307433.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 6.360797882080078,
|
|
"epoch": 1.0617426428159262,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004899018072541204,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.1604166179895401,
|
|
"num_tokens": 23320265.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 6.2488456726074215,
|
|
"epoch": 1.0623196768609349,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004898895802348715,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.16586936563253402,
|
|
"num_tokens": 23331951.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 6.276108264923096,
|
|
"epoch": 1.0628967109059435,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004898773459879183,
|
|
"loss": 6.2023,
|
|
"mean_token_accuracy": 0.15901616886258124,
|
|
"num_tokens": 23344862.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 6.370738840103149,
|
|
"epoch": 1.0634737449509521,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004898651045136724,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.15551743656396866,
|
|
"num_tokens": 23357212.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 6.334261131286621,
|
|
"epoch": 1.0640507789959608,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004898528558125453,
|
|
"loss": 6.1547,
|
|
"mean_token_accuracy": 0.16699836254119874,
|
|
"num_tokens": 23370114.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 6.3864648818969725,
|
|
"epoch": 1.0646278130409694,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004898405998849492,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.15924877747893335,
|
|
"num_tokens": 23382295.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 6.2677223682403564,
|
|
"epoch": 1.065204847085978,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004898283367312962,
|
|
"loss": 6.1904,
|
|
"mean_token_accuracy": 0.1685797780752182,
|
|
"num_tokens": 23395477.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 6.282564926147461,
|
|
"epoch": 1.0657818811309867,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004898160663519988,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.16062789410352707,
|
|
"num_tokens": 23407868.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 6.367104148864746,
|
|
"epoch": 1.0663589151759953,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004898037887474697,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.1604292392730713,
|
|
"num_tokens": 23422156.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 6.323754930496216,
|
|
"epoch": 1.066935949221004,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004897915039181219,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.1669705554842949,
|
|
"num_tokens": 23433951.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 6.293605089187622,
|
|
"epoch": 1.0675129832660126,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004897792118643685,
|
|
"loss": 6.1905,
|
|
"mean_token_accuracy": 0.16886758506298066,
|
|
"num_tokens": 23447174.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 6.372821855545044,
|
|
"epoch": 1.0680900173110213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004897669125866231,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.16654045432806014,
|
|
"num_tokens": 23458502.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 6.351552820205688,
|
|
"epoch": 1.06866705135603,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004897546060852993,
|
|
"loss": 6.2567,
|
|
"mean_token_accuracy": 0.15953566431999205,
|
|
"num_tokens": 23471572.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 6.332253694534302,
|
|
"epoch": 1.0692440854010385,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004897422923608108,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.16287099570035934,
|
|
"num_tokens": 23484454.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 6.344149446487426,
|
|
"epoch": 1.0698211194460474,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004897299714135721,
|
|
"loss": 6.2177,
|
|
"mean_token_accuracy": 0.15650669634342193,
|
|
"num_tokens": 23497022.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 6.39455246925354,
|
|
"epoch": 1.070398153491056,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004897176432439974,
|
|
"loss": 6.2155,
|
|
"mean_token_accuracy": 0.16501809060573577,
|
|
"num_tokens": 23510714.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 6.408887195587158,
|
|
"epoch": 1.0709751875360647,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004897053078525016,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.15856562554836273,
|
|
"num_tokens": 23522927.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 6.287023735046387,
|
|
"epoch": 1.0715522215810733,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004896929652394993,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.16473745703697204,
|
|
"num_tokens": 23536042.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 6.364973068237305,
|
|
"epoch": 1.072129255626082,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004896806154054057,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.15745574235916138,
|
|
"num_tokens": 23549002.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 6.400933647155762,
|
|
"epoch": 1.0727062896710906,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004896682583506363,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.15413917899131774,
|
|
"num_tokens": 23563080.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 6.418299388885498,
|
|
"epoch": 1.0732833237160992,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004896558940756067,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.15697152465581893,
|
|
"num_tokens": 23577431.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 6.302762603759765,
|
|
"epoch": 1.0738603577611079,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004896435225807327,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.16009364873170853,
|
|
"num_tokens": 23591191.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 6.322522497177124,
|
|
"epoch": 1.0744373918061165,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004896311438664304,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.17335233688354493,
|
|
"num_tokens": 23603195.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 6.314301586151123,
|
|
"epoch": 1.0750144258511252,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004896187579331163,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.16357824355363845,
|
|
"num_tokens": 23615278.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 6.371065235137939,
|
|
"epoch": 1.0755914598961338,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004896063647812068,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.16097504198551177,
|
|
"num_tokens": 23627311.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 6.334024095535279,
|
|
"epoch": 1.0761684939411424,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004895939644111189,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.1588624119758606,
|
|
"num_tokens": 23640338.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 6.397532653808594,
|
|
"epoch": 1.076745527986151,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004895815568232694,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.15749427080154418,
|
|
"num_tokens": 23654541.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 6.384134292602539,
|
|
"epoch": 1.07732256203116,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004895691420180759,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.16097208261489868,
|
|
"num_tokens": 23666837.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 6.424416351318359,
|
|
"epoch": 1.0778995960761686,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000489556719995956,
|
|
"loss": 6.22,
|
|
"mean_token_accuracy": 0.15995656698942184,
|
|
"num_tokens": 23679270.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 6.345190954208374,
|
|
"epoch": 1.0784766301211772,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004895442907573274,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.1626092180609703,
|
|
"num_tokens": 23691640.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 6.308082056045532,
|
|
"epoch": 1.0790536641661859,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000489531854302608,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.1572630599141121,
|
|
"num_tokens": 23704545.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 6.277027750015259,
|
|
"epoch": 1.0796306982111945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004895194106322164,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.17247570157051087,
|
|
"num_tokens": 23716319.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 6.384001874923706,
|
|
"epoch": 1.0802077322562031,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004895069597465709,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.16064286977052689,
|
|
"num_tokens": 23728633.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 6.416384887695313,
|
|
"epoch": 1.0807847663012118,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004894945016460904,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.1609300494194031,
|
|
"num_tokens": 23741370.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 6.349208211898803,
|
|
"epoch": 1.0813618003462204,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894820363311938,
|
|
"loss": 6.1808,
|
|
"mean_token_accuracy": 0.16120522022247313,
|
|
"num_tokens": 23754026.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 6.358585834503174,
|
|
"epoch": 1.081938834391229,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004894695638023005,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.1550566226243973,
|
|
"num_tokens": 23766950.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 6.364051389694214,
|
|
"epoch": 1.0825158684362377,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048945708405983,
|
|
"loss": 6.2438,
|
|
"mean_token_accuracy": 0.16189382672309877,
|
|
"num_tokens": 23780858.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 6.405634260177612,
|
|
"epoch": 1.0830929024812463,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004894445971042019,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.1622998982667923,
|
|
"num_tokens": 23793213.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 6.302175426483155,
|
|
"epoch": 1.083669936526255,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004894321029358364,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.1612499751150608,
|
|
"num_tokens": 23804754.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 6.287882852554321,
|
|
"epoch": 1.0842469705712636,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004894196015551536,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.16173621714115144,
|
|
"num_tokens": 23817503.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 6.3686400890350345,
|
|
"epoch": 1.0848240046162723,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000489407092962574,
|
|
"loss": 6.2052,
|
|
"mean_token_accuracy": 0.1568010240793228,
|
|
"num_tokens": 23830263.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 6.36795973777771,
|
|
"epoch": 1.085401038661281,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893945771585183,
|
|
"loss": 6.1213,
|
|
"mean_token_accuracy": 0.16961509138345718,
|
|
"num_tokens": 23843734.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 6.360470724105835,
|
|
"epoch": 1.0859780727062898,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004893820541434075,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.16234959214925765,
|
|
"num_tokens": 23856857.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 6.344463777542114,
|
|
"epoch": 1.0865551067512984,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004893695239176629,
|
|
"loss": 6.1358,
|
|
"mean_token_accuracy": 0.16343702822923661,
|
|
"num_tokens": 23869961.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 6.357371282577515,
|
|
"epoch": 1.087132140796307,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004893569864817057,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.15537794083356857,
|
|
"num_tokens": 23884551.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 6.3662666320800785,
|
|
"epoch": 1.0877091748413157,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004893444418359579,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.15453500151634217,
|
|
"num_tokens": 23897240.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 6.384363794326783,
|
|
"epoch": 1.0882862088863243,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000489331889980841,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.1617793247103691,
|
|
"num_tokens": 23909677.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 6.378599834442139,
|
|
"epoch": 1.088863242931333,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004893193309167778,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.15970574617385863,
|
|
"num_tokens": 23921552.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 6.402880382537842,
|
|
"epoch": 1.0894402769763416,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.0004893067646441902,
|
|
"loss": 6.2554,
|
|
"mean_token_accuracy": 0.15138119906187059,
|
|
"num_tokens": 23936315.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 6.350248575210571,
|
|
"epoch": 1.0900173110213502,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000489294191163501,
|
|
"loss": 6.229,
|
|
"mean_token_accuracy": 0.15604216903448104,
|
|
"num_tokens": 23948939.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 6.410356950759888,
|
|
"epoch": 1.0905943450663589,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004892816104751331,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.15622987747192382,
|
|
"num_tokens": 23961657.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 6.4098145961761475,
|
|
"epoch": 1.0911713791113675,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004892690225795096,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.14848166555166245,
|
|
"num_tokens": 23974085.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 6.303513717651367,
|
|
"epoch": 1.0917484131563762,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004892564274770542,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.1626450762152672,
|
|
"num_tokens": 23987038.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 6.442585802078247,
|
|
"epoch": 1.0923254472013848,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004892438251681901,
|
|
"loss": 6.2233,
|
|
"mean_token_accuracy": 0.16099887639284133,
|
|
"num_tokens": 24001051.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 6.355003547668457,
|
|
"epoch": 1.0929024812463934,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004892312156533413,
|
|
"loss": 6.1834,
|
|
"mean_token_accuracy": 0.15782278925180435,
|
|
"num_tokens": 24013817.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 6.28466534614563,
|
|
"epoch": 1.0934795152914023,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004892185989329321,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.164686119556427,
|
|
"num_tokens": 24025810.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 6.277740526199341,
|
|
"epoch": 1.094056549336411,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004892059750073868,
|
|
"loss": 6.1332,
|
|
"mean_token_accuracy": 0.16929626762866973,
|
|
"num_tokens": 24039796.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 6.366404342651367,
|
|
"epoch": 1.0946335833814196,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004891933438771299,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.16250718981027604,
|
|
"num_tokens": 24052721.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 6.3012937068939205,
|
|
"epoch": 1.0952106174264282,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004891807055425862,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.17106976062059404,
|
|
"num_tokens": 24064515.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 6.254371690750122,
|
|
"epoch": 1.0957876514714369,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004891680600041809,
|
|
"loss": 6.1401,
|
|
"mean_token_accuracy": 0.15985100865364074,
|
|
"num_tokens": 24078537.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 6.410112905502319,
|
|
"epoch": 1.0963646855164455,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004891554072623392,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.15630560666322707,
|
|
"num_tokens": 24092067.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 6.368152618408203,
|
|
"epoch": 1.0969417195614541,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004891427473174869,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.15990003943443298,
|
|
"num_tokens": 24105625.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 6.396222496032715,
|
|
"epoch": 1.0975187536064628,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004891300801700496,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.15077004134654998,
|
|
"num_tokens": 24119714.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 6.329865121841431,
|
|
"epoch": 1.0980957876514714,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004891174058204534,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.1595097690820694,
|
|
"num_tokens": 24132873.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 6.31348352432251,
|
|
"epoch": 1.09867282169648,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004891047242691246,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.15776203125715255,
|
|
"num_tokens": 24145550.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 6.367596292495728,
|
|
"epoch": 1.0992498557414887,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004890920355164897,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.15608249455690384,
|
|
"num_tokens": 24158232.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 6.392232513427734,
|
|
"epoch": 1.0998268897864973,
|
|
"grad_norm": 5.21875,
|
|
"learning_rate": 0.0004890793395629756,
|
|
"loss": 6.2952,
|
|
"mean_token_accuracy": 0.1520036354660988,
|
|
"num_tokens": 24170780.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 6.346212100982666,
|
|
"epoch": 1.100403923831506,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004890666364090093,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.16291800290346145,
|
|
"num_tokens": 24182347.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 6.402856874465942,
|
|
"epoch": 1.1009809578765146,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004890539260550181,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.15678591281175613,
|
|
"num_tokens": 24195215.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 6.30384635925293,
|
|
"epoch": 1.1015579919215233,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004890412085014292,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.16906683444976806,
|
|
"num_tokens": 24208214.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 6.382722663879394,
|
|
"epoch": 1.1021350259665321,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004890284837486706,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.1664133921265602,
|
|
"num_tokens": 24220883.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 6.351633214950562,
|
|
"epoch": 1.1027120600115408,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004890157517971704,
|
|
"loss": 6.1088,
|
|
"mean_token_accuracy": 0.16918679922819138,
|
|
"num_tokens": 24233918.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 6.356971645355225,
|
|
"epoch": 1.1032890940565494,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004890030126473566,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.15816302448511124,
|
|
"num_tokens": 24247307.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 6.337526273727417,
|
|
"epoch": 1.103866128101558,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004889902662996578,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.15724012702703477,
|
|
"num_tokens": 24260149.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 6.375165748596191,
|
|
"epoch": 1.1044431621465667,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004889775127545027,
|
|
"loss": 6.238,
|
|
"mean_token_accuracy": 0.15898802280426025,
|
|
"num_tokens": 24273675.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 6.340470027923584,
|
|
"epoch": 1.1050201961915753,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004889647520123202,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.1621945694088936,
|
|
"num_tokens": 24285575.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 6.410197305679321,
|
|
"epoch": 1.105597230236584,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004889519840735396,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.16513626426458358,
|
|
"num_tokens": 24297908.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 6.233777141571045,
|
|
"epoch": 1.1061742642815926,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004889392089385903,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.16366908550262452,
|
|
"num_tokens": 24310714.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 6.280074691772461,
|
|
"epoch": 1.1067512983266012,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004889264266079019,
|
|
"loss": 6.1752,
|
|
"mean_token_accuracy": 0.16871743351221086,
|
|
"num_tokens": 24322367.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 6.287104368209839,
|
|
"epoch": 1.1073283323716099,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004889136370819045,
|
|
"loss": 6.1854,
|
|
"mean_token_accuracy": 0.15897441729903222,
|
|
"num_tokens": 24334256.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 6.3352649211883545,
|
|
"epoch": 1.1079053664166185,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004889008403610281,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.1653594493865967,
|
|
"num_tokens": 24346968.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 6.436962127685547,
|
|
"epoch": 1.1084824004616272,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004888880364457033,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.1597901850938797,
|
|
"num_tokens": 24360468.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 6.369411945343018,
|
|
"epoch": 1.1090594345066358,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004888752253363604,
|
|
"loss": 6.1868,
|
|
"mean_token_accuracy": 0.16491993069648742,
|
|
"num_tokens": 24372330.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 6.2847589492797855,
|
|
"epoch": 1.1096364685516447,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004888624070334308,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.16332882195711135,
|
|
"num_tokens": 24384864.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 6.321532726287842,
|
|
"epoch": 1.1102135025966533,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004888495815373452,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.16914285868406295,
|
|
"num_tokens": 24397408.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 6.317392492294312,
|
|
"epoch": 1.110790536641662,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004888367488485351,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.1612032026052475,
|
|
"num_tokens": 24409113.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 6.314182138442993,
|
|
"epoch": 1.1113675706866706,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004888239089674323,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.16142479479312896,
|
|
"num_tokens": 24420818.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 6.383041763305664,
|
|
"epoch": 1.1119446047316792,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004888110618944686,
|
|
"loss": 6.2779,
|
|
"mean_token_accuracy": 0.15037421733140946,
|
|
"num_tokens": 24434452.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 6.427024078369141,
|
|
"epoch": 1.1125216387766879,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004887982076300759,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.15480797290802,
|
|
"num_tokens": 24448674.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 6.376167249679566,
|
|
"epoch": 1.1130986728216965,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004887853461746867,
|
|
"loss": 6.1727,
|
|
"mean_token_accuracy": 0.15854671001434326,
|
|
"num_tokens": 24461388.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 6.356609535217285,
|
|
"epoch": 1.1136757068667051,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004887724775287336,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.16579209119081498,
|
|
"num_tokens": 24474304.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 6.258968782424927,
|
|
"epoch": 1.1142527409117138,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004887596016926494,
|
|
"loss": 6.117,
|
|
"mean_token_accuracy": 0.16495985984802247,
|
|
"num_tokens": 24487175.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 6.345869302749634,
|
|
"epoch": 1.1148297749567224,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004887467186668673,
|
|
"loss": 6.1624,
|
|
"mean_token_accuracy": 0.1574894145131111,
|
|
"num_tokens": 24500160.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 6.4012657642364506,
|
|
"epoch": 1.115406809001731,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004887338284518204,
|
|
"loss": 6.2653,
|
|
"mean_token_accuracy": 0.15609754621982574,
|
|
"num_tokens": 24513358.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 6.367801094055176,
|
|
"epoch": 1.1159838430467397,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004887209310479423,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.16932276785373687,
|
|
"num_tokens": 24526254.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 6.327196407318115,
|
|
"epoch": 1.1165608770917483,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004887080264556668,
|
|
"loss": 6.082,
|
|
"mean_token_accuracy": 0.16644769310951232,
|
|
"num_tokens": 24540023.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 6.344431686401367,
|
|
"epoch": 1.117137911136757,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004886951146754282,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.1614872083067894,
|
|
"num_tokens": 24553270.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 6.389737462997436,
|
|
"epoch": 1.1177149451817656,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004886821957076603,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.16487915813922882,
|
|
"num_tokens": 24565576.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 6.313331651687622,
|
|
"epoch": 1.1182919792267745,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000488669269552798,
|
|
"loss": 6.2514,
|
|
"mean_token_accuracy": 0.16085973232984543,
|
|
"num_tokens": 24578825.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 6.3549232006073,
|
|
"epoch": 1.1188690132717831,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000488656336211276,
|
|
"loss": 6.2449,
|
|
"mean_token_accuracy": 0.15805209577083587,
|
|
"num_tokens": 24592058.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 6.404150485992432,
|
|
"epoch": 1.1194460473167918,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004886433956835292,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.16113292276859284,
|
|
"num_tokens": 24605956.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 6.3350914478302,
|
|
"epoch": 1.1200230813618004,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004886304479699929,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.16226267218589782,
|
|
"num_tokens": 24618904.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 6.391560220718384,
|
|
"epoch": 1.120600115406809,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004886174930711027,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.16147204041481017,
|
|
"num_tokens": 24632720.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 6.404454040527344,
|
|
"epoch": 1.1211771494518177,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004886045309872941,
|
|
"loss": 6.2417,
|
|
"mean_token_accuracy": 0.15741440653800964,
|
|
"num_tokens": 24644863.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 6.412680292129517,
|
|
"epoch": 1.1217541834968263,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004885915617190034,
|
|
"loss": 6.2241,
|
|
"mean_token_accuracy": 0.15678914189338683,
|
|
"num_tokens": 24656884.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 6.399668502807617,
|
|
"epoch": 1.122331217541835,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004885785852666664,
|
|
"loss": 6.2334,
|
|
"mean_token_accuracy": 0.15685741007328033,
|
|
"num_tokens": 24671008.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 6.36036114692688,
|
|
"epoch": 1.1229082515868436,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004885656016307199,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.15478505194187164,
|
|
"num_tokens": 24685787.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 6.463143396377563,
|
|
"epoch": 1.1234852856318522,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004885526108116004,
|
|
"loss": 6.2564,
|
|
"mean_token_accuracy": 0.16071103662252426,
|
|
"num_tokens": 24697233.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 6.365033102035523,
|
|
"epoch": 1.1240623196768609,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000488539612809745,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.162790547311306,
|
|
"num_tokens": 24709409.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 6.303580236434937,
|
|
"epoch": 1.1246393537218695,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004885266076255907,
|
|
"loss": 6.2484,
|
|
"mean_token_accuracy": 0.15676273554563522,
|
|
"num_tokens": 24722006.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 6.456765222549438,
|
|
"epoch": 1.1252163877668782,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000488513595259575,
|
|
"loss": 6.2482,
|
|
"mean_token_accuracy": 0.15536370426416396,
|
|
"num_tokens": 24736060.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 6.362082052230835,
|
|
"epoch": 1.125793421811887,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004885005757121357,
|
|
"loss": 6.222,
|
|
"mean_token_accuracy": 0.1529646933078766,
|
|
"num_tokens": 24748008.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 6.346718120574951,
|
|
"epoch": 1.1263704558568954,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004884875489837105,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.15854579210281372,
|
|
"num_tokens": 24760631.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 6.198451948165894,
|
|
"epoch": 1.1269474899019043,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004884745150747378,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.17826538532972336,
|
|
"num_tokens": 24772646.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 6.310153341293335,
|
|
"epoch": 1.127524523946913,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004884614739856556,
|
|
"loss": 6.2322,
|
|
"mean_token_accuracy": 0.15513329356908798,
|
|
"num_tokens": 24784571.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 6.441531229019165,
|
|
"epoch": 1.1281015579919216,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004884484257169028,
|
|
"loss": 6.218,
|
|
"mean_token_accuracy": 0.16059867888689042,
|
|
"num_tokens": 24797810.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 6.338571166992187,
|
|
"epoch": 1.1286785920369302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004884353702689183,
|
|
"loss": 6.2187,
|
|
"mean_token_accuracy": 0.16038416177034379,
|
|
"num_tokens": 24810677.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 6.347803831100464,
|
|
"epoch": 1.1292556260819389,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004884223076421411,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.16551823019981385,
|
|
"num_tokens": 24823138.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 6.200040245056153,
|
|
"epoch": 1.1298326601269475,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004884092378370106,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.17274417281150817,
|
|
"num_tokens": 24834548.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 6.300217199325561,
|
|
"epoch": 1.1304096941719561,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004883961608539664,
|
|
"loss": 6.2222,
|
|
"mean_token_accuracy": 0.16022792905569078,
|
|
"num_tokens": 24847326.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 6.326699066162109,
|
|
"epoch": 1.1309867282169648,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004883830766934484,
|
|
"loss": 6.07,
|
|
"mean_token_accuracy": 0.16643578335642814,
|
|
"num_tokens": 24860417.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 6.307373332977295,
|
|
"epoch": 1.1315637622619734,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004883699853558965,
|
|
"loss": 6.1698,
|
|
"mean_token_accuracy": 0.15934834480285645,
|
|
"num_tokens": 24872759.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 6.354069089889526,
|
|
"epoch": 1.132140796306982,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004883568868417511,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.15413878858089447,
|
|
"num_tokens": 24885278.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 6.389302158355713,
|
|
"epoch": 1.1327178303519907,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004883437811514528,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.15297829508781433,
|
|
"num_tokens": 24898596.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 6.396500825881958,
|
|
"epoch": 1.1332948643969993,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004883306682854424,
|
|
"loss": 6.1644,
|
|
"mean_token_accuracy": 0.163560388982296,
|
|
"num_tokens": 24911755.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 6.341898441314697,
|
|
"epoch": 1.133871898442008,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004883175482441611,
|
|
"loss": 6.2487,
|
|
"mean_token_accuracy": 0.1547734707593918,
|
|
"num_tokens": 24925197.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 6.277676725387574,
|
|
"epoch": 1.1344489324870168,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004883044210280499,
|
|
"loss": 6.0629,
|
|
"mean_token_accuracy": 0.17149295508861542,
|
|
"num_tokens": 24938204.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 6.299826765060425,
|
|
"epoch": 1.1350259665320255,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004882912866375505,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.16771370023489,
|
|
"num_tokens": 24949382.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 6.248973083496094,
|
|
"epoch": 1.1356030005770341,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048827814507310455,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.15670545101165773,
|
|
"num_tokens": 24961685.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 6.33607850074768,
|
|
"epoch": 1.1361800346220428,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048826499633515416,
|
|
"loss": 6.1412,
|
|
"mean_token_accuracy": 0.1669670268893242,
|
|
"num_tokens": 24973619.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 6.331471538543701,
|
|
"epoch": 1.1367570686670514,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048825184042414156,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.1675176814198494,
|
|
"num_tokens": 24985156.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 6.311733245849609,
|
|
"epoch": 1.13733410271206,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004882386773405092,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.17118309289216996,
|
|
"num_tokens": 24997891.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 6.35788254737854,
|
|
"epoch": 1.1379111367570687,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004882255070846999,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.16182998716831207,
|
|
"num_tokens": 25009824.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 6.362553501129151,
|
|
"epoch": 1.1384881708020773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048821232965715663,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.16237591803073884,
|
|
"num_tokens": 25021574.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 6.32572078704834,
|
|
"epoch": 1.139065204847086,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004881991450583225,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.1635513037443161,
|
|
"num_tokens": 25033315.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 6.2788228511810305,
|
|
"epoch": 1.1396422388920946,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000488185953288641,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.16586582809686662,
|
|
"num_tokens": 25046284.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 6.362651920318603,
|
|
"epoch": 1.1402192729371032,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004881727543485559,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.15997907221317292,
|
|
"num_tokens": 25058484.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 6.3163597106933596,
|
|
"epoch": 1.1407963069821119,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048815954823851107,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.1663131073117256,
|
|
"num_tokens": 25070555.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 6.389148378372193,
|
|
"epoch": 1.1413733410271205,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048814633495895067,
|
|
"loss": 6.2474,
|
|
"mean_token_accuracy": 0.15366053134202956,
|
|
"num_tokens": 25083492.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 6.3734739303588865,
|
|
"epoch": 1.1419503750721294,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004881331145103192,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.15353629887104034,
|
|
"num_tokens": 25096332.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 6.382818603515625,
|
|
"epoch": 1.1425274091171378,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004881198868930614,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.15331874191761016,
|
|
"num_tokens": 25110447.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 6.479769325256347,
|
|
"epoch": 1.1431044431621467,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048810665210762195,
|
|
"loss": 6.2074,
|
|
"mean_token_accuracy": 0.16485313773155214,
|
|
"num_tokens": 25123852.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 6.382903051376343,
|
|
"epoch": 1.1436814772071553,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048809341015444615,
|
|
"loss": 6.2096,
|
|
"mean_token_accuracy": 0.15939941108226777,
|
|
"num_tokens": 25136151.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 6.3541422367095945,
|
|
"epoch": 1.144258511252164,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00048808016103397934,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.16297494173049926,
|
|
"num_tokens": 25149642.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 6.3219459533691404,
|
|
"epoch": 1.1448355452971726,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004880669047466671,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.17158780246973038,
|
|
"num_tokens": 25162022.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 6.376477193832398,
|
|
"epoch": 1.1454125793421812,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048805364129295554,
|
|
"loss": 6.2791,
|
|
"mean_token_accuracy": 0.1544181153178215,
|
|
"num_tokens": 25175404.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 6.315047931671143,
|
|
"epoch": 1.1459896133871899,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048804037067329037,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.16884433776140212,
|
|
"num_tokens": 25188148.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 6.355247545242309,
|
|
"epoch": 1.1465666474321985,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004880270928881183,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.1672818660736084,
|
|
"num_tokens": 25199960.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 6.2450096130371096,
|
|
"epoch": 1.1471436814772071,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004880138079378857,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.16437119990587234,
|
|
"num_tokens": 25211054.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 6.339324235916138,
|
|
"epoch": 1.1477207155222158,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004880005158230395,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.17020729631185533,
|
|
"num_tokens": 25222553.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 6.344603872299194,
|
|
"epoch": 1.1482977495672244,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004879872165440268,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.155762979388237,
|
|
"num_tokens": 25235472.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 6.270013475418091,
|
|
"epoch": 1.148874783612233,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004879739101012948,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.1624113589525223,
|
|
"num_tokens": 25250209.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 6.363943099975586,
|
|
"epoch": 1.1494518176572417,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004879605964952911,
|
|
"loss": 6.2106,
|
|
"mean_token_accuracy": 0.1601069986820221,
|
|
"num_tokens": 25262064.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 6.420304775238037,
|
|
"epoch": 1.1500288517022503,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048794727572646366,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.1625082701444626,
|
|
"num_tokens": 25274833.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 6.368671655654907,
|
|
"epoch": 1.1506058857472592,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004879339477952603,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.16648445650935173,
|
|
"num_tokens": 25288397.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 6.307248640060425,
|
|
"epoch": 1.1511829197922678,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048792061270212935,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.17006682157516478,
|
|
"num_tokens": 25300887.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 6.401169538497925,
|
|
"epoch": 1.1517599538372765,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004879072704475193,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.16358886212110518,
|
|
"num_tokens": 25314686.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 6.440695905685425,
|
|
"epoch": 1.1523369878822851,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048789392103187906,
|
|
"loss": 6.2611,
|
|
"mean_token_accuracy": 0.16165925413370133,
|
|
"num_tokens": 25328253.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 6.404678010940552,
|
|
"epoch": 1.1529140219272938,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004878805644556575,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.16324919015169143,
|
|
"num_tokens": 25340583.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 6.297409296035767,
|
|
"epoch": 1.1534910559723024,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000487867200719304,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.1642940953373909,
|
|
"num_tokens": 25352513.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 6.331809711456299,
|
|
"epoch": 1.154068090017311,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004878538298232678,
|
|
"loss": 6.2146,
|
|
"mean_token_accuracy": 0.15754812508821486,
|
|
"num_tokens": 25365044.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 6.367120790481567,
|
|
"epoch": 1.1546451240623197,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004878404517679988,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.15582527220249176,
|
|
"num_tokens": 25377381.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 6.400685453414917,
|
|
"epoch": 1.1552221581073283,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048782706655394695,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.1643991768360138,
|
|
"num_tokens": 25390723.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 6.296201992034912,
|
|
"epoch": 1.155799192152337,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004878136741815624,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.16537229716777802,
|
|
"num_tokens": 25403501.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 6.271032047271729,
|
|
"epoch": 1.1563762261973456,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004878002746512956,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.17037995159626007,
|
|
"num_tokens": 25415565.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 6.283905696868897,
|
|
"epoch": 1.1569532602423542,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004877868679635974,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.16751373708248138,
|
|
"num_tokens": 25428261.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 6.377343845367432,
|
|
"epoch": 1.1575302942873629,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004877734541189185,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.15702162981033324,
|
|
"num_tokens": 25439758.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 6.360610103607177,
|
|
"epoch": 1.1581073283323717,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048776003311771013,
|
|
"loss": 6.2364,
|
|
"mean_token_accuracy": 0.15337282419204712,
|
|
"num_tokens": 25452162.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 6.4076014995574955,
|
|
"epoch": 1.1586843623773802,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004877466049604238,
|
|
"loss": 6.2545,
|
|
"mean_token_accuracy": 0.15962868332862853,
|
|
"num_tokens": 25463741.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 6.320121145248413,
|
|
"epoch": 1.159261396422389,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048773316964751106,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.15946279913187028,
|
|
"num_tokens": 25476466.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 6.422423934936523,
|
|
"epoch": 1.1598384304673977,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004877197271794239,
|
|
"loss": 6.1692,
|
|
"mean_token_accuracy": 0.1618300974369049,
|
|
"num_tokens": 25488453.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 6.3750358581542965,
|
|
"epoch": 1.1604154645124063,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004877062775566142,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.16088102161884307,
|
|
"num_tokens": 25501803.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 6.349880695343018,
|
|
"epoch": 1.160992498557415,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048769282077953464,
|
|
"loss": 6.2892,
|
|
"mean_token_accuracy": 0.15862567573785782,
|
|
"num_tokens": 25515844.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 6.369120979309082,
|
|
"epoch": 1.1615695326024236,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048767935684863775,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.16268929988145828,
|
|
"num_tokens": 25528529.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 6.397540330886841,
|
|
"epoch": 1.1621465666474322,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004876658857643762,
|
|
"loss": 6.2204,
|
|
"mean_token_accuracy": 0.15767233669757844,
|
|
"num_tokens": 25540110.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 6.364495658874512,
|
|
"epoch": 1.1627236006924409,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004876524075272034,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.158960822224617,
|
|
"num_tokens": 25553332.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 6.348095035552978,
|
|
"epoch": 1.1633006347374495,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048763892213757234,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.16090085208415986,
|
|
"num_tokens": 25565852.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 6.36542158126831,
|
|
"epoch": 1.1638776687824581,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048762542959593683,
|
|
"loss": 6.1672,
|
|
"mean_token_accuracy": 0.1625974088907242,
|
|
"num_tokens": 25579642.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 6.2937578678131105,
|
|
"epoch": 1.1644547028274668,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004876119299027506,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.16866278797388076,
|
|
"num_tokens": 25591452.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 6.290343618392944,
|
|
"epoch": 1.1650317368724754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048759842305846766,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.16313421428203584,
|
|
"num_tokens": 25603426.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 6.355361557006836,
|
|
"epoch": 1.165608770917484,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004875849090635425,
|
|
"loss": 6.2365,
|
|
"mean_token_accuracy": 0.15997890681028365,
|
|
"num_tokens": 25617014.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 6.37194595336914,
|
|
"epoch": 1.1661858049624927,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048757138791842943,
|
|
"loss": 6.1972,
|
|
"mean_token_accuracy": 0.16384346783161163,
|
|
"num_tokens": 25629916.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 6.3468346118927,
|
|
"epoch": 1.1667628390075016,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004875578596235832,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.16534270495176315,
|
|
"num_tokens": 25642301.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 6.327104473114014,
|
|
"epoch": 1.1673398730525102,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004875443241794591,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.16186633408069612,
|
|
"num_tokens": 25653976.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 6.33780460357666,
|
|
"epoch": 1.1679169070975188,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048753078158651227,
|
|
"loss": 6.1864,
|
|
"mean_token_accuracy": 0.1554411083459854,
|
|
"num_tokens": 25666078.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 6.343927383422852,
|
|
"epoch": 1.1684939411425275,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000487517231845198,
|
|
"loss": 6.2353,
|
|
"mean_token_accuracy": 0.15490031838417054,
|
|
"num_tokens": 25679780.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 6.408223009109497,
|
|
"epoch": 1.169070975187536,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004875036749559724,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.1544538825750351,
|
|
"num_tokens": 25694179.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 6.275277757644654,
|
|
"epoch": 1.1696480092325447,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048749011091929115,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.17059712260961532,
|
|
"num_tokens": 25707281.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 6.383667278289795,
|
|
"epoch": 1.1702250432775534,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004874765397356105,
|
|
"loss": 6.1877,
|
|
"mean_token_accuracy": 0.16059649288654326,
|
|
"num_tokens": 25719901.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 6.355267190933228,
|
|
"epoch": 1.170802077322562,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004874629614053871,
|
|
"loss": 6.1934,
|
|
"mean_token_accuracy": 0.1627344861626625,
|
|
"num_tokens": 25732063.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 6.267529439926148,
|
|
"epoch": 1.1713791113675707,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004874493759290775,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.16306477189064025,
|
|
"num_tokens": 25743966.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 6.147643136978149,
|
|
"epoch": 1.1719561454125793,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.00048743578330713854,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.1810133144259453,
|
|
"num_tokens": 25757053.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 6.152535343170166,
|
|
"epoch": 1.172533179457588,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004874221835400277,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.17614102661609649,
|
|
"num_tokens": 25769430.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 6.3164385795593265,
|
|
"epoch": 1.1731102135025966,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004874085766282022,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.1642584428191185,
|
|
"num_tokens": 25781687.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 6.316783618927002,
|
|
"epoch": 1.1736872475476052,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048739496257211966,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.1690356597304344,
|
|
"num_tokens": 25793646.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 6.33498969078064,
|
|
"epoch": 1.1742642815926139,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048738134137223815,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.1570924326777458,
|
|
"num_tokens": 25807757.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 6.342399215698242,
|
|
"epoch": 1.1748413156376225,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.00048736771302901566,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.16174473017454147,
|
|
"num_tokens": 25820063.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 6.319576597213745,
|
|
"epoch": 1.1754183496826314,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048735407754291063,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.16988920718431472,
|
|
"num_tokens": 25832974.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 6.379149007797241,
|
|
"epoch": 1.17599538372764,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048734043491438175,
|
|
"loss": 6.2003,
|
|
"mean_token_accuracy": 0.15487931072711944,
|
|
"num_tokens": 25845939.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 6.3196595191955565,
|
|
"epoch": 1.1765724177726486,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048732678514388773,
|
|
"loss": 6.1455,
|
|
"mean_token_accuracy": 0.16049207746982574,
|
|
"num_tokens": 25857480.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 6.291083765029907,
|
|
"epoch": 1.1771494518176573,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004873131282318878,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.1705268293619156,
|
|
"num_tokens": 25869384.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 6.30240650177002,
|
|
"epoch": 1.177726485862666,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048729946417884126,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.16226058602333068,
|
|
"num_tokens": 25881705.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 6.36404013633728,
|
|
"epoch": 1.1783035199076746,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004872857929852076,
|
|
"loss": 6.1753,
|
|
"mean_token_accuracy": 0.15568970143795013,
|
|
"num_tokens": 25894072.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 6.363600587844848,
|
|
"epoch": 1.1788805539526832,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004872721146514469,
|
|
"loss": 6.0612,
|
|
"mean_token_accuracy": 0.17028955072164537,
|
|
"num_tokens": 25907358.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 6.243066787719727,
|
|
"epoch": 1.1794575879976918,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000487258429178019,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.17397456020116805,
|
|
"num_tokens": 25918746.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 6.3143209457397464,
|
|
"epoch": 1.1800346220427005,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048724473656538427,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.1687172085046768,
|
|
"num_tokens": 25930759.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 6.290168237686157,
|
|
"epoch": 1.1806116560877091,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004872310368140032,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.16777861267328262,
|
|
"num_tokens": 25942364.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 6.269335699081421,
|
|
"epoch": 1.1811886901327178,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004872173299243368,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.17016907334327697,
|
|
"num_tokens": 25954254.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 6.335594272613525,
|
|
"epoch": 1.1817657241777264,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00048720361589684575,
|
|
"loss": 6.2474,
|
|
"mean_token_accuracy": 0.16507446467876435,
|
|
"num_tokens": 25966708.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 6.332195568084717,
|
|
"epoch": 1.182342758222735,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048718989473199147,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.1564444601535797,
|
|
"num_tokens": 25979301.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 6.362717962265014,
|
|
"epoch": 1.182919792267744,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004871761664302356,
|
|
"loss": 6.1521,
|
|
"mean_token_accuracy": 0.16474512219429016,
|
|
"num_tokens": 25992195.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 6.284235668182373,
|
|
"epoch": 1.1834968263127525,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004871624309920397,
|
|
"loss": 6.041,
|
|
"mean_token_accuracy": 0.1756657689809799,
|
|
"num_tokens": 26005078.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 6.291142082214355,
|
|
"epoch": 1.1840738603577612,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048714868841786586,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.16087482869625092,
|
|
"num_tokens": 26017227.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 6.382811117172241,
|
|
"epoch": 1.1846508944027698,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048713493870817626,
|
|
"loss": 6.2511,
|
|
"mean_token_accuracy": 0.16183987408876419,
|
|
"num_tokens": 26030782.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 6.279626083374024,
|
|
"epoch": 1.1852279284477785,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048712118186343336,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.1711464300751686,
|
|
"num_tokens": 26042327.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 6.340450572967529,
|
|
"epoch": 1.185804962492787,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048710741788409985,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.15717075914144515,
|
|
"num_tokens": 26055298.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 6.387430858612061,
|
|
"epoch": 1.1863819965377957,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004870936467706387,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.15629870891571046,
|
|
"num_tokens": 26067389.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 6.354550886154175,
|
|
"epoch": 1.1869590305828044,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004870798685235131,
|
|
"loss": 6.1647,
|
|
"mean_token_accuracy": 0.1612406626343727,
|
|
"num_tokens": 26080527.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 6.320342922210694,
|
|
"epoch": 1.187536064627813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048706608314318654,
|
|
"loss": 6.2134,
|
|
"mean_token_accuracy": 0.15583257228136063,
|
|
"num_tokens": 26093684.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 6.312257146835327,
|
|
"epoch": 1.1881130986728217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004870522906301225,
|
|
"loss": 6.1227,
|
|
"mean_token_accuracy": 0.16510868221521377,
|
|
"num_tokens": 26105235.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 6.306887769699097,
|
|
"epoch": 1.1886901327178303,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000487038490984785,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.1623164415359497,
|
|
"num_tokens": 26117542.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 6.345963191986084,
|
|
"epoch": 1.189267166762839,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00048702468420763826,
|
|
"loss": 6.2605,
|
|
"mean_token_accuracy": 0.15688117891550063,
|
|
"num_tokens": 26130722.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 6.332888174057007,
|
|
"epoch": 1.1898442008078476,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048701087029914657,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.16274466514587402,
|
|
"num_tokens": 26143420.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 6.385124921798706,
|
|
"epoch": 1.1904212348528562,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004869970492597745,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.15256087481975555,
|
|
"num_tokens": 26156041.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 6.275911903381347,
|
|
"epoch": 1.1909982688978649,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004869832210899871,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.16806990206241607,
|
|
"num_tokens": 26168075.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 6.313507080078125,
|
|
"epoch": 1.1915753029428737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048696938579024927,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.1636284902691841,
|
|
"num_tokens": 26180285.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 6.27633147239685,
|
|
"epoch": 1.1921523369878824,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048695554336102644,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.16393174827098847,
|
|
"num_tokens": 26193095.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 6.305689954757691,
|
|
"epoch": 1.192729371032891,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048694169380278417,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.16732767075300217,
|
|
"num_tokens": 26205477.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 6.285434341430664,
|
|
"epoch": 1.1933064050778996,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004869278371159884,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.17125446498394012,
|
|
"num_tokens": 26220057.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 6.371880960464478,
|
|
"epoch": 1.1938834391229083,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048691397330110503,
|
|
"loss": 6.1986,
|
|
"mean_token_accuracy": 0.15532726496458055,
|
|
"num_tokens": 26232327.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 6.229359245300293,
|
|
"epoch": 1.194460473167917,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004869001023586005,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.1645748496055603,
|
|
"num_tokens": 26245087.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 6.387897205352783,
|
|
"epoch": 1.1950375072129256,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004868862242889413,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.15893673598766328,
|
|
"num_tokens": 26258041.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 6.408567094802857,
|
|
"epoch": 1.1956145412579342,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000486872339092594,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.15730382800102233,
|
|
"num_tokens": 26270443.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 6.262932157516479,
|
|
"epoch": 1.1961915753029428,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000486858446770026,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.1608057364821434,
|
|
"num_tokens": 26282685.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 6.319109964370727,
|
|
"epoch": 1.1967686093479515,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004868445473217043,
|
|
"loss": 6.2158,
|
|
"mean_token_accuracy": 0.161103555560112,
|
|
"num_tokens": 26296003.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 6.2928773880004885,
|
|
"epoch": 1.1973456433929601,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004868306407480965,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.16285141408443451,
|
|
"num_tokens": 26309102.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 6.35385308265686,
|
|
"epoch": 1.1979226774379688,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048681672704967036,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.164886237680912,
|
|
"num_tokens": 26321571.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 6.421018648147583,
|
|
"epoch": 1.1984997114829774,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004868028062268938,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.15964062064886092,
|
|
"num_tokens": 26334761.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 6.310076951980591,
|
|
"epoch": 1.1990767455279863,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00048678887828023504,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.1698111414909363,
|
|
"num_tokens": 26348815.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 6.309312057495117,
|
|
"epoch": 1.1996537795729947,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004867749432101626,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.1607862025499344,
|
|
"num_tokens": 26361675.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 6.306365489959717,
|
|
"epoch": 1.2002308136180035,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004867610010171451,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.15660690665245056,
|
|
"num_tokens": 26375010.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 6.455476760864258,
|
|
"epoch": 1.2008078476630122,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048674705170165147,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.16162673979997635,
|
|
"num_tokens": 26388217.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 6.3156548023223875,
|
|
"epoch": 1.2013848817080208,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.000486733095264151,
|
|
"loss": 6.1713,
|
|
"mean_token_accuracy": 0.1644631251692772,
|
|
"num_tokens": 26402088.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 6.300989246368408,
|
|
"epoch": 1.2019619157530295,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048671913170511306,
|
|
"loss": 6.1699,
|
|
"mean_token_accuracy": 0.16167462170124053,
|
|
"num_tokens": 26414816.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 6.333500766754151,
|
|
"epoch": 1.202538949798038,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004867051610250073,
|
|
"loss": 6.1075,
|
|
"mean_token_accuracy": 0.16527679413557053,
|
|
"num_tokens": 26426345.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 6.232378339767456,
|
|
"epoch": 1.2031159838430467,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004866911832243035,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.1687069922685623,
|
|
"num_tokens": 26437982.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 6.195571947097778,
|
|
"epoch": 1.2036930178880554,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048667719830347203,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.15564415901899337,
|
|
"num_tokens": 26449855.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 6.404849576950073,
|
|
"epoch": 1.204270051933064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048666320626298307,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.16427553296089173,
|
|
"num_tokens": 26462927.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 6.369866466522216,
|
|
"epoch": 1.2048470859780727,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048664920710330735,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.16102144569158555,
|
|
"num_tokens": 26475022.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 6.272254943847656,
|
|
"epoch": 1.2054241200230813,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048663520082491564,
|
|
"loss": 6.1338,
|
|
"mean_token_accuracy": 0.1697706624865532,
|
|
"num_tokens": 26486959.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 6.312459659576416,
|
|
"epoch": 1.20600115406809,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004866211874282791,
|
|
"loss": 6.2305,
|
|
"mean_token_accuracy": 0.16129841059446334,
|
|
"num_tokens": 26500345.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 6.3494813442230225,
|
|
"epoch": 1.2065781881130986,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000486607166913869,
|
|
"loss": 6.2039,
|
|
"mean_token_accuracy": 0.16385735422372819,
|
|
"num_tokens": 26511625.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 6.3159326076507565,
|
|
"epoch": 1.2071552221581072,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048659313928215705,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.16436698138713837,
|
|
"num_tokens": 26523764.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 6.311506223678589,
|
|
"epoch": 1.207732256203116,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004865791045336149,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.1606744185090065,
|
|
"num_tokens": 26536925.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 6.241578531265259,
|
|
"epoch": 1.2083092902481247,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004865650626687146,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.17650363296270372,
|
|
"num_tokens": 26549201.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 6.305879020690918,
|
|
"epoch": 1.2088863242931334,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048655101368792866,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.16642459928989412,
|
|
"num_tokens": 26561495.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 6.3534986019134525,
|
|
"epoch": 1.209463358338142,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004865369575917293,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.15989347100257872,
|
|
"num_tokens": 26573820.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 6.335755109786987,
|
|
"epoch": 1.2100403923831506,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048652289438058953,
|
|
"loss": 6.1832,
|
|
"mean_token_accuracy": 0.16023981124162673,
|
|
"num_tokens": 26587468.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 6.260964012145996,
|
|
"epoch": 1.2106174264281593,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048650882405498226,
|
|
"loss": 6.2022,
|
|
"mean_token_accuracy": 0.16167952865362167,
|
|
"num_tokens": 26599884.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 6.255992984771728,
|
|
"epoch": 1.211194460473168,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004864947466153808,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.16567855775356294,
|
|
"num_tokens": 26612501.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 6.383900165557861,
|
|
"epoch": 1.2117714945181766,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004864806620622585,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.17049698084592818,
|
|
"num_tokens": 26624559.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 6.350470304489136,
|
|
"epoch": 1.2123485285631852,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004864665703960892,
|
|
"loss": 6.1593,
|
|
"mean_token_accuracy": 0.1594645231962204,
|
|
"num_tokens": 26636903.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 6.318430614471436,
|
|
"epoch": 1.2129255626081938,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004864524716173469,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.16265250593423844,
|
|
"num_tokens": 26649393.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 6.26350040435791,
|
|
"epoch": 1.2135025966532025,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004864383657265058,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.1690155252814293,
|
|
"num_tokens": 26661134.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 6.280627727508545,
|
|
"epoch": 1.2140796306982111,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048642425272404016,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.16160008162260056,
|
|
"num_tokens": 26674451.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 6.328465127944947,
|
|
"epoch": 1.2146566647432198,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004864101326104248,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.1652497887611389,
|
|
"num_tokens": 26686382.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 6.283163166046142,
|
|
"epoch": 1.2152336987882286,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004863960053861348,
|
|
"loss": 6.1057,
|
|
"mean_token_accuracy": 0.1680065721273422,
|
|
"num_tokens": 26698491.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 6.267314338684082,
|
|
"epoch": 1.215810732833237,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048638187105164507,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.16545756608247758,
|
|
"num_tokens": 26710836.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 6.323285484313965,
|
|
"epoch": 1.216387766878246,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004863677296074311,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.16326241195201874,
|
|
"num_tokens": 26723195.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 6.319986152648926,
|
|
"epoch": 1.2169648009232545,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004863535810539686,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.17019888758659363,
|
|
"num_tokens": 26736048.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 6.2805334568023685,
|
|
"epoch": 1.2175418349682632,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048633942539173325,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.1601146176457405,
|
|
"num_tokens": 26748712.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 6.339949321746826,
|
|
"epoch": 1.2181188690132718,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048632526262120144,
|
|
"loss": 6.2048,
|
|
"mean_token_accuracy": 0.15875715762376785,
|
|
"num_tokens": 26760546.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 6.344151830673217,
|
|
"epoch": 1.2186959030582805,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004863110927428493,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.16397978961467743,
|
|
"num_tokens": 26772792.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 6.23669023513794,
|
|
"epoch": 1.219272937103289,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004862969157571536,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.16881214827299118,
|
|
"num_tokens": 26785321.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 6.264487791061401,
|
|
"epoch": 1.2198499711482977,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048628273166459105,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.165188530087471,
|
|
"num_tokens": 26797481.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 6.337562322616577,
|
|
"epoch": 1.2204270051933064,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048626854046563876,
|
|
"loss": 6.2219,
|
|
"mean_token_accuracy": 0.1599225729703903,
|
|
"num_tokens": 26810644.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 6.375046730041504,
|
|
"epoch": 1.221004039238315,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048625434216077404,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.16600160151720048,
|
|
"num_tokens": 26822545.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 6.209045267105102,
|
|
"epoch": 1.2215810732833237,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048624013675047453,
|
|
"loss": 6.168,
|
|
"mean_token_accuracy": 0.1631156712770462,
|
|
"num_tokens": 26836221.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 6.313969373703003,
|
|
"epoch": 1.2221581073283323,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048622592423521783,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.1565389335155487,
|
|
"num_tokens": 26848543.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 6.435025596618653,
|
|
"epoch": 1.222735141373341,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004862117046154822,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.16341440230607987,
|
|
"num_tokens": 26859833.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 6.351103830337524,
|
|
"epoch": 1.2233121754183496,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048619747789174577,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.1668863445520401,
|
|
"num_tokens": 26873450.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 6.2641448974609375,
|
|
"epoch": 1.2238892094633584,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004861832440644871,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.1593625470995903,
|
|
"num_tokens": 26886545.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 6.28742151260376,
|
|
"epoch": 1.224466243508367,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048616900313418486,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.16876358091831206,
|
|
"num_tokens": 26898394.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 6.3268989562988285,
|
|
"epoch": 1.2250432775533757,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048615475510131815,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.16805960536003112,
|
|
"num_tokens": 26910172.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 6.253440999984742,
|
|
"epoch": 1.2256203115983844,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048614049996636614,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.17637682110071182,
|
|
"num_tokens": 26922496.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 6.295119285583496,
|
|
"epoch": 1.226197345643393,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00048612623772980825,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.17071359008550643,
|
|
"num_tokens": 26935264.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 6.306150913238525,
|
|
"epoch": 1.2267743796884016,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048611196839212426,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.1753847971558571,
|
|
"num_tokens": 26949006.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 6.194625997543335,
|
|
"epoch": 1.2273514137334103,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000486097691953794,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.16946956366300583,
|
|
"num_tokens": 26961305.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 6.303498363494873,
|
|
"epoch": 1.227928447778419,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048608340841529784,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.16096686720848083,
|
|
"num_tokens": 26973445.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 6.2427514553070065,
|
|
"epoch": 1.2285054818234276,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000486069117777116,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.16666444391012192,
|
|
"num_tokens": 26986286.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 6.36623592376709,
|
|
"epoch": 1.2290825158684362,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004860548200397293,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.16069630533456802,
|
|
"num_tokens": 26999281.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 6.38177375793457,
|
|
"epoch": 1.2296595499134448,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048604051520361846,
|
|
"loss": 6.2931,
|
|
"mean_token_accuracy": 0.15522295832633973,
|
|
"num_tokens": 27011916.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 6.38488450050354,
|
|
"epoch": 1.2302365839584535,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048602620326926484,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.1675037696957588,
|
|
"num_tokens": 27024442.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 6.414252138137817,
|
|
"epoch": 1.2308136180034621,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048601188423714965,
|
|
"loss": 6.2689,
|
|
"mean_token_accuracy": 0.15624295622110368,
|
|
"num_tokens": 27037978.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 6.334872579574585,
|
|
"epoch": 1.231390652048471,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004859975581077545,
|
|
"loss": 6.2598,
|
|
"mean_token_accuracy": 0.15260412395000458,
|
|
"num_tokens": 27049447.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 6.296382093429566,
|
|
"epoch": 1.2319676860934794,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004859832248815614,
|
|
"loss": 6.1431,
|
|
"mean_token_accuracy": 0.17176230102777482,
|
|
"num_tokens": 27062961.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 6.392310857772827,
|
|
"epoch": 1.2325447201384883,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004859688845590522,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.16266993284225464,
|
|
"num_tokens": 27076297.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 6.316580009460449,
|
|
"epoch": 1.233121754183497,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048595453714070944,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.15837038457393646,
|
|
"num_tokens": 27088496.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 6.401510953903198,
|
|
"epoch": 1.2336987882285055,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004859401826270156,
|
|
"loss": 6.2055,
|
|
"mean_token_accuracy": 0.15987962186336518,
|
|
"num_tokens": 27100695.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 6.322301721572876,
|
|
"epoch": 1.2342758222735142,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004859258210184536,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.16477376520633696,
|
|
"num_tokens": 27113703.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 6.351233863830567,
|
|
"epoch": 1.2348528563185228,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048591145231550623,
|
|
"loss": 6.2269,
|
|
"mean_token_accuracy": 0.15568701475858687,
|
|
"num_tokens": 27128669.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 6.387229156494141,
|
|
"epoch": 1.2354298903635315,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048589707651865697,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.16083226203918458,
|
|
"num_tokens": 27141311.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 6.387057733535767,
|
|
"epoch": 1.23600692440854,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004858826936283893,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.16173309981822967,
|
|
"num_tokens": 27152935.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 6.302968740463257,
|
|
"epoch": 1.2365839584535487,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000485868303645187,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.16808868646621705,
|
|
"num_tokens": 27166775.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 6.193493843078613,
|
|
"epoch": 1.2371609924985574,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048585390656953397,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.16636423021554947,
|
|
"num_tokens": 27179406.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 6.3158278465271,
|
|
"epoch": 1.237738026543566,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004858395024019147,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.1683789536356926,
|
|
"num_tokens": 27191562.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 6.365101718902588,
|
|
"epoch": 1.2383150605885747,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004858250911428133,
|
|
"loss": 6.1614,
|
|
"mean_token_accuracy": 0.16290413737297058,
|
|
"num_tokens": 27203827.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 6.311492300033569,
|
|
"epoch": 1.2388920946335833,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004858106727927148,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.16150906234979628,
|
|
"num_tokens": 27217645.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 6.31927604675293,
|
|
"epoch": 1.239469128678592,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000485796247352104,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.1700813129544258,
|
|
"num_tokens": 27230794.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 6.310563325881958,
|
|
"epoch": 1.2400461627236008,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004857818148214662,
|
|
"loss": 6.2377,
|
|
"mean_token_accuracy": 0.15220990478992463,
|
|
"num_tokens": 27243965.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 6.406279706954956,
|
|
"epoch": 1.2406231967686094,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004857673752012866,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.16095540374517442,
|
|
"num_tokens": 27256951.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 6.376666307449341,
|
|
"epoch": 1.241200230813618,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048575292849205114,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.1572696790099144,
|
|
"num_tokens": 27268556.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 6.281139230728149,
|
|
"epoch": 1.2417772648586267,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004857384746942456,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.15756804049015044,
|
|
"num_tokens": 27280367.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 6.36142110824585,
|
|
"epoch": 1.2423542989036354,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004857240138083562,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.17009591162204743,
|
|
"num_tokens": 27293727.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 6.4208721160888675,
|
|
"epoch": 1.242931332948644,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004857095458348692,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.16630731970071794,
|
|
"num_tokens": 27306677.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 6.421437358856201,
|
|
"epoch": 1.2435083669936526,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048569507077427134,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.16194156408309937,
|
|
"num_tokens": 27319317.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 6.349999570846558,
|
|
"epoch": 1.2440854010386613,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004856805886270494,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.1680565133690834,
|
|
"num_tokens": 27332021.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 6.234192276000977,
|
|
"epoch": 1.24466243508367,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004856660993936905,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.17493621557950972,
|
|
"num_tokens": 27343972.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 6.339166927337646,
|
|
"epoch": 1.2452394691286786,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000485651603074682,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.15476678535342217,
|
|
"num_tokens": 27356712.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 6.254733991622925,
|
|
"epoch": 1.2458165031736872,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004856370996705115,
|
|
"loss": 6.1038,
|
|
"mean_token_accuracy": 0.16964900642633438,
|
|
"num_tokens": 27369028.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 6.296901226043701,
|
|
"epoch": 1.2463935372186958,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004856225891816667,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.1664896309375763,
|
|
"num_tokens": 27380789.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 6.33326268196106,
|
|
"epoch": 1.2469705712637045,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004856080716086358,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.1629282146692276,
|
|
"num_tokens": 27394098.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 6.316369342803955,
|
|
"epoch": 1.2475476053087133,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000485593546951907,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.16884668171405792,
|
|
"num_tokens": 27407270.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 6.313498497009277,
|
|
"epoch": 1.2481246393537218,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004855790152119688,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.16334105879068375,
|
|
"num_tokens": 27420397.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 6.3574518203735355,
|
|
"epoch": 1.2487016733987306,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004855644763893102,
|
|
"loss": 6.1963,
|
|
"mean_token_accuracy": 0.16616567373275756,
|
|
"num_tokens": 27433007.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 6.296497392654419,
|
|
"epoch": 1.2492787074437393,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048554993048441987,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.15731592178344728,
|
|
"num_tokens": 27446683.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 6.3187668800354,
|
|
"epoch": 1.249855741488748,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004855353774977873,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.15644395351409912,
|
|
"num_tokens": 27459298.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 6.342638778686523,
|
|
"epoch": 1.2504327755337565,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048552081742990184,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.1627936080098152,
|
|
"num_tokens": 27472287.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 6.380952024459839,
|
|
"epoch": 1.2510098095787652,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048550625028125327,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.16333349347114562,
|
|
"num_tokens": 27484808.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 6.348484134674072,
|
|
"epoch": 1.2515868436237738,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004854916760523315,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.16139520555734635,
|
|
"num_tokens": 27496980.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 6.282923889160156,
|
|
"epoch": 1.2521638776687825,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048547709474362684,
|
|
"loss": 6.1984,
|
|
"mean_token_accuracy": 0.15698642879724503,
|
|
"num_tokens": 27509969.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 6.34557409286499,
|
|
"epoch": 1.252740911713791,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004854625063556296,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.16385020911693574,
|
|
"num_tokens": 27523410.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 6.387068557739258,
|
|
"epoch": 1.2533179457587997,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004854479108888305,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.1640760526061058,
|
|
"num_tokens": 27535183.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 6.349454069137574,
|
|
"epoch": 1.2538949798038084,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048543330834372047,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.1553926631808281,
|
|
"num_tokens": 27548028.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 6.322198343276978,
|
|
"epoch": 1.254472013848817,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048541869872079064,
|
|
"loss": 6.1347,
|
|
"mean_token_accuracy": 0.16066425293684006,
|
|
"num_tokens": 27561302.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 6.269003582000733,
|
|
"epoch": 1.2550490478938257,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004854040820205324,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.1691621169447899,
|
|
"num_tokens": 27572933.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 6.346168088912964,
|
|
"epoch": 1.2556260819388343,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004853894582434373,
|
|
"loss": 6.2337,
|
|
"mean_token_accuracy": 0.1564677447080612,
|
|
"num_tokens": 27586373.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 6.346892642974853,
|
|
"epoch": 1.2562031159838432,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004853748273899974,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.1748109444975853,
|
|
"num_tokens": 27599236.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 6.302681541442871,
|
|
"epoch": 1.2567801500288516,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004853601894607046,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.16508190482854843,
|
|
"num_tokens": 27611904.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 6.214655542373658,
|
|
"epoch": 1.2573571840738604,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004853455444560514,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.16355132162570954,
|
|
"num_tokens": 27625778.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 6.32364501953125,
|
|
"epoch": 1.257934218118869,
|
|
"grad_norm": 3.515625,
|
|
"learning_rate": 0.0004853308923765302,
|
|
"loss": 6.1785,
|
|
"mean_token_accuracy": 0.17193194329738617,
|
|
"num_tokens": 27638359.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 6.329800653457641,
|
|
"epoch": 1.2585112521638777,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000485316233222634,
|
|
"loss": 6.1046,
|
|
"mean_token_accuracy": 0.16803177893161775,
|
|
"num_tokens": 27651107.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 6.320554113388061,
|
|
"epoch": 1.2590882862088864,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004853015669948557,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.16287010610103608,
|
|
"num_tokens": 27664060.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 6.312152290344239,
|
|
"epoch": 1.259665320253895,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048528689369368863,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.16302927285432817,
|
|
"num_tokens": 27676678.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 6.390170764923096,
|
|
"epoch": 1.2602423542989036,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004852722133196264,
|
|
"loss": 6.2006,
|
|
"mean_token_accuracy": 0.15728381127119065,
|
|
"num_tokens": 27689696.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 6.302979755401611,
|
|
"epoch": 1.2608193883439123,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004852575258731627,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.16694856733083724,
|
|
"num_tokens": 27702144.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 6.359341430664062,
|
|
"epoch": 1.261396422388921,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004852428313547916,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.1572053074836731,
|
|
"num_tokens": 27714618.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 6.324438142776489,
|
|
"epoch": 1.2619734564339296,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048522812976500726,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.16266688853502273,
|
|
"num_tokens": 27727002.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 6.310562229156494,
|
|
"epoch": 1.2625504904789382,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048521342110430417,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.1592251852154732,
|
|
"num_tokens": 27739506.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 6.297001934051513,
|
|
"epoch": 1.2631275245239468,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048519870537317713,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.16531992256641387,
|
|
"num_tokens": 27751959.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 6.2629921436309814,
|
|
"epoch": 1.2637045585689557,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048518398257212103,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.16900534927845,
|
|
"num_tokens": 27762938.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 6.365654325485229,
|
|
"epoch": 1.2642815926139641,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004851692527016311,
|
|
"loss": 6.2081,
|
|
"mean_token_accuracy": 0.15454971194267272,
|
|
"num_tokens": 27776288.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 6.331540727615357,
|
|
"epoch": 1.264858626658973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004851545157622027,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.15178136229515077,
|
|
"num_tokens": 27788311.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 6.3813409328460695,
|
|
"epoch": 1.2654356607039816,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004851397717543316,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.15812337547540664,
|
|
"num_tokens": 27799589.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 6.274319410324097,
|
|
"epoch": 1.2660126947489903,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004851250206785137,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1667439490556717,
|
|
"num_tokens": 27813057.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 6.277303171157837,
|
|
"epoch": 1.266589728793999,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048511026253524503,
|
|
"loss": 6.1465,
|
|
"mean_token_accuracy": 0.16044363081455232,
|
|
"num_tokens": 27826465.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 6.309837818145752,
|
|
"epoch": 1.2671667628390075,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004850954973250221,
|
|
"loss": 6.1432,
|
|
"mean_token_accuracy": 0.16380210518836974,
|
|
"num_tokens": 27837157.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 6.386126470565796,
|
|
"epoch": 1.2677437968840162,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048508072504834144,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.16418514400720596,
|
|
"num_tokens": 27850101.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 6.272424221038818,
|
|
"epoch": 1.2683208309290248,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048506594570569997,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.16430216729640962,
|
|
"num_tokens": 27862786.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 6.425026226043701,
|
|
"epoch": 1.2688978649740335,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004850511592975947,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.16461049318313598,
|
|
"num_tokens": 27875196.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 6.349469900131226,
|
|
"epoch": 1.269474899019042,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004850363658245231,
|
|
"loss": 6.2633,
|
|
"mean_token_accuracy": 0.1542629912495613,
|
|
"num_tokens": 27888348.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 6.35367865562439,
|
|
"epoch": 1.2700519330640507,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004850215652869826,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.16688053011894227,
|
|
"num_tokens": 27901301.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 6.3888359546661375,
|
|
"epoch": 1.2706289671090594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004850067576854711,
|
|
"loss": 6.2115,
|
|
"mean_token_accuracy": 0.15654693841934203,
|
|
"num_tokens": 27915665.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 6.297394275665283,
|
|
"epoch": 1.271206001154068,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004849919430204867,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.16020799279212952,
|
|
"num_tokens": 27928333.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 6.3494425296783445,
|
|
"epoch": 1.2717830351990767,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004849771212925275,
|
|
"loss": 6.0888,
|
|
"mean_token_accuracy": 0.16375294476747512,
|
|
"num_tokens": 27940429.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 6.313184547424316,
|
|
"epoch": 1.2723600692440855,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048496229250209223,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.1601503983139992,
|
|
"num_tokens": 27953846.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 6.332328128814697,
|
|
"epoch": 1.272937103289094,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004849474566496795,
|
|
"loss": 6.0899,
|
|
"mean_token_accuracy": 0.16779401600360871,
|
|
"num_tokens": 27966393.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 6.264288711547851,
|
|
"epoch": 1.2735141373341028,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004849326137357883,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1776391953229904,
|
|
"num_tokens": 27979928.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 6.353927135467529,
|
|
"epoch": 1.2740911713791114,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000484917763760918,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.16302897185087203,
|
|
"num_tokens": 27991450.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 6.341830396652222,
|
|
"epoch": 1.27466820542412,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048490290672556784,
|
|
"loss": 6.1625,
|
|
"mean_token_accuracy": 0.16186770498752595,
|
|
"num_tokens": 28003696.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 6.251212215423584,
|
|
"epoch": 1.2752452394691287,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004848880426302378,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.167728927731514,
|
|
"num_tokens": 28015886.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 6.331211757659912,
|
|
"epoch": 1.2758222735141374,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004848731714754277,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.16511764675378798,
|
|
"num_tokens": 28029552.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 6.295982503890992,
|
|
"epoch": 1.276399307559146,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004848582932616377,
|
|
"loss": 6.2124,
|
|
"mean_token_accuracy": 0.16154432594776152,
|
|
"num_tokens": 28042275.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 6.2871945858001705,
|
|
"epoch": 1.2769763416041546,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004848434079893682,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.17026014775037765,
|
|
"num_tokens": 28054840.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 6.31745138168335,
|
|
"epoch": 1.2775533756491633,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004848285156591201,
|
|
"loss": 6.2333,
|
|
"mean_token_accuracy": 0.1593561977148056,
|
|
"num_tokens": 28068052.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 6.420611810684204,
|
|
"epoch": 1.278130409694172,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048481361627139384,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.15895957499742508,
|
|
"num_tokens": 28081157.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 6.396226978302002,
|
|
"epoch": 1.2787074437391805,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048479870982669096,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.16313387006521224,
|
|
"num_tokens": 28093842.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 6.40015058517456,
|
|
"epoch": 1.2792844777841892,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048478379632551266,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.17054009437561035,
|
|
"num_tokens": 28107529.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 6.291486501693726,
|
|
"epoch": 1.279861511829198,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004847688757683606,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.16051672995090485,
|
|
"num_tokens": 28119650.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 6.270731353759766,
|
|
"epoch": 1.2804385458742065,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004847539481557366,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.17015368193387986,
|
|
"num_tokens": 28131209.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 6.332563591003418,
|
|
"epoch": 1.2810155799192153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048473901348814277,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.1653625950217247,
|
|
"num_tokens": 28143624.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 6.43041090965271,
|
|
"epoch": 1.281592613964224,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004847240717660814,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.16168740540742874,
|
|
"num_tokens": 28156752.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 6.225031948089599,
|
|
"epoch": 1.2821696480092326,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048470912299005493,
|
|
"loss": 6.0443,
|
|
"mean_token_accuracy": 0.17290171086788178,
|
|
"num_tokens": 28169288.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 6.259183263778686,
|
|
"epoch": 1.2827466820542412,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048469416716056635,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.16693965941667557,
|
|
"num_tokens": 28181739.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 6.299275255203247,
|
|
"epoch": 1.28332371609925,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004846792042781187,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.16790862381458282,
|
|
"num_tokens": 28193861.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 6.28367805480957,
|
|
"epoch": 1.2839007501442585,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048466423434321513,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.1750580132007599,
|
|
"num_tokens": 28205453.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 6.2496013164520265,
|
|
"epoch": 1.2844777841892672,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048464925735635907,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.16223495900630952,
|
|
"num_tokens": 28217554.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 6.396459007263184,
|
|
"epoch": 1.2850548182342758,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048463427331805445,
|
|
"loss": 6.2473,
|
|
"mean_token_accuracy": 0.158101187646389,
|
|
"num_tokens": 28230091.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 6.279246997833252,
|
|
"epoch": 1.2856318522792844,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004846192822288052,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.16716209203004836,
|
|
"num_tokens": 28243285.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 6.256467676162719,
|
|
"epoch": 1.286208886324293,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004846042840891155,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.17056648582220077,
|
|
"num_tokens": 28256210.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 6.294454431533813,
|
|
"epoch": 1.2867859203693017,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004845892788994899,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.1733658105134964,
|
|
"num_tokens": 28268291.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 6.206016921997071,
|
|
"epoch": 1.2873629544143104,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004845742666604329,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.17029971033334732,
|
|
"num_tokens": 28281462.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 6.264611148834229,
|
|
"epoch": 1.287939988459319,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048455924737244953,
|
|
"loss": 6.2065,
|
|
"mean_token_accuracy": 0.1581377938389778,
|
|
"num_tokens": 28292766.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 6.273323631286621,
|
|
"epoch": 1.2885170225043279,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048454422103604505,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.17237376421689987,
|
|
"num_tokens": 28304500.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 6.362926387786866,
|
|
"epoch": 1.2890940565493363,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004845291876517247,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.16565798670053483,
|
|
"num_tokens": 28317262.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 6.215715932846069,
|
|
"epoch": 1.2896710905943451,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048451414721999424,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.17366328686475754,
|
|
"num_tokens": 28330313.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 6.207749509811402,
|
|
"epoch": 1.2902481246393538,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048449909974135954,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.16498281359672545,
|
|
"num_tokens": 28344058.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 6.276063632965088,
|
|
"epoch": 1.2908251586843624,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004844840452163267,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.1621875062584877,
|
|
"num_tokens": 28356664.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 6.368418121337891,
|
|
"epoch": 1.291402192729371,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000484468983645402,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.1614609658718109,
|
|
"num_tokens": 28369040.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 6.265853071212769,
|
|
"epoch": 1.2919792267743797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048445391502909213,
|
|
"loss": 6.159,
|
|
"mean_token_accuracy": 0.15824418812990187,
|
|
"num_tokens": 28381788.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 6.321166610717773,
|
|
"epoch": 1.2925562608193883,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048443883936790386,
|
|
"loss": 6.1928,
|
|
"mean_token_accuracy": 0.16284841299057007,
|
|
"num_tokens": 28394531.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 6.334868097305298,
|
|
"epoch": 1.293133294864397,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048442375666234427,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.16238492727279663,
|
|
"num_tokens": 28407766.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 6.2941638946533205,
|
|
"epoch": 1.2937103289094056,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004844086669129206,
|
|
"loss": 6.1924,
|
|
"mean_token_accuracy": 0.16062195599079132,
|
|
"num_tokens": 28420185.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 6.388847303390503,
|
|
"epoch": 1.2942873629544143,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048439357012014045,
|
|
"loss": 6.1364,
|
|
"mean_token_accuracy": 0.16039270013570786,
|
|
"num_tokens": 28432781.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 6.268585920333862,
|
|
"epoch": 1.294864396999423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004843784662845116,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.16846691071987152,
|
|
"num_tokens": 28446181.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 6.288886260986328,
|
|
"epoch": 1.2954414310444315,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000484363355406542,
|
|
"loss": 6.0599,
|
|
"mean_token_accuracy": 0.16910330504179,
|
|
"num_tokens": 28457959.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 6.279118585586548,
|
|
"epoch": 1.2960184650894404,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048434823748674,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.16250982731580735,
|
|
"num_tokens": 28470656.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 6.280978965759277,
|
|
"epoch": 1.2965954991344488,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048433311252561403,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.1643814906477928,
|
|
"num_tokens": 28483359.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 6.279931116104126,
|
|
"epoch": 1.2971725331794577,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004843179805236728,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.16412907987833023,
|
|
"num_tokens": 28495984.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 6.2893836975097654,
|
|
"epoch": 1.297749567224466,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048430284148142516,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.1599840596318245,
|
|
"num_tokens": 28508629.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 6.3177934169769285,
|
|
"epoch": 1.298326601269475,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004842876953993805,
|
|
"loss": 6.2082,
|
|
"mean_token_accuracy": 0.16367824673652648,
|
|
"num_tokens": 28521952.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 6.315539360046387,
|
|
"epoch": 1.2989036353144836,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004842725422780482,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.1647193670272827,
|
|
"num_tokens": 28535210.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 6.339979457855224,
|
|
"epoch": 1.2994806693594922,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004842573821179378,
|
|
"loss": 6.216,
|
|
"mean_token_accuracy": 0.15640299618244172,
|
|
"num_tokens": 28547294.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 6.408569622039795,
|
|
"epoch": 1.3000577034045009,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004842422149195593,
|
|
"loss": 6.2359,
|
|
"mean_token_accuracy": 0.15522149056196213,
|
|
"num_tokens": 28558934.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 6.27472767829895,
|
|
"epoch": 1.3006347374495095,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048422704068342294,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.15930722355842591,
|
|
"num_tokens": 28571897.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 6.294620418548584,
|
|
"epoch": 1.3012117714945182,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004842118594100389,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.16027718931436538,
|
|
"num_tokens": 28584320.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 6.250262880325318,
|
|
"epoch": 1.3017888055395268,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048419667109991793,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.16860387623310089,
|
|
"num_tokens": 28597018.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 6.248487567901611,
|
|
"epoch": 1.3023658395845354,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048418147575357085,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.16950415819883347,
|
|
"num_tokens": 28609145.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 6.32426905632019,
|
|
"epoch": 1.302942873629544,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004841662733715087,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.16909146755933763,
|
|
"num_tokens": 28622208.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 6.208732604980469,
|
|
"epoch": 1.3035199076745527,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048415106395424294,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.1594777375459671,
|
|
"num_tokens": 28634719.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 6.29807767868042,
|
|
"epoch": 1.3040969417195614,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048413584750228494,
|
|
"loss": 6.164,
|
|
"mean_token_accuracy": 0.1640383556485176,
|
|
"num_tokens": 28647138.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 6.19341287612915,
|
|
"epoch": 1.3046739757645702,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048412062401614653,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.16587843000888824,
|
|
"num_tokens": 28660898.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 6.344057846069336,
|
|
"epoch": 1.3052510098095786,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048410539349634,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.16715804785490035,
|
|
"num_tokens": 28672898.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 6.31997652053833,
|
|
"epoch": 1.3058280438545875,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048409015594337725,
|
|
"loss": 6.2326,
|
|
"mean_token_accuracy": 0.16915102154016495,
|
|
"num_tokens": 28684608.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 6.339677190780639,
|
|
"epoch": 1.3064050778995961,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000484074911357771,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.17026219218969346,
|
|
"num_tokens": 28696867.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 6.284737062454224,
|
|
"epoch": 1.3069821119446048,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048405965974003404,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.1607493944466114,
|
|
"num_tokens": 28709533.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 6.273362398147583,
|
|
"epoch": 1.3075591459896134,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048404440109067927,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.15757483690977098,
|
|
"num_tokens": 28721647.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 6.358157205581665,
|
|
"epoch": 1.308136180034622,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004840291354102198,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.1579637810587883,
|
|
"num_tokens": 28735261.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 6.355404090881348,
|
|
"epoch": 1.3087132140796307,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004840138626991693,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.16192290782928467,
|
|
"num_tokens": 28747930.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 6.281838083267212,
|
|
"epoch": 1.3092902481246393,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004839985829580413,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.16236553341150284,
|
|
"num_tokens": 28760497.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 6.378918027877807,
|
|
"epoch": 1.309867282169648,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048398329618734977,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.16250278949737548,
|
|
"num_tokens": 28772787.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 6.279808425903321,
|
|
"epoch": 1.3104443162146566,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004839680023876089,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.16467889100313188,
|
|
"num_tokens": 28784901.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 6.267178392410278,
|
|
"epoch": 1.3110213502596653,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004839527015593331,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.155230500549078,
|
|
"num_tokens": 28797376.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 6.296201229095459,
|
|
"epoch": 1.311598384304674,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048393739370303684,
|
|
"loss": 6.0965,
|
|
"mean_token_accuracy": 0.16835566163063048,
|
|
"num_tokens": 28808805.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 6.336475372314453,
|
|
"epoch": 1.3121754183496828,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004839220788192353,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.15595455914735795,
|
|
"num_tokens": 28821734.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 6.313124322891236,
|
|
"epoch": 1.3127524523946912,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048390675690844335,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.15779682695865632,
|
|
"num_tokens": 28834864.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 6.213588857650757,
|
|
"epoch": 1.3133294864397,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004838914279711764,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.16101833879947663,
|
|
"num_tokens": 28848154.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 6.278816747665405,
|
|
"epoch": 1.3139065204847085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048387609200795003,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.16542939245700836,
|
|
"num_tokens": 28861562.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 6.3024074077606205,
|
|
"epoch": 1.3144835545297173,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048386074901928,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.1619145765900612,
|
|
"num_tokens": 28873921.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 6.294253396987915,
|
|
"epoch": 1.315060588574726,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004838453990056825,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.15534769594669343,
|
|
"num_tokens": 28886126.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 6.3025377750396725,
|
|
"epoch": 1.3156376226197346,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048383004196767373,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.16867079287767411,
|
|
"num_tokens": 28897980.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 6.36027307510376,
|
|
"epoch": 1.3162146566647432,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004838146779057702,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.1627037927508354,
|
|
"num_tokens": 28910105.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 6.22172999382019,
|
|
"epoch": 1.3167916907097519,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004837993068204887,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.16126993000507356,
|
|
"num_tokens": 28922004.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 6.219480228424072,
|
|
"epoch": 1.3173687247547605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048378392871234634,
|
|
"loss": 6.0341,
|
|
"mean_token_accuracy": 0.17347660958766936,
|
|
"num_tokens": 28935990.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 6.357144784927368,
|
|
"epoch": 1.3179457587997692,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004837685435818601,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.1658763289451599,
|
|
"num_tokens": 28948274.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 6.311680173873901,
|
|
"epoch": 1.3185227928447778,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004837531514295477,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.155182783305645,
|
|
"num_tokens": 28960101.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 6.284453725814819,
|
|
"epoch": 1.3190998268897864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004837377522559267,
|
|
"loss": 6.1773,
|
|
"mean_token_accuracy": 0.16812565177679062,
|
|
"num_tokens": 28972408.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 6.337407922744751,
|
|
"epoch": 1.319676860934795,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048372234606151507,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.16081255227327346,
|
|
"num_tokens": 28985025.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 6.349707365036011,
|
|
"epoch": 1.3202538949798037,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048370693284683106,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.16389241069555283,
|
|
"num_tokens": 28997568.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 6.323847770690918,
|
|
"epoch": 1.3208309290248126,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048369151261239303,
|
|
"loss": 6.2415,
|
|
"mean_token_accuracy": 0.15582263171672822,
|
|
"num_tokens": 29009567.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 6.289740896224975,
|
|
"epoch": 1.321407963069821,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004836760853587196,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.16066635698080062,
|
|
"num_tokens": 29021403.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 6.277720832824707,
|
|
"epoch": 1.3219849971148299,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048366065108632967,
|
|
"loss": 6.1198,
|
|
"mean_token_accuracy": 0.16584020256996154,
|
|
"num_tokens": 29033430.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 6.319123935699463,
|
|
"epoch": 1.3225620311598385,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048364520979574246,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.1609363466501236,
|
|
"num_tokens": 29045659.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 6.234172105789185,
|
|
"epoch": 1.3231390652048471,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048362976148747715,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.1620397835969925,
|
|
"num_tokens": 29058962.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 6.299294567108154,
|
|
"epoch": 1.3237160992498558,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004836143061620536,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.165127757191658,
|
|
"num_tokens": 29072009.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 6.163762044906616,
|
|
"epoch": 1.3242931332948644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004835988438199914,
|
|
"loss": 6.0393,
|
|
"mean_token_accuracy": 0.17196400761604308,
|
|
"num_tokens": 29084174.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 6.279996156692505,
|
|
"epoch": 1.324870167339873,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004835833744618107,
|
|
"loss": 6.1329,
|
|
"mean_token_accuracy": 0.16213522255420684,
|
|
"num_tokens": 29096189.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 6.312683248519898,
|
|
"epoch": 1.3254472013848817,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004835678980880318,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.16390204429626465,
|
|
"num_tokens": 29108212.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 6.309130334854126,
|
|
"epoch": 1.3260242354298903,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004835524146991753,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.16586587578058243,
|
|
"num_tokens": 29121058.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 6.241234064102173,
|
|
"epoch": 1.326601269474899,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048353692429576185,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.16660408526659012,
|
|
"num_tokens": 29132981.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 6.332604503631591,
|
|
"epoch": 1.3271783035199076,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004835214268783126,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.15822002291679382,
|
|
"num_tokens": 29145143.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 6.333203220367432,
|
|
"epoch": 1.3277553375649163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048350592244734866,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.16814986616373062,
|
|
"num_tokens": 29157548.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 6.203010225296021,
|
|
"epoch": 1.3283323716099251,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004834904110033917,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.16850072741508484,
|
|
"num_tokens": 29170243.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 6.297244215011597,
|
|
"epoch": 1.3289094056549335,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048347489254696327,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.16527609378099442,
|
|
"num_tokens": 29181769.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 6.33937406539917,
|
|
"epoch": 1.3294864396999424,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004834593670785854,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.15585944056510925,
|
|
"num_tokens": 29194196.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 6.325269174575806,
|
|
"epoch": 1.3300634737449508,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048344383459878024,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.1619534283876419,
|
|
"num_tokens": 29206101.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 6.217943239212036,
|
|
"epoch": 1.3306405077899597,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048342829510807024,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.16871753782033921,
|
|
"num_tokens": 29217851.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 6.189042425155639,
|
|
"epoch": 1.3312175418349683,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000483412748606978,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.17444779425859452,
|
|
"num_tokens": 29231497.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 6.353026437759399,
|
|
"epoch": 1.331794575879977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004833971950960266,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.1626723363995552,
|
|
"num_tokens": 29245227.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 6.34786024093628,
|
|
"epoch": 1.3323716099249856,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004833816345757391,
|
|
"loss": 6.1389,
|
|
"mean_token_accuracy": 0.159043388068676,
|
|
"num_tokens": 29259403.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 6.323790502548218,
|
|
"epoch": 1.3329486439699942,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004833660670466387,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.16409413069486617,
|
|
"num_tokens": 29270938.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 6.297755861282349,
|
|
"epoch": 1.3335256780150029,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004833504925092492,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.16037169843912125,
|
|
"num_tokens": 29284078.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 6.286835145950318,
|
|
"epoch": 1.3341027120600115,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004833349109640944,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.16069846004247665,
|
|
"num_tokens": 29295698.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 6.289292192459106,
|
|
"epoch": 1.3346797461050202,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004833193224116983,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.16754496693611146,
|
|
"num_tokens": 29307585.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 6.301826333999633,
|
|
"epoch": 1.3352567801500288,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048330372685258526,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.16277503669261933,
|
|
"num_tokens": 29321027.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 6.293691682815552,
|
|
"epoch": 1.3358338141950374,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004832881242872799,
|
|
"loss": 6.1722,
|
|
"mean_token_accuracy": 0.1613366723060608,
|
|
"num_tokens": 29333121.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 6.3491006851196286,
|
|
"epoch": 1.336410848240046,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004832725147163069,
|
|
"loss": 6.1535,
|
|
"mean_token_accuracy": 0.15993758887052537,
|
|
"num_tokens": 29346120.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 6.324691343307495,
|
|
"epoch": 1.336987882285055,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048325689814019134,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.16394416689872743,
|
|
"num_tokens": 29357872.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 6.338229036331176,
|
|
"epoch": 1.3375649163300634,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004832412745594585,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.1639093592762947,
|
|
"num_tokens": 29370657.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 6.240398502349853,
|
|
"epoch": 1.3381419503750722,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048322564397463376,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.17317451536655426,
|
|
"num_tokens": 29384880.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 6.3124298572540285,
|
|
"epoch": 1.3387189844200809,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048321000638624296,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.16322875767946243,
|
|
"num_tokens": 29397215.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 6.282052659988404,
|
|
"epoch": 1.3392960184650895,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000483194361794812,
|
|
"loss": 6.1033,
|
|
"mean_token_accuracy": 0.16651321500539779,
|
|
"num_tokens": 29409634.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 6.286690282821655,
|
|
"epoch": 1.3398730525100981,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000483178710200867,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.17319692820310592,
|
|
"num_tokens": 29422404.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 6.323809862136841,
|
|
"epoch": 1.3404500865551068,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004831630516049346,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.16090573668479918,
|
|
"num_tokens": 29434727.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 6.316535472869873,
|
|
"epoch": 1.3410271206001154,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004831473860075414,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.15914638340473175,
|
|
"num_tokens": 29447176.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 6.277497625350952,
|
|
"epoch": 1.341604154645124,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00048313171340921417,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.17469708025455474,
|
|
"num_tokens": 29460080.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 6.240986299514771,
|
|
"epoch": 1.3421811886901327,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048311603381048025,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.1626189112663269,
|
|
"num_tokens": 29472503.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 6.272552442550659,
|
|
"epoch": 1.3427582227351413,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004831003472118668,
|
|
"loss": 6.0962,
|
|
"mean_token_accuracy": 0.16392599642276764,
|
|
"num_tokens": 29485139.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 6.398651361465454,
|
|
"epoch": 1.34333525678015,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004830846536139016,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.16744163930416106,
|
|
"num_tokens": 29497455.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 6.3032959461212155,
|
|
"epoch": 1.3439122908251586,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004830689530171124,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.1687514752149582,
|
|
"num_tokens": 29509859.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 6.352106809616089,
|
|
"epoch": 1.3444893248701673,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004830532454220273,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.1648508906364441,
|
|
"num_tokens": 29523117.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 6.255600261688232,
|
|
"epoch": 1.345066358915176,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00048303753082917474,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.16598070561885833,
|
|
"num_tokens": 29535943.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 6.291255092620849,
|
|
"epoch": 1.3456433929601848,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048302180923908306,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.16465048789978026,
|
|
"num_tokens": 29549036.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 6.290594291687012,
|
|
"epoch": 1.3462204270051932,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048300608065228126,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.1643916040658951,
|
|
"num_tokens": 29563465.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 6.274702882766723,
|
|
"epoch": 1.346797461050202,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048299034506929815,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.17369044125080108,
|
|
"num_tokens": 29575891.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 6.33291220664978,
|
|
"epoch": 1.3473744950952107,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00048297460249066315,
|
|
"loss": 6.2557,
|
|
"mean_token_accuracy": 0.15672912448644638,
|
|
"num_tokens": 29589162.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 6.331118774414063,
|
|
"epoch": 1.3479515291402193,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004829588529169057,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.1665223941206932,
|
|
"num_tokens": 29602735.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 6.220363473892212,
|
|
"epoch": 1.348528563185228,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004829430963485555,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.1701531946659088,
|
|
"num_tokens": 29615683.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 6.316802501678467,
|
|
"epoch": 1.3491055972302366,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004829273327861426,
|
|
"loss": 6.1707,
|
|
"mean_token_accuracy": 0.16423047631978988,
|
|
"num_tokens": 29629606.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 6.291276979446411,
|
|
"epoch": 1.3496826312752452,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004829115622301971,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.17152973264455795,
|
|
"num_tokens": 29642250.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 6.3764811038970945,
|
|
"epoch": 1.3502596653202539,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048289578468124956,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.16525790095329285,
|
|
"num_tokens": 29655689.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 6.153978443145752,
|
|
"epoch": 1.3508366993652625,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048288000013983046,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.16323120892047882,
|
|
"num_tokens": 29670084.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 6.329030132293701,
|
|
"epoch": 1.3514137334102712,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048286420860647086,
|
|
"loss": 6.1822,
|
|
"mean_token_accuracy": 0.1604864478111267,
|
|
"num_tokens": 29683453.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 6.313185548782348,
|
|
"epoch": 1.3519907674552798,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048284841008170185,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.16783878356218337,
|
|
"num_tokens": 29695514.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 6.30164647102356,
|
|
"epoch": 1.3525678015002884,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048283260456605487,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.1725817874073982,
|
|
"num_tokens": 29708544.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 6.364648389816284,
|
|
"epoch": 1.3531448355452973,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004828167920600614,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.16400440484285356,
|
|
"num_tokens": 29721310.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 6.348964786529541,
|
|
"epoch": 1.3537218695903057,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004828009725642534,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.16307055801153184,
|
|
"num_tokens": 29733995.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 6.314385557174683,
|
|
"epoch": 1.3542989036353146,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004827851460791628,
|
|
"loss": 6.1939,
|
|
"mean_token_accuracy": 0.15663280338048935,
|
|
"num_tokens": 29745896.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 6.3260167121887205,
|
|
"epoch": 1.3548759376803232,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048276931260532213,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.16611895859241485,
|
|
"num_tokens": 29758967.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 6.299111270904541,
|
|
"epoch": 1.3554529717253319,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004827534721432639,
|
|
"loss": 6.1453,
|
|
"mean_token_accuracy": 0.15984882563352584,
|
|
"num_tokens": 29772167.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 6.265276765823364,
|
|
"epoch": 1.3560300057703405,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004827376246935207,
|
|
"loss": 6.0998,
|
|
"mean_token_accuracy": 0.16514657139778138,
|
|
"num_tokens": 29783841.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 6.3505817413330075,
|
|
"epoch": 1.3566070398153491,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004827217702566257,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.16244319677352906,
|
|
"num_tokens": 29795993.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 6.288106441497803,
|
|
"epoch": 1.3571840738603578,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048270590883311217,
|
|
"loss": 6.1015,
|
|
"mean_token_accuracy": 0.17155284732580184,
|
|
"num_tokens": 29807692.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 6.287062501907348,
|
|
"epoch": 1.3577611079053664,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048269004042351363,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.16180962175130845,
|
|
"num_tokens": 29820778.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 6.317913389205932,
|
|
"epoch": 1.358338141950375,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004826741650283637,
|
|
"loss": 6.1186,
|
|
"mean_token_accuracy": 0.1640876680612564,
|
|
"num_tokens": 29833976.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 6.251207447052002,
|
|
"epoch": 1.3589151759953837,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004826582826481963,
|
|
"loss": 6.0767,
|
|
"mean_token_accuracy": 0.17455727756023406,
|
|
"num_tokens": 29846226.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 6.219823408126831,
|
|
"epoch": 1.3594922100403923,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004826423932835458,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.16895576119422911,
|
|
"num_tokens": 29858483.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 6.314107465744018,
|
|
"epoch": 1.360069244085401,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048262649693494653,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.16297580003738404,
|
|
"num_tokens": 29871178.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 6.4023756980896,
|
|
"epoch": 1.3606462781304096,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004826105936029332,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.15794295221567153,
|
|
"num_tokens": 29885477.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 6.298975467681885,
|
|
"epoch": 1.3612233121754183,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004825946832880406,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.16285300999879837,
|
|
"num_tokens": 29897917.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 6.278939914703369,
|
|
"epoch": 1.3618003462204271,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048257876599080404,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.16165986955165862,
|
|
"num_tokens": 29911321.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 6.305810499191284,
|
|
"epoch": 1.3623773802654355,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048256284171175874,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.17238346338272095,
|
|
"num_tokens": 29924651.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 6.1934586524963375,
|
|
"epoch": 1.3629544143104444,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00048254691045144035,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.16324946731328965,
|
|
"num_tokens": 29937334.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 6.265475225448609,
|
|
"epoch": 1.363531448355453,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004825309722103848,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.17350615113973616,
|
|
"num_tokens": 29949751.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 6.2313230514526365,
|
|
"epoch": 1.3641084824004617,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000482515026989128,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1747325286269188,
|
|
"num_tokens": 29961675.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 6.3038712501525875,
|
|
"epoch": 1.3646855164454703,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048249907478820634,
|
|
"loss": 6.2137,
|
|
"mean_token_accuracy": 0.1612464517354965,
|
|
"num_tokens": 29973222.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 6.353469610214233,
|
|
"epoch": 1.365262550490479,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00048248311560815637,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.16309360787272453,
|
|
"num_tokens": 29985845.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 6.320858573913574,
|
|
"epoch": 1.3658395845354876,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004824671494495149,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.16458719223737717,
|
|
"num_tokens": 29998252.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 6.346536493301391,
|
|
"epoch": 1.3664166185804962,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 0.0004824511763128189,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.17218410074710847,
|
|
"num_tokens": 30011150.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 6.357008361816407,
|
|
"epoch": 1.3669936526255049,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048243519619860567,
|
|
"loss": 6.2157,
|
|
"mean_token_accuracy": 0.1605319306254387,
|
|
"num_tokens": 30024750.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 6.286159610748291,
|
|
"epoch": 1.3675706866705135,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004824192091074126,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.1729810953140259,
|
|
"num_tokens": 30038317.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 6.283872461318969,
|
|
"epoch": 1.3681477207155222,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004824032150397775,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.17048034220933914,
|
|
"num_tokens": 30052156.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 6.305463886260986,
|
|
"epoch": 1.3687247547605308,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048238721399623824,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.16549787670373917,
|
|
"num_tokens": 30063463.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 6.304179716110229,
|
|
"epoch": 1.3693017888055397,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048237120597733316,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.17041393965482712,
|
|
"num_tokens": 30075090.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 6.236459493637085,
|
|
"epoch": 1.369878822850548,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004823551909836005,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.16820509731769562,
|
|
"num_tokens": 30087618.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 6.319930219650269,
|
|
"epoch": 1.370455856895557,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048233916901557896,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.16947691589593888,
|
|
"num_tokens": 30098781.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 6.3354767799377445,
|
|
"epoch": 1.3710328909405656,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048232314007380753,
|
|
"loss": 6.1378,
|
|
"mean_token_accuracy": 0.1753944605588913,
|
|
"num_tokens": 30111163.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 6.294744157791138,
|
|
"epoch": 1.3716099249855742,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048230710415882524,
|
|
"loss": 6.1374,
|
|
"mean_token_accuracy": 0.16997584998607634,
|
|
"num_tokens": 30124609.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 6.316244983673096,
|
|
"epoch": 1.3721869590305829,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048229106127117144,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.16650330871343613,
|
|
"num_tokens": 30137823.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 6.389352178573608,
|
|
"epoch": 1.3727639930755915,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004822750114113858,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.16203177869319915,
|
|
"num_tokens": 30150295.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 6.263393402099609,
|
|
"epoch": 1.3733410271206001,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004822589545800081,
|
|
"loss": 6.072,
|
|
"mean_token_accuracy": 0.1705651491880417,
|
|
"num_tokens": 30163533.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 6.308654689788819,
|
|
"epoch": 1.3739180611656088,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004822428907775784,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.15814722031354905,
|
|
"num_tokens": 30176437.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 6.218947982788086,
|
|
"epoch": 1.3744950952106174,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048222682000463704,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.17379665672779082,
|
|
"num_tokens": 30190181.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 6.212062406539917,
|
|
"epoch": 1.375072129255626,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004822107422617245,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.16834926456212998,
|
|
"num_tokens": 30202374.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 6.24512882232666,
|
|
"epoch": 1.3756491633006347,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048219465754938156,
|
|
"loss": 6.0318,
|
|
"mean_token_accuracy": 0.16531560868024825,
|
|
"num_tokens": 30215009.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 6.35242805480957,
|
|
"epoch": 1.3762261973456433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048217856586814926,
|
|
"loss": 6.1363,
|
|
"mean_token_accuracy": 0.16434847116470336,
|
|
"num_tokens": 30226688.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 6.3303159236907955,
|
|
"epoch": 1.376803231390652,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048216246721856875,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.16100845187902452,
|
|
"num_tokens": 30238501.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 6.335440397262573,
|
|
"epoch": 1.3773802654356606,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048214636160118164,
|
|
"loss": 6.107,
|
|
"mean_token_accuracy": 0.16803493201732636,
|
|
"num_tokens": 30250216.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 6.3147039890289305,
|
|
"epoch": 1.3779572994806695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004821302490165295,
|
|
"loss": 6.1213,
|
|
"mean_token_accuracy": 0.16672479808330537,
|
|
"num_tokens": 30262555.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 6.233082962036133,
|
|
"epoch": 1.378534333525678,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004821141294651544,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.1772979751229286,
|
|
"num_tokens": 30274593.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 6.325069808959961,
|
|
"epoch": 1.3791113675706868,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048209800294759836,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.17313085049390792,
|
|
"num_tokens": 30286579.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 6.351945686340332,
|
|
"epoch": 1.3796884016156954,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004820818694644039,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.16453606635332108,
|
|
"num_tokens": 30299186.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 6.3624310970306395,
|
|
"epoch": 1.380265435660704,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048206572901611364,
|
|
"loss": 6.1881,
|
|
"mean_token_accuracy": 0.15905419141054153,
|
|
"num_tokens": 30311429.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 6.3475316047668455,
|
|
"epoch": 1.3808424697057127,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048204958160327034,
|
|
"loss": 6.1504,
|
|
"mean_token_accuracy": 0.1662835657596588,
|
|
"num_tokens": 30323323.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 6.276279354095459,
|
|
"epoch": 1.3814195037507213,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048203342722641726,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.16957689821720123,
|
|
"num_tokens": 30335815.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 6.24206919670105,
|
|
"epoch": 1.38199653779573,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048201726588609776,
|
|
"loss": 6.0503,
|
|
"mean_token_accuracy": 0.1701612576842308,
|
|
"num_tokens": 30347426.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 6.314512062072754,
|
|
"epoch": 1.3825735718407386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048200109758285534,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.16389783024787902,
|
|
"num_tokens": 30359781.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 6.318188142776489,
|
|
"epoch": 1.3831506058857472,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004819849223172337,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.16730300784111024,
|
|
"num_tokens": 30373399.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 6.202302885055542,
|
|
"epoch": 1.3837276399307559,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048196874008977716,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.17317621558904647,
|
|
"num_tokens": 30386296.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 6.289775609970093,
|
|
"epoch": 1.3843046739757645,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004819525509010298,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.17061251550912857,
|
|
"num_tokens": 30399496.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 6.286764621734619,
|
|
"epoch": 1.3848817080207732,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004819363547515361,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.16182739287614822,
|
|
"num_tokens": 30412491.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.3848817080207732,
|
|
"eval_entropy": 6.224000952614618,
|
|
"eval_loss": 6.247929573059082,
|
|
"eval_mean_token_accuracy": 0.16458880992324,
|
|
"eval_num_tokens": 30412491.0,
|
|
"eval_runtime": 22.6792,
|
|
"eval_samples_per_second": 1240.607,
|
|
"eval_steps_per_second": 155.076,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 6.369675827026367,
|
|
"epoch": 1.385458742065782,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000481920151641841,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.16291867345571517,
|
|
"num_tokens": 30427600.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 6.355693054199219,
|
|
"epoch": 1.3860357761107904,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048190394157248935,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.171800796687603,
|
|
"num_tokens": 30440534.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 6.275745153427124,
|
|
"epoch": 1.3866128101557993,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004818877245440264,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.16982559263706207,
|
|
"num_tokens": 30453996.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 6.300146865844726,
|
|
"epoch": 1.3871898442008077,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048187150055699763,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.16266092360019685,
|
|
"num_tokens": 30465667.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 6.351484680175782,
|
|
"epoch": 1.3877668782458166,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004818552696119487,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.1609213873744011,
|
|
"num_tokens": 30478950.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 6.2422269821167,
|
|
"epoch": 1.3883439122908252,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004818390317094255,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.17113839089870453,
|
|
"num_tokens": 30490979.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 6.311171054840088,
|
|
"epoch": 1.3889209463358339,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004818227868499742,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.17111729681491852,
|
|
"num_tokens": 30504242.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 6.25700569152832,
|
|
"epoch": 1.3894979803808425,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004818065350341412,
|
|
"loss": 6.1619,
|
|
"mean_token_accuracy": 0.16251288056373597,
|
|
"num_tokens": 30515739.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 6.387627744674683,
|
|
"epoch": 1.3900750144258511,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048179027626247325,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.15438068956136702,
|
|
"num_tokens": 30528338.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 6.408785104751587,
|
|
"epoch": 1.3906520484708598,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004817740105355169,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.16251056343317033,
|
|
"num_tokens": 30540572.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 6.360489416122436,
|
|
"epoch": 1.3912290825158684,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048175773785381947,
|
|
"loss": 6.196,
|
|
"mean_token_accuracy": 0.1643637403845787,
|
|
"num_tokens": 30554317.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 6.341495227813721,
|
|
"epoch": 1.391806116560877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048174145821792833,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.16100704222917556,
|
|
"num_tokens": 30567177.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 6.35797700881958,
|
|
"epoch": 1.3923831506058857,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004817251716283908,
|
|
"loss": 6.1489,
|
|
"mean_token_accuracy": 0.1654942288994789,
|
|
"num_tokens": 30577948.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 6.228287220001221,
|
|
"epoch": 1.3929601846508943,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004817088780857548,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.16523568630218505,
|
|
"num_tokens": 30590548.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 6.303491497039795,
|
|
"epoch": 1.393537218695903,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048169257759056845,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.17548049986362457,
|
|
"num_tokens": 30602735.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 6.357599115371704,
|
|
"epoch": 1.3941142527409118,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048167627014337994,
|
|
"loss": 6.1888,
|
|
"mean_token_accuracy": 0.16183228939771652,
|
|
"num_tokens": 30615112.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 6.253079414367676,
|
|
"epoch": 1.3946912867859202,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048165995574473764,
|
|
"loss": 6.1103,
|
|
"mean_token_accuracy": 0.1625622555613518,
|
|
"num_tokens": 30627406.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 6.312600135803223,
|
|
"epoch": 1.395268320830929,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048164363439519043,
|
|
"loss": 6.1182,
|
|
"mean_token_accuracy": 0.1654726192355156,
|
|
"num_tokens": 30639764.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 6.347026824951172,
|
|
"epoch": 1.3958453548759377,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004816273060952873,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.16689932197332383,
|
|
"num_tokens": 30652181.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 6.306456422805786,
|
|
"epoch": 1.3964223889209464,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048161097084557726,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.1631346881389618,
|
|
"num_tokens": 30663586.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 6.374965047836303,
|
|
"epoch": 1.396999422965955,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048159462864660993,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.15762596130371093,
|
|
"num_tokens": 30676218.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 6.339052629470825,
|
|
"epoch": 1.3975764570109637,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004815782794989348,
|
|
"loss": 6.1864,
|
|
"mean_token_accuracy": 0.1606118932366371,
|
|
"num_tokens": 30688532.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 6.2383440971374515,
|
|
"epoch": 1.3981534910559723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004815619234031019,
|
|
"loss": 6.1052,
|
|
"mean_token_accuracy": 0.16475950181484222,
|
|
"num_tokens": 30700698.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 6.2884252071380615,
|
|
"epoch": 1.398730525100981,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004815455603596613,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.16549549996852875,
|
|
"num_tokens": 30713032.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 6.294129419326782,
|
|
"epoch": 1.3993075591459896,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004815291903691634,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.1696466714143753,
|
|
"num_tokens": 30726829.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 6.337021923065185,
|
|
"epoch": 1.3998845931909982,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048151281343215873,
|
|
"loss": 6.1566,
|
|
"mean_token_accuracy": 0.1605507642030716,
|
|
"num_tokens": 30740280.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 6.21012511253357,
|
|
"epoch": 1.4004616272360069,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004814964295491982,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.17915696054697036,
|
|
"num_tokens": 30753467.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 6.279628944396973,
|
|
"epoch": 1.4010386612810155,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048148003872083286,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.17217430621385574,
|
|
"num_tokens": 30766958.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 6.305673313140869,
|
|
"epoch": 1.4016156953260244,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048146364094761384,
|
|
"loss": 6.1684,
|
|
"mean_token_accuracy": 0.1595797434449196,
|
|
"num_tokens": 30779114.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 6.294431924819946,
|
|
"epoch": 1.4021927293710328,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048144723623009297,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.16946638971567154,
|
|
"num_tokens": 30792063.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 6.3064147472381595,
|
|
"epoch": 1.4027697634160416,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004814308245688218,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.16511736810207367,
|
|
"num_tokens": 30804404.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 6.235158681869507,
|
|
"epoch": 1.40334679746105,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048141440596435235,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.17058005332946777,
|
|
"num_tokens": 30817607.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 6.2955762386322025,
|
|
"epoch": 1.403923831506059,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004813979804172369,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.1665330022573471,
|
|
"num_tokens": 30831077.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 6.28407392501831,
|
|
"epoch": 1.4045008655510676,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048138154792802795,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.1606106773018837,
|
|
"num_tokens": 30844096.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 6.323961544036865,
|
|
"epoch": 1.4050778995960762,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004813651084972781,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.1660185769200325,
|
|
"num_tokens": 30856147.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 6.302383995056152,
|
|
"epoch": 1.4056549336410848,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048134866212554036,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.15867800861597062,
|
|
"num_tokens": 30869436.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 6.245109987258911,
|
|
"epoch": 1.4062319676860935,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004813322088133679,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.16820482015609742,
|
|
"num_tokens": 30882313.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 6.295883369445801,
|
|
"epoch": 1.4068090017311021,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048131574856131407,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.16215179339051247,
|
|
"num_tokens": 30895062.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 6.299847841262817,
|
|
"epoch": 1.4073860357761108,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004812992813699324,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.1652792364358902,
|
|
"num_tokens": 30907736.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 6.322113800048828,
|
|
"epoch": 1.4079630698211194,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000481282807239777,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.16788258105516435,
|
|
"num_tokens": 30920462.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 6.28887448310852,
|
|
"epoch": 1.408540103866128,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004812663261714019,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.17208631336688995,
|
|
"num_tokens": 30933501.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 6.288034152984619,
|
|
"epoch": 1.4091171379111367,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004812498381653613,
|
|
"loss": 6.0682,
|
|
"mean_token_accuracy": 0.17028167694807053,
|
|
"num_tokens": 30944780.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 6.348947048187256,
|
|
"epoch": 1.4096941719561453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004812333432222098,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.16152927428483962,
|
|
"num_tokens": 30957730.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 6.068280220031738,
|
|
"epoch": 1.4102712060011542,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004812168413425023,
|
|
"loss": 5.9705,
|
|
"mean_token_accuracy": 0.181918466091156,
|
|
"num_tokens": 30969371.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 6.326417303085327,
|
|
"epoch": 1.4108482400461626,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048120033252679374,
|
|
"loss": 6.1889,
|
|
"mean_token_accuracy": 0.16231568902730942,
|
|
"num_tokens": 30983662.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 6.430174541473389,
|
|
"epoch": 1.4114252740911715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048118381677563946,
|
|
"loss": 6.1601,
|
|
"mean_token_accuracy": 0.1615968704223633,
|
|
"num_tokens": 30995641.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 6.362520742416382,
|
|
"epoch": 1.41200230813618,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004811672940895949,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.16106947362422944,
|
|
"num_tokens": 31008508.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 6.3622204780578615,
|
|
"epoch": 1.4125793421811887,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004811507644692158,
|
|
"loss": 6.1686,
|
|
"mean_token_accuracy": 0.16129661202430726,
|
|
"num_tokens": 31020903.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 6.325216770172119,
|
|
"epoch": 1.4131563762261974,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004811342279150581,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.16731538027524948,
|
|
"num_tokens": 31033668.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 6.345950746536255,
|
|
"epoch": 1.413733410271206,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004811176844276781,
|
|
"loss": 6.1887,
|
|
"mean_token_accuracy": 0.1661725699901581,
|
|
"num_tokens": 31046980.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 6.335570049285889,
|
|
"epoch": 1.4143104443162147,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004811011340076322,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.16766103059053422,
|
|
"num_tokens": 31059023.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 6.250242805480957,
|
|
"epoch": 1.4148874783612233,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048108457665547695,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.17201029807329177,
|
|
"num_tokens": 31070449.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 6.257473611831665,
|
|
"epoch": 1.415464512406232,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004810680123717694,
|
|
"loss": 6.06,
|
|
"mean_token_accuracy": 0.17232086062431334,
|
|
"num_tokens": 31081974.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 6.306641006469727,
|
|
"epoch": 1.4160415464512406,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004810514411570666,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.1588302806019783,
|
|
"num_tokens": 31094825.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 6.242742490768433,
|
|
"epoch": 1.4166185804962492,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004810348630119259,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.16637780368328095,
|
|
"num_tokens": 31106589.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 6.383942031860352,
|
|
"epoch": 1.4171956145412579,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048101827793690493,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.157748444378376,
|
|
"num_tokens": 31118228.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 6.387330436706543,
|
|
"epoch": 1.4177726485862667,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004810016859325615,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.16304440647363663,
|
|
"num_tokens": 31131396.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 6.327767467498779,
|
|
"epoch": 1.4183496826312751,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004809850869994537,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.16658884882926941,
|
|
"num_tokens": 31145524.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 6.349434852600098,
|
|
"epoch": 1.418926716676284,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004809684811381398,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.17099672704935073,
|
|
"num_tokens": 31157866.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 6.213384199142456,
|
|
"epoch": 1.4195037507212924,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004809518683491785,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.17853738218545914,
|
|
"num_tokens": 31170634.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 6.281233596801758,
|
|
"epoch": 1.4200807847663013,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048093524863312823,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.16574939489364623,
|
|
"num_tokens": 31183585.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 6.327755784988403,
|
|
"epoch": 1.42065781881131,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004809186219905482,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.16455602496862412,
|
|
"num_tokens": 31196375.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 6.266958808898925,
|
|
"epoch": 1.4212348528563186,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004809019884219976,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.17540175914764405,
|
|
"num_tokens": 31209797.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 6.20970196723938,
|
|
"epoch": 1.4218118869013272,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048088534792803595,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.17160076051950454,
|
|
"num_tokens": 31221196.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 6.305485630035401,
|
|
"epoch": 1.4223889209463358,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00048086870050922286,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.1657287821173668,
|
|
"num_tokens": 31234126.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 6.313985776901245,
|
|
"epoch": 1.4229659549913445,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048085204616611833,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.16098834723234176,
|
|
"num_tokens": 31245933.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 6.293331670761108,
|
|
"epoch": 1.4235429890363531,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048083538489928246,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.15946199297904967,
|
|
"num_tokens": 31258734.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 6.274984502792359,
|
|
"epoch": 1.4241200230813618,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004808187167092757,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.16822846084833146,
|
|
"num_tokens": 31272487.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 6.23299126625061,
|
|
"epoch": 1.4246970571263704,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004808020415966586,
|
|
"loss": 6.1069,
|
|
"mean_token_accuracy": 0.16606823056936265,
|
|
"num_tokens": 31285117.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 6.254212093353272,
|
|
"epoch": 1.425274091171379,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000480785359561992,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.1718271940946579,
|
|
"num_tokens": 31297772.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 6.278341388702392,
|
|
"epoch": 1.4258511252163877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048076867060583704,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.1666000247001648,
|
|
"num_tokens": 31310901.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 6.279241514205933,
|
|
"epoch": 1.4264281592613965,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004807519747287551,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.16237711459398269,
|
|
"num_tokens": 31323090.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 6.275631761550903,
|
|
"epoch": 1.427005193306405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004807352719313078,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.16846050322055817,
|
|
"num_tokens": 31335883.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 6.350681781768799,
|
|
"epoch": 1.4275822273514138,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004807185622140567,
|
|
"loss": 6.1694,
|
|
"mean_token_accuracy": 0.16167529821395873,
|
|
"num_tokens": 31348237.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 6.219129180908203,
|
|
"epoch": 1.4281592613964225,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048070184557756396,
|
|
"loss": 6.0196,
|
|
"mean_token_accuracy": 0.17124342024326325,
|
|
"num_tokens": 31360414.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 6.2988440990448,
|
|
"epoch": 1.428736295441431,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048068512202239177,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.16669683009386063,
|
|
"num_tokens": 31372765.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 6.306262874603272,
|
|
"epoch": 1.4293133294864397,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004806683915491028,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.16952491849660872,
|
|
"num_tokens": 31386176.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 6.350312519073486,
|
|
"epoch": 1.4298903635314484,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004806516541582596,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.15940093100070954,
|
|
"num_tokens": 31398385.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 6.2261138439178465,
|
|
"epoch": 1.430467397576457,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048063490985042506,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.16982655823230744,
|
|
"num_tokens": 31410841.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 6.241001892089844,
|
|
"epoch": 1.4310444316214657,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004806181586261626,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.1683602899312973,
|
|
"num_tokens": 31425586.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 6.321263217926026,
|
|
"epoch": 1.4316214656664743,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048060140048603544,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.17428047508001326,
|
|
"num_tokens": 31438943.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 6.241196346282959,
|
|
"epoch": 1.432198499711483,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004805846354306073,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.1756817027926445,
|
|
"num_tokens": 31452284.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 6.28016357421875,
|
|
"epoch": 1.4327755337564916,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048056786346044214,
|
|
"loss": 6.2197,
|
|
"mean_token_accuracy": 0.1551727384328842,
|
|
"num_tokens": 31466311.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 6.351090955734253,
|
|
"epoch": 1.4333525678015002,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048055108457610395,
|
|
"loss": 6.0679,
|
|
"mean_token_accuracy": 0.1721023514866829,
|
|
"num_tokens": 31478916.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 6.31014575958252,
|
|
"epoch": 1.4339296018465089,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004805342987781571,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.16851240694522857,
|
|
"num_tokens": 31490337.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 6.290010833740235,
|
|
"epoch": 1.4345066358915175,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004805175060671663,
|
|
"loss": 6.1066,
|
|
"mean_token_accuracy": 0.16243394911289216,
|
|
"num_tokens": 31502625.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 6.323895978927612,
|
|
"epoch": 1.4350836699365264,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004805007064436962,
|
|
"loss": 6.1662,
|
|
"mean_token_accuracy": 0.1605980172753334,
|
|
"num_tokens": 31515440.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 6.297709703445435,
|
|
"epoch": 1.4356607039815348,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004804838999083119,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.16135017722845077,
|
|
"num_tokens": 31527812.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 6.344575595855713,
|
|
"epoch": 1.4362377380265436,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004804670864615787,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.16526193022727967,
|
|
"num_tokens": 31540249.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 6.285081386566162,
|
|
"epoch": 1.4368147720715523,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048045026610406223,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.17280279397964476,
|
|
"num_tokens": 31552312.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 6.2848773956298825,
|
|
"epoch": 1.437391806116561,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000480433438836328,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.16405625715851785,
|
|
"num_tokens": 31564496.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 6.360372257232666,
|
|
"epoch": 1.4379688401615696,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048041660465894206,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.16145581156015396,
|
|
"num_tokens": 31577705.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 6.3164557933807375,
|
|
"epoch": 1.4385458742065782,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004803997635724707,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.16466890573501586,
|
|
"num_tokens": 31589566.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 6.304163312911987,
|
|
"epoch": 1.4391229082515868,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004803829155774804,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.16303829699754716,
|
|
"num_tokens": 31602379.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 6.294868755340576,
|
|
"epoch": 1.4396999422965955,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004803660606745377,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.17045496106147767,
|
|
"num_tokens": 31615469.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 6.249364948272705,
|
|
"epoch": 1.4402769763416041,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048034919886420953,
|
|
"loss": 6.198,
|
|
"mean_token_accuracy": 0.1614298328757286,
|
|
"num_tokens": 31627129.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 6.392160129547119,
|
|
"epoch": 1.4408540103866128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048033233014706304,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.16891637742519378,
|
|
"num_tokens": 31639564.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 6.259813594818115,
|
|
"epoch": 1.4414310444316214,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048031545452366565,
|
|
"loss": 6.0918,
|
|
"mean_token_accuracy": 0.16519918888807297,
|
|
"num_tokens": 31651984.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 6.27579026222229,
|
|
"epoch": 1.44200807847663,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048029857199458493,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.17073165774345397,
|
|
"num_tokens": 31664850.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 6.299057912826538,
|
|
"epoch": 1.442585112521639,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048028168256038873,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.17626596838235856,
|
|
"num_tokens": 31676993.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 6.314305353164673,
|
|
"epoch": 1.4431621465666473,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048026478622164513,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.1673912525177002,
|
|
"num_tokens": 31689632.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 6.3189842224121096,
|
|
"epoch": 1.4437391806116562,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048024788297892234,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.16439658850431443,
|
|
"num_tokens": 31701610.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 6.324826955795288,
|
|
"epoch": 1.4443162146566648,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000480230972832789,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.16393847912549972,
|
|
"num_tokens": 31713838.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 6.257188940048218,
|
|
"epoch": 1.4448932487016735,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048021405578381384,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.16817671060562134,
|
|
"num_tokens": 31726097.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 6.286736917495728,
|
|
"epoch": 1.445470282746682,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004801971318325659,
|
|
"loss": 6.0761,
|
|
"mean_token_accuracy": 0.1660412147641182,
|
|
"num_tokens": 31739646.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 6.279177141189575,
|
|
"epoch": 1.4460473167916907,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004801802009796142,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.16675680130720139,
|
|
"num_tokens": 31752161.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 6.275993585586548,
|
|
"epoch": 1.4466243508366994,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004801632632255285,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.1660511910915375,
|
|
"num_tokens": 31764498.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 6.336894416809082,
|
|
"epoch": 1.447201384881708,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004801463185708783,
|
|
"loss": 6.1314,
|
|
"mean_token_accuracy": 0.16206191182136537,
|
|
"num_tokens": 31776453.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 6.299965858459473,
|
|
"epoch": 1.4477784189267167,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048012936701623363,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.16327776312828063,
|
|
"num_tokens": 31789761.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 6.394418525695801,
|
|
"epoch": 1.4483554529717253,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00048011240856216456,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.16258420944213867,
|
|
"num_tokens": 31802689.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 6.29752893447876,
|
|
"epoch": 1.448932487016734,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048009544320924154,
|
|
"loss": 6.169,
|
|
"mean_token_accuracy": 0.16543462723493577,
|
|
"num_tokens": 31816768.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 6.260969018936157,
|
|
"epoch": 1.4495095210617426,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004800784709580351,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.16824788302183152,
|
|
"num_tokens": 31828920.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 6.357678985595703,
|
|
"epoch": 1.4500865551067512,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004800614918091161,
|
|
"loss": 6.1638,
|
|
"mean_token_accuracy": 0.1669384077191353,
|
|
"num_tokens": 31841467.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 6.349787187576294,
|
|
"epoch": 1.4506635891517599,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004800445057630558,
|
|
"loss": 6.1629,
|
|
"mean_token_accuracy": 0.1676136553287506,
|
|
"num_tokens": 31855254.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 6.27349066734314,
|
|
"epoch": 1.4512406231967687,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004800275128204254,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.1662316232919693,
|
|
"num_tokens": 31868234.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 6.35194959640503,
|
|
"epoch": 1.4518176572417771,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048001051298179637,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.17040657103061677,
|
|
"num_tokens": 31880014.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 6.3423114776611325,
|
|
"epoch": 1.452394691286786,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004799935062477407,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.16711047291755676,
|
|
"num_tokens": 31892019.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 6.354385280609131,
|
|
"epoch": 1.4529717253317946,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047997649261883013,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.15655057430267333,
|
|
"num_tokens": 31905837.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 6.31659779548645,
|
|
"epoch": 1.4535487593768033,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004799594720956371,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.16454610973596573,
|
|
"num_tokens": 31917823.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 6.348938417434693,
|
|
"epoch": 1.454125793421812,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.00047994244467873407,
|
|
"loss": 6.1813,
|
|
"mean_token_accuracy": 0.1576891675591469,
|
|
"num_tokens": 31931221.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 6.339001035690307,
|
|
"epoch": 1.4547028274668206,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047992541036869364,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.16306519508361816,
|
|
"num_tokens": 31943739.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 6.3493794918060305,
|
|
"epoch": 1.4552798615118292,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004799083691660889,
|
|
"loss": 6.1816,
|
|
"mean_token_accuracy": 0.16041698455810546,
|
|
"num_tokens": 31957805.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 6.352484798431396,
|
|
"epoch": 1.4558568955568378,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004798913210714929,
|
|
"loss": 6.1328,
|
|
"mean_token_accuracy": 0.17066436260938644,
|
|
"num_tokens": 31970983.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 6.307969427108764,
|
|
"epoch": 1.4564339296018465,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047987426608547915,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.1637205332517624,
|
|
"num_tokens": 31982985.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 6.25712218284607,
|
|
"epoch": 1.4570109636468551,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004798572042086212,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.16790583580732346,
|
|
"num_tokens": 31994854.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 6.328677368164063,
|
|
"epoch": 1.4575879976918638,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047984013544149286,
|
|
"loss": 6.2202,
|
|
"mean_token_accuracy": 0.15574894845485687,
|
|
"num_tokens": 32007476.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 6.4281259059906,
|
|
"epoch": 1.4581650317368724,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047982305978466836,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.16399176120758058,
|
|
"num_tokens": 32021417.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 6.320074844360351,
|
|
"epoch": 1.4587420657818813,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047980597723872205,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1619710475206375,
|
|
"num_tokens": 32033997.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 6.289112663269043,
|
|
"epoch": 1.4593190998268897,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004797888878042283,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.1678844302892685,
|
|
"num_tokens": 32046797.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 6.276427221298218,
|
|
"epoch": 1.4598961338718985,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047977179148176217,
|
|
"loss": 6.1286,
|
|
"mean_token_accuracy": 0.1663985624909401,
|
|
"num_tokens": 32060797.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 6.30776014328003,
|
|
"epoch": 1.4604731679169072,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004797546882718985,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.15766320675611495,
|
|
"num_tokens": 32073936.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 6.3672514915466305,
|
|
"epoch": 1.4610502019619158,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.00047973757817521256,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.1655890852212906,
|
|
"num_tokens": 32086730.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 6.404605484008789,
|
|
"epoch": 1.4616272360069245,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004797204611922799,
|
|
"loss": 6.1674,
|
|
"mean_token_accuracy": 0.16363464891910554,
|
|
"num_tokens": 32099201.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 6.250916290283203,
|
|
"epoch": 1.462204270051933,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047970333732367626,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.16768237501382827,
|
|
"num_tokens": 32112475.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 6.351142501831054,
|
|
"epoch": 1.4627813040969417,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047968620656997754,
|
|
"loss": 6.1456,
|
|
"mean_token_accuracy": 0.16002534329891205,
|
|
"num_tokens": 32124411.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 6.312311601638794,
|
|
"epoch": 1.4633583381419504,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047966906893175994,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.17081220149993898,
|
|
"num_tokens": 32136665.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 6.348316621780396,
|
|
"epoch": 1.463935372186959,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004796519244095998,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.16716521829366685,
|
|
"num_tokens": 32149546.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 6.273695564270019,
|
|
"epoch": 1.4645124062319677,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047963477300407394,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.16554967164993287,
|
|
"num_tokens": 32161327.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 6.307106685638428,
|
|
"epoch": 1.4650894402769763,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047961761471575903,
|
|
"loss": 6.0782,
|
|
"mean_token_accuracy": 0.16557173281908036,
|
|
"num_tokens": 32173678.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 6.207534408569336,
|
|
"epoch": 1.465666474321985,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047960044954523237,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.1673967197537422,
|
|
"num_tokens": 32186834.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 6.304496192932129,
|
|
"epoch": 1.4662435083669936,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047958327749307117,
|
|
"loss": 6.1396,
|
|
"mean_token_accuracy": 0.17024445086717604,
|
|
"num_tokens": 32198876.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 6.291701412200927,
|
|
"epoch": 1.4668205424120022,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047956609855985305,
|
|
"loss": 6.0548,
|
|
"mean_token_accuracy": 0.16752492636442184,
|
|
"num_tokens": 32212190.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 6.335958576202392,
|
|
"epoch": 1.467397576457011,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004795489127461559,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.165318101644516,
|
|
"num_tokens": 32226129.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 6.2873485565185545,
|
|
"epoch": 1.4679746105020195,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047953172005255756,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.15961160510778427,
|
|
"num_tokens": 32240116.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 6.333165073394776,
|
|
"epoch": 1.4685516445470284,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004795145204796365,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.16849917322397232,
|
|
"num_tokens": 32252781.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 6.2766618728637695,
|
|
"epoch": 1.469128678592037,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004794973140279711,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.17072835117578505,
|
|
"num_tokens": 32265625.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 6.324501991271973,
|
|
"epoch": 1.4697057126370456,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047948010069814005,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.16713138967752456,
|
|
"num_tokens": 32278942.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 6.299522256851196,
|
|
"epoch": 1.4702827466820543,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004794628804907225,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.16506323367357253,
|
|
"num_tokens": 32292085.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 6.298580837249756,
|
|
"epoch": 1.470859780727063,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047944565340629755,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.16882706582546234,
|
|
"num_tokens": 32303880.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 6.234088325500489,
|
|
"epoch": 1.4714368147720716,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047942841944544453,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.17083367854356765,
|
|
"num_tokens": 32315711.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 6.344754409790039,
|
|
"epoch": 1.4720138488170802,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004794111786087431,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.1633049726486206,
|
|
"num_tokens": 32329344.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 6.303945016860962,
|
|
"epoch": 1.4725908828620888,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004793939308967733,
|
|
"loss": 6.1848,
|
|
"mean_token_accuracy": 0.16809794306755066,
|
|
"num_tokens": 32343335.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 6.258049535751343,
|
|
"epoch": 1.4731679169070975,
|
|
"grad_norm": 6.78125,
|
|
"learning_rate": 0.0004793766763101152,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.16625706404447554,
|
|
"num_tokens": 32357663.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 6.259440612792969,
|
|
"epoch": 1.4737449509521061,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047935941484934905,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.1702799528837204,
|
|
"num_tokens": 32369310.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 6.247601699829102,
|
|
"epoch": 1.4743219849971148,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047934214651505547,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.16637591719627381,
|
|
"num_tokens": 32381478.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 6.2855452537536625,
|
|
"epoch": 1.4748990190421236,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047932487130781533,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.17474593371152877,
|
|
"num_tokens": 32394697.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 6.227901601791382,
|
|
"epoch": 1.475476053087132,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004793075892282097,
|
|
"loss": 5.9675,
|
|
"mean_token_accuracy": 0.17708137333393098,
|
|
"num_tokens": 32405456.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 6.235746669769287,
|
|
"epoch": 1.476053087132141,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004792903002768197,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.1676441565155983,
|
|
"num_tokens": 32416772.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 6.221759462356568,
|
|
"epoch": 1.4766301211771495,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047927300445422687,
|
|
"loss": 6.0199,
|
|
"mean_token_accuracy": 0.17797380387783052,
|
|
"num_tokens": 32429319.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 6.217854356765747,
|
|
"epoch": 1.4772071552221582,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004792557017610131,
|
|
"loss": 5.9956,
|
|
"mean_token_accuracy": 0.18017663508653642,
|
|
"num_tokens": 32442017.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 6.242416000366211,
|
|
"epoch": 1.4777841892671668,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047923839219776027,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.17175121158361434,
|
|
"num_tokens": 32454255.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 6.161380672454834,
|
|
"epoch": 1.4783612233121755,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004792210757650506,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.1737545147538185,
|
|
"num_tokens": 32465471.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 6.248135375976562,
|
|
"epoch": 1.478938257357184,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047920375246346636,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.16704308986663818,
|
|
"num_tokens": 32478271.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 6.362189865112304,
|
|
"epoch": 1.4795152914021927,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047918642229359044,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.16624097675085067,
|
|
"num_tokens": 32490239.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 6.296052885055542,
|
|
"epoch": 1.4800923254472014,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004791690852560056,
|
|
"loss": 6.1359,
|
|
"mean_token_accuracy": 0.16350751668214797,
|
|
"num_tokens": 32503511.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 6.24784746170044,
|
|
"epoch": 1.48066935949221,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000479151741351295,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.16343062818050386,
|
|
"num_tokens": 32515652.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 6.277792072296142,
|
|
"epoch": 1.4812463935372187,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000479134390580042,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.16031728088855743,
|
|
"num_tokens": 32527620.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 6.39299464225769,
|
|
"epoch": 1.4818234275822273,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047911703294283015,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.16917325854301452,
|
|
"num_tokens": 32540948.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 6.256704425811767,
|
|
"epoch": 1.482400461627236,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047909966844024334,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.1677668496966362,
|
|
"num_tokens": 32553311.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 6.193738842010498,
|
|
"epoch": 1.4829774956722446,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047908229707286547,
|
|
"loss": 5.9834,
|
|
"mean_token_accuracy": 0.17342813462018966,
|
|
"num_tokens": 32564639.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 6.245530033111573,
|
|
"epoch": 1.4835545297172534,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000479064918841281,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.164619517326355,
|
|
"num_tokens": 32577255.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 6.2433384418487545,
|
|
"epoch": 1.4841315637622619,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047904753374607427,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.16741010099649428,
|
|
"num_tokens": 32590201.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 6.279276657104492,
|
|
"epoch": 1.4847085978072707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047903014178783015,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.16273524165153502,
|
|
"num_tokens": 32603010.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 6.354335880279541,
|
|
"epoch": 1.4852856318522794,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004790127429671335,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.1656494528055191,
|
|
"num_tokens": 32614579.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 6.246316576004029,
|
|
"epoch": 1.485862665897288,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004789953372845697,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.1642582133412361,
|
|
"num_tokens": 32627696.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 6.24684886932373,
|
|
"epoch": 1.4864396999422966,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000478977924740724,
|
|
"loss": 6.171,
|
|
"mean_token_accuracy": 0.15860685259103774,
|
|
"num_tokens": 32640824.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 6.320673418045044,
|
|
"epoch": 1.4870167339873053,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004789605053361821,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.16608539447188378,
|
|
"num_tokens": 32654373.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 6.3553577899932865,
|
|
"epoch": 1.487593768032314,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004789430790715299,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.1578859195113182,
|
|
"num_tokens": 32667717.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 6.260083961486816,
|
|
"epoch": 1.4881708020773226,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047892564594735355,
|
|
"loss": 6.1414,
|
|
"mean_token_accuracy": 0.16327641457319259,
|
|
"num_tokens": 32681529.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 6.357323503494262,
|
|
"epoch": 1.4887478361223312,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047890820596423943,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.16188809275627136,
|
|
"num_tokens": 32694883.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 6.320400857925415,
|
|
"epoch": 1.4893248701673398,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000478890759122774,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.1698184132575989,
|
|
"num_tokens": 32706908.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 6.324786186218262,
|
|
"epoch": 1.4899019042123485,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004788733054235443,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.1591644510626793,
|
|
"num_tokens": 32720057.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 6.208461332321167,
|
|
"epoch": 1.4904789382573571,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047885584486713717,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.17133676409721374,
|
|
"num_tokens": 32732200.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 6.282963752746582,
|
|
"epoch": 1.491055972302366,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004788383774541399,
|
|
"loss": 6.0879,
|
|
"mean_token_accuracy": 0.16833843439817428,
|
|
"num_tokens": 32745144.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 6.295819664001465,
|
|
"epoch": 1.4916330063473744,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004788209031851402,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.1617732271552086,
|
|
"num_tokens": 32757495.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 6.223090553283692,
|
|
"epoch": 1.4922100403923833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004788034220607256,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.1723991960287094,
|
|
"num_tokens": 32769562.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 6.260346746444702,
|
|
"epoch": 1.4927870744373917,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047878593408148405,
|
|
"loss": 6.0792,
|
|
"mean_token_accuracy": 0.16787715405225753,
|
|
"num_tokens": 32782234.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 6.21394419670105,
|
|
"epoch": 1.4933641084824005,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047876843924800393,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.16682145297527312,
|
|
"num_tokens": 32795274.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 6.271086740493774,
|
|
"epoch": 1.4939411425274092,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004787509375608735,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.15776642337441443,
|
|
"num_tokens": 32808338.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 6.294681644439697,
|
|
"epoch": 1.4945181765724178,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047873342902068157,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.16260672509670257,
|
|
"num_tokens": 32820204.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 6.337964868545532,
|
|
"epoch": 1.4950952106174265,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047871591362801694,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.1639711320400238,
|
|
"num_tokens": 32832998.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 6.223607349395752,
|
|
"epoch": 1.495672244662435,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004786983913834687,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.16615548431873323,
|
|
"num_tokens": 32845484.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 6.414913702011108,
|
|
"epoch": 1.4962492787074437,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047868086228762633,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.16196768283843993,
|
|
"num_tokens": 32857718.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 6.343223285675049,
|
|
"epoch": 1.4968263127524524,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047866332634107926,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.16523806303739547,
|
|
"num_tokens": 32869908.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 6.271601438522339,
|
|
"epoch": 1.497403346797461,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047864578354441743,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.16479604095220565,
|
|
"num_tokens": 32882549.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 6.2289995670318605,
|
|
"epoch": 1.4979803808424696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004786282338982308,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.1769894078373909,
|
|
"num_tokens": 32894587.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 6.339492082595825,
|
|
"epoch": 1.4985574148874783,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004786106774031096,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.16558513790369034,
|
|
"num_tokens": 32907001.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 6.32451868057251,
|
|
"epoch": 1.499134448932487,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004785931140596445,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.167315773665905,
|
|
"num_tokens": 32919498.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 6.3400568008422855,
|
|
"epoch": 1.4997114829774958,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047857554386842606,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.1587929204106331,
|
|
"num_tokens": 32932611.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 6.306359529495239,
|
|
"epoch": 1.5002885170225042,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047855796683004534,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.16214493662118912,
|
|
"num_tokens": 32944845.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 6.368089056015014,
|
|
"epoch": 1.500865551067513,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047854038294509356,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.1523377075791359,
|
|
"num_tokens": 32958076.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 6.357781219482422,
|
|
"epoch": 1.5014425851125215,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004785227922141621,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.1753346249461174,
|
|
"num_tokens": 32968984.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 6.359879016876221,
|
|
"epoch": 1.5020196191575304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047850519463784263,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.1593037635087967,
|
|
"num_tokens": 32981488.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 6.3068126201629635,
|
|
"epoch": 1.502596653202539,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047848759021672693,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.16349516659975052,
|
|
"num_tokens": 32994156.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 6.335974407196045,
|
|
"epoch": 1.5031736872475476,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004784699789514073,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.16241802722215654,
|
|
"num_tokens": 33007135.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 6.35773777961731,
|
|
"epoch": 1.5037507212925563,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000478452360842476,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.15925257354974748,
|
|
"num_tokens": 33021259.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 6.268192148208618,
|
|
"epoch": 1.504327755337565,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047843473589052557,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.16721211671829223,
|
|
"num_tokens": 33033690.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 6.382220840454101,
|
|
"epoch": 1.5049047893825735,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047841710409614893,
|
|
"loss": 6.1256,
|
|
"mean_token_accuracy": 0.16039337813854218,
|
|
"num_tokens": 33045744.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 6.359376525878906,
|
|
"epoch": 1.5054818234275822,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004783994654599389,
|
|
"loss": 6.1675,
|
|
"mean_token_accuracy": 0.15905430912971497,
|
|
"num_tokens": 33058307.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 6.391716718673706,
|
|
"epoch": 1.5060588574725908,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047838181998248897,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.15556481406092643,
|
|
"num_tokens": 33073622.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 6.295185232162476,
|
|
"epoch": 1.5066358915175995,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004783641676643925,
|
|
"loss": 6.0359,
|
|
"mean_token_accuracy": 0.16836757212877274,
|
|
"num_tokens": 33087286.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 6.236673784255982,
|
|
"epoch": 1.5072129255626083,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047834650850624334,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.1679818168282509,
|
|
"num_tokens": 33100333.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 6.2044658184051515,
|
|
"epoch": 1.5077899596076167,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004783288425086353,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.1649872049689293,
|
|
"num_tokens": 33111318.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 6.406934833526611,
|
|
"epoch": 1.5083669936526256,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004783111696721627,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.16137512922286987,
|
|
"num_tokens": 33123766.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 6.325654792785644,
|
|
"epoch": 1.508944027697634,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004782934899974199,
|
|
"loss": 6.0832,
|
|
"mean_token_accuracy": 0.17172017246484755,
|
|
"num_tokens": 33136042.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 6.260492467880249,
|
|
"epoch": 1.5095210617426429,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047827580348500147,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.17097728699445724,
|
|
"num_tokens": 33148451.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 6.268058347702026,
|
|
"epoch": 1.5100980957876513,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047825811013550246,
|
|
"loss": 6.0869,
|
|
"mean_token_accuracy": 0.1745191514492035,
|
|
"num_tokens": 33161886.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 6.308102035522461,
|
|
"epoch": 1.5106751298326602,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047824040994951786,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.16559694707393646,
|
|
"num_tokens": 33174812.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 6.3163261890411375,
|
|
"epoch": 1.5112521638776688,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004782227029276429,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.17115537822246552,
|
|
"num_tokens": 33187389.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 6.218478345870972,
|
|
"epoch": 1.5118291979226774,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047820498907047345,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.16387352347373962,
|
|
"num_tokens": 33200106.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 6.287623453140259,
|
|
"epoch": 1.512406231967686,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.000478187268378605,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.16405822485685348,
|
|
"num_tokens": 33212929.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 6.3526145935058596,
|
|
"epoch": 1.5129832660126947,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047816954085263375,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.1622457042336464,
|
|
"num_tokens": 33226068.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 6.265248584747314,
|
|
"epoch": 1.5135603000577034,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004781518064931559,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.16928547471761704,
|
|
"num_tokens": 33237677.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 6.333219432830811,
|
|
"epoch": 1.514137334102712,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000478134065300768,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.16705526113510133,
|
|
"num_tokens": 33250640.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 6.280381155014038,
|
|
"epoch": 1.5147143681477209,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004781163172760667,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.17093583345413207,
|
|
"num_tokens": 33262899.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 6.378185701370239,
|
|
"epoch": 1.5152914021927293,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047809856241964893,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.16901710629463196,
|
|
"num_tokens": 33275073.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 6.205471515655518,
|
|
"epoch": 1.5158684362377381,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004780808007321119,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.16522097885608672,
|
|
"num_tokens": 33286285.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 6.32527985572815,
|
|
"epoch": 1.5164454702827466,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004780630322140531,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.1732782319188118,
|
|
"num_tokens": 33297745.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 6.356187438964843,
|
|
"epoch": 1.5170225043277554,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047804525686607,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.15876830518245696,
|
|
"num_tokens": 33309463.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 6.308989381790161,
|
|
"epoch": 1.5175995383727638,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004780274746887606,
|
|
"loss": 6.147,
|
|
"mean_token_accuracy": 0.15899598598480225,
|
|
"num_tokens": 33322352.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 6.343785285949707,
|
|
"epoch": 1.5181765724177727,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047800968568272284,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.16358117014169693,
|
|
"num_tokens": 33336051.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 6.3434113502502445,
|
|
"epoch": 1.5187536064627813,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004779918898485551,
|
|
"loss": 6.1022,
|
|
"mean_token_accuracy": 0.16069099232554435,
|
|
"num_tokens": 33350321.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 6.337099504470825,
|
|
"epoch": 1.51933064050779,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047797408718685614,
|
|
"loss": 6.0725,
|
|
"mean_token_accuracy": 0.16448751240968704,
|
|
"num_tokens": 33363637.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 6.224223947525024,
|
|
"epoch": 1.5199076745527986,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047795627769822447,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.17334780991077423,
|
|
"num_tokens": 33376257.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 6.165194988250732,
|
|
"epoch": 1.5204847085978073,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047793846138325925,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.1717988818883896,
|
|
"num_tokens": 33388812.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 6.248253870010376,
|
|
"epoch": 1.521061742642816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004779206382425598,
|
|
"loss": 6.1,
|
|
"mean_token_accuracy": 0.1664251208305359,
|
|
"num_tokens": 33401141.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 6.297205305099487,
|
|
"epoch": 1.5216387766878245,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004779028082767253,
|
|
"loss": 6.0997,
|
|
"mean_token_accuracy": 0.16420046240091324,
|
|
"num_tokens": 33412821.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 6.258190584182739,
|
|
"epoch": 1.5222158107328332,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004778849714863557,
|
|
"loss": 6.1259,
|
|
"mean_token_accuracy": 0.1637619987130165,
|
|
"num_tokens": 33424709.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 6.308904504776001,
|
|
"epoch": 1.5227928447778418,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004778671278720508,
|
|
"loss": 6.1683,
|
|
"mean_token_accuracy": 0.1601940304040909,
|
|
"num_tokens": 33437069.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 6.263119840621949,
|
|
"epoch": 1.5233698788228507,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004778492774344109,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.1729772388935089,
|
|
"num_tokens": 33449441.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 6.2551123142242435,
|
|
"epoch": 1.523946912867859,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004778314201740363,
|
|
"loss": 6.1833,
|
|
"mean_token_accuracy": 0.15870602279901505,
|
|
"num_tokens": 33463184.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 6.308429145812989,
|
|
"epoch": 1.524523946912868,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047781355609152764,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.17487031370401382,
|
|
"num_tokens": 33476118.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 6.277584075927734,
|
|
"epoch": 1.5251009809578764,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004777956851874858,
|
|
"loss": 6.0615,
|
|
"mean_token_accuracy": 0.16608939617872237,
|
|
"num_tokens": 33487575.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 6.237762451171875,
|
|
"epoch": 1.5256780150028852,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047777780746251176,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.1641905725002289,
|
|
"num_tokens": 33499507.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 6.2443382263183596,
|
|
"epoch": 1.5262550490478937,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047775992291720687,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.16951340883970262,
|
|
"num_tokens": 33513818.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 6.284352970123291,
|
|
"epoch": 1.5268320830929025,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004777420315521728,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.16708099693059922,
|
|
"num_tokens": 33525762.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 6.191858911514283,
|
|
"epoch": 1.5274091171379112,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004777241333680111,
|
|
"loss": 5.9738,
|
|
"mean_token_accuracy": 0.1767125442624092,
|
|
"num_tokens": 33537469.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 6.221562433242798,
|
|
"epoch": 1.5279861511829198,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004777062283653239,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.17175007611513138,
|
|
"num_tokens": 33550226.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 6.314879369735718,
|
|
"epoch": 1.5285631852279284,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.00047768831654471333,
|
|
"loss": 6.1739,
|
|
"mean_token_accuracy": 0.16319517195224761,
|
|
"num_tokens": 33564164.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 6.277708244323731,
|
|
"epoch": 1.529140219272937,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047767039790678204,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.16776868253946303,
|
|
"num_tokens": 33576295.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 6.210209226608276,
|
|
"epoch": 1.5297172533179457,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047765247245213255,
|
|
"loss": 6.055,
|
|
"mean_token_accuracy": 0.17595264613628386,
|
|
"num_tokens": 33587950.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 6.216668558120728,
|
|
"epoch": 1.5302942873629544,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004776345401813678,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.17725253403186797,
|
|
"num_tokens": 33600201.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 6.2638702392578125,
|
|
"epoch": 1.5308713214079632,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047761660109509095,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.1715979754924774,
|
|
"num_tokens": 33612355.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 6.342147922515869,
|
|
"epoch": 1.5314483554529716,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004775986551939054,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.16366921961307526,
|
|
"num_tokens": 33626322.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 6.246899604797363,
|
|
"epoch": 1.5320253894979805,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047758070247841465,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.16893962174654006,
|
|
"num_tokens": 33638433.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 6.2625486850738525,
|
|
"epoch": 1.532602423542989,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047756274294922266,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.1695482537150383,
|
|
"num_tokens": 33651743.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 6.351377201080322,
|
|
"epoch": 1.5331794575879978,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004775447766069334,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.1712990552186966,
|
|
"num_tokens": 33663546.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 6.283286142349243,
|
|
"epoch": 1.5337564916330062,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047752680345215115,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.16872385144233704,
|
|
"num_tokens": 33675358.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 6.26472840309143,
|
|
"epoch": 1.534333525678015,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004775088234854805,
|
|
"loss": 6.0767,
|
|
"mean_token_accuracy": 0.16253549009561538,
|
|
"num_tokens": 33688066.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 6.2303605556488035,
|
|
"epoch": 1.5349105597230237,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004774908367075262,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.17206478714942933,
|
|
"num_tokens": 33700829.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 6.2332827091217045,
|
|
"epoch": 1.5354875937680323,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004774728431188931,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1641959458589554,
|
|
"num_tokens": 33714049.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 6.240980577468872,
|
|
"epoch": 1.536064627813041,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047745484272018664,
|
|
"loss": 6.0188,
|
|
"mean_token_accuracy": 0.17436153143644334,
|
|
"num_tokens": 33727026.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 6.289119005203247,
|
|
"epoch": 1.5366416618580496,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004774368355120119,
|
|
"loss": 6.057,
|
|
"mean_token_accuracy": 0.17154422402381897,
|
|
"num_tokens": 33740400.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 6.1061982154846195,
|
|
"epoch": 1.5372186959030583,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000477418821494975,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1809625193476677,
|
|
"num_tokens": 33753621.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 6.258587503433228,
|
|
"epoch": 1.537795729948067,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004774008006696814,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.1636723607778549,
|
|
"num_tokens": 33765458.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 6.32735013961792,
|
|
"epoch": 1.5383727639930755,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004773827730367375,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.16260947287082672,
|
|
"num_tokens": 33777264.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 6.311409664154053,
|
|
"epoch": 1.5389497980380842,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047736473859674955,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.17010506838560105,
|
|
"num_tokens": 33789837.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 6.123340892791748,
|
|
"epoch": 1.539526832083093,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047734669735032404,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.17906959354877472,
|
|
"num_tokens": 33801666.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 6.2019556045532225,
|
|
"epoch": 1.5401038661281015,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047732864929806796,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.1611937940120697,
|
|
"num_tokens": 33813909.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 6.256455135345459,
|
|
"epoch": 1.5406809001731103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004773105944405883,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.17180472016334533,
|
|
"num_tokens": 33827081.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 6.224641418457031,
|
|
"epoch": 1.5412579342181187,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047729253277849226,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.17465359568595887,
|
|
"num_tokens": 33838261.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 6.285533332824707,
|
|
"epoch": 1.5418349682631276,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047727446431238734,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.16222093552350997,
|
|
"num_tokens": 33850189.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 6.394769525527954,
|
|
"epoch": 1.542412002308136,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004772563890428813,
|
|
"loss": 6.1958,
|
|
"mean_token_accuracy": 0.16250339150428772,
|
|
"num_tokens": 33863570.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 6.269595718383789,
|
|
"epoch": 1.5429890363531449,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004772383069705821,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.1639903500676155,
|
|
"num_tokens": 33876583.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 6.305620288848877,
|
|
"epoch": 1.5435660703981535,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004772202180960978,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.16432901620864868,
|
|
"num_tokens": 33889744.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 6.382720422744751,
|
|
"epoch": 1.5441431044431622,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047720212242003703,
|
|
"loss": 6.1648,
|
|
"mean_token_accuracy": 0.16586382687091827,
|
|
"num_tokens": 33904129.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 6.2075355052948,
|
|
"epoch": 1.5447201384881708,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047718401994300825,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.173862124979496,
|
|
"num_tokens": 33916277.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 6.262147378921509,
|
|
"epoch": 1.5452971725331794,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047716591066562043,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.167170250415802,
|
|
"num_tokens": 33929434.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 6.284850931167602,
|
|
"epoch": 1.545874206578188,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047714779458848255,
|
|
"loss": 6.1036,
|
|
"mean_token_accuracy": 0.16530850380659104,
|
|
"num_tokens": 33942376.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 6.329345703125,
|
|
"epoch": 1.5464512406231967,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004771296717122041,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.16672763228416443,
|
|
"num_tokens": 33955013.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 6.318344497680664,
|
|
"epoch": 1.5470282746682056,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004771115420373945,
|
|
"loss": 6.1355,
|
|
"mean_token_accuracy": 0.1615862876176834,
|
|
"num_tokens": 33966673.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 6.227231454849243,
|
|
"epoch": 1.547605308713214,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047709340556466366,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1722373753786087,
|
|
"num_tokens": 33978400.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 6.331748580932617,
|
|
"epoch": 1.5481823427582229,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047707526229462144,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.1605384096503258,
|
|
"num_tokens": 33990690.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 6.308060550689698,
|
|
"epoch": 1.5487593768032313,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047705711222787816,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.16687259823083878,
|
|
"num_tokens": 34003992.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 6.286748695373535,
|
|
"epoch": 1.5493364108482401,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047703895536504423,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.1681692436337471,
|
|
"num_tokens": 34016075.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 6.280511522293091,
|
|
"epoch": 1.5499134448932486,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004770207917067305,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.16778141260147095,
|
|
"num_tokens": 34029143.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 6.256841468811035,
|
|
"epoch": 1.5504904789382574,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047700262125354765,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.17276279330253602,
|
|
"num_tokens": 34041269.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 6.292127561569214,
|
|
"epoch": 1.551067512983266,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047698444400610707,
|
|
"loss": 6.1481,
|
|
"mean_token_accuracy": 0.16719116121530533,
|
|
"num_tokens": 34054561.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 6.344380474090576,
|
|
"epoch": 1.5516445470282747,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047696625996502,
|
|
"loss": 6.0748,
|
|
"mean_token_accuracy": 0.1604306936264038,
|
|
"num_tokens": 34068009.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 6.280494642257691,
|
|
"epoch": 1.5522215810732833,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047694806913089815,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.16584864556789397,
|
|
"num_tokens": 34081217.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 6.321868991851806,
|
|
"epoch": 1.552798615118292,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004769298715043533,
|
|
"loss": 6.1148,
|
|
"mean_token_accuracy": 0.1603361338376999,
|
|
"num_tokens": 34093903.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 6.34748387336731,
|
|
"epoch": 1.5533756491633006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004769116670859975,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.16427400708198547,
|
|
"num_tokens": 34105891.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 6.295809173583985,
|
|
"epoch": 1.5539526832083093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047689345587644314,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.16782208383083344,
|
|
"num_tokens": 34118438.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 6.269343376159668,
|
|
"epoch": 1.554529717253318,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047687523787630256,
|
|
"loss": 6.0041,
|
|
"mean_token_accuracy": 0.17534742504358292,
|
|
"num_tokens": 34130383.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 6.214257144927979,
|
|
"epoch": 1.5551067512983265,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004768570130861887,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.16669410318136216,
|
|
"num_tokens": 34143805.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 6.295845174789429,
|
|
"epoch": 1.5556837853433354,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004768387815067144,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.1684045284986496,
|
|
"num_tokens": 34157053.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 6.367346620559692,
|
|
"epoch": 1.5562608193883438,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047682054313849304,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.16520717442035676,
|
|
"num_tokens": 34168804.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 6.327089548110962,
|
|
"epoch": 1.5568378534333527,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004768022979821379,
|
|
"loss": 6.142,
|
|
"mean_token_accuracy": 0.16089055836200714,
|
|
"num_tokens": 34181201.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 6.327263450622558,
|
|
"epoch": 1.557414887478361,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004767840460382628,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.16688635051250458,
|
|
"num_tokens": 34193906.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 6.298494577407837,
|
|
"epoch": 1.55799192152337,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004767657873074815,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.16546330600976944,
|
|
"num_tokens": 34207462.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 6.263404703140258,
|
|
"epoch": 1.5585689555683784,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004767475217904081,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1721050813794136,
|
|
"num_tokens": 34219696.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 6.25515718460083,
|
|
"epoch": 1.5591459896133872,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.00047672924948765705,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.17219026386737823,
|
|
"num_tokens": 34232413.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 6.330908012390137,
|
|
"epoch": 1.5597230236583959,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047671097039984293,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.16325631588697434,
|
|
"num_tokens": 34245150.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 6.307193422317505,
|
|
"epoch": 1.5603000577034045,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047669268452758053,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.1737485185265541,
|
|
"num_tokens": 34257416.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 6.241674613952637,
|
|
"epoch": 1.5608770917484132,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.00047667439187148476,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.17202006727457048,
|
|
"num_tokens": 34269518.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 6.244004392623902,
|
|
"epoch": 1.5614541257934218,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004766560924321711,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.1732081651687622,
|
|
"num_tokens": 34280965.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 6.3121312141418455,
|
|
"epoch": 1.5620311598384304,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047663778621025496,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.16684572100639344,
|
|
"num_tokens": 34294051.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 6.288514518737793,
|
|
"epoch": 1.562608193883439,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004766194732063519,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.15813490897417068,
|
|
"num_tokens": 34308052.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 6.302996253967285,
|
|
"epoch": 1.563185227928448,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.00047660115342107814,
|
|
"loss": 6.1005,
|
|
"mean_token_accuracy": 0.16520090252161027,
|
|
"num_tokens": 34321802.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 6.25574312210083,
|
|
"epoch": 1.5637622619734564,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047658282685504973,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.17565805912017823,
|
|
"num_tokens": 34334789.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 6.323505210876465,
|
|
"epoch": 1.5643392960184652,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000476564493508883,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1631614997982979,
|
|
"num_tokens": 34347167.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 6.392896747589111,
|
|
"epoch": 1.5649163300634736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047654615338319466,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.15777474641799927,
|
|
"num_tokens": 34360468.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 6.371495723724365,
|
|
"epoch": 1.5654933641084825,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004765278064786016,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.16007252633571625,
|
|
"num_tokens": 34373835.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 6.312303352355957,
|
|
"epoch": 1.566070398153491,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047650945279572085,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.16909689903259278,
|
|
"num_tokens": 34385591.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 6.34000563621521,
|
|
"epoch": 1.5666474321984998,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004764910923351698,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.15573060512542725,
|
|
"num_tokens": 34398980.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 6.33928861618042,
|
|
"epoch": 1.5672244662435084,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047647272509756584,
|
|
"loss": 6.1339,
|
|
"mean_token_accuracy": 0.1675115406513214,
|
|
"num_tokens": 34412274.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 6.297660255432129,
|
|
"epoch": 1.567801500288517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004764543510835269,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.1719527691602707,
|
|
"num_tokens": 34425043.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 6.312202835083008,
|
|
"epoch": 1.5683785343335257,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000476435970293671,
|
|
"loss": 6.154,
|
|
"mean_token_accuracy": 0.16889333426952363,
|
|
"num_tokens": 34437022.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 6.268210458755493,
|
|
"epoch": 1.5689555683785343,
|
|
"grad_norm": 4.0625,
|
|
"learning_rate": 0.00047641758272861626,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.17029512375593187,
|
|
"num_tokens": 34449668.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 6.270573329925537,
|
|
"epoch": 1.569532602423543,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004763991883889811,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.16294163167476655,
|
|
"num_tokens": 34461588.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 6.220047664642334,
|
|
"epoch": 1.5701096364685516,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004763807872753843,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.16750042587518693,
|
|
"num_tokens": 34474696.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 6.280921459197998,
|
|
"epoch": 1.5706866705135603,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047636237938844484,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.16470820903778077,
|
|
"num_tokens": 34488477.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 6.263820552825928,
|
|
"epoch": 1.571263704558569,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004763439647287817,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.16895479708909988,
|
|
"num_tokens": 34502159.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 6.248439455032349,
|
|
"epoch": 1.5718407386035778,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004763255432970144,
|
|
"loss": 6.0714,
|
|
"mean_token_accuracy": 0.1683644562959671,
|
|
"num_tokens": 34516247.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 6.161786127090454,
|
|
"epoch": 1.5724177726485862,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047630711509376235,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.17339649200439453,
|
|
"num_tokens": 34528599.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 6.315026569366455,
|
|
"epoch": 1.572994806693595,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004762886801196455,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.15327844619750977,
|
|
"num_tokens": 34541346.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 6.389235925674439,
|
|
"epoch": 1.5735718407386035,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047627023837528386,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.16337597817182542,
|
|
"num_tokens": 34553934.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 6.329330778121948,
|
|
"epoch": 1.5741488747836123,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047625178986129775,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.1708940386772156,
|
|
"num_tokens": 34565739.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 6.214039516448975,
|
|
"epoch": 1.5747259088286207,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004762333345783078,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.17032964378595353,
|
|
"num_tokens": 34579062.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 6.2890371799469,
|
|
"epoch": 1.5753029428736296,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047621487252693436,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.17146503627300264,
|
|
"num_tokens": 34592090.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 6.215422916412353,
|
|
"epoch": 1.5758799769186382,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047619640370779876,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.16550679504871368,
|
|
"num_tokens": 34604626.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 6.333647632598877,
|
|
"epoch": 1.5764570109636469,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047617792812152207,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.1639261156320572,
|
|
"num_tokens": 34617174.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 6.230650806427002,
|
|
"epoch": 1.5770340450086555,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004761594457687256,
|
|
"loss": 5.9971,
|
|
"mean_token_accuracy": 0.17324588149785997,
|
|
"num_tokens": 34629909.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 6.257308387756348,
|
|
"epoch": 1.5776110790536642,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004761409566500313,
|
|
"loss": 6.0872,
|
|
"mean_token_accuracy": 0.17212423384189607,
|
|
"num_tokens": 34643640.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 6.281475162506103,
|
|
"epoch": 1.5781881130986728,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047612246076606066,
|
|
"loss": 6.0142,
|
|
"mean_token_accuracy": 0.1610131159424782,
|
|
"num_tokens": 34655250.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 6.323982858657837,
|
|
"epoch": 1.5787651471436814,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047610395811743594,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.16235461086034775,
|
|
"num_tokens": 34669318.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 6.237914276123047,
|
|
"epoch": 1.5793421811886903,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047608544870477956,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1697299838066101,
|
|
"num_tokens": 34680932.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 6.323851537704468,
|
|
"epoch": 1.5799192152336987,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00047606693252871395,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.16352701634168626,
|
|
"num_tokens": 34693091.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 6.353163433074951,
|
|
"epoch": 1.5804962492787076,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000476048409589862,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.16994237452745437,
|
|
"num_tokens": 34706645.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 6.312082672119141,
|
|
"epoch": 1.581073283323716,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004760298798888466,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.16166957914829255,
|
|
"num_tokens": 34718974.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 6.258579730987549,
|
|
"epoch": 1.5816503173687249,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004760113434262911,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.1639259859919548,
|
|
"num_tokens": 34732424.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 6.27340145111084,
|
|
"epoch": 1.5822273514137333,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047599280020281894,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.17224159985780715,
|
|
"num_tokens": 34743865.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 6.236146402359009,
|
|
"epoch": 1.5828043854587421,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047597425021905364,
|
|
"loss": 5.9892,
|
|
"mean_token_accuracy": 0.1733963370323181,
|
|
"num_tokens": 34756415.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 6.32954421043396,
|
|
"epoch": 1.5833814195037508,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004759556934756194,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.1598810486495495,
|
|
"num_tokens": 34769666.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 6.132478141784668,
|
|
"epoch": 1.5839584535487594,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047593712997314017,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.18104538768529893,
|
|
"num_tokens": 34781523.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 6.255754470825195,
|
|
"epoch": 1.584535487593768,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047591855971224035,
|
|
"loss": 6.0319,
|
|
"mean_token_accuracy": 0.16793281435966492,
|
|
"num_tokens": 34794597.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 6.303833389282227,
|
|
"epoch": 1.5851125216387767,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004758999826935446,
|
|
"loss": 6.1652,
|
|
"mean_token_accuracy": 0.1641547754406929,
|
|
"num_tokens": 34807791.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 6.454448127746582,
|
|
"epoch": 1.5856895556837853,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004758813989176778,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.16815381050109862,
|
|
"num_tokens": 34821456.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 6.289196872711182,
|
|
"epoch": 1.586266589728794,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047586280838526483,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.17699868679046632,
|
|
"num_tokens": 34834786.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 6.2721411228179935,
|
|
"epoch": 1.5868436237738026,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004758442110969312,
|
|
"loss": 6.0719,
|
|
"mean_token_accuracy": 0.16389156579971315,
|
|
"num_tokens": 34846125.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 6.36556601524353,
|
|
"epoch": 1.5874206578188113,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004758256070533022,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.1652582183480263,
|
|
"num_tokens": 34858438.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 6.269256162643432,
|
|
"epoch": 1.5879976918638201,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004758069962550037,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.16086930483579637,
|
|
"num_tokens": 34871340.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 6.320274209976196,
|
|
"epoch": 1.5885747259088285,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047578837870266156,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.16528169810771942,
|
|
"num_tokens": 34882111.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 6.327654838562012,
|
|
"epoch": 1.5891517599538374,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047576975439690206,
|
|
"loss": 6.1363,
|
|
"mean_token_accuracy": 0.16278501451015473,
|
|
"num_tokens": 34895539.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 6.314521789550781,
|
|
"epoch": 1.5897287939988458,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047575112333835164,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.16338768899440764,
|
|
"num_tokens": 34907860.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 6.347145318984985,
|
|
"epoch": 1.5903058280438547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047573248552763684,
|
|
"loss": 6.1797,
|
|
"mean_token_accuracy": 0.16526250541210175,
|
|
"num_tokens": 34920595.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 6.345773601531983,
|
|
"epoch": 1.590882862088863,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047571384096538474,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.16914000362157822,
|
|
"num_tokens": 34933458.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 6.261147594451904,
|
|
"epoch": 1.591459896133872,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004756951896522222,
|
|
"loss": 6.0385,
|
|
"mean_token_accuracy": 0.17352436035871505,
|
|
"num_tokens": 34946872.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 6.304848003387451,
|
|
"epoch": 1.5920369301788806,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004756765315887766,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.16546263694763183,
|
|
"num_tokens": 34959384.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 6.362481641769409,
|
|
"epoch": 1.5926139642238892,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004756578667756756,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.16471261978149415,
|
|
"num_tokens": 34971571.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 6.298099565505981,
|
|
"epoch": 1.5931909982688979,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004756391952135469,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.17933578938245773,
|
|
"num_tokens": 34984897.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 6.322285318374634,
|
|
"epoch": 1.5937680323139065,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047562051690301855,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.1619904324412346,
|
|
"num_tokens": 34998185.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 6.395644950866699,
|
|
"epoch": 1.5943450663589152,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047560183184471873,
|
|
"loss": 6.0972,
|
|
"mean_token_accuracy": 0.1668487012386322,
|
|
"num_tokens": 35010985.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 6.311239624023438,
|
|
"epoch": 1.5949221004039238,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000475583140039276,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.16769470274448395,
|
|
"num_tokens": 35023785.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 6.369430828094482,
|
|
"epoch": 1.5954991344489324,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047556444148731897,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.15731503814458847,
|
|
"num_tokens": 35035926.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 6.3039085388183596,
|
|
"epoch": 1.596076168493941,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004755457361894766,
|
|
"loss": 6.1064,
|
|
"mean_token_accuracy": 0.16659609824419022,
|
|
"num_tokens": 35048290.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 6.290177297592163,
|
|
"epoch": 1.59665320253895,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047552702414637793,
|
|
"loss": 6.0144,
|
|
"mean_token_accuracy": 0.17391386926174163,
|
|
"num_tokens": 35059883.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 6.334092044830323,
|
|
"epoch": 1.5972302365839584,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047550830535865245,
|
|
"loss": 6.1131,
|
|
"mean_token_accuracy": 0.16483326703310014,
|
|
"num_tokens": 35071747.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 6.252234888076782,
|
|
"epoch": 1.5978072706289672,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047548957982692974,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.16601303368806838,
|
|
"num_tokens": 35083774.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 6.295589828491211,
|
|
"epoch": 1.5983843046739756,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004754708475518396,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.17326804846525193,
|
|
"num_tokens": 35095757.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 6.31047887802124,
|
|
"epoch": 1.5989613387189845,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047545210853401214,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.16631067395210267,
|
|
"num_tokens": 35108788.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 6.352183723449707,
|
|
"epoch": 1.599538372763993,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047543336277407753,
|
|
"loss": 6.2169,
|
|
"mean_token_accuracy": 0.16050542891025543,
|
|
"num_tokens": 35121641.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 6.352316522598267,
|
|
"epoch": 1.6001154068090018,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047541461027266624,
|
|
"loss": 6.1502,
|
|
"mean_token_accuracy": 0.16059670001268386,
|
|
"num_tokens": 35133960.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 6.363188743591309,
|
|
"epoch": 1.6006924408540104,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004753958510304091,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.1658671870827675,
|
|
"num_tokens": 35146027.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 6.350321197509766,
|
|
"epoch": 1.601269474899019,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047537708504793714,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.16653528958559036,
|
|
"num_tokens": 35158728.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 6.2908519268035885,
|
|
"epoch": 1.6018465089440277,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047535831232588146,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.16270237565040588,
|
|
"num_tokens": 35171734.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 6.360332727432251,
|
|
"epoch": 1.6024235429890363,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047533953286487345,
|
|
"loss": 6.1369,
|
|
"mean_token_accuracy": 0.15890816748142242,
|
|
"num_tokens": 35185074.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 6.3325221061706545,
|
|
"epoch": 1.603000577034045,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004753207466655447,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.16376099586486817,
|
|
"num_tokens": 35197972.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 6.334444665908814,
|
|
"epoch": 1.6035776110790536,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004753019537285273,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.1678009122610092,
|
|
"num_tokens": 35210939.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 6.386923742294312,
|
|
"epoch": 1.6041546451240625,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047528315405445296,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.16232287734746934,
|
|
"num_tokens": 35223521.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 6.303661584854126,
|
|
"epoch": 1.604731679169071,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047526434764395435,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.16882762908935547,
|
|
"num_tokens": 35235713.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 6.249205541610718,
|
|
"epoch": 1.6053087132140798,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047524553449766386,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.16625256538391114,
|
|
"num_tokens": 35248938.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 6.343287229537964,
|
|
"epoch": 1.6058857472590882,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047522671461621433,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.16260135173797607,
|
|
"num_tokens": 35260916.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 6.35877799987793,
|
|
"epoch": 1.606462781304097,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004752078880002386,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.16499348878860473,
|
|
"num_tokens": 35273529.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 6.319088792800903,
|
|
"epoch": 1.6070398153491054,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047518905465037005,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.16407953053712845,
|
|
"num_tokens": 35285500.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 6.29489312171936,
|
|
"epoch": 1.6076168493941143,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047517021456724214,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.1632474958896637,
|
|
"num_tokens": 35300039.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 6.309400177001953,
|
|
"epoch": 1.608193883439123,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047515136775148843,
|
|
"loss": 6.1973,
|
|
"mean_token_accuracy": 0.15550429224967957,
|
|
"num_tokens": 35313091.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 6.329781770706177,
|
|
"epoch": 1.6087709174841316,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004751325142037429,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.16518935412168503,
|
|
"num_tokens": 35325890.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 6.278371334075928,
|
|
"epoch": 1.6093479515291402,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047511365392463974,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.17123775631189347,
|
|
"num_tokens": 35339395.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 6.252002334594726,
|
|
"epoch": 1.6099249855741489,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047509478691481317,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.16890290081501008,
|
|
"num_tokens": 35351163.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 6.394436597824097,
|
|
"epoch": 1.6105020196191575,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.00047507591317489783,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.1712552562355995,
|
|
"num_tokens": 35364099.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 6.3305333137512205,
|
|
"epoch": 1.6110790536641661,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004750570327055286,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.1640000745654106,
|
|
"num_tokens": 35376768.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 6.344961166381836,
|
|
"epoch": 1.6116560877091748,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047503814550734034,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1643372043967247,
|
|
"num_tokens": 35388892.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 6.371452808380127,
|
|
"epoch": 1.6122331217541834,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004750192515809685,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.16151557713747025,
|
|
"num_tokens": 35401573.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 6.332014751434326,
|
|
"epoch": 1.6128101557991923,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047500035092704843,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.16190767139196396,
|
|
"num_tokens": 35415073.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 6.248025035858154,
|
|
"epoch": 1.6133871898442007,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004749814435462159,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.1728854924440384,
|
|
"num_tokens": 35428756.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 6.308794832229614,
|
|
"epoch": 1.6139642238892096,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004749625294391069,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.16338517218828202,
|
|
"num_tokens": 35440387.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 6.26749005317688,
|
|
"epoch": 1.614541257934218,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047494360860635755,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.18377355188131334,
|
|
"num_tokens": 35454105.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 6.304738330841064,
|
|
"epoch": 1.6151182919792268,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004749246810486042,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.16615962982177734,
|
|
"num_tokens": 35467775.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 6.271231174468994,
|
|
"epoch": 1.6156953260242353,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004749057467664836,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.16965964138507844,
|
|
"num_tokens": 35479217.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 6.302905178070068,
|
|
"epoch": 1.6162723600692441,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047488680576063247,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.1761475294828415,
|
|
"num_tokens": 35490676.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 6.224405097961426,
|
|
"epoch": 1.6168493941142528,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004748678580316878,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.16903021633625032,
|
|
"num_tokens": 35503440.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 6.247961568832397,
|
|
"epoch": 1.6174264281592614,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047484890358028714,
|
|
"loss": 6.0403,
|
|
"mean_token_accuracy": 0.1722070872783661,
|
|
"num_tokens": 35515717.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 6.377208995819092,
|
|
"epoch": 1.61800346220427,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004748299424070678,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.16644570976495743,
|
|
"num_tokens": 35528445.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 6.203998327255249,
|
|
"epoch": 1.6185804962492787,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004748109745126677,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.17228845208883287,
|
|
"num_tokens": 35541652.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 6.157395648956299,
|
|
"epoch": 1.6191575302942873,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047479199989772464,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.1703417792916298,
|
|
"num_tokens": 35555310.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 6.334373998641968,
|
|
"epoch": 1.619734564339296,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000474773018562877,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.16538431942462922,
|
|
"num_tokens": 35567830.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 6.271333789825439,
|
|
"epoch": 1.6203115983843048,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047475403050876297,
|
|
"loss": 6.0555,
|
|
"mean_token_accuracy": 0.16785277426242828,
|
|
"num_tokens": 35579054.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 6.363547706604004,
|
|
"epoch": 1.6208886324293132,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004747350357360214,
|
|
"loss": 6.1628,
|
|
"mean_token_accuracy": 0.16527276188135148,
|
|
"num_tokens": 35592463.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 6.34897894859314,
|
|
"epoch": 1.621465666474322,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004747160342452912,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.1657451093196869,
|
|
"num_tokens": 35605127.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 6.232157468795776,
|
|
"epoch": 1.6220427005193305,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047469702603721134,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.17249712347984314,
|
|
"num_tokens": 35617509.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 6.257739067077637,
|
|
"epoch": 1.6226197345643394,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004746780111124212,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.16773395836353303,
|
|
"num_tokens": 35630788.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 6.354380941390991,
|
|
"epoch": 1.6231967686093478,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047465898947156033,
|
|
"loss": 6.1451,
|
|
"mean_token_accuracy": 0.16356271356344224,
|
|
"num_tokens": 35643613.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 6.372706079483033,
|
|
"epoch": 1.6237738026543567,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00047463996111526854,
|
|
"loss": 6.1067,
|
|
"mean_token_accuracy": 0.1694120690226555,
|
|
"num_tokens": 35656495.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 6.3641197681427,
|
|
"epoch": 1.6243508366993653,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047462092604418576,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.1535666763782501,
|
|
"num_tokens": 35669661.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 6.269794607162476,
|
|
"epoch": 1.624927870744374,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047460188425895236,
|
|
"loss": 6.0978,
|
|
"mean_token_accuracy": 0.16541868150234224,
|
|
"num_tokens": 35682675.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 6.331015968322754,
|
|
"epoch": 1.6255049047893826,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047458283576020874,
|
|
"loss": 6.1263,
|
|
"mean_token_accuracy": 0.16866612434387207,
|
|
"num_tokens": 35694571.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 6.305769634246826,
|
|
"epoch": 1.6260819388343912,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047456378054859554,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.1698611244559288,
|
|
"num_tokens": 35707196.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 6.2425220012664795,
|
|
"epoch": 1.6266589728793999,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047454471862475375,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.17151181250810624,
|
|
"num_tokens": 35719682.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 6.317946672439575,
|
|
"epoch": 1.6272360069244085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047452564998932446,
|
|
"loss": 6.1473,
|
|
"mean_token_accuracy": 0.16216070652008058,
|
|
"num_tokens": 35732595.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 6.355157709121704,
|
|
"epoch": 1.6278130409694171,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000474506574642949,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.1663676917552948,
|
|
"num_tokens": 35744611.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 6.2730059146881105,
|
|
"epoch": 1.6283900750144258,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000474487492586269,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.16661421656608583,
|
|
"num_tokens": 35757288.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 6.374433422088623,
|
|
"epoch": 1.6289671090594346,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004744684038199263,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.16418022513389588,
|
|
"num_tokens": 35769747.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 6.3676992893219,
|
|
"epoch": 1.629544143104443,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047444930834456293,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.16366525143384933,
|
|
"num_tokens": 35781656.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 6.329796028137207,
|
|
"epoch": 1.630121177149452,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004744302061608212,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.16873974055051805,
|
|
"num_tokens": 35794618.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 6.369326257705689,
|
|
"epoch": 1.6306982111944603,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047441109726934345,
|
|
"loss": 6.0348,
|
|
"mean_token_accuracy": 0.16814184337854385,
|
|
"num_tokens": 35807504.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 6.217661762237549,
|
|
"epoch": 1.6312752452394692,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047439198167077256,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.17050414085388182,
|
|
"num_tokens": 35819668.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 6.300717782974243,
|
|
"epoch": 1.6318522792844776,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004743728593657514,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.17155559360980988,
|
|
"num_tokens": 35832078.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 6.3105512142181395,
|
|
"epoch": 1.6324293133294865,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004743537303549231,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.17244088500738144,
|
|
"num_tokens": 35843580.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 6.236100673675537,
|
|
"epoch": 1.6330063473744951,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004743345946389311,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.17535771280527115,
|
|
"num_tokens": 35857146.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 6.253125715255737,
|
|
"epoch": 1.6335833814195038,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.00047431545221841907,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.16937452852725982,
|
|
"num_tokens": 35869374.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 6.396531057357788,
|
|
"epoch": 1.6341604154645124,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047429630309403086,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.15818234384059907,
|
|
"num_tokens": 35881882.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 6.185387468338012,
|
|
"epoch": 1.634737449509521,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047427714726641044,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.179660464823246,
|
|
"num_tokens": 35895512.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 6.18449034690857,
|
|
"epoch": 1.6353144835545297,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047425798473620215,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.1764688104391098,
|
|
"num_tokens": 35908020.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 6.300310659408569,
|
|
"epoch": 1.6358915175995383,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004742388155040505,
|
|
"loss": 6.0202,
|
|
"mean_token_accuracy": 0.17187013179063798,
|
|
"num_tokens": 35920261.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 6.360107517242431,
|
|
"epoch": 1.6364685516445472,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047421963957060026,
|
|
"loss": 6.1752,
|
|
"mean_token_accuracy": 0.16400312632322311,
|
|
"num_tokens": 35932135.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 6.245635604858398,
|
|
"epoch": 1.6370455856895556,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004742004569364964,
|
|
"loss": 6.0604,
|
|
"mean_token_accuracy": 0.16876980662345886,
|
|
"num_tokens": 35944574.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 6.269022464752197,
|
|
"epoch": 1.6376226197345645,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047418126760238416,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.1743795841932297,
|
|
"num_tokens": 35956877.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 6.316147232055664,
|
|
"epoch": 1.6381996537795729,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047416207156890887,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.16733625382184983,
|
|
"num_tokens": 35968616.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 6.280966711044312,
|
|
"epoch": 1.6387766878245817,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004741428688367164,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.16590285897254944,
|
|
"num_tokens": 35982401.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 6.303164863586426,
|
|
"epoch": 1.6393537218695902,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047412365940645225,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.17370134890079497,
|
|
"num_tokens": 35994907.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 6.327745819091797,
|
|
"epoch": 1.639930755914599,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00047410444327876286,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.16742120534181595,
|
|
"num_tokens": 36007109.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 6.253001260757446,
|
|
"epoch": 1.6405077899596077,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047408522045429426,
|
|
"loss": 6.1394,
|
|
"mean_token_accuracy": 0.16436311453580857,
|
|
"num_tokens": 36018734.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 6.322027969360351,
|
|
"epoch": 1.6410848240046163,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004740659909336933,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.16763557493686676,
|
|
"num_tokens": 36031427.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 6.3208245754241945,
|
|
"epoch": 1.641661858049625,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047404675471760655,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.16826531291007996,
|
|
"num_tokens": 36044726.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 6.2171959400177,
|
|
"epoch": 1.6422388920946336,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004740275118066811,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.16296851485967637,
|
|
"num_tokens": 36056882.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 6.3228593349456785,
|
|
"epoch": 1.6428159261396422,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047400826220156416,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.162416909635067,
|
|
"num_tokens": 36068548.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 6.356378126144409,
|
|
"epoch": 1.6433929601846509,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00047398900590290313,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.16246748268604277,
|
|
"num_tokens": 36080652.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 6.2382556915283205,
|
|
"epoch": 1.6439699942296595,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047396974291134575,
|
|
"loss": 6.0953,
|
|
"mean_token_accuracy": 0.16950343698263168,
|
|
"num_tokens": 36093372.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 6.337120532989502,
|
|
"epoch": 1.6445470282746681,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047395047322754,
|
|
"loss": 6.1044,
|
|
"mean_token_accuracy": 0.17220360785722733,
|
|
"num_tokens": 36106023.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 6.349548196792602,
|
|
"epoch": 1.645124062319677,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047393119685213374,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1731447085738182,
|
|
"num_tokens": 36119627.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 6.130048561096191,
|
|
"epoch": 1.6457010963646854,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004739119137857756,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.1846640169620514,
|
|
"num_tokens": 36132835.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 6.287685298919678,
|
|
"epoch": 1.6462781304096943,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.00047389262402911404,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.16985928565263747,
|
|
"num_tokens": 36144234.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 6.28140811920166,
|
|
"epoch": 1.6468551644547027,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047387332758279784,
|
|
"loss": 6.0292,
|
|
"mean_token_accuracy": 0.16954858899116515,
|
|
"num_tokens": 36158556.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 6.276857662200928,
|
|
"epoch": 1.6474321984997116,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047385402444747606,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.1673444241285324,
|
|
"num_tokens": 36171698.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 6.280260753631592,
|
|
"epoch": 1.64800923254472,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.00047383471462379803,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.16841488927602768,
|
|
"num_tokens": 36184649.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 6.3320068359375,
|
|
"epoch": 1.6485862665897288,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000473815398112413,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.17274200022220612,
|
|
"num_tokens": 36197127.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 6.297778749465943,
|
|
"epoch": 1.6491633006347375,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004737960749139708,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.16634163707494737,
|
|
"num_tokens": 36209471.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 6.3453363418579105,
|
|
"epoch": 1.6497403346797461,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004737767450291215,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.16584311574697494,
|
|
"num_tokens": 36221798.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 6.23340950012207,
|
|
"epoch": 1.6503173687247548,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047375740845851506,
|
|
"loss": 6.0453,
|
|
"mean_token_accuracy": 0.16708384156227113,
|
|
"num_tokens": 36235758.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 6.240923690795898,
|
|
"epoch": 1.6508944027697634,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004737380652028019,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.16766662746667862,
|
|
"num_tokens": 36248484.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 6.218803548812867,
|
|
"epoch": 1.651471436814772,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047371871526263263,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.18093321323394776,
|
|
"num_tokens": 36260796.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 6.229616022109985,
|
|
"epoch": 1.6520484708597807,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004736993586386581,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.16974446326494216,
|
|
"num_tokens": 36273617.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 6.202992248535156,
|
|
"epoch": 1.6526255049047895,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00047367999533152934,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.17423105984926224,
|
|
"num_tokens": 36286285.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 6.307953596115112,
|
|
"epoch": 1.653202538949798,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00047366062534189756,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.16763816475868226,
|
|
"num_tokens": 36298970.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 6.276805305480957,
|
|
"epoch": 1.6537795729948068,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047364124867041446,
|
|
"loss": 6.0462,
|
|
"mean_token_accuracy": 0.176275734603405,
|
|
"num_tokens": 36312684.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 6.253661394119263,
|
|
"epoch": 1.6543566070398152,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047362186531773156,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.16896721422672273,
|
|
"num_tokens": 36326300.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 6.266036891937256,
|
|
"epoch": 1.654933641084824,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004736024752845008,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.169168621301651,
|
|
"num_tokens": 36338234.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 6.282933187484741,
|
|
"epoch": 1.6555106751298325,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004735830785713746,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.16418775916099548,
|
|
"num_tokens": 36351032.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 6.279763555526733,
|
|
"epoch": 1.6560877091748414,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004735636751790051,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.1654868558049202,
|
|
"num_tokens": 36363267.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 6.2751750469207765,
|
|
"epoch": 1.65666474321985,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000473544265108045,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.17139649987220765,
|
|
"num_tokens": 36375628.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 6.262072467803955,
|
|
"epoch": 1.6572417772648587,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047352484835914716,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.16745211482048034,
|
|
"num_tokens": 36388161.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 6.334037446975708,
|
|
"epoch": 1.6578188113098673,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004735054249329647,
|
|
"loss": 6.082,
|
|
"mean_token_accuracy": 0.169405734539032,
|
|
"num_tokens": 36400287.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 6.40230073928833,
|
|
"epoch": 1.658395845354876,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047348599483015087,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.16180269569158554,
|
|
"num_tokens": 36413896.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 6.28045129776001,
|
|
"epoch": 1.6589728793998846,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047346655805135916,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.17025929540395737,
|
|
"num_tokens": 36425812.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 6.212641954421997,
|
|
"epoch": 1.6595499134448932,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004734471145972434,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.1649244725704193,
|
|
"num_tokens": 36438977.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 6.310390663146973,
|
|
"epoch": 1.6601269474899019,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047342766446845753,
|
|
"loss": 6.0707,
|
|
"mean_token_accuracy": 0.1669655993580818,
|
|
"num_tokens": 36453173.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 6.309250164031982,
|
|
"epoch": 1.6607039815349105,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004734082076656557,
|
|
"loss": 6.0591,
|
|
"mean_token_accuracy": 0.1656690925359726,
|
|
"num_tokens": 36464977.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 6.293370246887207,
|
|
"epoch": 1.6612810155799194,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047338874418949235,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.16307076811790466,
|
|
"num_tokens": 36476951.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 6.3167040824890135,
|
|
"epoch": 1.6618580496249278,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047336927404062213,
|
|
"loss": 6.1511,
|
|
"mean_token_accuracy": 0.16583692729473115,
|
|
"num_tokens": 36490387.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 6.362817287445068,
|
|
"epoch": 1.6624350836699366,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047334979721969995,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.1716933622956276,
|
|
"num_tokens": 36501958.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 6.351159572601318,
|
|
"epoch": 1.663012117714945,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004733303137273808,
|
|
"loss": 6.182,
|
|
"mean_token_accuracy": 0.16345127671957016,
|
|
"num_tokens": 36515355.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 6.361408281326294,
|
|
"epoch": 1.663589151759954,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047331082356432015,
|
|
"loss": 6.19,
|
|
"mean_token_accuracy": 0.16078285574913026,
|
|
"num_tokens": 36528288.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 6.388300895690918,
|
|
"epoch": 1.6641661858049623,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004732913267311734,
|
|
"loss": 6.17,
|
|
"mean_token_accuracy": 0.16457592099905013,
|
|
"num_tokens": 36541577.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 6.301159620285034,
|
|
"epoch": 1.6647432198499712,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004732718232285964,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.1722007229924202,
|
|
"num_tokens": 36554802.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 6.259671449661255,
|
|
"epoch": 1.6653202538949798,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047325231305724507,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.1640797436237335,
|
|
"num_tokens": 36567175.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 6.251500034332276,
|
|
"epoch": 1.6658972879399885,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004732327962177757,
|
|
"loss": 6.0171,
|
|
"mean_token_accuracy": 0.18299563825130463,
|
|
"num_tokens": 36579391.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 6.341972541809082,
|
|
"epoch": 1.6664743219849971,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004732132727108447,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.16472519487142562,
|
|
"num_tokens": 36592684.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 6.3064422607421875,
|
|
"epoch": 1.6670513560300058,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047319374253710874,
|
|
"loss": 6.1486,
|
|
"mean_token_accuracy": 0.16581295132637025,
|
|
"num_tokens": 36604996.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 6.350444650650024,
|
|
"epoch": 1.6676283900750144,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004731742056972247,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.16828773766756058,
|
|
"num_tokens": 36618914.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 6.259874773025513,
|
|
"epoch": 1.668205424120023,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004731546621918497,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.1697782725095749,
|
|
"num_tokens": 36630527.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 6.252018451690674,
|
|
"epoch": 1.668782458165032,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.000473135112021641,
|
|
"loss": 6.1106,
|
|
"mean_token_accuracy": 0.16840582937002183,
|
|
"num_tokens": 36642605.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 6.2921864032745365,
|
|
"epoch": 1.6693594922100403,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047311555518725617,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.16681113839149475,
|
|
"num_tokens": 36655075.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 6.240460395812988,
|
|
"epoch": 1.6699365262550492,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047309599168935323,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.16931247115135192,
|
|
"num_tokens": 36667684.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 6.286182641983032,
|
|
"epoch": 1.6705135603000576,
|
|
"grad_norm": 4.625,
|
|
"learning_rate": 0.00047307642152858993,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.1699221059679985,
|
|
"num_tokens": 36679656.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 6.269905281066895,
|
|
"epoch": 1.6710905943450665,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.00047305684470562453,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.1783604308962822,
|
|
"num_tokens": 36691691.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 6.258505725860596,
|
|
"epoch": 1.6716676283900749,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004730372612211156,
|
|
"loss": 6.077,
|
|
"mean_token_accuracy": 0.1736406207084656,
|
|
"num_tokens": 36703615.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 6.27036304473877,
|
|
"epoch": 1.6722446624350837,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00047301767107572174,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.16444099098443984,
|
|
"num_tokens": 36716299.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 6.333795166015625,
|
|
"epoch": 1.6728216964800924,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004729980742701018,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.16901907622814177,
|
|
"num_tokens": 36727723.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 6.242728137969971,
|
|
"epoch": 1.673398730525101,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004729784708049151,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.17809747010469437,
|
|
"num_tokens": 36740497.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 6.122395133972168,
|
|
"epoch": 1.6739757645701097,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004729588606808209,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.1696045443415642,
|
|
"num_tokens": 36752862.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 6.329869270324707,
|
|
"epoch": 1.6745527986151183,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047293924389847864,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.16898933798074722,
|
|
"num_tokens": 36765948.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 6.2872460842132565,
|
|
"epoch": 1.675129832660127,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004729196204585483,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.16923158019781112,
|
|
"num_tokens": 36778768.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 6.289277219772339,
|
|
"epoch": 1.6757068667051356,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00047289999036168983,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.1675689622759819,
|
|
"num_tokens": 36790941.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 6.314367389678955,
|
|
"epoch": 1.6762839007501442,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004728803536085634,
|
|
"loss": 6.1636,
|
|
"mean_token_accuracy": 0.1690709784626961,
|
|
"num_tokens": 36803984.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 6.267935705184937,
|
|
"epoch": 1.6768609347951529,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047286071019982974,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.172528937458992,
|
|
"num_tokens": 36815079.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 6.230243587493897,
|
|
"epoch": 1.6774379688401617,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047284106013614926,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.17123476564884185,
|
|
"num_tokens": 36828007.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 6.433234691619873,
|
|
"epoch": 1.6780150028851701,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.000472821403418183,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.15828924477100373,
|
|
"num_tokens": 36841762.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 6.321075105667115,
|
|
"epoch": 1.678592036930179,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004728017400465921,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.16850826889276505,
|
|
"num_tokens": 36854624.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 6.263060855865478,
|
|
"epoch": 1.6791690709751874,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047278207002203796,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.1637829512357712,
|
|
"num_tokens": 36866266.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 6.309200429916382,
|
|
"epoch": 1.6797461050201963,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047276239334518216,
|
|
"loss": 6.1123,
|
|
"mean_token_accuracy": 0.16346139907836915,
|
|
"num_tokens": 36878813.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 6.256145763397217,
|
|
"epoch": 1.6803231390652047,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047274271001668646,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.16486488208174704,
|
|
"num_tokens": 36891848.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 6.230090188980102,
|
|
"epoch": 1.6809001731102136,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047272302003721286,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.17097180038690568,
|
|
"num_tokens": 36903861.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 6.310818386077881,
|
|
"epoch": 1.6814772071552222,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047270332340742377,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.16238213181495667,
|
|
"num_tokens": 36916849.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 6.360727548599243,
|
|
"epoch": 1.6820542412002308,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047268362012798157,
|
|
"loss": 6.1313,
|
|
"mean_token_accuracy": 0.1568854719400406,
|
|
"num_tokens": 36929559.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 6.244599103927612,
|
|
"epoch": 1.6826312752452395,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004726639101995491,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.1702466532588005,
|
|
"num_tokens": 36943958.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 6.22980580329895,
|
|
"epoch": 1.6832083092902481,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047264419362278906,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.1754392057657242,
|
|
"num_tokens": 36956542.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 6.289747095108032,
|
|
"epoch": 1.6837853433352568,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047262447039836484,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1649500235915184,
|
|
"num_tokens": 36968872.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 6.285870981216431,
|
|
"epoch": 1.6843623773802654,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047260474052693963,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.1678180992603302,
|
|
"num_tokens": 36982234.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 6.246563816070557,
|
|
"epoch": 1.684939411425274,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047258500400917724,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.16805330067873,
|
|
"num_tokens": 36994407.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 6.325880527496338,
|
|
"epoch": 1.6855164454702827,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047256526084574137,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.1641208603978157,
|
|
"num_tokens": 37006147.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 6.266071701049805,
|
|
"epoch": 1.6860934795152915,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047254551103729597,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.16772838830947875,
|
|
"num_tokens": 37018206.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 6.275664186477661,
|
|
"epoch": 1.6866705135603,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004725257545845055,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.16369811147451402,
|
|
"num_tokens": 37030632.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 6.217998313903808,
|
|
"epoch": 1.6872475476053088,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047250599148803443,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.1760655924677849,
|
|
"num_tokens": 37041700.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 6.268389558792114,
|
|
"epoch": 1.6878245816503172,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047248622174854746,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.1739245593547821,
|
|
"num_tokens": 37054467.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 6.202273797988892,
|
|
"epoch": 1.688401615695326,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004724664453667094,
|
|
"loss": 5.9802,
|
|
"mean_token_accuracy": 0.17177198827266693,
|
|
"num_tokens": 37066596.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 6.2765673160552975,
|
|
"epoch": 1.6889786497403345,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004724466623431857,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.1682032197713852,
|
|
"num_tokens": 37078812.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 6.285689496994019,
|
|
"epoch": 1.6895556837853434,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004724268726786415,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.16566502600908278,
|
|
"num_tokens": 37090916.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 6.204647207260132,
|
|
"epoch": 1.690132717830352,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004724070763737424,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.1659800134599209,
|
|
"num_tokens": 37104687.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 6.312428569793701,
|
|
"epoch": 1.6907097518753607,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004723872734291545,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.16727470308542253,
|
|
"num_tokens": 37117763.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 6.279324579238891,
|
|
"epoch": 1.6912867859203693,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047236746384554364,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.1683202251791954,
|
|
"num_tokens": 37130355.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 6.299044466018676,
|
|
"epoch": 1.691863819965378,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004723476476235762,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.17116303145885467,
|
|
"num_tokens": 37142116.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 6.232453632354736,
|
|
"epoch": 1.6924408540103866,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004723278247639186,
|
|
"loss": 6.023,
|
|
"mean_token_accuracy": 0.1750013381242752,
|
|
"num_tokens": 37153841.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 6.205951595306397,
|
|
"epoch": 1.6930178880553952,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004723079952672377,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.1719754680991173,
|
|
"num_tokens": 37165119.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 6.308799934387207,
|
|
"epoch": 1.693594922100404,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047228815913420035,
|
|
"loss": 6.1138,
|
|
"mean_token_accuracy": 0.16897120028734208,
|
|
"num_tokens": 37178188.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 6.232822418212891,
|
|
"epoch": 1.6941719561454125,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004722683163654738,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.17685008347034453,
|
|
"num_tokens": 37190211.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 6.244020748138428,
|
|
"epoch": 1.6947489901904214,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004722484669617254,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.17107994109392166,
|
|
"num_tokens": 37202408.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 6.241586112976075,
|
|
"epoch": 1.6953260242354298,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047222861092362277,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.16470692306756973,
|
|
"num_tokens": 37214393.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 6.283365488052368,
|
|
"epoch": 1.6959030582804386,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00047220874825183387,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.16655275076627732,
|
|
"num_tokens": 37227212.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 6.161387777328491,
|
|
"epoch": 1.696480092325447,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047218887894702656,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.1703656107187271,
|
|
"num_tokens": 37239742.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 6.316285276412964,
|
|
"epoch": 1.697057126370456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004721690030098693,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.16381090879440308,
|
|
"num_tokens": 37254037.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 6.318480205535889,
|
|
"epoch": 1.6976341604154646,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004721491204410305,
|
|
"loss": 6.0954,
|
|
"mean_token_accuracy": 0.16951050013303756,
|
|
"num_tokens": 37265221.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 6.3138233661651615,
|
|
"epoch": 1.6982111944604732,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047212923124117915,
|
|
"loss": 6.0778,
|
|
"mean_token_accuracy": 0.16995845586061478,
|
|
"num_tokens": 37277992.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 6.260839462280273,
|
|
"epoch": 1.6987882285054818,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004721093354109839,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.1694336861371994,
|
|
"num_tokens": 37291608.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 6.2488401412963865,
|
|
"epoch": 1.6993652625504905,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047208943295111406,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.16663674563169478,
|
|
"num_tokens": 37303619.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 6.286404466629028,
|
|
"epoch": 1.6999422965954991,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047206952386223905,
|
|
"loss": 6.1235,
|
|
"mean_token_accuracy": 0.1630891889333725,
|
|
"num_tokens": 37316215.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 6.264311647415161,
|
|
"epoch": 1.7005193306405078,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004720496081450285,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.17511145025491714,
|
|
"num_tokens": 37328643.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 6.204177665710449,
|
|
"epoch": 1.7010963646855164,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047202968580015224,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.17457183748483657,
|
|
"num_tokens": 37340792.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 6.296930885314941,
|
|
"epoch": 1.701673398730525,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047200975682828045,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.16684187352657318,
|
|
"num_tokens": 37353866.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 6.251866245269776,
|
|
"epoch": 1.702250432775534,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004719898212300832,
|
|
"loss": 6.0468,
|
|
"mean_token_accuracy": 0.16618564426898957,
|
|
"num_tokens": 37365403.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 6.303374767303467,
|
|
"epoch": 1.7028274668205423,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047196987900623134,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.16828102320432664,
|
|
"num_tokens": 37379487.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 6.296183347702026,
|
|
"epoch": 1.7034045008655512,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00047194993015739527,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.16699840426445006,
|
|
"num_tokens": 37392497.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 6.2065503120422365,
|
|
"epoch": 1.7039815349105596,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047192997468424624,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.16989068686962128,
|
|
"num_tokens": 37407126.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 6.148230314254761,
|
|
"epoch": 1.7045585689555685,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004719100125874553,
|
|
"loss": 6.0219,
|
|
"mean_token_accuracy": 0.17883527129888535,
|
|
"num_tokens": 37419768.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 6.247872018814087,
|
|
"epoch": 1.7051356030005769,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004718900438676939,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.1680767372250557,
|
|
"num_tokens": 37432512.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 6.35809907913208,
|
|
"epoch": 1.7057126370455857,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004718700685256337,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.1664692386984825,
|
|
"num_tokens": 37445006.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 6.297749042510986,
|
|
"epoch": 1.7062896710905944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004718500865619465,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.16584955304861068,
|
|
"num_tokens": 37457386.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 6.260836982727051,
|
|
"epoch": 1.706866705135603,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004718300979773044,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.1740827426314354,
|
|
"num_tokens": 37469773.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 6.3344052791595455,
|
|
"epoch": 1.7074437391806117,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047181010277237977,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.1703534796833992,
|
|
"num_tokens": 37483301.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 6.317808389663696,
|
|
"epoch": 1.7080207732256203,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004717901009478451,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1657814547419548,
|
|
"num_tokens": 37495110.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 6.229995775222778,
|
|
"epoch": 1.708597807270629,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047177009250437313,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.17732647508382798,
|
|
"num_tokens": 37509281.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 6.24862265586853,
|
|
"epoch": 1.7091748413156376,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047175007744263683,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.1722698614001274,
|
|
"num_tokens": 37522690.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 6.26502947807312,
|
|
"epoch": 1.7097518753606464,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047173005576330935,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.1729898691177368,
|
|
"num_tokens": 37534737.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 6.346290874481201,
|
|
"epoch": 1.7103289094056549,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047171002746706424,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.16451414823532104,
|
|
"num_tokens": 37547486.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 6.410305833816528,
|
|
"epoch": 1.7109059434506637,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047168999255457506,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.16630878448486328,
|
|
"num_tokens": 37560083.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 6.255903625488282,
|
|
"epoch": 1.7114829774956721,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047166995102651565,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.17067583948373793,
|
|
"num_tokens": 37573260.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 6.331271076202393,
|
|
"epoch": 1.712060011540681,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004716499028835601,
|
|
"loss": 6.1287,
|
|
"mean_token_accuracy": 0.16774001866579055,
|
|
"num_tokens": 37586403.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 6.257412528991699,
|
|
"epoch": 1.7126370455856894,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004716298481263828,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.17623667418956757,
|
|
"num_tokens": 37600771.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 6.320488119125367,
|
|
"epoch": 1.7132140796306983,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004716097867556583,
|
|
"loss": 6.0556,
|
|
"mean_token_accuracy": 0.16797322779893875,
|
|
"num_tokens": 37613623.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 6.303245306015015,
|
|
"epoch": 1.713791113675707,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047158971877206114,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.17387645542621613,
|
|
"num_tokens": 37624539.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 6.279318332672119,
|
|
"epoch": 1.7143681477207156,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004715696441762665,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.16603559702634813,
|
|
"num_tokens": 37636556.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 6.298802757263184,
|
|
"epoch": 1.7149451817657242,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047154956296894954,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.168888820707798,
|
|
"num_tokens": 37648369.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 6.315916061401367,
|
|
"epoch": 1.7155222158107328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004715294751507856,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.1606738820672035,
|
|
"num_tokens": 37661118.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 6.247011470794678,
|
|
"epoch": 1.7160992498557415,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004715093807224505,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.16982904225587844,
|
|
"num_tokens": 37673915.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 6.208894538879394,
|
|
"epoch": 1.71667628390075,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047148927968462,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.1695188343524933,
|
|
"num_tokens": 37687359.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 6.257250356674194,
|
|
"epoch": 1.7172533179457588,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047146917203797,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.16386288702487944,
|
|
"num_tokens": 37700111.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 6.407634592056274,
|
|
"epoch": 1.7178303519907674,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004714490577831771,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.1564957782626152,
|
|
"num_tokens": 37712707.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 6.378075122833252,
|
|
"epoch": 1.7184073860357763,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004714289369209177,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.1596768781542778,
|
|
"num_tokens": 37724242.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 6.327669858932495,
|
|
"epoch": 1.7189844200807847,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047140880945186863,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.16967980414628983,
|
|
"num_tokens": 37737451.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 6.327920198440552,
|
|
"epoch": 1.7195614541257935,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047138867537670676,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.16197078824043273,
|
|
"num_tokens": 37749968.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 6.268460416793824,
|
|
"epoch": 1.720138488170802,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047136853469610933,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.17554560899734498,
|
|
"num_tokens": 37761961.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 6.233225727081299,
|
|
"epoch": 1.7207155222158108,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047134838741075383,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.17252259254455565,
|
|
"num_tokens": 37775089.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 6.273133707046509,
|
|
"epoch": 1.7212925562608192,
|
|
"grad_norm": 3.875,
|
|
"learning_rate": 0.00047132823352131787,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.1664955273270607,
|
|
"num_tokens": 37787072.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 6.251991224288941,
|
|
"epoch": 1.721869590305828,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004713080730284793,
|
|
"loss": 6.0785,
|
|
"mean_token_accuracy": 0.1657878965139389,
|
|
"num_tokens": 37799162.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 6.262150382995605,
|
|
"epoch": 1.7224466243508367,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047128790593291617,
|
|
"loss": 6.079,
|
|
"mean_token_accuracy": 0.17039323300123216,
|
|
"num_tokens": 37811560.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 6.338023710250854,
|
|
"epoch": 1.7230236583958454,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047126773223530677,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.1752539336681366,
|
|
"num_tokens": 37823832.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 6.280074548721314,
|
|
"epoch": 1.723600692440854,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047124755193632975,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.1672136142849922,
|
|
"num_tokens": 37836718.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 6.227765607833862,
|
|
"epoch": 1.7241777264858626,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047122736503666377,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.16516398787498474,
|
|
"num_tokens": 37850001.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 6.167520570755005,
|
|
"epoch": 1.7247547605308713,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004712071715369878,
|
|
"loss": 5.9453,
|
|
"mean_token_accuracy": 0.1785365030169487,
|
|
"num_tokens": 37862425.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 6.249232196807862,
|
|
"epoch": 1.72533179457588,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004711869714379812,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.17359684109687806,
|
|
"num_tokens": 37874429.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 6.233495426177979,
|
|
"epoch": 1.7259088286208888,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004711667647403232,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.17523322850465775,
|
|
"num_tokens": 37888317.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 6.216939306259155,
|
|
"epoch": 1.7264858626658972,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047114655144469354,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.17252569198608397,
|
|
"num_tokens": 37901101.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 6.268746280670166,
|
|
"epoch": 1.727062896710906,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047112633155177203,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.16735256612300872,
|
|
"num_tokens": 37914013.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 6.229385900497436,
|
|
"epoch": 1.7276399307559145,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004711061050622388,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.17679166793823242,
|
|
"num_tokens": 37926799.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 6.24853138923645,
|
|
"epoch": 1.7282169648009233,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047108587197677404,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.17115989178419114,
|
|
"num_tokens": 37939173.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 6.348738718032837,
|
|
"epoch": 1.7287939988459318,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047106563229605845,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.16205629259347915,
|
|
"num_tokens": 37951030.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 6.321481847763062,
|
|
"epoch": 1.7293710328909406,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047104538602077276,
|
|
"loss": 6.1005,
|
|
"mean_token_accuracy": 0.16491590738296508,
|
|
"num_tokens": 37964005.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 6.220985364913941,
|
|
"epoch": 1.7299480669359493,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004710251331515978,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.170199716091156,
|
|
"num_tokens": 37975851.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 6.298024463653564,
|
|
"epoch": 1.730525100980958,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047100487368921485,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.16759447902441024,
|
|
"num_tokens": 37988008.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 6.294814109802246,
|
|
"epoch": 1.7311021350259665,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004709846076343055,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.16583738923072816,
|
|
"num_tokens": 38000915.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.7311021350259665,
|
|
"eval_entropy": 6.123954276588447,
|
|
"eval_loss": 6.1699981689453125,
|
|
"eval_mean_token_accuracy": 0.16904069022094115,
|
|
"eval_num_tokens": 38000915.0,
|
|
"eval_runtime": 22.6623,
|
|
"eval_samples_per_second": 1241.532,
|
|
"eval_steps_per_second": 155.191,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 6.24792218208313,
|
|
"epoch": 1.7316791690709752,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047096433498755103,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.17191755622625352,
|
|
"num_tokens": 38013109.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 6.256828117370605,
|
|
"epoch": 1.7322562031159838,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047094405574963364,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.17066695243120195,
|
|
"num_tokens": 38025969.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 6.28236403465271,
|
|
"epoch": 1.7328332371609925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047092376992123516,
|
|
"loss": 6.048,
|
|
"mean_token_accuracy": 0.16960776448249817,
|
|
"num_tokens": 38039104.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 6.308421182632446,
|
|
"epoch": 1.733410271206001,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047090347750303803,
|
|
"loss": 6.1151,
|
|
"mean_token_accuracy": 0.17100338786840438,
|
|
"num_tokens": 38053453.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 6.361363124847412,
|
|
"epoch": 1.7339873052510097,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004708831784957247,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.15991011261940002,
|
|
"num_tokens": 38064932.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 6.315028858184815,
|
|
"epoch": 1.7345643392960186,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004708628728999781,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.1607021138072014,
|
|
"num_tokens": 38078904.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 6.308137226104736,
|
|
"epoch": 1.735141373341027,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004708425607164809,
|
|
"loss": 6.1239,
|
|
"mean_token_accuracy": 0.16347237974405288,
|
|
"num_tokens": 38092605.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 6.280299425125122,
|
|
"epoch": 1.7357184073860359,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004708222419459165,
|
|
"loss": 6.0219,
|
|
"mean_token_accuracy": 0.1774211421608925,
|
|
"num_tokens": 38105953.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 6.285515403747558,
|
|
"epoch": 1.7362954414310443,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004708019165889683,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.16232980489730836,
|
|
"num_tokens": 38118485.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 6.34949746131897,
|
|
"epoch": 1.7368724754760532,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004707815846463199,
|
|
"loss": 6.1597,
|
|
"mean_token_accuracy": 0.16315972208976745,
|
|
"num_tokens": 38131220.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 6.239033269882202,
|
|
"epoch": 1.7374495095210616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004707612461186552,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.17054777294397355,
|
|
"num_tokens": 38143012.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 6.256315422058106,
|
|
"epoch": 1.7380265435660704,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.00047074090100665805,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.17277972102165223,
|
|
"num_tokens": 38155810.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 6.285384273529052,
|
|
"epoch": 1.738603577611079,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047072054931101306,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.16316191703081132,
|
|
"num_tokens": 38169183.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 6.235709571838379,
|
|
"epoch": 1.7391806116560877,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004707001910324046,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.1654953509569168,
|
|
"num_tokens": 38182098.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 6.342658376693725,
|
|
"epoch": 1.7397576457010964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047067982617151737,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.16227303296327591,
|
|
"num_tokens": 38194950.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 6.27519679069519,
|
|
"epoch": 1.740334679746105,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004706594547290365,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.17537856101989746,
|
|
"num_tokens": 38207600.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 6.234506750106812,
|
|
"epoch": 1.7409117137911136,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047063907670564695,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.18101305812597274,
|
|
"num_tokens": 38219489.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 6.29203085899353,
|
|
"epoch": 1.7414887478361223,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004706186921020342,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.16346038281917571,
|
|
"num_tokens": 38233240.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 6.314747762680054,
|
|
"epoch": 1.7420657818811311,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047059830091888407,
|
|
"loss": 6.059,
|
|
"mean_token_accuracy": 0.16740975230932237,
|
|
"num_tokens": 38245967.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 6.268871784210205,
|
|
"epoch": 1.7426428159261396,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004705779031568821,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.16653717309236526,
|
|
"num_tokens": 38258586.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 6.25105881690979,
|
|
"epoch": 1.7432198499711484,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047055749881671463,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.17233491986989974,
|
|
"num_tokens": 38270007.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 6.320896196365356,
|
|
"epoch": 1.7437968840161568,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004705370878990677,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.17320594638586045,
|
|
"num_tokens": 38282580.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 6.226344156265259,
|
|
"epoch": 1.7443739180611657,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047051667040462806,
|
|
"loss": 6.0185,
|
|
"mean_token_accuracy": 0.16522823870182038,
|
|
"num_tokens": 38295577.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 6.269693994522095,
|
|
"epoch": 1.7449509521061741,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047049624633408224,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.16538017094135285,
|
|
"num_tokens": 38307924.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 6.359875202178955,
|
|
"epoch": 1.745527986151183,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047047581568811724,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.16466730535030366,
|
|
"num_tokens": 38321573.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 6.304333209991455,
|
|
"epoch": 1.7461050201961916,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047045537846742043,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.17050682455301286,
|
|
"num_tokens": 38333953.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 6.261137628555298,
|
|
"epoch": 1.7466820542412003,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000470434934672679,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.16425079554319383,
|
|
"num_tokens": 38346028.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 6.317224311828613,
|
|
"epoch": 1.747259088286209,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047041448430458054,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.17166270464658737,
|
|
"num_tokens": 38358806.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 6.222446775436401,
|
|
"epoch": 1.7478361223312175,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047039402736381305,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.1746882528066635,
|
|
"num_tokens": 38370396.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 6.24567985534668,
|
|
"epoch": 1.7484131563762262,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004703735638510645,
|
|
"loss": 6.172,
|
|
"mean_token_accuracy": 0.16677465289831161,
|
|
"num_tokens": 38383747.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 6.333199834823608,
|
|
"epoch": 1.7489901904212348,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004703530937670232,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.1690805047750473,
|
|
"num_tokens": 38396611.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 6.281210470199585,
|
|
"epoch": 1.7495672244662435,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004703326171123776,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.16737785041332245,
|
|
"num_tokens": 38407627.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 6.160182142257691,
|
|
"epoch": 1.750144258511252,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004703121338878164,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.17774373441934585,
|
|
"num_tokens": 38420522.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 6.282178735733032,
|
|
"epoch": 1.750721292556261,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004702916440940286,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.16249785125255584,
|
|
"num_tokens": 38433968.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 6.312160015106201,
|
|
"epoch": 1.7512983266012694,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004702711477317034,
|
|
"loss": 6.0757,
|
|
"mean_token_accuracy": 0.17204999625682832,
|
|
"num_tokens": 38445819.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 6.340288782119751,
|
|
"epoch": 1.7518753606462782,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004702506448015301,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.16886577010154724,
|
|
"num_tokens": 38458823.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 6.2418297290802,
|
|
"epoch": 1.7524523946912867,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047023013530419843,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.16895245462656022,
|
|
"num_tokens": 38472553.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 6.294234561920166,
|
|
"epoch": 1.7530294287362955,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004702096192403981,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1733073890209198,
|
|
"num_tokens": 38484143.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 6.221842432022095,
|
|
"epoch": 1.753606462781304,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004701890966108192,
|
|
"loss": 6.0565,
|
|
"mean_token_accuracy": 0.16363780051469803,
|
|
"num_tokens": 38496795.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 6.2286309719085695,
|
|
"epoch": 1.7541834968263128,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000470168567416152,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.17548104077577592,
|
|
"num_tokens": 38509548.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 6.299403381347656,
|
|
"epoch": 1.7547605308713214,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004701480316570869,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.16311995685100555,
|
|
"num_tokens": 38524011.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 6.3120521068572994,
|
|
"epoch": 1.75533756491633,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004701274893343147,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.1634999006986618,
|
|
"num_tokens": 38536913.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 6.233125972747803,
|
|
"epoch": 1.7559145989613387,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047010694044852643,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.17134792655706405,
|
|
"num_tokens": 38548759.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 6.314376878738403,
|
|
"epoch": 1.7564916330063474,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000470086385000413,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.17076184898614882,
|
|
"num_tokens": 38562071.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 6.2503444194793705,
|
|
"epoch": 1.757068667051356,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004700658229906661,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1687441125512123,
|
|
"num_tokens": 38573816.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 6.396673727035522,
|
|
"epoch": 1.7576457010963646,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.00047004525441997694,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.16280039995908738,
|
|
"num_tokens": 38586625.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 6.261827564239502,
|
|
"epoch": 1.7582227351413735,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004700246792890376,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.17354324609041213,
|
|
"num_tokens": 38599391.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 6.203934097290039,
|
|
"epoch": 1.758799769186382,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004700040975985401,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.1821871742606163,
|
|
"num_tokens": 38610822.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 6.23805685043335,
|
|
"epoch": 1.7593768032313908,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046998350934917654,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1770789697766304,
|
|
"num_tokens": 38623886.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 6.236564683914184,
|
|
"epoch": 1.7599538372763992,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046996291454163956,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.17420328557491302,
|
|
"num_tokens": 38636680.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 6.2587113857269285,
|
|
"epoch": 1.760530871321408,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004699423131766218,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.17095499336719513,
|
|
"num_tokens": 38648841.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 6.211136674880981,
|
|
"epoch": 1.7611079053664165,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004699217052548161,
|
|
"loss": 6.0056,
|
|
"mean_token_accuracy": 0.17292061299085618,
|
|
"num_tokens": 38660603.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 6.264367008209229,
|
|
"epoch": 1.7616849394114253,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046990109077691577,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.17040781825780868,
|
|
"num_tokens": 38674082.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 6.251727819442749,
|
|
"epoch": 1.762261973456434,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046988046974361406,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.17488901168107987,
|
|
"num_tokens": 38686274.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 6.312477970123291,
|
|
"epoch": 1.7628390075014426,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004698598421556045,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.17141490131616594,
|
|
"num_tokens": 38699260.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 6.240328598022461,
|
|
"epoch": 1.7634160415464513,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004698392080135809,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.17000517696142198,
|
|
"num_tokens": 38712054.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 6.236440801620484,
|
|
"epoch": 1.76399307559146,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004698185673182374,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.1765800029039383,
|
|
"num_tokens": 38724634.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 6.25202693939209,
|
|
"epoch": 1.7645701096364685,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046979792007026817,
|
|
"loss": 5.9628,
|
|
"mean_token_accuracy": 0.17394617944955826,
|
|
"num_tokens": 38737294.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 6.330475282669068,
|
|
"epoch": 1.7651471436814772,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004697772662703676,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.15854198187589646,
|
|
"num_tokens": 38749578.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 6.262237167358398,
|
|
"epoch": 1.7657241777264858,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046975660591923047,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.15982145816087723,
|
|
"num_tokens": 38762282.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 6.3007566928863525,
|
|
"epoch": 1.7663012117714945,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004697359390175516,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.17306247353553772,
|
|
"num_tokens": 38773861.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 6.301147747039795,
|
|
"epoch": 1.7668782458165033,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046971526556602625,
|
|
"loss": 6.1427,
|
|
"mean_token_accuracy": 0.16681707203388213,
|
|
"num_tokens": 38786427.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 6.30169415473938,
|
|
"epoch": 1.7674552798615117,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004696945855653495,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.16261772960424423,
|
|
"num_tokens": 38798496.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 6.261436891555786,
|
|
"epoch": 1.7680323139065206,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004696738990162172,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.16127245575189592,
|
|
"num_tokens": 38812069.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 6.29582257270813,
|
|
"epoch": 1.768609347951529,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000469653205919325,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.1679990828037262,
|
|
"num_tokens": 38824465.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 6.353593111038208,
|
|
"epoch": 1.7691863819965379,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046963250627536884,
|
|
"loss": 6.1229,
|
|
"mean_token_accuracy": 0.16071866005659102,
|
|
"num_tokens": 38837328.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 6.258993768692017,
|
|
"epoch": 1.7697634160415463,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004696118000850451,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.16911157071590424,
|
|
"num_tokens": 38849238.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 6.222685432434082,
|
|
"epoch": 1.7703404500865552,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046959108734905003,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1641075626015663,
|
|
"num_tokens": 38861479.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 6.246473884582519,
|
|
"epoch": 1.7709174841315638,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046957036806808045,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.1772461786866188,
|
|
"num_tokens": 38874342.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 6.231625413894653,
|
|
"epoch": 1.7714945181765724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004695496422428332,
|
|
"loss": 6.0482,
|
|
"mean_token_accuracy": 0.1703166276216507,
|
|
"num_tokens": 38886595.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 6.297798919677734,
|
|
"epoch": 1.772071552221581,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695289098740054,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.16702995151281358,
|
|
"num_tokens": 38899338.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 6.289673328399658,
|
|
"epoch": 1.7726485862665897,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004695081709622943,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.17137792557477952,
|
|
"num_tokens": 38911765.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 6.209077072143555,
|
|
"epoch": 1.7732256203115984,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046948742550839744,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.1811099350452423,
|
|
"num_tokens": 38924137.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 6.293831920623779,
|
|
"epoch": 1.773802654356607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004694666735130127,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.16767871677875518,
|
|
"num_tokens": 38936401.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 6.273082637786866,
|
|
"epoch": 1.7743796884016156,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000469445914976838,
|
|
"loss": 6.0749,
|
|
"mean_token_accuracy": 0.16592430025339128,
|
|
"num_tokens": 38948224.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 6.273223733901977,
|
|
"epoch": 1.7749567224466243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004694251499005715,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.17387449145317077,
|
|
"num_tokens": 38959924.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 6.215410614013672,
|
|
"epoch": 1.7755337564916331,
|
|
"grad_norm": 3.65625,
|
|
"learning_rate": 0.0004694043782849116,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.1672881633043289,
|
|
"num_tokens": 38973018.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 6.2906115531921385,
|
|
"epoch": 1.7761107905366416,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046938360013055715,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.16135561764240264,
|
|
"num_tokens": 38985634.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 6.3686277866363525,
|
|
"epoch": 1.7766878245816504,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046936281543820673,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.1644715130329132,
|
|
"num_tokens": 38999446.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 6.323219871520996,
|
|
"epoch": 1.7772648586266588,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046934202420855967,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.17120789289474486,
|
|
"num_tokens": 39012974.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 6.157790231704712,
|
|
"epoch": 1.7778418926716677,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046932122644231507,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.17291020452976227,
|
|
"num_tokens": 39025316.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 6.209767818450928,
|
|
"epoch": 1.7784189267166761,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046930042214017256,
|
|
"loss": 5.969,
|
|
"mean_token_accuracy": 0.1822973057627678,
|
|
"num_tokens": 39038174.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 6.363025379180908,
|
|
"epoch": 1.778995960761685,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004692796113028319,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.15527651011943816,
|
|
"num_tokens": 39051943.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 6.228987741470337,
|
|
"epoch": 1.7795729948066936,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000469258793930993,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.16570292711257933,
|
|
"num_tokens": 39064765.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 6.302031183242798,
|
|
"epoch": 1.7801500288517023,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046923797002535605,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.16474866718053818,
|
|
"num_tokens": 39077326.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 6.303848218917847,
|
|
"epoch": 1.780727062896711,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004692171395866214,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.17039090692996978,
|
|
"num_tokens": 39090049.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 6.22796106338501,
|
|
"epoch": 1.7813040969417195,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046919630261548986,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.17326881736516953,
|
|
"num_tokens": 39102805.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 6.148467016220093,
|
|
"epoch": 1.7818811309867282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046917545911266207,
|
|
"loss": 5.9339,
|
|
"mean_token_accuracy": 0.18568576574325563,
|
|
"num_tokens": 39115966.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 6.2328081130981445,
|
|
"epoch": 1.7824581650317368,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046915460907883923,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.16815552562475206,
|
|
"num_tokens": 39128417.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 6.260302972793579,
|
|
"epoch": 1.7830351990767457,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046913375251472246,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.17435874044895172,
|
|
"num_tokens": 39142338.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 6.25403733253479,
|
|
"epoch": 1.783612233121754,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.00046911288942101345,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.17178328335285187,
|
|
"num_tokens": 39155055.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 6.327509355545044,
|
|
"epoch": 1.784189267166763,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004690920197984138,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.16623275429010392,
|
|
"num_tokens": 39167170.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 6.431978321075439,
|
|
"epoch": 1.7847663012117714,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004690711436476254,
|
|
"loss": 6.1754,
|
|
"mean_token_accuracy": 0.1634928062558174,
|
|
"num_tokens": 39181389.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 6.399842214584351,
|
|
"epoch": 1.7853433352567802,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046905026096935056,
|
|
"loss": 6.1594,
|
|
"mean_token_accuracy": 0.16029439866542816,
|
|
"num_tokens": 39194728.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 6.165746212005615,
|
|
"epoch": 1.7859203693017887,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004690293717642916,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.1781982809305191,
|
|
"num_tokens": 39207945.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 6.262561368942261,
|
|
"epoch": 1.7864974033467975,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000469008476033151,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.1702757239341736,
|
|
"num_tokens": 39221314.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 6.340551853179932,
|
|
"epoch": 1.7870744373918062,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046898757377663176,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.16916078925132752,
|
|
"num_tokens": 39233910.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 6.28997769355774,
|
|
"epoch": 1.7876514714368148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046896666499543683,
|
|
"loss": 6.0606,
|
|
"mean_token_accuracy": 0.17222110480070113,
|
|
"num_tokens": 39246027.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 6.221077728271484,
|
|
"epoch": 1.7882285054818234,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046894574969026946,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.16958654075860977,
|
|
"num_tokens": 39258456.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 6.365782451629639,
|
|
"epoch": 1.788805539526832,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046892482786183313,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.16027437299489974,
|
|
"num_tokens": 39270624.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 6.262175798416138,
|
|
"epoch": 1.7893825735718407,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046890389951083155,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.16951557099819184,
|
|
"num_tokens": 39283350.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 6.29289026260376,
|
|
"epoch": 1.7899596076168494,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046888296463796857,
|
|
"loss": 6.0783,
|
|
"mean_token_accuracy": 0.17297891080379485,
|
|
"num_tokens": 39296321.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 6.256748819351197,
|
|
"epoch": 1.790536641661858,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004688620232439485,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.1770552009344101,
|
|
"num_tokens": 39309223.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 6.167249011993408,
|
|
"epoch": 1.7911136757068666,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046884107532947547,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.1709598571062088,
|
|
"num_tokens": 39322348.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 6.285998582839966,
|
|
"epoch": 1.7916907097518755,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046882012089525415,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.1638656571507454,
|
|
"num_tokens": 39335375.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 6.330535793304444,
|
|
"epoch": 1.792267743796884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004687991599419895,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.16950902789831163,
|
|
"num_tokens": 39347865.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 6.270843029022217,
|
|
"epoch": 1.7928447778418928,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046877819247038624,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.1685513213276863,
|
|
"num_tokens": 39361402.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 6.257634687423706,
|
|
"epoch": 1.7934218118869012,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004687572184811497,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.17115099728107452,
|
|
"num_tokens": 39372839.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 6.258444881439209,
|
|
"epoch": 1.79399884593191,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046873623797498545,
|
|
"loss": 5.9962,
|
|
"mean_token_accuracy": 0.16875378042459488,
|
|
"num_tokens": 39385189.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 6.356871175765991,
|
|
"epoch": 1.7945758799769185,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.000468715250952599,
|
|
"loss": 6.1782,
|
|
"mean_token_accuracy": 0.16155981868505478,
|
|
"num_tokens": 39397871.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 6.331059503555298,
|
|
"epoch": 1.7951529140219273,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046869425741469635,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.16324354857206344,
|
|
"num_tokens": 39411222.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 6.283884048461914,
|
|
"epoch": 1.795729948066936,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004686732573619835,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.1666042074561119,
|
|
"num_tokens": 39423614.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 6.3039412021636965,
|
|
"epoch": 1.7963069821119446,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004686522507951669,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.16653052419424058,
|
|
"num_tokens": 39436299.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 6.258326625823974,
|
|
"epoch": 1.7968840161569533,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004686312377149531,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.15843801349401473,
|
|
"num_tokens": 39448994.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 6.3444324970245365,
|
|
"epoch": 1.797461050201962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046861021812204874,
|
|
"loss": 6.1192,
|
|
"mean_token_accuracy": 0.1605915457010269,
|
|
"num_tokens": 39462387.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 6.342525243759155,
|
|
"epoch": 1.7980380842469705,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046858919201716085,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.1640731140971184,
|
|
"num_tokens": 39475082.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 6.29853310585022,
|
|
"epoch": 1.7986151182919792,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004685681594009966,
|
|
"loss": 6.0898,
|
|
"mean_token_accuracy": 0.16256304532289506,
|
|
"num_tokens": 39487272.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 6.239833211898803,
|
|
"epoch": 1.799192152336988,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046854712027426357,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.16334139704704284,
|
|
"num_tokens": 39502499.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 6.328673505783081,
|
|
"epoch": 1.7997691863819965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046852607463766923,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.16911648958921432,
|
|
"num_tokens": 39514652.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 6.401641321182251,
|
|
"epoch": 1.8003462204270053,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004685050224919215,
|
|
"loss": 6.1618,
|
|
"mean_token_accuracy": 0.1580326199531555,
|
|
"num_tokens": 39527859.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 6.261534261703491,
|
|
"epoch": 1.8009232544720137,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046848396383772844,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.1679571434855461,
|
|
"num_tokens": 39541099.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 6.204374647140503,
|
|
"epoch": 1.8015002885170226,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004684628986757984,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1721584215760231,
|
|
"num_tokens": 39553233.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 6.285806322097779,
|
|
"epoch": 1.802077322562031,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004684418270068398,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.16974806785583496,
|
|
"num_tokens": 39565379.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 6.238617944717407,
|
|
"epoch": 1.8026543566070399,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004684207488315615,
|
|
"loss": 5.975,
|
|
"mean_token_accuracy": 0.17460445761680604,
|
|
"num_tokens": 39577509.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 6.322760725021363,
|
|
"epoch": 1.8032313906520485,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004683996641506724,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.1633619874715805,
|
|
"num_tokens": 39589960.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 6.227279090881348,
|
|
"epoch": 1.8038084246970572,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046837857296488163,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.17601959705352782,
|
|
"num_tokens": 39602231.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 6.260754919052124,
|
|
"epoch": 1.8043854587420658,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046835747527489857,
|
|
"loss": 6.0532,
|
|
"mean_token_accuracy": 0.1809969499707222,
|
|
"num_tokens": 39615756.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 6.310202407836914,
|
|
"epoch": 1.8049624927870744,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000468336371081433,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.1634535536170006,
|
|
"num_tokens": 39627810.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 6.2715802669525145,
|
|
"epoch": 1.805539526832083,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046831526038519444,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.16980360597372054,
|
|
"num_tokens": 39640930.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 6.269176197052002,
|
|
"epoch": 1.8061165608770917,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004682941431868933,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.1734122857451439,
|
|
"num_tokens": 39652146.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 6.161038208007812,
|
|
"epoch": 1.8066935949221004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046827301948723963,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.17960268557071685,
|
|
"num_tokens": 39665156.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 6.255029582977295,
|
|
"epoch": 1.807270628967109,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046825188928694393,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.16673412621021272,
|
|
"num_tokens": 39677346.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 6.312059164047241,
|
|
"epoch": 1.8078476630121179,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004682307525867169,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.1778455853462219,
|
|
"num_tokens": 39690613.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 6.335729742050171,
|
|
"epoch": 1.8084246970571263,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004682096093872695,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.17328280210494995,
|
|
"num_tokens": 39703111.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 6.2205384254455565,
|
|
"epoch": 1.8090017311021351,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046818845968931284,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.1691240191459656,
|
|
"num_tokens": 39715441.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 6.262801313400269,
|
|
"epoch": 1.8095787651471436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046816730349355843,
|
|
"loss": 6.0161,
|
|
"mean_token_accuracy": 0.17307625114917755,
|
|
"num_tokens": 39728437.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 6.241965198516846,
|
|
"epoch": 1.8101557991921524,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046814614080071756,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.17203230857849122,
|
|
"num_tokens": 39740324.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 6.294243240356446,
|
|
"epoch": 1.8107328332371608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046812497161150224,
|
|
"loss": 6.0171,
|
|
"mean_token_accuracy": 0.16689405590295792,
|
|
"num_tokens": 39752158.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 6.28272008895874,
|
|
"epoch": 1.8113098672821697,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046810379592662445,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.17248584032058717,
|
|
"num_tokens": 39766296.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 6.234416913986206,
|
|
"epoch": 1.8118869013271783,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046808261374679637,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.17033150643110276,
|
|
"num_tokens": 39779690.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 6.25835657119751,
|
|
"epoch": 1.812463935372187,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004680614250727305,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.1731962352991104,
|
|
"num_tokens": 39790617.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 6.252574872970581,
|
|
"epoch": 1.8130409694171956,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004680402299051395,
|
|
"loss": 6.036,
|
|
"mean_token_accuracy": 0.1660449355840683,
|
|
"num_tokens": 39802994.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 6.25236554145813,
|
|
"epoch": 1.8136180034622043,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004680190282447363,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.169236396253109,
|
|
"num_tokens": 39815618.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 6.24625039100647,
|
|
"epoch": 1.814195037507213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004679978200922339,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.1698412522673607,
|
|
"num_tokens": 39827283.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 6.2522207736969,
|
|
"epoch": 1.8147720715522215,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004679766054483457,
|
|
"loss": 5.9816,
|
|
"mean_token_accuracy": 0.17221676111221312,
|
|
"num_tokens": 39840116.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 6.15627088546753,
|
|
"epoch": 1.8153491055972304,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004679553843137852,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.18153376132249832,
|
|
"num_tokens": 39851770.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 6.156879806518555,
|
|
"epoch": 1.8159261396422388,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046793415668926625,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.17151160389184952,
|
|
"num_tokens": 39863803.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 6.248953819274902,
|
|
"epoch": 1.8165031736872477,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004679129225755028,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.17617322951555253,
|
|
"num_tokens": 39875713.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 6.18450894355774,
|
|
"epoch": 1.817080207732256,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000467891681973209,
|
|
"loss": 5.9588,
|
|
"mean_token_accuracy": 0.17611952871084213,
|
|
"num_tokens": 39888670.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 6.142603588104248,
|
|
"epoch": 1.817657241777265,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00046787043488309926,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.18451358526945114,
|
|
"num_tokens": 39900845.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 6.346268844604492,
|
|
"epoch": 1.8182342758222734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004678491813058882,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.1648651421070099,
|
|
"num_tokens": 39912268.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 6.277725410461426,
|
|
"epoch": 1.8188113098672822,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004678279212422908,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.1688872143626213,
|
|
"num_tokens": 39924213.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 6.276968383789063,
|
|
"epoch": 1.8193883439122909,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004678066546930221,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1626095324754715,
|
|
"num_tokens": 39937069.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 6.237314939498901,
|
|
"epoch": 1.8199653779572995,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046778538165879725,
|
|
"loss": 6.0041,
|
|
"mean_token_accuracy": 0.16766275614500045,
|
|
"num_tokens": 39948988.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 6.2724080085754395,
|
|
"epoch": 1.8205424120023082,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046776410214033185,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.16913768351078035,
|
|
"num_tokens": 39962177.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 6.317848825454712,
|
|
"epoch": 1.8211194460473168,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004677428161383417,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.16904523521661757,
|
|
"num_tokens": 39975329.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 6.264898729324341,
|
|
"epoch": 1.8216964800923254,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004677215236535426,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.16779443323612214,
|
|
"num_tokens": 39987923.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 6.34999647140503,
|
|
"epoch": 1.822273514137334,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004677002246866508,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.16695744693279266,
|
|
"num_tokens": 40001596.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 6.289482831954956,
|
|
"epoch": 1.8228505481823427,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046767891923838264,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.1737503945827484,
|
|
"num_tokens": 40014207.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 6.369691467285156,
|
|
"epoch": 1.8234275822273514,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004676576073094548,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.16101481169462203,
|
|
"num_tokens": 40027931.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 6.339088201522827,
|
|
"epoch": 1.8240046162723602,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046763628890058396,
|
|
"loss": 6.0971,
|
|
"mean_token_accuracy": 0.16571219712495805,
|
|
"num_tokens": 40040463.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 6.221599912643432,
|
|
"epoch": 1.8245816503173686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046761496401248734,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.17340231388807298,
|
|
"num_tokens": 40053085.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 6.316984224319458,
|
|
"epoch": 1.8251586843623775,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000467593632645882,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.1690345823764801,
|
|
"num_tokens": 40065771.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 6.296414136886597,
|
|
"epoch": 1.825735718407386,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004675722948014855,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.17363547384738923,
|
|
"num_tokens": 40078939.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 6.23414626121521,
|
|
"epoch": 1.8263127524523948,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046755095048001556,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.17467279732227325,
|
|
"num_tokens": 40091565.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 6.167823934555054,
|
|
"epoch": 1.8268897864974032,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004675295996821899,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.16983738988637925,
|
|
"num_tokens": 40103619.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 6.311656141281128,
|
|
"epoch": 1.827466820542412,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000467508242408727,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.1673286721110344,
|
|
"num_tokens": 40116370.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 6.304900693893432,
|
|
"epoch": 1.8280438545874207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004674868786603448,
|
|
"loss": 5.9791,
|
|
"mean_token_accuracy": 0.1691321074962616,
|
|
"num_tokens": 40129015.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 6.241245222091675,
|
|
"epoch": 1.8286208886324293,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004674655084377622,
|
|
"loss": 5.9891,
|
|
"mean_token_accuracy": 0.1670050650835037,
|
|
"num_tokens": 40141437.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 6.212176847457886,
|
|
"epoch": 1.829197922677438,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004674441317416978,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.16276399046182632,
|
|
"num_tokens": 40154516.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 6.238998651504517,
|
|
"epoch": 1.8297749567224466,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046742274857287057,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.1708405777812004,
|
|
"num_tokens": 40166598.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 6.257824850082398,
|
|
"epoch": 1.8303519907674553,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004674013589319998,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.1640569418668747,
|
|
"num_tokens": 40178905.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 6.317538118362426,
|
|
"epoch": 1.830929024812464,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004673799628198049,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.16486846506595612,
|
|
"num_tokens": 40191678.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 6.285384607315064,
|
|
"epoch": 1.8315060588574728,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046735856023700546,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.16484537124633789,
|
|
"num_tokens": 40204680.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 6.233611536026001,
|
|
"epoch": 1.8320830929024812,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004673371511843215,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.17095134109258653,
|
|
"num_tokens": 40217026.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 6.258399248123169,
|
|
"epoch": 1.83266012694749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004673157356624729,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.1706467315554619,
|
|
"num_tokens": 40228950.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 6.287282991409302,
|
|
"epoch": 1.8332371609924984,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004672943136721801,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.16891248077154158,
|
|
"num_tokens": 40241294.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 6.341698074340821,
|
|
"epoch": 1.8338141950375073,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004672728852141636,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.16762983351945876,
|
|
"num_tokens": 40253331.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 6.258095550537109,
|
|
"epoch": 1.8343912290825157,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046725145028914404,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.16581851840019227,
|
|
"num_tokens": 40266059.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 6.256051778793335,
|
|
"epoch": 1.8349682631275246,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004672300088978425,
|
|
"loss": 6.0242,
|
|
"mean_token_accuracy": 0.1764928877353668,
|
|
"num_tokens": 40278732.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 6.2313501834869385,
|
|
"epoch": 1.8355452971725332,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004672085610409801,
|
|
"loss": 5.946,
|
|
"mean_token_accuracy": 0.18284683674573898,
|
|
"num_tokens": 40290428.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 6.177774572372437,
|
|
"epoch": 1.8361223312175419,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046718710671927815,
|
|
"loss": 6.0255,
|
|
"mean_token_accuracy": 0.17687230110168456,
|
|
"num_tokens": 40302153.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 6.310884857177735,
|
|
"epoch": 1.8366993652625505,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046716564593345843,
|
|
"loss": 6.0497,
|
|
"mean_token_accuracy": 0.1659906193614006,
|
|
"num_tokens": 40315493.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 6.3170911312103275,
|
|
"epoch": 1.8372763993075591,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046714417868424265,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.1596185088157654,
|
|
"num_tokens": 40328157.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 6.326702356338501,
|
|
"epoch": 1.8378534333525678,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046712270497235284,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.1661912366747856,
|
|
"num_tokens": 40341684.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 6.280466222763062,
|
|
"epoch": 1.8384304673975764,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004671012247985112,
|
|
"loss": 6.1368,
|
|
"mean_token_accuracy": 0.16310458034276962,
|
|
"num_tokens": 40354002.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 6.223762655258179,
|
|
"epoch": 1.839007501442585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046707973816344044,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.17710338532924652,
|
|
"num_tokens": 40366211.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 6.310409069061279,
|
|
"epoch": 1.8395845354875937,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046705824506786304,
|
|
"loss": 6.098,
|
|
"mean_token_accuracy": 0.1691246896982193,
|
|
"num_tokens": 40377957.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 6.291127347946167,
|
|
"epoch": 1.8401615695326026,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.00046703674551250193,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.16395938247442246,
|
|
"num_tokens": 40391018.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 6.228165149688721,
|
|
"epoch": 1.840738603577611,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004670152394980803,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.168018639087677,
|
|
"num_tokens": 40405134.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 6.349109077453614,
|
|
"epoch": 1.8413156376226198,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.0004669937270253214,
|
|
"loss": 6.1221,
|
|
"mean_token_accuracy": 0.1632961302995682,
|
|
"num_tokens": 40418131.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 6.31708927154541,
|
|
"epoch": 1.8418926716676283,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000466972208094949,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.16544150561094284,
|
|
"num_tokens": 40430614.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 6.308804941177368,
|
|
"epoch": 1.8424697057126371,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046695068270768665,
|
|
"loss": 6.0683,
|
|
"mean_token_accuracy": 0.16248993575572968,
|
|
"num_tokens": 40443200.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 6.2004454135894775,
|
|
"epoch": 1.8430467397576455,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046692915086425846,
|
|
"loss": 6.0024,
|
|
"mean_token_accuracy": 0.1657170385122299,
|
|
"num_tokens": 40455662.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 6.319042015075683,
|
|
"epoch": 1.8436237738026544,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046690761256538857,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.1710167035460472,
|
|
"num_tokens": 40468247.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 6.324203443527222,
|
|
"epoch": 1.844200807847663,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004668860678118015,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.16913821399211884,
|
|
"num_tokens": 40480607.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 6.323934125900268,
|
|
"epoch": 1.8447778418926717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046686451660422185,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.16791746020317078,
|
|
"num_tokens": 40492140.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 6.285348176956177,
|
|
"epoch": 1.8453548759376803,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046684295894337455,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.16872338950634003,
|
|
"num_tokens": 40504513.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 6.237533950805664,
|
|
"epoch": 1.845931909982689,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004668213948299845,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.16824758648872376,
|
|
"num_tokens": 40517258.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 6.234326934814453,
|
|
"epoch": 1.8465089440276976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004667998242647772,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.16491250544786454,
|
|
"num_tokens": 40529092.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 6.266136550903321,
|
|
"epoch": 1.8470859780727062,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000466778247248478,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.1642804428935051,
|
|
"num_tokens": 40543586.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 6.313886404037476,
|
|
"epoch": 1.847663012117715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046675666378181275,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.17515656352043152,
|
|
"num_tokens": 40555721.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 6.2824138641357425,
|
|
"epoch": 1.8482400461627235,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004667350738655074,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.1662580594420433,
|
|
"num_tokens": 40567547.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 6.233053827285767,
|
|
"epoch": 1.8488170802077324,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046671347750028806,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.17195529937744142,
|
|
"num_tokens": 40579498.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 6.263859844207763,
|
|
"epoch": 1.8493941142527408,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004666918746868811,
|
|
"loss": 6.1004,
|
|
"mean_token_accuracy": 0.1605726420879364,
|
|
"num_tokens": 40593853.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 6.250426197052002,
|
|
"epoch": 1.8499711482977497,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004666702654260133,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.17157431542873383,
|
|
"num_tokens": 40605737.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 6.225319910049438,
|
|
"epoch": 1.850548182342758,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046664864971841113,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.172415129840374,
|
|
"num_tokens": 40617839.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 6.265378141403199,
|
|
"epoch": 1.851125216387767,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046662702756480195,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.17276886850595474,
|
|
"num_tokens": 40630247.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 6.222239351272583,
|
|
"epoch": 1.8517022504327756,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046660539896591286,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.17419626861810683,
|
|
"num_tokens": 40643869.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 6.3070024967193605,
|
|
"epoch": 1.8522792844777842,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004665837639224713,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.16875723153352737,
|
|
"num_tokens": 40655389.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 6.279503965377808,
|
|
"epoch": 1.8528563185227929,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046656212243520505,
|
|
"loss": 6.0528,
|
|
"mean_token_accuracy": 0.165364670753479,
|
|
"num_tokens": 40667663.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 6.244712591171265,
|
|
"epoch": 1.8534333525678015,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046654047450484193,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.17057995349168778,
|
|
"num_tokens": 40680623.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 6.220044422149658,
|
|
"epoch": 1.8540103866128101,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004665188201321102,
|
|
"loss": 5.9599,
|
|
"mean_token_accuracy": 0.1741309642791748,
|
|
"num_tokens": 40692679.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 6.258392667770385,
|
|
"epoch": 1.8545874206578188,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046649715931773795,
|
|
"loss": 6.1387,
|
|
"mean_token_accuracy": 0.1673455372452736,
|
|
"num_tokens": 40705187.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 6.291736078262329,
|
|
"epoch": 1.8551644547028274,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000466475492062454,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.17339060008525847,
|
|
"num_tokens": 40717854.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 6.2766063690185545,
|
|
"epoch": 1.855741488747836,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046645381836698684,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.16265238225460052,
|
|
"num_tokens": 40731039.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 6.2548644065856935,
|
|
"epoch": 1.856318522792845,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004664321382320657,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.17314105480909348,
|
|
"num_tokens": 40745065.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 6.258414602279663,
|
|
"epoch": 1.8568955568378533,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046641045165841965,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.16226121485233308,
|
|
"num_tokens": 40758107.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 6.270643854141236,
|
|
"epoch": 1.8574725908828622,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046638875864677814,
|
|
"loss": 6.1105,
|
|
"mean_token_accuracy": 0.16872740387916565,
|
|
"num_tokens": 40771082.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 6.305703115463257,
|
|
"epoch": 1.8580496249278706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004663670591978708,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.16707999408245086,
|
|
"num_tokens": 40784165.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 6.237900972366333,
|
|
"epoch": 1.8586266589728795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004663453533124275,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.1778552234172821,
|
|
"num_tokens": 40796279.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 6.1860754013061525,
|
|
"epoch": 1.859203693017888,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004663236409911783,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.1731626346707344,
|
|
"num_tokens": 40809074.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 6.17712368965149,
|
|
"epoch": 1.8597807270628968,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046630192223485345,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.17486831545829773,
|
|
"num_tokens": 40821086.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 6.314848279953003,
|
|
"epoch": 1.8603577611079054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046628019704418345,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.16555711328983308,
|
|
"num_tokens": 40832697.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 6.169562435150146,
|
|
"epoch": 1.860934795152914,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000466258465419899,
|
|
"loss": 6.0551,
|
|
"mean_token_accuracy": 0.16342287957668306,
|
|
"num_tokens": 40845268.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 6.295875883102417,
|
|
"epoch": 1.8615118291979227,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004662367273627312,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.15954152941703797,
|
|
"num_tokens": 40858314.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 6.303014135360717,
|
|
"epoch": 1.8620888632429313,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000466214982873411,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.17139186710119247,
|
|
"num_tokens": 40869982.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 6.248759126663208,
|
|
"epoch": 1.86266589728794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046619323195266975,
|
|
"loss": 5.9716,
|
|
"mean_token_accuracy": 0.1751272961497307,
|
|
"num_tokens": 40881831.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 6.161066722869873,
|
|
"epoch": 1.8632429313329486,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004661714746012392,
|
|
"loss": 6.008,
|
|
"mean_token_accuracy": 0.17016322016716004,
|
|
"num_tokens": 40894279.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 6.233482503890992,
|
|
"epoch": 1.8638199653779572,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000466149710819851,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.16817092448472976,
|
|
"num_tokens": 40906960.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 6.340131759643555,
|
|
"epoch": 1.8643969994229659,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004661279406092373,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.16523224860429764,
|
|
"num_tokens": 40920688.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 6.30043215751648,
|
|
"epoch": 1.8649740334679747,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046610616397013027,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.1653803125023842,
|
|
"num_tokens": 40933017.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 6.219679450988769,
|
|
"epoch": 1.8655510675129832,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004660843809032623,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.17148686349391937,
|
|
"num_tokens": 40947179.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 6.283222913742065,
|
|
"epoch": 1.866128101557992,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004660625914093661,
|
|
"loss": 6.0981,
|
|
"mean_token_accuracy": 0.1636438712477684,
|
|
"num_tokens": 40958806.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 6.313401699066162,
|
|
"epoch": 1.8667051356030004,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004660407954891745,
|
|
"loss": 6.0434,
|
|
"mean_token_accuracy": 0.17289685904979707,
|
|
"num_tokens": 40970667.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 6.22429256439209,
|
|
"epoch": 1.8672821696480093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004660189931434207,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.16919858902692794,
|
|
"num_tokens": 40982663.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 6.23825216293335,
|
|
"epoch": 1.8678592036930177,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004659971843728379,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.16918305009603501,
|
|
"num_tokens": 40995168.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 6.307004165649414,
|
|
"epoch": 1.8684362377380266,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004659753691781597,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.1678227812051773,
|
|
"num_tokens": 41007159.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 6.231713056564331,
|
|
"epoch": 1.8690132717830352,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004659535475601198,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.16688550263643265,
|
|
"num_tokens": 41019860.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 6.203270149230957,
|
|
"epoch": 1.8695903058280439,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046593171951945226,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.1657431960105896,
|
|
"num_tokens": 41031635.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 6.259737777709961,
|
|
"epoch": 1.8701673398730525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046590988505689114,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.16913105845451354,
|
|
"num_tokens": 41044678.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 6.280846738815308,
|
|
"epoch": 1.8707443739180611,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046588804417317084,
|
|
"loss": 6.1166,
|
|
"mean_token_accuracy": 0.16795769333839417,
|
|
"num_tokens": 41056799.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 6.287213611602783,
|
|
"epoch": 1.8713214079630698,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046586619686902597,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.16530012637376784,
|
|
"num_tokens": 41069700.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 6.308014869689941,
|
|
"epoch": 1.8718984420080784,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046584434314519144,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.17250948995351792,
|
|
"num_tokens": 41081427.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 6.290389108657837,
|
|
"epoch": 1.8724754760530873,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004658224830024022,
|
|
"loss": 6.0395,
|
|
"mean_token_accuracy": 0.17142314016819,
|
|
"num_tokens": 41094770.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 6.228277778625488,
|
|
"epoch": 1.8730525100980957,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004658006164413935,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.1729537844657898,
|
|
"num_tokens": 41106802.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 6.216348171234131,
|
|
"epoch": 1.8736295441431046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004657787434629009,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.17646737545728683,
|
|
"num_tokens": 41120125.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 6.105568265914917,
|
|
"epoch": 1.874206578188113,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046575686406765993,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.17620332092046737,
|
|
"num_tokens": 41134267.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 6.314919900894165,
|
|
"epoch": 1.8747836122331218,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046573497825640664,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1711890734732151,
|
|
"num_tokens": 41147266.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 6.271852016448975,
|
|
"epoch": 1.8753606462781303,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004657130860298771,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.17353598028421402,
|
|
"num_tokens": 41159666.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 6.266560459136963,
|
|
"epoch": 1.8759376803231391,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004656911873888077,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.16777328699827193,
|
|
"num_tokens": 41171947.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 6.214862108230591,
|
|
"epoch": 1.8765147143681478,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004656692823339349,
|
|
"loss": 6.0512,
|
|
"mean_token_accuracy": 0.1780415490269661,
|
|
"num_tokens": 41186376.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 6.257151699066162,
|
|
"epoch": 1.8770917484131564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004656473708659955,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.1731489807367325,
|
|
"num_tokens": 41199730.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 6.250900554656982,
|
|
"epoch": 1.877668782458165,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046562545298572646,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.17911915779113768,
|
|
"num_tokens": 41212502.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 6.185820722579956,
|
|
"epoch": 1.8782458165031737,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000465603528693865,
|
|
"loss": 5.9887,
|
|
"mean_token_accuracy": 0.17167483866214753,
|
|
"num_tokens": 41226006.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 6.316561460494995,
|
|
"epoch": 1.8788228505481823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046558159799114853,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.16871319115161895,
|
|
"num_tokens": 41239172.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 6.207419347763062,
|
|
"epoch": 1.879399884593191,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004655596608783147,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.17857006043195725,
|
|
"num_tokens": 41251307.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 6.265816640853882,
|
|
"epoch": 1.8799769186381996,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046553771735610136,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.16932079792022706,
|
|
"num_tokens": 41264634.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 6.2975006103515625,
|
|
"epoch": 1.8805539526832082,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004655157674252465,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.15814897865056993,
|
|
"num_tokens": 41278205.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 6.317185497283935,
|
|
"epoch": 1.881130986728217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046549381108648843,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.1710874080657959,
|
|
"num_tokens": 41290447.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 6.305042934417725,
|
|
"epoch": 1.8817080207732255,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004654718483405656,
|
|
"loss": 5.9676,
|
|
"mean_token_accuracy": 0.17561424076557158,
|
|
"num_tokens": 41302948.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 6.232265901565552,
|
|
"epoch": 1.8822850548182344,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046544987918821685,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.16179861277341842,
|
|
"num_tokens": 41315237.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 6.131192016601562,
|
|
"epoch": 1.8828620888632428,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.000465427903630181,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.18151000291109085,
|
|
"num_tokens": 41327426.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 6.361543273925781,
|
|
"epoch": 1.8834391229082517,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004654059216671972,
|
|
"loss": 6.1255,
|
|
"mean_token_accuracy": 0.1627553418278694,
|
|
"num_tokens": 41340517.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 6.213067150115966,
|
|
"epoch": 1.88401615695326,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004653839333000048,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.1693815842270851,
|
|
"num_tokens": 41353520.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 6.259006404876709,
|
|
"epoch": 1.884593190998269,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046536193852934334,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.1702921360731125,
|
|
"num_tokens": 41366326.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 6.230393600463867,
|
|
"epoch": 1.8851702250432776,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046533993735595273,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.17455315291881562,
|
|
"num_tokens": 41377405.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 6.313044166564941,
|
|
"epoch": 1.8857472590882862,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046531792978057277,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.1636503666639328,
|
|
"num_tokens": 41391038.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 6.267929553985596,
|
|
"epoch": 1.8863242931332949,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004652959158039438,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.1683339387178421,
|
|
"num_tokens": 41404069.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 6.2727337837219235,
|
|
"epoch": 1.8869013271783035,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004652738954268062,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.1729697972536087,
|
|
"num_tokens": 41416698.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 6.213017225265503,
|
|
"epoch": 1.8874783612233121,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00046525186864990073,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.17483233362436296,
|
|
"num_tokens": 41429953.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 6.182444763183594,
|
|
"epoch": 1.8880553952683208,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046522983547396806,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.16858932971954346,
|
|
"num_tokens": 41442824.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 6.258214044570923,
|
|
"epoch": 1.8886324293133296,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004652077958997494,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.17258467972278596,
|
|
"num_tokens": 41455062.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 6.214363622665405,
|
|
"epoch": 1.889209463358338,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046518574992798604,
|
|
"loss": 5.9594,
|
|
"mean_token_accuracy": 0.18245875984430313,
|
|
"num_tokens": 41468147.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 6.234375715255737,
|
|
"epoch": 1.889786497403347,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046516369755941945,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.1727774828672409,
|
|
"num_tokens": 41480664.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 6.266945314407349,
|
|
"epoch": 1.8903635314483553,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004651416387947914,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.16870816498994828,
|
|
"num_tokens": 41494578.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 6.309160470962524,
|
|
"epoch": 1.8909405654933642,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004651195736348437,
|
|
"loss": 6.0935,
|
|
"mean_token_accuracy": 0.1649898260831833,
|
|
"num_tokens": 41506528.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 6.325799036026001,
|
|
"epoch": 1.8915175995383726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004650975020803186,
|
|
"loss": 6.1549,
|
|
"mean_token_accuracy": 0.16303233057260513,
|
|
"num_tokens": 41520861.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 6.268583345413208,
|
|
"epoch": 1.8920946335833815,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004650754241319584,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.17048420161008834,
|
|
"num_tokens": 41533811.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 6.324508285522461,
|
|
"epoch": 1.8926716676283901,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046505333979050573,
|
|
"loss": 6.0909,
|
|
"mean_token_accuracy": 0.16676845252513886,
|
|
"num_tokens": 41546291.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 6.226980972290039,
|
|
"epoch": 1.8932487016733988,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004650312490567035,
|
|
"loss": 5.9405,
|
|
"mean_token_accuracy": 0.18085718005895615,
|
|
"num_tokens": 41558157.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 6.266756439208985,
|
|
"epoch": 1.8938257357184074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004650091519312945,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.17133705019950868,
|
|
"num_tokens": 41571346.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 6.298261976242065,
|
|
"epoch": 1.894402769763416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046498704841502203,
|
|
"loss": 6.1362,
|
|
"mean_token_accuracy": 0.16385228782892228,
|
|
"num_tokens": 41583973.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 6.292732286453247,
|
|
"epoch": 1.8949798038084247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004649649385086296,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.16712913364171983,
|
|
"num_tokens": 41596210.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 6.289768648147583,
|
|
"epoch": 1.8955568378534333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004649428222128608,
|
|
"loss": 6.1271,
|
|
"mean_token_accuracy": 0.16882113367319107,
|
|
"num_tokens": 41608297.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 6.313119888305664,
|
|
"epoch": 1.896133871898442,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046492069952845953,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.1669365108013153,
|
|
"num_tokens": 41621319.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 6.320606660842896,
|
|
"epoch": 1.8967109059434506,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046489857045617,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.17546855211257933,
|
|
"num_tokens": 41633282.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 6.16384072303772,
|
|
"epoch": 1.8972879399884595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046487643499673625,
|
|
"loss": 6.0354,
|
|
"mean_token_accuracy": 0.16361497044563295,
|
|
"num_tokens": 41646573.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 6.252078866958618,
|
|
"epoch": 1.8978649740334679,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004648542931509029,
|
|
"loss": 5.999,
|
|
"mean_token_accuracy": 0.17221661657094955,
|
|
"num_tokens": 41659596.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 6.289477062225342,
|
|
"epoch": 1.8984420080784767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004648321449194148,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.16427045613527297,
|
|
"num_tokens": 41673612.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 6.313947153091431,
|
|
"epoch": 1.8990190421234852,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046480999030301673,
|
|
"loss": 6.1183,
|
|
"mean_token_accuracy": 0.1691570982336998,
|
|
"num_tokens": 41686583.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 6.2747705459594725,
|
|
"epoch": 1.899596076168494,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046478782930245395,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.16731169670820237,
|
|
"num_tokens": 41698542.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 6.274620056152344,
|
|
"epoch": 1.9001731102135024,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046476566191847176,
|
|
"loss": 6.0712,
|
|
"mean_token_accuracy": 0.16262018978595733,
|
|
"num_tokens": 41712461.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 6.319371175765991,
|
|
"epoch": 1.9007501442585113,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004647434881518159,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.16481758207082747,
|
|
"num_tokens": 41725450.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 6.324736642837524,
|
|
"epoch": 1.90132717830352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046472130800323194,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.17140338122844695,
|
|
"num_tokens": 41737255.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 6.234397840499878,
|
|
"epoch": 1.9019042123485286,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004646991214734661,
|
|
"loss": 6.0915,
|
|
"mean_token_accuracy": 0.1634446457028389,
|
|
"num_tokens": 41749459.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 6.248945045471191,
|
|
"epoch": 1.9024812463935372,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004646769285632645,
|
|
"loss": 6.0365,
|
|
"mean_token_accuracy": 0.17080003917217254,
|
|
"num_tokens": 41761603.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 6.2919713973999025,
|
|
"epoch": 1.9030582804385459,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004646547292733737,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.16482744812965394,
|
|
"num_tokens": 41774865.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 6.240364503860474,
|
|
"epoch": 1.9036353144835545,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004646325236045402,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.17352937161922455,
|
|
"num_tokens": 41787558.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 6.2833081722259525,
|
|
"epoch": 1.9042123485285631,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000464610311557511,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.1723578542470932,
|
|
"num_tokens": 41800754.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 6.26614818572998,
|
|
"epoch": 1.904789382573572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004645880931330331,
|
|
"loss": 5.9604,
|
|
"mean_token_accuracy": 0.1790569856762886,
|
|
"num_tokens": 41813133.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 6.22602105140686,
|
|
"epoch": 1.9053664166185804,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004645658683318539,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.16803948283195497,
|
|
"num_tokens": 41825288.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 6.312449026107788,
|
|
"epoch": 1.9059434506635893,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004645436371547209,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.1666354864835739,
|
|
"num_tokens": 41837331.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 6.313289451599121,
|
|
"epoch": 1.9065204847085977,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046452139960238186,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.170522104203701,
|
|
"num_tokens": 41850536.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 6.264101219177246,
|
|
"epoch": 1.9070975187536066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046449915567558467,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.17788014858961104,
|
|
"num_tokens": 41862199.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 6.239650011062622,
|
|
"epoch": 1.907674552798615,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004644769053750775,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.17359801530838012,
|
|
"num_tokens": 41872945.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 6.2783403396606445,
|
|
"epoch": 1.9082515868436238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004644546487016087,
|
|
"loss": 5.9911,
|
|
"mean_token_accuracy": 0.1715606838464737,
|
|
"num_tokens": 41884223.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 6.246064186096191,
|
|
"epoch": 1.9088286208886325,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046443238565592687,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.16985336393117906,
|
|
"num_tokens": 41896997.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 6.231339931488037,
|
|
"epoch": 1.9094056549336411,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046441011623878087,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.16984277367591857,
|
|
"num_tokens": 41910210.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 6.087150573730469,
|
|
"epoch": 1.9099826889786498,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004643878404509197,
|
|
"loss": 5.8959,
|
|
"mean_token_accuracy": 0.18043217658996583,
|
|
"num_tokens": 41922882.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 6.229480791091919,
|
|
"epoch": 1.9105597230236584,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046436555829309264,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.1844248279929161,
|
|
"num_tokens": 41934655.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 6.253088045120239,
|
|
"epoch": 1.911136757068667,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000464343269766049,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.16934573352336885,
|
|
"num_tokens": 41947946.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 6.3426737785339355,
|
|
"epoch": 1.9117137911136757,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046432097487053857,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.16838859617710114,
|
|
"num_tokens": 41962316.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 6.282298374176025,
|
|
"epoch": 1.9122908251586843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046429867360731124,
|
|
"loss": 6.0264,
|
|
"mean_token_accuracy": 0.17507038414478301,
|
|
"num_tokens": 41976076.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 6.328230476379394,
|
|
"epoch": 1.912867859203693,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046427636597711695,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.16239470541477202,
|
|
"num_tokens": 41988762.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 6.192126226425171,
|
|
"epoch": 1.9134448932487018,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046425405198070624,
|
|
"loss": 5.9454,
|
|
"mean_token_accuracy": 0.17111702710390092,
|
|
"num_tokens": 42000525.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 6.195065450668335,
|
|
"epoch": 1.9140219272937102,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046423173161882944,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.17092446684837342,
|
|
"num_tokens": 42013716.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 6.277429103851318,
|
|
"epoch": 1.914598961338719,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046420940489223735,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.17426891773939132,
|
|
"num_tokens": 42026689.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 6.289929008483886,
|
|
"epoch": 1.9151759953837275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004641870718016809,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.16388041228055955,
|
|
"num_tokens": 42039907.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 6.276375436782837,
|
|
"epoch": 1.9157530294287364,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004641647323479113,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.173135207593441,
|
|
"num_tokens": 42052781.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 6.243412160873413,
|
|
"epoch": 1.9163300634737448,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004641423865316798,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.17488401681184768,
|
|
"num_tokens": 42066695.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 6.1937644481658936,
|
|
"epoch": 1.9169070975187537,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004641200343537381,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.17501333504915237,
|
|
"num_tokens": 42079315.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 6.265763568878174,
|
|
"epoch": 1.9174841315637623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000464097675814838,
|
|
"loss": 6.058,
|
|
"mean_token_accuracy": 0.16800168603658677,
|
|
"num_tokens": 42091915.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 6.3285560131073,
|
|
"epoch": 1.918061165608771,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004640753109157316,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.16329863667488098,
|
|
"num_tokens": 42105316.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 6.2566338062286375,
|
|
"epoch": 1.9186381996537796,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046405293965717093,
|
|
"loss": 5.9762,
|
|
"mean_token_accuracy": 0.1756441429257393,
|
|
"num_tokens": 42118078.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 6.134314250946045,
|
|
"epoch": 1.9192152336987882,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004640305620399086,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.18055089563131332,
|
|
"num_tokens": 42130845.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 6.211712741851807,
|
|
"epoch": 1.9197922677437969,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004640081780646971,
|
|
"loss": 6.0069,
|
|
"mean_token_accuracy": 0.17803016901016236,
|
|
"num_tokens": 42142487.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 6.216660976409912,
|
|
"epoch": 1.9203693017888055,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046398578773228954,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.17111165076494217,
|
|
"num_tokens": 42154747.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 6.373775386810303,
|
|
"epoch": 1.9209463358338144,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046396339104343886,
|
|
"loss": 6.0687,
|
|
"mean_token_accuracy": 0.1637737326323986,
|
|
"num_tokens": 42167697.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 6.2525794506073,
|
|
"epoch": 1.9215233698788228,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004639409879988984,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.17294813096523284,
|
|
"num_tokens": 42179874.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 6.323226881027222,
|
|
"epoch": 1.9221004039238316,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004639185785994216,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.1681394025683403,
|
|
"num_tokens": 42192747.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 6.206807041168213,
|
|
"epoch": 1.92267743796884,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046389616284576226,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.16698787957429886,
|
|
"num_tokens": 42205534.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 6.251869058609008,
|
|
"epoch": 1.923254472013849,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.00046387374073867435,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.17046794891357422,
|
|
"num_tokens": 42217825.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 6.248140335083008,
|
|
"epoch": 1.9238315060588573,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046385131227891197,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.17224513739347458,
|
|
"num_tokens": 42230162.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 6.189965867996216,
|
|
"epoch": 1.9244085401038662,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004638288774672295,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.17534219622612,
|
|
"num_tokens": 42242458.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 6.134315395355225,
|
|
"epoch": 1.9249855741488748,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004638064363043816,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.17521344423294066,
|
|
"num_tokens": 42254389.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 6.185854196548462,
|
|
"epoch": 1.9255626081938835,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046378398879112293,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.17561282962560654,
|
|
"num_tokens": 42266421.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 6.145219898223877,
|
|
"epoch": 1.9261396422388921,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004637615349282086,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.17165957987308503,
|
|
"num_tokens": 42279189.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 6.226276779174805,
|
|
"epoch": 1.9267166762839008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004637390747163938,
|
|
"loss": 6.0187,
|
|
"mean_token_accuracy": 0.17052838951349258,
|
|
"num_tokens": 42291970.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 6.288958930969239,
|
|
"epoch": 1.9272937103289094,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004637166081564339,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.16882906556129457,
|
|
"num_tokens": 42305185.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 6.345633840560913,
|
|
"epoch": 1.927870744373918,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046369413524908473,
|
|
"loss": 6.0885,
|
|
"mean_token_accuracy": 0.16870655864477158,
|
|
"num_tokens": 42317823.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 6.186788845062256,
|
|
"epoch": 1.9284477784189267,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046367165599510207,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.17140022963285445,
|
|
"num_tokens": 42330540.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 6.201239490509034,
|
|
"epoch": 1.9290248124639353,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004636491703952419,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.18321040272712708,
|
|
"num_tokens": 42342347.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 6.2329206466674805,
|
|
"epoch": 1.9296018465089442,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046362667845026057,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.17573418319225312,
|
|
"num_tokens": 42355004.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 6.245389366149903,
|
|
"epoch": 1.9301788805539526,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046360418016091467,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.17386723011732103,
|
|
"num_tokens": 42366700.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 6.2483916759490965,
|
|
"epoch": 1.9307559145989615,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046358167552796085,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.16806585043668748,
|
|
"num_tokens": 42379723.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 6.20191330909729,
|
|
"epoch": 1.9313329486439699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046355916455215597,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.18643948137760163,
|
|
"num_tokens": 42393505.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 6.259112405776977,
|
|
"epoch": 1.9319099826889787,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004635366472342573,
|
|
"loss": 6.003,
|
|
"mean_token_accuracy": 0.164619180560112,
|
|
"num_tokens": 42406334.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 6.253616046905518,
|
|
"epoch": 1.9324870167339872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004635141235750222,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.1686533898115158,
|
|
"num_tokens": 42418585.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 6.243710851669311,
|
|
"epoch": 1.933064050778996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046349159357520815,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.18272491544485092,
|
|
"num_tokens": 42430741.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 6.187639904022217,
|
|
"epoch": 1.9336410848240047,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000463469057235573,
|
|
"loss": 5.9783,
|
|
"mean_token_accuracy": 0.17807655930519103,
|
|
"num_tokens": 42443241.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 6.195738410949707,
|
|
"epoch": 1.9342181188690133,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046344651455687476,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.17015268355607988,
|
|
"num_tokens": 42456476.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 6.336266040802002,
|
|
"epoch": 1.934795152914022,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046342396553987155,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.16396595537662506,
|
|
"num_tokens": 42468875.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 6.288597249984742,
|
|
"epoch": 1.9353721869590306,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046340141018532186,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.16845245212316512,
|
|
"num_tokens": 42483300.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 6.210137605667114,
|
|
"epoch": 1.9359492210040392,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004633788484939843,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.17025937288999557,
|
|
"num_tokens": 42497748.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 6.2557402610778805,
|
|
"epoch": 1.9365262550490479,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046335628046661776,
|
|
"loss": 6.0758,
|
|
"mean_token_accuracy": 0.1684375673532486,
|
|
"num_tokens": 42510464.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 6.335916376113891,
|
|
"epoch": 1.9371032890940567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046333370610398135,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.16555423587560653,
|
|
"num_tokens": 42522298.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 6.318788480758667,
|
|
"epoch": 1.9376803231390651,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004633111254068342,
|
|
"loss": 6.0237,
|
|
"mean_token_accuracy": 0.16976431906223297,
|
|
"num_tokens": 42535094.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 6.217743253707885,
|
|
"epoch": 1.938257357184074,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004632885383759359,
|
|
"loss": 5.9903,
|
|
"mean_token_accuracy": 0.17622564733028412,
|
|
"num_tokens": 42547272.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 6.130745124816895,
|
|
"epoch": 1.9388343912290824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046326594501204624,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.1842793568968773,
|
|
"num_tokens": 42559568.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 6.2765467166900635,
|
|
"epoch": 1.9394114252740913,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000463243345315925,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.16390738338232042,
|
|
"num_tokens": 42573177.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 6.263757228851318,
|
|
"epoch": 1.9399884593190997,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046322073928833224,
|
|
"loss": 5.9897,
|
|
"mean_token_accuracy": 0.17142129838466644,
|
|
"num_tokens": 42585436.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 6.274092197418213,
|
|
"epoch": 1.9405654933641086,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004631981269300285,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.16510260999202728,
|
|
"num_tokens": 42599826.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 6.223218488693237,
|
|
"epoch": 1.9411425274091172,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004631755082417742,
|
|
"loss": 6.0508,
|
|
"mean_token_accuracy": 0.1671837419271469,
|
|
"num_tokens": 42613901.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 6.325699520111084,
|
|
"epoch": 1.9417195614541258,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004631528832243302,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.1655432403087616,
|
|
"num_tokens": 42626592.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 6.229167652130127,
|
|
"epoch": 1.9422965954991345,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046313025187845735,
|
|
"loss": 5.9619,
|
|
"mean_token_accuracy": 0.17458304166793823,
|
|
"num_tokens": 42639754.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 6.262476778030395,
|
|
"epoch": 1.942873629544143,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046310761420491705,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.16979699730873107,
|
|
"num_tokens": 42651321.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 6.246843433380127,
|
|
"epoch": 1.9434506635891518,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004630849702044705,
|
|
"loss": 6.0391,
|
|
"mean_token_accuracy": 0.17260385304689407,
|
|
"num_tokens": 42664188.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 6.198481512069702,
|
|
"epoch": 1.9440276976341604,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046306231987787937,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.1676759049296379,
|
|
"num_tokens": 42677882.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 6.212922239303589,
|
|
"epoch": 1.944604731679169,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046303966322590556,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.17638970911502838,
|
|
"num_tokens": 42690595.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 6.2258812427520756,
|
|
"epoch": 1.9451817657241777,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004630170002493111,
|
|
"loss": 5.9277,
|
|
"mean_token_accuracy": 0.17367104142904283,
|
|
"num_tokens": 42704784.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 6.168443441390991,
|
|
"epoch": 1.9457587997691865,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046299433094885826,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.17192557603120803,
|
|
"num_tokens": 42717012.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 6.279626703262329,
|
|
"epoch": 1.946335833814195,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046297165532530944,
|
|
"loss": 6.0293,
|
|
"mean_token_accuracy": 0.16916215866804124,
|
|
"num_tokens": 42728879.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 6.295999956130982,
|
|
"epoch": 1.9469128678592038,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004629489733794274,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.16610499918460847,
|
|
"num_tokens": 42742688.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 6.300163602828979,
|
|
"epoch": 1.9474899019042122,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000462926285111975,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.17265246957540512,
|
|
"num_tokens": 42754955.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 6.188889646530152,
|
|
"epoch": 1.948066935949221,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046290359052371535,
|
|
"loss": 6.0522,
|
|
"mean_token_accuracy": 0.16892243772745133,
|
|
"num_tokens": 42767760.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 6.246478271484375,
|
|
"epoch": 1.9486439699942295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004628808896154117,
|
|
"loss": 6.0019,
|
|
"mean_token_accuracy": 0.16956818401813506,
|
|
"num_tokens": 42779683.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 6.2639851570129395,
|
|
"epoch": 1.9492210040392384,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004628581823878277,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.16905308216810228,
|
|
"num_tokens": 42791289.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 6.233004856109619,
|
|
"epoch": 1.949798038084247,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000462835468841727,
|
|
"loss": 6.0669,
|
|
"mean_token_accuracy": 0.17280749827623368,
|
|
"num_tokens": 42803318.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 6.268746852874756,
|
|
"epoch": 1.9503750721292556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004628127489778737,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.1690628483891487,
|
|
"num_tokens": 42815935.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 6.278210783004761,
|
|
"epoch": 1.9509521061742643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004627900227970318,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.1742333874106407,
|
|
"num_tokens": 42827759.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 6.227267503738403,
|
|
"epoch": 1.951529140219273,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046276729029996576,
|
|
"loss": 6.003,
|
|
"mean_token_accuracy": 0.17346829771995545,
|
|
"num_tokens": 42840479.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 6.2318909645080565,
|
|
"epoch": 1.9521061742642816,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046274455148744025,
|
|
"loss": 6.0952,
|
|
"mean_token_accuracy": 0.1659419283270836,
|
|
"num_tokens": 42853972.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 6.221674251556396,
|
|
"epoch": 1.9526832083092902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046272180636022,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.16805387735366822,
|
|
"num_tokens": 42866192.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 6.2549063205719,
|
|
"epoch": 1.953260242354299,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046269905491907,
|
|
"loss": 5.9968,
|
|
"mean_token_accuracy": 0.17463415563106538,
|
|
"num_tokens": 42878661.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 6.230676937103271,
|
|
"epoch": 1.9538372763993075,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004626762971647555,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.17351190000772476,
|
|
"num_tokens": 42891498.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 6.232025623321533,
|
|
"epoch": 1.9544143104443163,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046265353309804205,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.1768836870789528,
|
|
"num_tokens": 42904657.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 6.22298035621643,
|
|
"epoch": 1.9549913444893248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004626307627196952,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.17455218583345414,
|
|
"num_tokens": 42916824.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 6.279146289825439,
|
|
"epoch": 1.9555683785343336,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004626079860304808,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.17725331634283065,
|
|
"num_tokens": 42929366.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 6.147270822525025,
|
|
"epoch": 1.956145412579342,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046258520303116496,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.18031210005283355,
|
|
"num_tokens": 42941955.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 6.272320032119751,
|
|
"epoch": 1.956722446624351,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004625624137225141,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.166519957780838,
|
|
"num_tokens": 42954302.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 6.343348264694214,
|
|
"epoch": 1.9572994806693593,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004625396181052945,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.16592449694871902,
|
|
"num_tokens": 42967225.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 6.157590579986572,
|
|
"epoch": 1.9578765147143682,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046251681618027316,
|
|
"loss": 6.0209,
|
|
"mean_token_accuracy": 0.1752626806497574,
|
|
"num_tokens": 42981388.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 6.245779943466187,
|
|
"epoch": 1.9584535487593768,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004624940079482167,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.17435730695724488,
|
|
"num_tokens": 42993110.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 6.225678825378418,
|
|
"epoch": 1.9590305828043855,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046247119340989254,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.16311826258897782,
|
|
"num_tokens": 43007309.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 6.3057647228240965,
|
|
"epoch": 1.959607616849394,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004624483725660678,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.17937014997005463,
|
|
"num_tokens": 43020813.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 6.267711973190307,
|
|
"epoch": 1.9601846508944027,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004624255454175102,
|
|
"loss": 6.0235,
|
|
"mean_token_accuracy": 0.1743055358529091,
|
|
"num_tokens": 43033357.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 6.227343893051147,
|
|
"epoch": 1.9607616849394114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004624027119649875,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.16687651872634887,
|
|
"num_tokens": 43046685.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 6.339546060562133,
|
|
"epoch": 1.96133871898442,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046237987220926766,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.1672934964299202,
|
|
"num_tokens": 43059670.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 6.22210693359375,
|
|
"epoch": 1.9619157530294289,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046235702615111886,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.17477399855852127,
|
|
"num_tokens": 43073515.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 6.229201745986939,
|
|
"epoch": 1.9624927870744373,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004623341737913096,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.17302633225917816,
|
|
"num_tokens": 43086046.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 6.224934053421021,
|
|
"epoch": 1.9630698211194462,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004623113151306085,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.17834639847278594,
|
|
"num_tokens": 43097703.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 6.266271162033081,
|
|
"epoch": 1.9636468551644546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046228845016978425,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.16586049050092697,
|
|
"num_tokens": 43110378.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 6.296831846237183,
|
|
"epoch": 1.9642238892094634,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004622655789096061,
|
|
"loss": 6.042,
|
|
"mean_token_accuracy": 0.1670925036072731,
|
|
"num_tokens": 43122978.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 6.284532690048218,
|
|
"epoch": 1.9648009232544719,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00046224270135084315,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.1697956383228302,
|
|
"num_tokens": 43135371.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 6.197793197631836,
|
|
"epoch": 1.9653779572994807,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046221981749426503,
|
|
"loss": 5.9921,
|
|
"mean_token_accuracy": 0.1699984058737755,
|
|
"num_tokens": 43147251.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 6.269783020019531,
|
|
"epoch": 1.9659549913444894,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046219692734064124,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.16827934384346008,
|
|
"num_tokens": 43160276.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 6.286127424240112,
|
|
"epoch": 1.966532025389498,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004621740308907419,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.17274793982505798,
|
|
"num_tokens": 43172443.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 6.257483434677124,
|
|
"epoch": 1.9671090594345066,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004621511281453369,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.16886429041624068,
|
|
"num_tokens": 43186350.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 6.218119812011719,
|
|
"epoch": 1.9676860934795153,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004621282191051967,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.17662974447011948,
|
|
"num_tokens": 43198936.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 6.324996995925903,
|
|
"epoch": 1.968263127524524,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004621053037710918,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.1648729309439659,
|
|
"num_tokens": 43211793.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 6.251626491546631,
|
|
"epoch": 1.9688401615695326,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000462082382143793,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.17532301992177962,
|
|
"num_tokens": 43223817.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 6.19627890586853,
|
|
"epoch": 1.9694171956145412,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046205945422407113,
|
|
"loss": 6.0233,
|
|
"mean_token_accuracy": 0.17594825774431228,
|
|
"num_tokens": 43235769.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 6.22838978767395,
|
|
"epoch": 1.9699942296595498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046203652001269754,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.17000845670700074,
|
|
"num_tokens": 43249309.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 6.279005813598633,
|
|
"epoch": 1.9705712637045587,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00046201357951044337,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.1684460759162903,
|
|
"num_tokens": 43262814.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 6.315310621261597,
|
|
"epoch": 1.9711482977495671,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.00046199063271808047,
|
|
"loss": 6.1099,
|
|
"mean_token_accuracy": 0.16198794841766356,
|
|
"num_tokens": 43276898.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 6.245305490493775,
|
|
"epoch": 1.971725331794576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004619676796363804,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.17359111309051514,
|
|
"num_tokens": 43288902.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 6.257856369018555,
|
|
"epoch": 1.9723023658395844,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046194472026611546,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.17116419225931168,
|
|
"num_tokens": 43301644.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 6.231047248840332,
|
|
"epoch": 1.9728793998845933,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004619217546080576,
|
|
"loss": 6.024,
|
|
"mean_token_accuracy": 0.1758951172232628,
|
|
"num_tokens": 43315550.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 6.350954198837281,
|
|
"epoch": 1.9734564339296017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004618987826629794,
|
|
"loss": 6.1074,
|
|
"mean_token_accuracy": 0.16367050707340242,
|
|
"num_tokens": 43328095.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 6.213918876647949,
|
|
"epoch": 1.9740334679746105,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046187580443165344,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.17428866624832154,
|
|
"num_tokens": 43340461.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 6.293837833404541,
|
|
"epoch": 1.9746105020196192,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004618528199148527,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.17793631553649902,
|
|
"num_tokens": 43352322.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 6.2946436405181885,
|
|
"epoch": 1.9751875360646278,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046182982911335016,
|
|
"loss": 6.0919,
|
|
"mean_token_accuracy": 0.17028756439685822,
|
|
"num_tokens": 43366212.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 6.314712762832642,
|
|
"epoch": 1.9757645701096365,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046180683202791905,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.16482252925634383,
|
|
"num_tokens": 43379123.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 6.320395517349243,
|
|
"epoch": 1.976341604154645,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000461783828659333,
|
|
"loss": 6.1507,
|
|
"mean_token_accuracy": 0.15963018387556077,
|
|
"num_tokens": 43393188.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 6.330562162399292,
|
|
"epoch": 1.9769186381996537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046176081900836565,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.16618767976760865,
|
|
"num_tokens": 43407448.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 6.234742307662964,
|
|
"epoch": 1.9774956722446624,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00046173780307579086,
|
|
"loss": 5.9955,
|
|
"mean_token_accuracy": 0.16900865137577056,
|
|
"num_tokens": 43420202.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 6.276762580871582,
|
|
"epoch": 1.9780727062896712,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004617147808623829,
|
|
"loss": 6.0736,
|
|
"mean_token_accuracy": 0.16688749194145203,
|
|
"num_tokens": 43433218.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 6.230731058120727,
|
|
"epoch": 1.9786497403346797,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046169175236891605,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.17231394499540328,
|
|
"num_tokens": 43445721.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 6.259533452987671,
|
|
"epoch": 1.9792267743796885,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004616687175961648,
|
|
"loss": 6.0316,
|
|
"mean_token_accuracy": 0.1742004543542862,
|
|
"num_tokens": 43457470.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 6.2746974468231205,
|
|
"epoch": 1.979803808424697,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004616456765449039,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.17770297527313234,
|
|
"num_tokens": 43470693.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 6.29163088798523,
|
|
"epoch": 1.9803808424697058,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046162262921590845,
|
|
"loss": 6.0524,
|
|
"mean_token_accuracy": 0.1658223256468773,
|
|
"num_tokens": 43482890.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 6.346973514556884,
|
|
"epoch": 1.9809578765147142,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004615995756099535,
|
|
"loss": 6.074,
|
|
"mean_token_accuracy": 0.1686537370085716,
|
|
"num_tokens": 43495444.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 6.248704862594605,
|
|
"epoch": 1.981534910559723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004615765157278146,
|
|
"loss": 6.0425,
|
|
"mean_token_accuracy": 0.16893480867147445,
|
|
"num_tokens": 43507415.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 6.229138278961182,
|
|
"epoch": 1.9821119446047317,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046155344957026726,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.16631700247526168,
|
|
"num_tokens": 43520832.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 6.310163736343384,
|
|
"epoch": 1.9826889786497404,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004615303771380873,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.17154231816530227,
|
|
"num_tokens": 43534459.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 6.201480484008789,
|
|
"epoch": 1.983266012694749,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046150729843205077,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.18204520791769027,
|
|
"num_tokens": 43546466.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 6.220339441299439,
|
|
"epoch": 1.9838430467397576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046148421345293384,
|
|
"loss": 5.9301,
|
|
"mean_token_accuracy": 0.17631548196077346,
|
|
"num_tokens": 43558285.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 6.1403234004974365,
|
|
"epoch": 1.9844200807847663,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004614611222015131,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.18074734061956405,
|
|
"num_tokens": 43572117.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 6.262120151519776,
|
|
"epoch": 1.984997114829775,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.00046143802467856507,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.16410153955221177,
|
|
"num_tokens": 43586951.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 6.277947902679443,
|
|
"epoch": 1.9855741488747836,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046141492088486673,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.17765239626169205,
|
|
"num_tokens": 43600542.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 6.247993421554566,
|
|
"epoch": 1.9861511829197922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004613918108211951,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1717355266213417,
|
|
"num_tokens": 43612928.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 6.333569145202636,
|
|
"epoch": 1.986728216964801,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004613686944883275,
|
|
"loss": 6.0304,
|
|
"mean_token_accuracy": 0.17236097604036332,
|
|
"num_tokens": 43625362.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 6.213045835494995,
|
|
"epoch": 1.9873052510098095,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00046134557188704146,
|
|
"loss": 6.0204,
|
|
"mean_token_accuracy": 0.17817834466695787,
|
|
"num_tokens": 43638165.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 6.135746431350708,
|
|
"epoch": 1.9878822850548183,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046132244301811466,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.17782478779554367,
|
|
"num_tokens": 43650688.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 6.326607179641724,
|
|
"epoch": 1.9884593190998268,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046129930788232497,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.16792702078819274,
|
|
"num_tokens": 43663168.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 6.254304552078247,
|
|
"epoch": 1.9890363531448356,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046127616648045073,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.16387904584407806,
|
|
"num_tokens": 43676391.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 6.3034281730651855,
|
|
"epoch": 1.989613387189844,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046125301881327007,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.16842008978128434,
|
|
"num_tokens": 43689631.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 6.273438882827759,
|
|
"epoch": 1.990190421234853,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046122986488156167,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.17078548073768615,
|
|
"num_tokens": 43703176.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 6.339113378524781,
|
|
"epoch": 1.9907674552798615,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046120670468610426,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.16192102879285813,
|
|
"num_tokens": 43717439.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 6.272079277038574,
|
|
"epoch": 1.9913444893248702,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046118353822767683,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.1686514735221863,
|
|
"num_tokens": 43730500.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 6.155890417098999,
|
|
"epoch": 1.9919215233698788,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004611603655070586,
|
|
"loss": 5.9199,
|
|
"mean_token_accuracy": 0.17832320630550386,
|
|
"num_tokens": 43744807.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 6.255143928527832,
|
|
"epoch": 1.9924985574148875,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046113718652502896,
|
|
"loss": 6.0038,
|
|
"mean_token_accuracy": 0.17497580498456955,
|
|
"num_tokens": 43756748.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 6.257786607742309,
|
|
"epoch": 1.993075591459896,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004611140012823675,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.16814451068639755,
|
|
"num_tokens": 43769309.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 6.215093517303467,
|
|
"epoch": 1.9936526255049047,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046109080977985395,
|
|
"loss": 6.0178,
|
|
"mean_token_accuracy": 0.1774963155388832,
|
|
"num_tokens": 43781057.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 6.306448173522949,
|
|
"epoch": 1.9942296595499136,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046106761201826854,
|
|
"loss": 6.0576,
|
|
"mean_token_accuracy": 0.16839146763086318,
|
|
"num_tokens": 43794504.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 6.134201717376709,
|
|
"epoch": 1.994806693594922,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046104440799839145,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.18590227514505386,
|
|
"num_tokens": 43810214.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 6.216445350646973,
|
|
"epoch": 1.9953837276399309,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000461021197721003,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.16848865598440171,
|
|
"num_tokens": 43822197.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 6.314849901199341,
|
|
"epoch": 1.9959607616849393,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046099798118688407,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.1691252052783966,
|
|
"num_tokens": 43835585.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 6.326150131225586,
|
|
"epoch": 1.9965377957299482,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004609747583968154,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.1651899218559265,
|
|
"num_tokens": 43848542.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 6.180682373046875,
|
|
"epoch": 1.9971148297749566,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004609515293515781,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.17395762950181962,
|
|
"num_tokens": 43860717.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 6.2602049827575685,
|
|
"epoch": 1.9976918638199654,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004609282940519535,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.1715341955423355,
|
|
"num_tokens": 43873193.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 6.3034483909606935,
|
|
"epoch": 1.998268897864974,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004609050524987231,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.16786195784807206,
|
|
"num_tokens": 43886241.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 6.274380493164062,
|
|
"epoch": 1.9988459319099827,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004608818046926686,
|
|
"loss": 6.018,
|
|
"mean_token_accuracy": 0.17538921535015106,
|
|
"num_tokens": 43899429.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 6.220386648178101,
|
|
"epoch": 1.9994229659549914,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004608585506345719,
|
|
"loss": 6.0432,
|
|
"mean_token_accuracy": 0.16782113611698152,
|
|
"num_tokens": 43913073.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 6.264380693435669,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004608352903252152,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.17643982023000718,
|
|
"num_tokens": 43926234.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 6.297075891494751,
|
|
"epoch": 2.000577034045009,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046081202376538084,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.1705596461892128,
|
|
"num_tokens": 43937787.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 6.214798879623413,
|
|
"epoch": 2.0011540680900173,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004607887509558513,
|
|
"loss": 6.0,
|
|
"mean_token_accuracy": 0.17187341153621674,
|
|
"num_tokens": 43951429.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 6.2717287063598635,
|
|
"epoch": 2.001731102135026,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004607654718974094,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.17009468674659728,
|
|
"num_tokens": 43964257.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 6.300295209884643,
|
|
"epoch": 2.0023081361800346,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004607421865908382,
|
|
"loss": 5.929,
|
|
"mean_token_accuracy": 0.1742121919989586,
|
|
"num_tokens": 43975995.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 6.187320327758789,
|
|
"epoch": 2.0028851702250434,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004607188950369207,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.17936831712722778,
|
|
"num_tokens": 43989191.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 6.265660429000855,
|
|
"epoch": 2.003462204270052,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004606955972364405,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.17080468833446502,
|
|
"num_tokens": 44000583.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 6.1407544136047365,
|
|
"epoch": 2.0040392383150607,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004606722931901812,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.1786182105541229,
|
|
"num_tokens": 44013894.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 6.202847480773926,
|
|
"epoch": 2.004616272360069,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004606489828989264,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.17088600397109985,
|
|
"num_tokens": 44026701.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 6.175824975967407,
|
|
"epoch": 2.005193306405078,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004606256663634604,
|
|
"loss": 5.9326,
|
|
"mean_token_accuracy": 0.1767387419939041,
|
|
"num_tokens": 44039775.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 6.25781946182251,
|
|
"epoch": 2.0057703404500864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004606023435845672,
|
|
"loss": 5.974,
|
|
"mean_token_accuracy": 0.17226887345314026,
|
|
"num_tokens": 44052352.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 6.250827646255493,
|
|
"epoch": 2.0063473744950953,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004605790145630314,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.17064084112644196,
|
|
"num_tokens": 44066147.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 6.238795328140259,
|
|
"epoch": 2.0069244085401037,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004605556792996377,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.17261969149112702,
|
|
"num_tokens": 44078692.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 6.296038961410522,
|
|
"epoch": 2.0075014425851125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004605323377951709,
|
|
"loss": 6.006,
|
|
"mean_token_accuracy": 0.16696172207593918,
|
|
"num_tokens": 44091511.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 6.22690978050232,
|
|
"epoch": 2.008078476630121,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000460508990050416,
|
|
"loss": 5.9448,
|
|
"mean_token_accuracy": 0.170767118036747,
|
|
"num_tokens": 44103423.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 6.131740474700928,
|
|
"epoch": 2.00865551067513,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004604856360661584,
|
|
"loss": 5.8242,
|
|
"mean_token_accuracy": 0.18300881683826448,
|
|
"num_tokens": 44116024.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 6.136595010757446,
|
|
"epoch": 2.0092325447201387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004604622758431835,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.17836426347494125,
|
|
"num_tokens": 44128595.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 6.280027580261231,
|
|
"epoch": 2.009809578765147,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046043890938227724,
|
|
"loss": 5.9718,
|
|
"mean_token_accuracy": 0.1769594207406044,
|
|
"num_tokens": 44140104.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 6.2423299789428714,
|
|
"epoch": 2.010386612810156,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046041553668422526,
|
|
"loss": 5.9318,
|
|
"mean_token_accuracy": 0.1780355080962181,
|
|
"num_tokens": 44152681.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 6.12680401802063,
|
|
"epoch": 2.0109636468551644,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046039215774981376,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.17880391776561738,
|
|
"num_tokens": 44165728.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 6.262257671356201,
|
|
"epoch": 2.0115406809001732,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046036877257982917,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.16699692755937576,
|
|
"num_tokens": 44178182.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 6.2879571437835695,
|
|
"epoch": 2.0121177149451817,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000460345381175058,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.17570238560438156,
|
|
"num_tokens": 44190954.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 6.242337083816528,
|
|
"epoch": 2.0126947489901905,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000460321983536287,
|
|
"loss": 5.9239,
|
|
"mean_token_accuracy": 0.17687204331159592,
|
|
"num_tokens": 44204123.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 6.183831357955933,
|
|
"epoch": 2.013271783035199,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00046029857966430315,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.17197465896606445,
|
|
"num_tokens": 44218656.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 6.203491353988648,
|
|
"epoch": 2.013848817080208,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046027516955989364,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.1783543273806572,
|
|
"num_tokens": 44231191.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 6.273696565628052,
|
|
"epoch": 2.014425851125216,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046025175322384577,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.17753272205591203,
|
|
"num_tokens": 44244564.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 6.272516918182373,
|
|
"epoch": 2.015002885170225,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046022833065694727,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.17100428342819213,
|
|
"num_tokens": 44257545.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 6.192347669601441,
|
|
"epoch": 2.0155799192152335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046020490185998575,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.17826618552207946,
|
|
"num_tokens": 44270416.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 6.214372444152832,
|
|
"epoch": 2.0161569532602424,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004601814668337495,
|
|
"loss": 5.9211,
|
|
"mean_token_accuracy": 0.17736995220184326,
|
|
"num_tokens": 44283366.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 6.20364727973938,
|
|
"epoch": 2.016733987305251,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046015802557902654,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.17061620205640793,
|
|
"num_tokens": 44296079.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 6.216525363922119,
|
|
"epoch": 2.0173110213502596,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00046013457809660537,
|
|
"loss": 5.9299,
|
|
"mean_token_accuracy": 0.173180291056633,
|
|
"num_tokens": 44308409.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 6.206072568893433,
|
|
"epoch": 2.0178880553952685,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046011112438727454,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.17291929721832275,
|
|
"num_tokens": 44321826.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 6.285996961593628,
|
|
"epoch": 2.018465089440277,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004600876644518231,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.1680159881711006,
|
|
"num_tokens": 44335630.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 6.087948226928711,
|
|
"epoch": 2.0190421234852858,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046006419829104,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.18672087639570237,
|
|
"num_tokens": 44349059.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 6.192037963867188,
|
|
"epoch": 2.019619157530294,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004600407259057145,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.17351363152265548,
|
|
"num_tokens": 44361908.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 6.220724296569824,
|
|
"epoch": 2.020196191575303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004600172472966361,
|
|
"loss": 5.9722,
|
|
"mean_token_accuracy": 0.16882861256599427,
|
|
"num_tokens": 44375487.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 6.192804622650146,
|
|
"epoch": 2.0207732256203115,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00045999376246459446,
|
|
"loss": 5.9108,
|
|
"mean_token_accuracy": 0.17260125130414963,
|
|
"num_tokens": 44387881.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 6.209100961685181,
|
|
"epoch": 2.0213502596653203,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004599702714103795,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.17245278358459473,
|
|
"num_tokens": 44400609.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 6.170619869232178,
|
|
"epoch": 2.0219272937103288,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004599467741347814,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.1790915235877037,
|
|
"num_tokens": 44413341.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 6.221302604675293,
|
|
"epoch": 2.0225043277553376,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004599232706385904,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.17114851176738738,
|
|
"num_tokens": 44425790.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 6.184481763839722,
|
|
"epoch": 2.023081361800346,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000459899760922597,
|
|
"loss": 5.8961,
|
|
"mean_token_accuracy": 0.18134428858757018,
|
|
"num_tokens": 44438204.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 6.192145204544067,
|
|
"epoch": 2.023658395845355,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004598762449875921,
|
|
"loss": 5.8576,
|
|
"mean_token_accuracy": 0.17917026430368424,
|
|
"num_tokens": 44450717.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 6.228597211837768,
|
|
"epoch": 2.0242354298903633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004598527228343665,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.1814187839627266,
|
|
"num_tokens": 44463391.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 6.161728239059448,
|
|
"epoch": 2.024812463935372,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004598291944637112,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.17788388729095458,
|
|
"num_tokens": 44477022.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 6.250133514404297,
|
|
"epoch": 2.025389497980381,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00045980565987641797,
|
|
"loss": 5.9895,
|
|
"mean_token_accuracy": 0.17265195846557618,
|
|
"num_tokens": 44490616.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 6.236105871200562,
|
|
"epoch": 2.0259665320253895,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045978211907327804,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.17624759078025817,
|
|
"num_tokens": 44503307.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 6.265711402893066,
|
|
"epoch": 2.0265435660703983,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004597585720550834,
|
|
"loss": 5.9679,
|
|
"mean_token_accuracy": 0.1739831820130348,
|
|
"num_tokens": 44516078.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 6.231649446487427,
|
|
"epoch": 2.0271206001154067,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000459735018822626,
|
|
"loss": 5.9245,
|
|
"mean_token_accuracy": 0.17394810765981675,
|
|
"num_tokens": 44528485.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 6.240048360824585,
|
|
"epoch": 2.0276976341604156,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045971145937669794,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.17736487239599227,
|
|
"num_tokens": 44539946.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 6.132218885421753,
|
|
"epoch": 2.028274668205424,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004596878937180917,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.1710592895746231,
|
|
"num_tokens": 44552828.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 6.226531219482422,
|
|
"epoch": 2.028851702250433,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004596643218475999,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.1757684901356697,
|
|
"num_tokens": 44564930.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 6.2708100318908695,
|
|
"epoch": 2.0294287362954413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045964074376601534,
|
|
"loss": 5.9457,
|
|
"mean_token_accuracy": 0.17014985233545304,
|
|
"num_tokens": 44578226.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 6.195923471450806,
|
|
"epoch": 2.03000577034045,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045961715947413106,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.17502938061952591,
|
|
"num_tokens": 44590704.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 6.199918508529663,
|
|
"epoch": 2.0305828043854586,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004595935689727404,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.18110113143920897,
|
|
"num_tokens": 44602758.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 6.124384832382202,
|
|
"epoch": 2.0311598384304674,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004595699722626367,
|
|
"loss": 5.8945,
|
|
"mean_token_accuracy": 0.1795112207531929,
|
|
"num_tokens": 44614733.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 6.308047533035278,
|
|
"epoch": 2.031736872475476,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045954636934461367,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.17096339911222458,
|
|
"num_tokens": 44628339.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 6.294468355178833,
|
|
"epoch": 2.0323139065204847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004595227602194652,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.17322905659675597,
|
|
"num_tokens": 44641382.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 6.156301641464234,
|
|
"epoch": 2.0328909405654936,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004594991448879853,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.1699449121952057,
|
|
"num_tokens": 44654618.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 6.299897193908691,
|
|
"epoch": 2.033467974610502,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004594755233509683,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.16198293268680572,
|
|
"num_tokens": 44667961.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 6.191911935806274,
|
|
"epoch": 2.034045008655511,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045945189560920875,
|
|
"loss": 5.9306,
|
|
"mean_token_accuracy": 0.17262049913406372,
|
|
"num_tokens": 44682185.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 6.27217288017273,
|
|
"epoch": 2.0346220427005193,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004594282616635013,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.17757879346609115,
|
|
"num_tokens": 44695513.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 6.232735204696655,
|
|
"epoch": 2.035199076745528,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004594046215146409,
|
|
"loss": 5.9928,
|
|
"mean_token_accuracy": 0.17601801156997682,
|
|
"num_tokens": 44707051.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 6.237101078033447,
|
|
"epoch": 2.0357761107905366,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045938097516342257,
|
|
"loss": 5.982,
|
|
"mean_token_accuracy": 0.17229001522064208,
|
|
"num_tokens": 44719915.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 6.118812084197998,
|
|
"epoch": 2.0363531448355454,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045935732261064184,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.1862248256802559,
|
|
"num_tokens": 44733115.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 6.205551958084106,
|
|
"epoch": 2.036930178880554,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045933366385709405,
|
|
"loss": 5.9436,
|
|
"mean_token_accuracy": 0.1748773232102394,
|
|
"num_tokens": 44744480.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 6.203357934951782,
|
|
"epoch": 2.0375072129255627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004593099989035751,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.17659931629896164,
|
|
"num_tokens": 44758200.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 6.316721200942993,
|
|
"epoch": 2.038084246970571,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004592863277508809,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.1700327605009079,
|
|
"num_tokens": 44771407.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 6.287095546722412,
|
|
"epoch": 2.03866128101558,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004592626503998076,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.17439333498477935,
|
|
"num_tokens": 44783765.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 6.228414916992188,
|
|
"epoch": 2.0392383150605884,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004592389668511515,
|
|
"loss": 5.9797,
|
|
"mean_token_accuracy": 0.1745125100016594,
|
|
"num_tokens": 44796550.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 6.192117929458618,
|
|
"epoch": 2.0398153491055973,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004592152771057093,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.17687230557203293,
|
|
"num_tokens": 44808802.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 6.250724363327026,
|
|
"epoch": 2.0403923831506057,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045919158116427785,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.17866400480270386,
|
|
"num_tokens": 44821023.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 6.220262145996093,
|
|
"epoch": 2.0409694171956145,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045916787902765396,
|
|
"loss": 5.9044,
|
|
"mean_token_accuracy": 0.175578336417675,
|
|
"num_tokens": 44833822.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 6.197280168533325,
|
|
"epoch": 2.0415464512406234,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004591441706966349,
|
|
"loss": 5.9274,
|
|
"mean_token_accuracy": 0.17216354012489318,
|
|
"num_tokens": 44846440.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 6.200249481201172,
|
|
"epoch": 2.042123485285632,
|
|
"grad_norm": 7.25,
|
|
"learning_rate": 0.0004591204561720183,
|
|
"loss": 5.9403,
|
|
"mean_token_accuracy": 0.1695069521665573,
|
|
"num_tokens": 44858257.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 6.175353002548218,
|
|
"epoch": 2.0427005193306407,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004590967354546015,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.1676792249083519,
|
|
"num_tokens": 44871339.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 6.270719003677368,
|
|
"epoch": 2.043277553375649,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004590730085451824,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.1787752777338028,
|
|
"num_tokens": 44884190.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 6.15546760559082,
|
|
"epoch": 2.043854587420658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045904927544455914,
|
|
"loss": 5.858,
|
|
"mean_token_accuracy": 0.17509367167949677,
|
|
"num_tokens": 44897530.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 6.192881536483765,
|
|
"epoch": 2.0444316214656664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045902553615353005,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.1834646299481392,
|
|
"num_tokens": 44910428.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 6.223622989654541,
|
|
"epoch": 2.0450086555106752,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004590017906728933,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.17263387590646745,
|
|
"num_tokens": 44922904.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 6.153698301315307,
|
|
"epoch": 2.0455856895556837,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045897803900344774,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.17572209388017654,
|
|
"num_tokens": 44935541.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 6.176003122329712,
|
|
"epoch": 2.0461627236006925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004589542811459923,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.1788767859339714,
|
|
"num_tokens": 44948483.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 6.233722305297851,
|
|
"epoch": 2.046739757645701,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004589305171013259,
|
|
"loss": 5.9362,
|
|
"mean_token_accuracy": 0.1753383070230484,
|
|
"num_tokens": 44961797.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 6.2383228778839115,
|
|
"epoch": 2.04731679169071,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000458906746870248,
|
|
"loss": 5.9733,
|
|
"mean_token_accuracy": 0.16818111687898635,
|
|
"num_tokens": 44975426.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 6.220548105239868,
|
|
"epoch": 2.047893825735718,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000458882970453558,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.17429644018411636,
|
|
"num_tokens": 44988272.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 6.1548073291778564,
|
|
"epoch": 2.048470859780727,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004588591878520556,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.17755962610244752,
|
|
"num_tokens": 45000609.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 6.313485479354858,
|
|
"epoch": 2.049047893825736,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004588353990665407,
|
|
"loss": 6.0308,
|
|
"mean_token_accuracy": 0.16356184035539628,
|
|
"num_tokens": 45012651.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 6.2108770370483395,
|
|
"epoch": 2.0496249278707444,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004588116040978136,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.17209396362304688,
|
|
"num_tokens": 45025237.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 6.18538384437561,
|
|
"epoch": 2.050201961915753,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045878780294667437,
|
|
"loss": 6.0153,
|
|
"mean_token_accuracy": 0.16943909376859664,
|
|
"num_tokens": 45038329.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 6.2096922397613525,
|
|
"epoch": 2.0507789959607616,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004587639956139237,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.17784364074468612,
|
|
"num_tokens": 45050251.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 6.265796804428101,
|
|
"epoch": 2.0513560300057705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004587401821003624,
|
|
"loss": 5.9827,
|
|
"mean_token_accuracy": 0.1691094607114792,
|
|
"num_tokens": 45062701.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 6.1350870609283445,
|
|
"epoch": 2.051933064050779,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045871636240679133,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.18649837225675583,
|
|
"num_tokens": 45077059.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 6.225623273849488,
|
|
"epoch": 2.0525100980957878,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004586925365340117,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.17775747776031495,
|
|
"num_tokens": 45089571.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 6.204924058914185,
|
|
"epoch": 2.053087132140796,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004586687044828247,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.174189892411232,
|
|
"num_tokens": 45101085.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 6.162897729873658,
|
|
"epoch": 2.053664166185805,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004586448662540322,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.1684534505009651,
|
|
"num_tokens": 45113844.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 6.239241313934326,
|
|
"epoch": 2.0542412002308135,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004586210218484358,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.1690887078642845,
|
|
"num_tokens": 45126297.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 6.265953493118286,
|
|
"epoch": 2.0548182342758223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045859717126683745,
|
|
"loss": 5.8603,
|
|
"mean_token_accuracy": 0.18210013806819916,
|
|
"num_tokens": 45139337.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 6.206180477142334,
|
|
"epoch": 2.0553952683208307,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045857331451003953,
|
|
"loss": 5.9986,
|
|
"mean_token_accuracy": 0.17050107568502426,
|
|
"num_tokens": 45151698.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 6.199662876129151,
|
|
"epoch": 2.0559723023658396,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045854945157884435,
|
|
"loss": 5.8944,
|
|
"mean_token_accuracy": 0.17789710760116578,
|
|
"num_tokens": 45164615.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 6.235444402694702,
|
|
"epoch": 2.056549336410848,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045852558247405455,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.17498012036085128,
|
|
"num_tokens": 45176630.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 6.209130382537841,
|
|
"epoch": 2.057126370455857,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00045850170719647287,
|
|
"loss": 5.8856,
|
|
"mean_token_accuracy": 0.18172849118709564,
|
|
"num_tokens": 45188879.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 6.245654630661011,
|
|
"epoch": 2.0577034045008658,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045847782574690254,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.16994517296552658,
|
|
"num_tokens": 45201694.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 6.198729944229126,
|
|
"epoch": 2.058280438545874,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045845393812614664,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.17356704622507096,
|
|
"num_tokens": 45215873.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 6.292256259918213,
|
|
"epoch": 2.058857472590883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004584300443350086,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.16657613068819047,
|
|
"num_tokens": 45229660.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 6.233248519897461,
|
|
"epoch": 2.0594345066358914,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004584061443742922,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.17116474509239196,
|
|
"num_tokens": 45243257.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 6.1754065990448,
|
|
"epoch": 2.0600115406809003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045838223824480124,
|
|
"loss": 5.8782,
|
|
"mean_token_accuracy": 0.18036632239818573,
|
|
"num_tokens": 45256212.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 6.207752275466919,
|
|
"epoch": 2.0605885747259087,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004583583259473397,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.1834060311317444,
|
|
"num_tokens": 45268292.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 6.1441535472869875,
|
|
"epoch": 2.0611656087709176,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045833440748271203,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.20127416551113128,
|
|
"num_tokens": 45284112.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 6.193862199783325,
|
|
"epoch": 2.061742642815926,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045831048285172266,
|
|
"loss": 5.8931,
|
|
"mean_token_accuracy": 0.1810559496283531,
|
|
"num_tokens": 45295839.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 6.141061782836914,
|
|
"epoch": 2.062319676860935,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004582865520551762,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.1708131492137909,
|
|
"num_tokens": 45309142.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 6.269522953033447,
|
|
"epoch": 2.0628967109059433,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045826261509387755,
|
|
"loss": 5.9701,
|
|
"mean_token_accuracy": 0.17792370170354843,
|
|
"num_tokens": 45322096.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 6.263595771789551,
|
|
"epoch": 2.063473744950952,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045823867196863197,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.17633334845304488,
|
|
"num_tokens": 45333685.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 6.1949646949768065,
|
|
"epoch": 2.0640507789959606,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004582147226802446,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.17821483314037323,
|
|
"num_tokens": 45345417.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 6.200151824951172,
|
|
"epoch": 2.0646278130409694,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004581907672295211,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.17727133482694626,
|
|
"num_tokens": 45357156.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 6.275757837295532,
|
|
"epoch": 2.065204847085978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045816680561726716,
|
|
"loss": 5.9526,
|
|
"mean_token_accuracy": 0.17532005161046982,
|
|
"num_tokens": 45369627.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 6.222644901275634,
|
|
"epoch": 2.0657818811309867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004581428378442886,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.1732523813843727,
|
|
"num_tokens": 45380603.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 6.197103118896484,
|
|
"epoch": 2.0663589151759956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045811886391139173,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.1877364158630371,
|
|
"num_tokens": 45394923.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 6.229747629165649,
|
|
"epoch": 2.066935949221004,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045809488381938284,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.17425263226032256,
|
|
"num_tokens": 45407351.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 6.097294044494629,
|
|
"epoch": 2.067512983266013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004580708975690684,
|
|
"loss": 5.9082,
|
|
"mean_token_accuracy": 0.17824243754148483,
|
|
"num_tokens": 45420783.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 6.217814922332764,
|
|
"epoch": 2.0680900173110213,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004580469051612554,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.17622975260019302,
|
|
"num_tokens": 45433208.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 6.249103021621704,
|
|
"epoch": 2.06866705135603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045802290659675057,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.16410011649131775,
|
|
"num_tokens": 45445872.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 6.2258580207824705,
|
|
"epoch": 2.0692440854010385,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045799890187636123,
|
|
"loss": 5.9794,
|
|
"mean_token_accuracy": 0.17026836425065994,
|
|
"num_tokens": 45458844.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 6.201646947860718,
|
|
"epoch": 2.0698211194460474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045797489100089464,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.17284089624881743,
|
|
"num_tokens": 45471919.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 6.218793487548828,
|
|
"epoch": 2.070398153491056,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004579508739711585,
|
|
"loss": 5.943,
|
|
"mean_token_accuracy": 0.17847752720117568,
|
|
"num_tokens": 45483769.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 6.286684274673462,
|
|
"epoch": 2.0709751875360647,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045792685078796075,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.1702808380126953,
|
|
"num_tokens": 45497077.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 6.243750429153442,
|
|
"epoch": 2.071552221581073,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000457902821452109,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.1820717990398407,
|
|
"num_tokens": 45509229.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 6.238589191436768,
|
|
"epoch": 2.072129255626082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045787878596441193,
|
|
"loss": 5.9315,
|
|
"mean_token_accuracy": 0.1709604248404503,
|
|
"num_tokens": 45521654.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 6.228718662261963,
|
|
"epoch": 2.0727062896710904,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004578547443256776,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.17131188362836838,
|
|
"num_tokens": 45533488.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 6.198116397857666,
|
|
"epoch": 2.0732833237160992,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004578306965367148,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.17840521186590194,
|
|
"num_tokens": 45544938.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 6.221617031097412,
|
|
"epoch": 2.073860357761108,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045780664259833235,
|
|
"loss": 5.9548,
|
|
"mean_token_accuracy": 0.17204647958278657,
|
|
"num_tokens": 45557085.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 6.249954557418823,
|
|
"epoch": 2.0744373918061165,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045778258251133924,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.17703141123056412,
|
|
"num_tokens": 45570174.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 6.208803415298462,
|
|
"epoch": 2.0750144258511254,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045775851627654474,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.17877745032310485,
|
|
"num_tokens": 45582174.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 6.200427007675171,
|
|
"epoch": 2.075591459896134,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004577344438947584,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.17164078503847122,
|
|
"num_tokens": 45595732.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 6.15403265953064,
|
|
"epoch": 2.0761684939411427,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045771036536678984,
|
|
"loss": 5.9319,
|
|
"mean_token_accuracy": 0.17511217743158342,
|
|
"num_tokens": 45609675.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 6.279201984405518,
|
|
"epoch": 2.076745527986151,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00045768628069344885,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.17805370539426804,
|
|
"num_tokens": 45622467.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 6.270020294189453,
|
|
"epoch": 2.07732256203116,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004576621898755455,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.16146025508642198,
|
|
"num_tokens": 45636246.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.07732256203116,
|
|
"eval_entropy": 6.116413441577485,
|
|
"eval_loss": 6.092830181121826,
|
|
"eval_mean_token_accuracy": 0.1729923587462968,
|
|
"eval_num_tokens": 45636246.0,
|
|
"eval_runtime": 22.6545,
|
|
"eval_samples_per_second": 1241.96,
|
|
"eval_steps_per_second": 155.245,
|
|
"step": 18000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"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": 6.7334621865984e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|