12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.6924408540103866,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691951370239257,
|
|
"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
|
|
}
|
|
],
|
|
"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": 2.2368043210752e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|