6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691951370239257,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1.1137442217984e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|