8035 lines
219 KiB
JSON
8035 lines
219 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.22382004868086058,
|
|
"eval_steps": 500,
|
|
"global_step": 4000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691505527496338,
|
|
"epoch": 0.0002797750608510757,
|
|
"grad_norm": 12.375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7862,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9833.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691538619995118,
|
|
"epoch": 0.0005595501217021514,
|
|
"grad_norm": 13.0,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7246,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 19666.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691145992279052,
|
|
"epoch": 0.0008393251825532272,
|
|
"grad_norm": 9.3125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4747,
|
|
"mean_token_accuracy": 0.019643833697773515,
|
|
"num_tokens": 28771.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.682477760314942,
|
|
"epoch": 0.0011191002434043028,
|
|
"grad_norm": 6.21875,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1639,
|
|
"mean_token_accuracy": 0.04193656481802464,
|
|
"num_tokens": 38625.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.617809772491455,
|
|
"epoch": 0.0013988753042553786,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8606,
|
|
"mean_token_accuracy": 0.04725950676947832,
|
|
"num_tokens": 47864.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.55274839401245,
|
|
"epoch": 0.0016786503651064545,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6963,
|
|
"mean_token_accuracy": 0.04289307370781899,
|
|
"num_tokens": 55926.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.584246730804443,
|
|
"epoch": 0.0019584254259575303,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6414,
|
|
"mean_token_accuracy": 0.044558577984571454,
|
|
"num_tokens": 64915.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.56161117553711,
|
|
"epoch": 0.0022382004868086057,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.6116,
|
|
"mean_token_accuracy": 0.041977206617593764,
|
|
"num_tokens": 73813.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.549141788482666,
|
|
"epoch": 0.0025179755476596815,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.5772,
|
|
"mean_token_accuracy": 0.04488353617489338,
|
|
"num_tokens": 83706.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.555339050292968,
|
|
"epoch": 0.0027977506085107573,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.5206,
|
|
"mean_token_accuracy": 0.041607250832021235,
|
|
"num_tokens": 92739.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.562696361541748,
|
|
"epoch": 0.003077525669361833,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4731,
|
|
"mean_token_accuracy": 0.04852877669036389,
|
|
"num_tokens": 101880.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.513782119750976,
|
|
"epoch": 0.003357300730212909,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4135,
|
|
"mean_token_accuracy": 0.05527102164924145,
|
|
"num_tokens": 111303.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.410881614685058,
|
|
"epoch": 0.0036370757910639847,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2608,
|
|
"mean_token_accuracy": 0.059278345108032225,
|
|
"num_tokens": 121022.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.35908842086792,
|
|
"epoch": 0.0039168508519150606,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.1931,
|
|
"mean_token_accuracy": 0.05288665182888508,
|
|
"num_tokens": 129764.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.414530277252197,
|
|
"epoch": 0.004196625912766136,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.12,
|
|
"mean_token_accuracy": 0.05712716057896614,
|
|
"num_tokens": 139543.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.420390224456787,
|
|
"epoch": 0.004476400973617211,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0894,
|
|
"mean_token_accuracy": 0.055438223481178286,
|
|
"num_tokens": 148772.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.439853763580322,
|
|
"epoch": 0.004756176034468288,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8746,
|
|
"mean_token_accuracy": 0.06480722092092037,
|
|
"num_tokens": 158786.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.333017063140868,
|
|
"epoch": 0.005035951095319363,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7978,
|
|
"mean_token_accuracy": 0.06817127540707588,
|
|
"num_tokens": 166989.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.257375049591065,
|
|
"epoch": 0.005315726156170439,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6945,
|
|
"mean_token_accuracy": 0.06792460419237614,
|
|
"num_tokens": 175840.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.24816074371338,
|
|
"epoch": 0.005595501217021515,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.6247,
|
|
"mean_token_accuracy": 0.06662830822169781,
|
|
"num_tokens": 185375.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.16532497406006,
|
|
"epoch": 0.005875276277872591,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.5206,
|
|
"mean_token_accuracy": 0.07044463530182839,
|
|
"num_tokens": 194647.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.170048713684082,
|
|
"epoch": 0.006155051338723666,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4143,
|
|
"mean_token_accuracy": 0.07247264273464679,
|
|
"num_tokens": 203882.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.117275524139405,
|
|
"epoch": 0.006434826399574742,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.2929,
|
|
"mean_token_accuracy": 0.06882111690938472,
|
|
"num_tokens": 212641.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.047082424163818,
|
|
"epoch": 0.006714601460425818,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1784,
|
|
"mean_token_accuracy": 0.07864802330732346,
|
|
"num_tokens": 221668.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.896892261505126,
|
|
"epoch": 0.006994376521276893,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0655,
|
|
"mean_token_accuracy": 0.07759866937994957,
|
|
"num_tokens": 230277.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.822550010681152,
|
|
"epoch": 0.0072741515821279695,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9853,
|
|
"mean_token_accuracy": 0.07847488112747669,
|
|
"num_tokens": 240191.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.653499507904053,
|
|
"epoch": 0.007553926642979045,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8597,
|
|
"mean_token_accuracy": 0.08022317960858345,
|
|
"num_tokens": 249600.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.487109375,
|
|
"epoch": 0.007833701703830121,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7858,
|
|
"mean_token_accuracy": 0.07919244170188904,
|
|
"num_tokens": 258766.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.301309394836426,
|
|
"epoch": 0.008113476764681197,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.5919,
|
|
"mean_token_accuracy": 0.08380925506353379,
|
|
"num_tokens": 268399.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.010336112976074,
|
|
"epoch": 0.008393251825532272,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5475,
|
|
"mean_token_accuracy": 0.08445582017302514,
|
|
"num_tokens": 278348.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.899579620361328,
|
|
"epoch": 0.008673026886383347,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5228,
|
|
"mean_token_accuracy": 0.07803246155381202,
|
|
"num_tokens": 288429.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.617181396484375,
|
|
"epoch": 0.008952801947234423,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.319,
|
|
"mean_token_accuracy": 0.09034765139222145,
|
|
"num_tokens": 297936.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.410243892669678,
|
|
"epoch": 0.0092325770080855,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.3897,
|
|
"mean_token_accuracy": 0.08498694151639938,
|
|
"num_tokens": 307390.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.320203971862792,
|
|
"epoch": 0.009512352068936575,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3416,
|
|
"mean_token_accuracy": 0.07727829068899154,
|
|
"num_tokens": 316381.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.236638164520263,
|
|
"epoch": 0.00979212712978765,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.3116,
|
|
"mean_token_accuracy": 0.07726738080382348,
|
|
"num_tokens": 325086.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.076795291900634,
|
|
"epoch": 0.010071902190638726,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.1784,
|
|
"mean_token_accuracy": 0.08438889384269714,
|
|
"num_tokens": 334438.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.889586877822876,
|
|
"epoch": 0.010351677251489803,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.1976,
|
|
"mean_token_accuracy": 0.0870728187263012,
|
|
"num_tokens": 343169.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.912118721008301,
|
|
"epoch": 0.010631452312340878,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.126,
|
|
"mean_token_accuracy": 0.08688639178872108,
|
|
"num_tokens": 352260.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.820125246047974,
|
|
"epoch": 0.010911227373191954,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.0827,
|
|
"mean_token_accuracy": 0.08836827799677849,
|
|
"num_tokens": 361436.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.675041007995605,
|
|
"epoch": 0.01119100243404303,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1613,
|
|
"mean_token_accuracy": 0.09058133289217948,
|
|
"num_tokens": 370232.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.803629922866821,
|
|
"epoch": 0.011470777494894105,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1257,
|
|
"mean_token_accuracy": 0.0905453845858574,
|
|
"num_tokens": 380211.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.76220006942749,
|
|
"epoch": 0.011750552555745182,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1154,
|
|
"mean_token_accuracy": 0.08261686339974403,
|
|
"num_tokens": 390089.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.6790376663208,
|
|
"epoch": 0.012030327616596257,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.0364,
|
|
"mean_token_accuracy": 0.08655178025364876,
|
|
"num_tokens": 398513.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.6753379821777346,
|
|
"epoch": 0.012310102677447332,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.1785,
|
|
"mean_token_accuracy": 0.08271857276558876,
|
|
"num_tokens": 408114.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.658677101135254,
|
|
"epoch": 0.012589877738298408,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0324,
|
|
"mean_token_accuracy": 0.08730659186840058,
|
|
"num_tokens": 417680.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.590711975097657,
|
|
"epoch": 0.012869652799149483,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.94,
|
|
"mean_token_accuracy": 0.0981583096086979,
|
|
"num_tokens": 426056.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.538638401031494,
|
|
"epoch": 0.01314942786000056,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.8994,
|
|
"mean_token_accuracy": 0.09497818350791931,
|
|
"num_tokens": 435465.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.547599267959595,
|
|
"epoch": 0.013429202920851636,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9882,
|
|
"mean_token_accuracy": 0.09514376819133759,
|
|
"num_tokens": 444295.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.532002258300781,
|
|
"epoch": 0.013708977981702711,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.9084,
|
|
"mean_token_accuracy": 0.09089445620775223,
|
|
"num_tokens": 453111.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.416005039215088,
|
|
"epoch": 0.013988753042553786,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8671,
|
|
"mean_token_accuracy": 0.09376973509788514,
|
|
"num_tokens": 462438.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.44201397895813,
|
|
"epoch": 0.014268528103404862,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8518,
|
|
"mean_token_accuracy": 0.0919196330010891,
|
|
"num_tokens": 471610.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.486415004730224,
|
|
"epoch": 0.014548303164255939,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.9342,
|
|
"mean_token_accuracy": 0.09321872368454934,
|
|
"num_tokens": 480849.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.40749454498291,
|
|
"epoch": 0.014828078225107014,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9376,
|
|
"mean_token_accuracy": 0.08951603546738625,
|
|
"num_tokens": 489756.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.461516523361206,
|
|
"epoch": 0.01510785328595809,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.9217,
|
|
"mean_token_accuracy": 0.09437951892614364,
|
|
"num_tokens": 498818.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.285744953155517,
|
|
"epoch": 0.015387628346809165,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8458,
|
|
"mean_token_accuracy": 0.09555465653538704,
|
|
"num_tokens": 508508.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.444489002227783,
|
|
"epoch": 0.015667403407660242,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0025,
|
|
"mean_token_accuracy": 0.09034469872713088,
|
|
"num_tokens": 518257.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.36638994216919,
|
|
"epoch": 0.015947178468511316,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9625,
|
|
"mean_token_accuracy": 0.08916445821523666,
|
|
"num_tokens": 527811.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.358241605758667,
|
|
"epoch": 0.016226953529362393,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.09337828531861306,
|
|
"num_tokens": 536991.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.320535326004029,
|
|
"epoch": 0.016506728590213467,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9245,
|
|
"mean_token_accuracy": 0.0914350025355816,
|
|
"num_tokens": 546498.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.351836109161377,
|
|
"epoch": 0.016786503651064544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8809,
|
|
"mean_token_accuracy": 0.09436944723129273,
|
|
"num_tokens": 556022.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.289101552963257,
|
|
"epoch": 0.01706627871191562,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8212,
|
|
"mean_token_accuracy": 0.09640712589025498,
|
|
"num_tokens": 565392.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.230247545242309,
|
|
"epoch": 0.017346053772766695,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8043,
|
|
"mean_token_accuracy": 0.09431554824113846,
|
|
"num_tokens": 574485.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.3728536605834964,
|
|
"epoch": 0.01762582883361777,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8343,
|
|
"mean_token_accuracy": 0.09452549517154693,
|
|
"num_tokens": 583149.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.280808210372925,
|
|
"epoch": 0.017905603894468845,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8855,
|
|
"mean_token_accuracy": 0.09358676373958588,
|
|
"num_tokens": 592876.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.064757013320923,
|
|
"epoch": 0.018185378955319922,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.09988230094313622,
|
|
"num_tokens": 602001.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.323857975006104,
|
|
"epoch": 0.018465154016171,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8667,
|
|
"mean_token_accuracy": 0.09093789532780647,
|
|
"num_tokens": 611602.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.089147615432739,
|
|
"epoch": 0.018744929077022073,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7506,
|
|
"mean_token_accuracy": 0.09642454162240029,
|
|
"num_tokens": 620905.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.273478889465332,
|
|
"epoch": 0.01902470413787315,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8279,
|
|
"mean_token_accuracy": 0.0952286258339882,
|
|
"num_tokens": 630151.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.070547962188721,
|
|
"epoch": 0.019304479198724227,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7905,
|
|
"mean_token_accuracy": 0.09692409187555313,
|
|
"num_tokens": 639864.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.4187744140625,
|
|
"epoch": 0.0195842542595753,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8707,
|
|
"mean_token_accuracy": 0.09315617531538009,
|
|
"num_tokens": 648819.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.169836378097534,
|
|
"epoch": 0.019864029320426378,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8027,
|
|
"mean_token_accuracy": 0.09456639736890793,
|
|
"num_tokens": 658438.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.143348264694214,
|
|
"epoch": 0.020143804381277452,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7459,
|
|
"mean_token_accuracy": 0.09843514785170555,
|
|
"num_tokens": 668140.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.207337665557861,
|
|
"epoch": 0.02042357944212853,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7733,
|
|
"mean_token_accuracy": 0.09692016914486885,
|
|
"num_tokens": 677505.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.047050952911377,
|
|
"epoch": 0.020703354502979606,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7596,
|
|
"mean_token_accuracy": 0.09099765941500663,
|
|
"num_tokens": 687911.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.110365295410157,
|
|
"epoch": 0.02098312956383068,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7002,
|
|
"mean_token_accuracy": 0.10557077825069427,
|
|
"num_tokens": 696565.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.068933725357056,
|
|
"epoch": 0.021262904624681757,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6321,
|
|
"mean_token_accuracy": 0.09727629125118256,
|
|
"num_tokens": 704918.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.053268480300903,
|
|
"epoch": 0.02154267968553283,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.6612,
|
|
"mean_token_accuracy": 0.1000488631427288,
|
|
"num_tokens": 716172.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.058245515823364,
|
|
"epoch": 0.021822454746383908,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.10481962487101555,
|
|
"num_tokens": 725075.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.085121202468872,
|
|
"epoch": 0.022102229807234985,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7861,
|
|
"mean_token_accuracy": 0.09666902050375939,
|
|
"num_tokens": 733314.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.137383270263672,
|
|
"epoch": 0.02238200486808606,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.10260491818189621,
|
|
"num_tokens": 742390.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.997572708129883,
|
|
"epoch": 0.022661779928937135,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.09590908735990525,
|
|
"num_tokens": 751464.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.058079195022583,
|
|
"epoch": 0.02294155498978821,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.10047566667199134,
|
|
"num_tokens": 760746.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.995281791687011,
|
|
"epoch": 0.023221330050639286,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5617,
|
|
"mean_token_accuracy": 0.10464712381362914,
|
|
"num_tokens": 769052.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.989618110656738,
|
|
"epoch": 0.023501105111490363,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7826,
|
|
"mean_token_accuracy": 0.09742124751210213,
|
|
"num_tokens": 778660.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.074799585342407,
|
|
"epoch": 0.023780880172341437,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6877,
|
|
"mean_token_accuracy": 0.10435819402337074,
|
|
"num_tokens": 787841.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.878971099853516,
|
|
"epoch": 0.024060655233192514,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.537,
|
|
"mean_token_accuracy": 0.10397473350167274,
|
|
"num_tokens": 796175.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.980287361145019,
|
|
"epoch": 0.024340430294043588,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.5959,
|
|
"mean_token_accuracy": 0.10773405581712722,
|
|
"num_tokens": 805941.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.9006028175354,
|
|
"epoch": 0.024620205354894665,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.09920870438218117,
|
|
"num_tokens": 815058.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.100294494628907,
|
|
"epoch": 0.024899980415745742,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.6593,
|
|
"mean_token_accuracy": 0.10117991864681244,
|
|
"num_tokens": 824459.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.872482252120972,
|
|
"epoch": 0.025179755476596816,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.656,
|
|
"mean_token_accuracy": 0.10260392725467682,
|
|
"num_tokens": 835250.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.986909580230713,
|
|
"epoch": 0.025459530537447893,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6617,
|
|
"mean_token_accuracy": 0.10458940342068672,
|
|
"num_tokens": 844643.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.96947169303894,
|
|
"epoch": 0.025739305598298966,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.5977,
|
|
"mean_token_accuracy": 0.10226123109459877,
|
|
"num_tokens": 853375.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.875414848327637,
|
|
"epoch": 0.026019080659150044,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.11177821755409241,
|
|
"num_tokens": 862244.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.945923662185669,
|
|
"epoch": 0.02629885572000112,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6286,
|
|
"mean_token_accuracy": 0.09996586814522743,
|
|
"num_tokens": 871828.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.8525604724884035,
|
|
"epoch": 0.026578630780852194,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.10374173521995544,
|
|
"num_tokens": 881087.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.889187860488891,
|
|
"epoch": 0.02685840584170327,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.10589562878012657,
|
|
"num_tokens": 890061.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.009466075897217,
|
|
"epoch": 0.027138180902554345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6192,
|
|
"mean_token_accuracy": 0.10268636345863343,
|
|
"num_tokens": 899388.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.763098287582397,
|
|
"epoch": 0.027417955963405422,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5255,
|
|
"mean_token_accuracy": 0.10589060559868813,
|
|
"num_tokens": 908295.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.7688929557800295,
|
|
"epoch": 0.0276977310242565,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.4924,
|
|
"mean_token_accuracy": 0.10882084742188454,
|
|
"num_tokens": 917514.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.904528284072876,
|
|
"epoch": 0.027977506085107573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5978,
|
|
"mean_token_accuracy": 0.10768755748867989,
|
|
"num_tokens": 927146.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.758494710922241,
|
|
"epoch": 0.02825728114595865,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4884,
|
|
"mean_token_accuracy": 0.10985259413719177,
|
|
"num_tokens": 935278.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.831978225708008,
|
|
"epoch": 0.028537056206809724,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5894,
|
|
"mean_token_accuracy": 0.10266794636845589,
|
|
"num_tokens": 945056.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.827414417266846,
|
|
"epoch": 0.0288168312676608,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5527,
|
|
"mean_token_accuracy": 0.10177932679653168,
|
|
"num_tokens": 954187.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.905342674255371,
|
|
"epoch": 0.029096606328511878,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.5899,
|
|
"mean_token_accuracy": 0.10657662600278854,
|
|
"num_tokens": 963075.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.886737442016601,
|
|
"epoch": 0.02937638138936295,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5683,
|
|
"mean_token_accuracy": 0.10781930312514305,
|
|
"num_tokens": 972110.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.684601259231568,
|
|
"epoch": 0.02965615645021403,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.4582,
|
|
"mean_token_accuracy": 0.11291620060801506,
|
|
"num_tokens": 980231.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.7892358779907225,
|
|
"epoch": 0.029935931511065102,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6105,
|
|
"mean_token_accuracy": 0.10551066771149635,
|
|
"num_tokens": 990018.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.703322696685791,
|
|
"epoch": 0.03021570657191618,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.10690677091479302,
|
|
"num_tokens": 999243.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.800885343551636,
|
|
"epoch": 0.030495481632767257,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.4947,
|
|
"mean_token_accuracy": 0.1084700345993042,
|
|
"num_tokens": 1008800.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.75251727104187,
|
|
"epoch": 0.03077525669361833,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5354,
|
|
"mean_token_accuracy": 0.10884697884321212,
|
|
"num_tokens": 1018880.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.796888923645019,
|
|
"epoch": 0.031055031754469407,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.4822,
|
|
"mean_token_accuracy": 0.10811220407485962,
|
|
"num_tokens": 1028508.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.65325436592102,
|
|
"epoch": 0.031334806815320485,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4371,
|
|
"mean_token_accuracy": 0.11171221733093262,
|
|
"num_tokens": 1037626.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.6531189441680905,
|
|
"epoch": 0.031614581876171555,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4237,
|
|
"mean_token_accuracy": 0.1133709043264389,
|
|
"num_tokens": 1046814.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.597415113449097,
|
|
"epoch": 0.03189435693702263,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.10929519906640053,
|
|
"num_tokens": 1056620.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.794770956039429,
|
|
"epoch": 0.03217413199787371,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.11290100738406181,
|
|
"num_tokens": 1064488.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.786476469039917,
|
|
"epoch": 0.032453907058724786,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.11080160588026047,
|
|
"num_tokens": 1074153.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.673076820373535,
|
|
"epoch": 0.03273368211957586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.452,
|
|
"mean_token_accuracy": 0.10839907601475715,
|
|
"num_tokens": 1083027.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.628738451004028,
|
|
"epoch": 0.03301345718042693,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.10820735022425651,
|
|
"num_tokens": 1092010.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.731857395172119,
|
|
"epoch": 0.03329323224127801,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4946,
|
|
"mean_token_accuracy": 0.10928055047988891,
|
|
"num_tokens": 1101776.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.651297473907471,
|
|
"epoch": 0.03357300730212909,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4487,
|
|
"mean_token_accuracy": 0.10809680670499802,
|
|
"num_tokens": 1110894.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.813410139083862,
|
|
"epoch": 0.033852782362980165,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4318,
|
|
"mean_token_accuracy": 0.10976689979434014,
|
|
"num_tokens": 1119512.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.574000358581543,
|
|
"epoch": 0.03413255742383124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.4217,
|
|
"mean_token_accuracy": 0.10791075751185417,
|
|
"num_tokens": 1129469.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.738797283172607,
|
|
"epoch": 0.03441233248468231,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.10540183559060097,
|
|
"num_tokens": 1137850.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.7057750701904295,
|
|
"epoch": 0.03469210754553339,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.11240374073386192,
|
|
"num_tokens": 1147405.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.679307174682617,
|
|
"epoch": 0.034971882606384466,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4446,
|
|
"mean_token_accuracy": 0.11059640496969222,
|
|
"num_tokens": 1156457.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.691693830490112,
|
|
"epoch": 0.03525165766723554,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4141,
|
|
"mean_token_accuracy": 0.11546503752470016,
|
|
"num_tokens": 1165943.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.4711555480957035,
|
|
"epoch": 0.03553143272808662,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.3521,
|
|
"mean_token_accuracy": 0.11288735195994377,
|
|
"num_tokens": 1175030.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.5566987037658695,
|
|
"epoch": 0.03581120778893769,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.4719,
|
|
"mean_token_accuracy": 0.11424087956547738,
|
|
"num_tokens": 1184988.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.78665771484375,
|
|
"epoch": 0.03609098284978877,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4706,
|
|
"mean_token_accuracy": 0.11168640255928039,
|
|
"num_tokens": 1194352.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.566987657546997,
|
|
"epoch": 0.036370757910639845,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3646,
|
|
"mean_token_accuracy": 0.1151100791990757,
|
|
"num_tokens": 1203744.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.640985155105591,
|
|
"epoch": 0.03665053297149092,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4265,
|
|
"mean_token_accuracy": 0.11166704073548317,
|
|
"num_tokens": 1212917.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.689370393753052,
|
|
"epoch": 0.036930308032342,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4567,
|
|
"mean_token_accuracy": 0.11746964305639267,
|
|
"num_tokens": 1221669.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.537262868881226,
|
|
"epoch": 0.037210083093193076,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.11580658480525016,
|
|
"num_tokens": 1230925.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.473914861679077,
|
|
"epoch": 0.037489858154044146,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3872,
|
|
"mean_token_accuracy": 0.12107581570744515,
|
|
"num_tokens": 1240317.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.532442855834961,
|
|
"epoch": 0.037769633214895224,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.11721108332276345,
|
|
"num_tokens": 1250285.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.558922338485718,
|
|
"epoch": 0.0380494082757463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3691,
|
|
"mean_token_accuracy": 0.11794314831495285,
|
|
"num_tokens": 1259272.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.556687736511231,
|
|
"epoch": 0.03832918333659738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.11026200056076049,
|
|
"num_tokens": 1269069.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.544914388656617,
|
|
"epoch": 0.038608958397448455,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3472,
|
|
"mean_token_accuracy": 0.1141720823943615,
|
|
"num_tokens": 1277942.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.516038227081299,
|
|
"epoch": 0.038888733458299525,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4464,
|
|
"mean_token_accuracy": 0.11829971224069595,
|
|
"num_tokens": 1286731.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.491542816162109,
|
|
"epoch": 0.0391685085191506,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.306,
|
|
"mean_token_accuracy": 0.11953174397349357,
|
|
"num_tokens": 1295685.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.41384859085083,
|
|
"epoch": 0.03944828358000168,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.1239193856716156,
|
|
"num_tokens": 1304375.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.570674753189087,
|
|
"epoch": 0.039728058640852756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.4673,
|
|
"mean_token_accuracy": 0.11799883842468262,
|
|
"num_tokens": 1313282.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.577246189117432,
|
|
"epoch": 0.040007833701703834,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3111,
|
|
"mean_token_accuracy": 0.11679205074906349,
|
|
"num_tokens": 1322035.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.528969764709473,
|
|
"epoch": 0.040287608762554904,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4596,
|
|
"mean_token_accuracy": 0.11984212100505828,
|
|
"num_tokens": 1331553.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.455485153198242,
|
|
"epoch": 0.04056738382340598,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.11634061336517335,
|
|
"num_tokens": 1340577.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.606705093383789,
|
|
"epoch": 0.04084715888425706,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3608,
|
|
"mean_token_accuracy": 0.12028084397315979,
|
|
"num_tokens": 1349635.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.485494136810303,
|
|
"epoch": 0.041126933945108135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2679,
|
|
"mean_token_accuracy": 0.11617309153079987,
|
|
"num_tokens": 1358628.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.461924934387207,
|
|
"epoch": 0.04140670900595921,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.1150215283036232,
|
|
"num_tokens": 1368023.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.4644389152526855,
|
|
"epoch": 0.04168648406681028,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.12105848267674446,
|
|
"num_tokens": 1377354.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.552575492858887,
|
|
"epoch": 0.04196625912766136,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4018,
|
|
"mean_token_accuracy": 0.1141360804438591,
|
|
"num_tokens": 1386428.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.4100508213043215,
|
|
"epoch": 0.04224603418851244,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.11664086356759071,
|
|
"num_tokens": 1395809.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.542036771774292,
|
|
"epoch": 0.042525809249363514,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.322,
|
|
"mean_token_accuracy": 0.12149200588464737,
|
|
"num_tokens": 1405440.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.500925827026367,
|
|
"epoch": 0.04280558431021459,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4325,
|
|
"mean_token_accuracy": 0.11671576723456382,
|
|
"num_tokens": 1414018.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.469825267791748,
|
|
"epoch": 0.04308535937106566,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3286,
|
|
"mean_token_accuracy": 0.1199316494166851,
|
|
"num_tokens": 1422853.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.4752647399902346,
|
|
"epoch": 0.04336513443191674,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.12002637311816215,
|
|
"num_tokens": 1431647.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.4410097122192385,
|
|
"epoch": 0.043644909492767815,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.12325269281864167,
|
|
"num_tokens": 1440547.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.460622024536133,
|
|
"epoch": 0.04392468455361889,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.12282432466745377,
|
|
"num_tokens": 1450310.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.4368048191070555,
|
|
"epoch": 0.04420445961446997,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3488,
|
|
"mean_token_accuracy": 0.11794603615999222,
|
|
"num_tokens": 1458544.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.315302181243896,
|
|
"epoch": 0.04448423467532104,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3146,
|
|
"mean_token_accuracy": 0.12033002376556397,
|
|
"num_tokens": 1467699.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.488300848007202,
|
|
"epoch": 0.04476400973617212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2519,
|
|
"mean_token_accuracy": 0.1236931897699833,
|
|
"num_tokens": 1477386.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.3928173065185545,
|
|
"epoch": 0.045043784797023194,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.11787274852395058,
|
|
"num_tokens": 1486660.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.316296100616455,
|
|
"epoch": 0.04532355985787427,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.12369973957538605,
|
|
"num_tokens": 1495408.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.420361280441284,
|
|
"epoch": 0.04560333491872535,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2966,
|
|
"mean_token_accuracy": 0.12109342366456985,
|
|
"num_tokens": 1503822.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.339131259918213,
|
|
"epoch": 0.04588310997957642,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2543,
|
|
"mean_token_accuracy": 0.11657608151435853,
|
|
"num_tokens": 1512822.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.436035680770874,
|
|
"epoch": 0.046162885040427495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3429,
|
|
"mean_token_accuracy": 0.11799641102552413,
|
|
"num_tokens": 1522321.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.388043451309204,
|
|
"epoch": 0.04644266010127857,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.11690129637718201,
|
|
"num_tokens": 1532071.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.446229124069214,
|
|
"epoch": 0.04672243516212965,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2658,
|
|
"mean_token_accuracy": 0.1248463362455368,
|
|
"num_tokens": 1541204.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.321492671966553,
|
|
"epoch": 0.04700221022298073,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.301,
|
|
"mean_token_accuracy": 0.11873220205307007,
|
|
"num_tokens": 1548994.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.387647390365601,
|
|
"epoch": 0.0472819852838318,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3317,
|
|
"mean_token_accuracy": 0.11347933784127236,
|
|
"num_tokens": 1558012.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.33697543144226,
|
|
"epoch": 0.047561760344682874,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.344,
|
|
"mean_token_accuracy": 0.12062845751643181,
|
|
"num_tokens": 1567183.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.517240285873413,
|
|
"epoch": 0.04784153540553395,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.12024350762367249,
|
|
"num_tokens": 1577213.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.327879953384399,
|
|
"epoch": 0.04812131046638503,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.12363175675272942,
|
|
"num_tokens": 1586814.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.303459978103637,
|
|
"epoch": 0.048401085527236105,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2858,
|
|
"mean_token_accuracy": 0.12493444457650185,
|
|
"num_tokens": 1596140.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.3528955459594725,
|
|
"epoch": 0.048680860588087176,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.12042548209428787,
|
|
"num_tokens": 1604811.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.2718658447265625,
|
|
"epoch": 0.04896063564893825,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1916,
|
|
"mean_token_accuracy": 0.12246528714895248,
|
|
"num_tokens": 1613975.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.39298005104065,
|
|
"epoch": 0.04924041070978933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.12414250522851944,
|
|
"num_tokens": 1622571.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.373995971679688,
|
|
"epoch": 0.04952018577064041,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3129,
|
|
"mean_token_accuracy": 0.12346948832273483,
|
|
"num_tokens": 1631203.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.396008825302124,
|
|
"epoch": 0.049799960831491484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.1246532879769802,
|
|
"num_tokens": 1640170.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.244958019256591,
|
|
"epoch": 0.050079735892342554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2958,
|
|
"mean_token_accuracy": 0.12313124164938927,
|
|
"num_tokens": 1649039.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.412044620513916,
|
|
"epoch": 0.05035951095319363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2599,
|
|
"mean_token_accuracy": 0.1271291956305504,
|
|
"num_tokens": 1658445.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.195079517364502,
|
|
"epoch": 0.05063928601404471,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1302,
|
|
"mean_token_accuracy": 0.13331740349531174,
|
|
"num_tokens": 1667097.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.290958261489868,
|
|
"epoch": 0.050919061074895786,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.11674268618226051,
|
|
"num_tokens": 1676874.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.34834885597229,
|
|
"epoch": 0.05119883613574686,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.12399802803993225,
|
|
"num_tokens": 1685547.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.189801597595215,
|
|
"epoch": 0.05147861119659793,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.12718559354543685,
|
|
"num_tokens": 1693753.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.277320146560669,
|
|
"epoch": 0.05175838625744901,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.12505132406949998,
|
|
"num_tokens": 1703747.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.1411545753479,
|
|
"epoch": 0.05203816131830009,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.12806382775306702,
|
|
"num_tokens": 1712656.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.263706398010254,
|
|
"epoch": 0.052317936379151164,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.12317869812250137,
|
|
"num_tokens": 1722695.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.419267845153809,
|
|
"epoch": 0.05259771144000224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3361,
|
|
"mean_token_accuracy": 0.1168564572930336,
|
|
"num_tokens": 1733003.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.101446342468262,
|
|
"epoch": 0.05287748650085331,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1556,
|
|
"mean_token_accuracy": 0.12313281893730163,
|
|
"num_tokens": 1742393.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.349677515029907,
|
|
"epoch": 0.05315726156170439,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.2524,
|
|
"mean_token_accuracy": 0.12328635305166244,
|
|
"num_tokens": 1752098.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.1572033882141115,
|
|
"epoch": 0.053437036622555466,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.12816244289278983,
|
|
"num_tokens": 1760835.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.283704566955566,
|
|
"epoch": 0.05371681168340654,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2603,
|
|
"mean_token_accuracy": 0.12562395483255387,
|
|
"num_tokens": 1770084.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.192875766754151,
|
|
"epoch": 0.05399658674425762,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2888,
|
|
"mean_token_accuracy": 0.11796638444066047,
|
|
"num_tokens": 1779321.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.382868099212646,
|
|
"epoch": 0.05427636180510869,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.12535162419080734,
|
|
"num_tokens": 1789268.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.16242561340332,
|
|
"epoch": 0.05455613686595977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1851,
|
|
"mean_token_accuracy": 0.12277970910072326,
|
|
"num_tokens": 1797765.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.156621074676513,
|
|
"epoch": 0.054835911926810844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.13391674682497978,
|
|
"num_tokens": 1807110.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.318566751480103,
|
|
"epoch": 0.05511568698766192,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2306,
|
|
"mean_token_accuracy": 0.1218092642724514,
|
|
"num_tokens": 1816767.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.220181655883789,
|
|
"epoch": 0.055395462048513,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2397,
|
|
"mean_token_accuracy": 0.12567930296063423,
|
|
"num_tokens": 1826012.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.257971334457397,
|
|
"epoch": 0.05567523710936407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2,
|
|
"mean_token_accuracy": 0.12385892570018768,
|
|
"num_tokens": 1835355.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.210480213165283,
|
|
"epoch": 0.055955012170215146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1559,
|
|
"mean_token_accuracy": 0.13025842383503913,
|
|
"num_tokens": 1844998.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.130459451675415,
|
|
"epoch": 0.05623478723106622,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499998026082006,
|
|
"loss": 6.0702,
|
|
"mean_token_accuracy": 0.13735647723078728,
|
|
"num_tokens": 1854117.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.147902154922486,
|
|
"epoch": 0.0565145622919173,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999900070995136,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.12924585863947868,
|
|
"num_tokens": 1863383.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.300161933898925,
|
|
"epoch": 0.05679433735276838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999758199023239,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.11939030215144157,
|
|
"num_tokens": 1872798.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.0971071243286135,
|
|
"epoch": 0.05707411241361945,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004999554648793858,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.13786051496863366,
|
|
"num_tokens": 1881698.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.258518314361572,
|
|
"epoch": 0.057353887474470525,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999289425887425,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.1295467123389244,
|
|
"num_tokens": 1890771.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.1218438148498535,
|
|
"epoch": 0.0576336625353216,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998962537575161,
|
|
"loss": 6.146,
|
|
"mean_token_accuracy": 0.12477104216814042,
|
|
"num_tokens": 1900278.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.2131085872650145,
|
|
"epoch": 0.05791343759617268,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998573992818874,
|
|
"loss": 6.2207,
|
|
"mean_token_accuracy": 0.13374545723199843,
|
|
"num_tokens": 1909374.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.18338713645935,
|
|
"epoch": 0.058193212657023756,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998123802270715,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.12723272889852524,
|
|
"num_tokens": 1917854.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.129993343353272,
|
|
"epoch": 0.058472987717874826,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004997611978272886,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.13106875866651535,
|
|
"num_tokens": 1926720.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.179345941543579,
|
|
"epoch": 0.0587527627787259,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997038534857298,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.1277387872338295,
|
|
"num_tokens": 1936803.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.182669401168823,
|
|
"epoch": 0.05903253783957698,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996403487745194,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.12981212735176087,
|
|
"num_tokens": 1946862.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.160896635055542,
|
|
"epoch": 0.05931231290042806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499570685434671,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.1319658190011978,
|
|
"num_tokens": 1956321.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.227955532073975,
|
|
"epoch": 0.059592087961279135,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994948653760405,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.13851428404450417,
|
|
"num_tokens": 1964784.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.041449022293091,
|
|
"epoch": 0.059871863022130205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994128906772729,
|
|
"loss": 6.0906,
|
|
"mean_token_accuracy": 0.13081432059407233,
|
|
"num_tokens": 1973918.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.093364238739014,
|
|
"epoch": 0.06015163808298128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499324763585746,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.13375769481062888,
|
|
"num_tokens": 1983252.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.210244464874267,
|
|
"epoch": 0.06043141314383236,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992304865175085,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.1372748613357544,
|
|
"num_tokens": 1991780.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.143740892410278,
|
|
"epoch": 0.060711188204683436,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991300620572138,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.12712325975298883,
|
|
"num_tokens": 2000620.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.2204633235931395,
|
|
"epoch": 0.06099096326553451,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990234929580494,
|
|
"loss": 6.1862,
|
|
"mean_token_accuracy": 0.12817292883992196,
|
|
"num_tokens": 2009193.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.248979568481445,
|
|
"epoch": 0.06127073832638558,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989107821416609,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.12865378484129905,
|
|
"num_tokens": 2019205.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.089492607116699,
|
|
"epoch": 0.06155051338723666,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987919326980723,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.12822083830833436,
|
|
"num_tokens": 2028613.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.210154104232788,
|
|
"epoch": 0.06183028844808774,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986669478856011,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.13177741691470146,
|
|
"num_tokens": 2037056.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.141370105743408,
|
|
"epoch": 0.062110063508938815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985358311307688,
|
|
"loss": 6.0923,
|
|
"mean_token_accuracy": 0.12338809072971343,
|
|
"num_tokens": 2046192.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.162001132965088,
|
|
"epoch": 0.06238983856978989,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983985860282081,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.1320735476911068,
|
|
"num_tokens": 2055290.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.185983371734619,
|
|
"epoch": 0.06266961363064097,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982552163405623,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.1298999786376953,
|
|
"num_tokens": 2064005.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.259249210357666,
|
|
"epoch": 0.06294938869149204,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981057259983839,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.13146117553114892,
|
|
"num_tokens": 2073362.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.084898853302002,
|
|
"epoch": 0.06322916375234311,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004979501191000262,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.1346506245434284,
|
|
"num_tokens": 2084147.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.200892496109009,
|
|
"epoch": 0.0635089388131942,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004977883999115311,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.13276908472180365,
|
|
"num_tokens": 2092935.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.094279527664185,
|
|
"epoch": 0.06378871387404526,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004976205728665113,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.12623411193490028,
|
|
"num_tokens": 2102171.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.0519288063049315,
|
|
"epoch": 0.06406848893489635,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974466425660307,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.12940095067024232,
|
|
"num_tokens": 2111058.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.045443391799926,
|
|
"epoch": 0.06434826399574742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972666137784759,
|
|
"loss": 6.1107,
|
|
"mean_token_accuracy": 0.12719337344169618,
|
|
"num_tokens": 2121625.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.138291120529175,
|
|
"epoch": 0.06462803905659849,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970804914394271,
|
|
"loss": 6.1483,
|
|
"mean_token_accuracy": 0.13135300874710082,
|
|
"num_tokens": 2130579.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.1703227996826175,
|
|
"epoch": 0.06490781411744957,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968882806515225,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.13054983094334602,
|
|
"num_tokens": 2139740.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.054456043243408,
|
|
"epoch": 0.06518758917830064,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966899866843177,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.1341743990778923,
|
|
"num_tokens": 2148979.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.132187175750732,
|
|
"epoch": 0.06546736423915173,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000496485614974142,
|
|
"loss": 6.0834,
|
|
"mean_token_accuracy": 0.13612435460090638,
|
|
"num_tokens": 2158763.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 5.968607091903687,
|
|
"epoch": 0.0657471393000028,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962751711239492,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.13252341449260713,
|
|
"num_tokens": 2167467.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.1014035701751705,
|
|
"epoch": 0.06602691436085387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960586609031636,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.1407083511352539,
|
|
"num_tokens": 2176301.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.166369771957397,
|
|
"epoch": 0.06630668942170495,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958360902475224,
|
|
"loss": 6.1894,
|
|
"mean_token_accuracy": 0.12619131281971932,
|
|
"num_tokens": 2186573.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.072562885284424,
|
|
"epoch": 0.06658646448255602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956074652589125,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.13995079696178436,
|
|
"num_tokens": 2196103.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.144318675994873,
|
|
"epoch": 0.0668662395434071,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953727922052035,
|
|
"loss": 6.1884,
|
|
"mean_token_accuracy": 0.1341054804623127,
|
|
"num_tokens": 2205054.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.119494533538818,
|
|
"epoch": 0.06714601460425818,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004951320775200756,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.13546809777617455,
|
|
"num_tokens": 2214393.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.104378938674927,
|
|
"epoch": 0.06742578966510925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004948853278028436,
|
|
"loss": 6.0984,
|
|
"mean_token_accuracy": 0.13463159203529357,
|
|
"num_tokens": 2223156.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 5.997931098937988,
|
|
"epoch": 0.06770556472596033,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004946325498182755,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.14642671197652818,
|
|
"num_tokens": 2232615.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.989495754241943,
|
|
"epoch": 0.0679853397868114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004943737504964076,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.13626188561320304,
|
|
"num_tokens": 2241861.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.171738052368164,
|
|
"epoch": 0.06826511484766248,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000494108936932354,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.13429959192872049,
|
|
"num_tokens": 2250560.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.999643325805664,
|
|
"epoch": 0.06854488990851355,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938381163861124,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.13456141278147699,
|
|
"num_tokens": 2259886.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.037774181365966,
|
|
"epoch": 0.06882466496936462,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004935612962823645,
|
|
"loss": 6.0568,
|
|
"mean_token_accuracy": 0.13611846044659615,
|
|
"num_tokens": 2269164.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.075514221191407,
|
|
"epoch": 0.06910444003021571,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004932784842102739,
|
|
"loss": 6.0526,
|
|
"mean_token_accuracy": 0.13547588810324668,
|
|
"num_tokens": 2279249.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 5.919833517074585,
|
|
"epoch": 0.06938421509106678,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004929896879232758,
|
|
"loss": 5.9801,
|
|
"mean_token_accuracy": 0.13657484874129294,
|
|
"num_tokens": 2288718.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.145425939559937,
|
|
"epoch": 0.06966399015191786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004926949153388668,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.12783288657665254,
|
|
"num_tokens": 2298229.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.909711217880249,
|
|
"epoch": 0.06994376521276893,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004923941745383859,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.13935036435723305,
|
|
"num_tokens": 2306653.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 5.887778854370117,
|
|
"epoch": 0.07022354027362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492087473766794,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.13955688923597337,
|
|
"num_tokens": 2315208.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.065791368484497,
|
|
"epoch": 0.07050331533447109,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000491774821432448,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.130626330524683,
|
|
"num_tokens": 2324961.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.033606243133545,
|
|
"epoch": 0.07078309039532216,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004914562261068693,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.13088881224393845,
|
|
"num_tokens": 2334256.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.069367837905884,
|
|
"epoch": 0.07106286545617324,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004911316965245098,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.1418687731027603,
|
|
"num_tokens": 2343492.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.121695137023925,
|
|
"epoch": 0.07134264051702431,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000490801241582512,
|
|
"loss": 6.0167,
|
|
"mean_token_accuracy": 0.1412626601755619,
|
|
"num_tokens": 2352727.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 5.919157314300537,
|
|
"epoch": 0.07162241557787538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000490464870340465,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.13838816434144974,
|
|
"num_tokens": 2360636.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.9637549877166744,
|
|
"epoch": 0.07190219063872647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901225920201563,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.13623869940638542,
|
|
"num_tokens": 2370125.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.089365005493164,
|
|
"epoch": 0.07218196569957754,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000489774416005319,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.1390392377972603,
|
|
"num_tokens": 2379304.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.113597965240478,
|
|
"epoch": 0.07246174076042862,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004894203518413742,
|
|
"loss": 6.09,
|
|
"mean_token_accuracy": 0.13678146675229072,
|
|
"num_tokens": 2387675.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.936979913711548,
|
|
"epoch": 0.07274151582127969,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004890604092351701,
|
|
"loss": 5.8828,
|
|
"mean_token_accuracy": 0.14058420360088347,
|
|
"num_tokens": 2397864.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.052834844589233,
|
|
"epoch": 0.07302129088213077,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000488694598054715,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1325170412659645,
|
|
"num_tokens": 2407331.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.074975156784058,
|
|
"epoch": 0.07330106594298184,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004883229283289071,
|
|
"loss": 6.1352,
|
|
"mean_token_accuracy": 0.13703541383147239,
|
|
"num_tokens": 2416223.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.142674922943115,
|
|
"epoch": 0.07358084100383291,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048794541024725993,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.13307311311364173,
|
|
"num_tokens": 2425613.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.002810144424439,
|
|
"epoch": 0.073860616064684,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004875620541596221,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.13989573642611502,
|
|
"num_tokens": 2435113.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.066500616073609,
|
|
"epoch": 0.07414039112553507,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048717287057589454,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.12933120951056482,
|
|
"num_tokens": 2445220.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.000797414779663,
|
|
"epoch": 0.07442016618638615,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004867778701657417,
|
|
"loss": 5.9754,
|
|
"mean_token_accuracy": 0.1440178468823433,
|
|
"num_tokens": 2454018.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.96698956489563,
|
|
"epoch": 0.07469994124723722,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048637706375829955,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.1343780502676964,
|
|
"num_tokens": 2462697.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.981861972808838,
|
|
"epoch": 0.07497971630808829,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000485970462341878,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14209071397781373,
|
|
"num_tokens": 2470955.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.978409051895142,
|
|
"epoch": 0.07525949136893938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048555807706366044,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.1370713584125042,
|
|
"num_tokens": 2481289.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.006068325042724,
|
|
"epoch": 0.07553926642979045,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048513991922939756,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.13935732543468476,
|
|
"num_tokens": 2490211.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.96335654258728,
|
|
"epoch": 0.07581904149064153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048471600030309744,
|
|
"loss": 5.9392,
|
|
"mean_token_accuracy": 0.1420755535364151,
|
|
"num_tokens": 2499427.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 5.9545855045318605,
|
|
"epoch": 0.0760988165514926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048428633190671186,
|
|
"loss": 6.0577,
|
|
"mean_token_accuracy": 0.14104050919413566,
|
|
"num_tokens": 2508949.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.962803792953491,
|
|
"epoch": 0.07637859161234367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004838509258198167,
|
|
"loss": 6.062,
|
|
"mean_token_accuracy": 0.13880110532045364,
|
|
"num_tokens": 2518095.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.13924994468689,
|
|
"epoch": 0.07665836667319476,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048340979397929,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.136734339594841,
|
|
"num_tokens": 2527117.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.99510087966919,
|
|
"epoch": 0.07693814173404583,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048296294847898386,
|
|
"loss": 5.9141,
|
|
"mean_token_accuracy": 0.13932174667716027,
|
|
"num_tokens": 2536279.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.921843957901001,
|
|
"epoch": 0.07721791679489691,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004825104015693934,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.14011373966932297,
|
|
"num_tokens": 2545626.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.997140789031983,
|
|
"epoch": 0.07749769185574798,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004820521656573208,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.14312618374824523,
|
|
"num_tokens": 2555344.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.960200071334839,
|
|
"epoch": 0.07777746691659905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048158825330553505,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.13562597557902337,
|
|
"num_tokens": 2563585.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.02376651763916,
|
|
"epoch": 0.07805724197745013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048111867723242763,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.13781619295477868,
|
|
"num_tokens": 2574271.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.9488640308380125,
|
|
"epoch": 0.0783370170383012,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004806434503116637,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.14232801273465157,
|
|
"num_tokens": 2583403.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.033678197860718,
|
|
"epoch": 0.07861679209915229,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004801625855718296,
|
|
"loss": 5.9564,
|
|
"mean_token_accuracy": 0.14341139122843743,
|
|
"num_tokens": 2592821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.933608961105347,
|
|
"epoch": 0.07889656716000336,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047967609619607477,
|
|
"loss": 5.9287,
|
|
"mean_token_accuracy": 0.14294352680444716,
|
|
"num_tokens": 2600722.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.951407432556152,
|
|
"epoch": 0.07917634222085443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004791839955217513,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.14061676412820817,
|
|
"num_tokens": 2610247.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.868547248840332,
|
|
"epoch": 0.07945611728170551,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047868629704004786,
|
|
"loss": 5.8516,
|
|
"mean_token_accuracy": 0.14847285747528077,
|
|
"num_tokens": 2619910.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.010308027267456,
|
|
"epoch": 0.07973589234255658,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047818301439561965,
|
|
"loss": 5.8662,
|
|
"mean_token_accuracy": 0.14154235720634462,
|
|
"num_tokens": 2630305.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.946945381164551,
|
|
"epoch": 0.08001566740340767,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047767416138621454,
|
|
"loss": 5.9705,
|
|
"mean_token_accuracy": 0.13330617398023606,
|
|
"num_tokens": 2640384.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.914110374450684,
|
|
"epoch": 0.08029544246425874,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477159751962295,
|
|
"loss": 5.9532,
|
|
"mean_token_accuracy": 0.14388398304581643,
|
|
"num_tokens": 2649581.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.905755853652954,
|
|
"epoch": 0.08057521752510981,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047663980022665507,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.14454542994499206,
|
|
"num_tokens": 2657869.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.033972454071045,
|
|
"epoch": 0.08085499258596089,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047611432043403437,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.14180536717176437,
|
|
"num_tokens": 2668168.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.979730415344238,
|
|
"epoch": 0.08113476764681196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004755833269907267,
|
|
"loss": 5.9536,
|
|
"mean_token_accuracy": 0.13616828471422196,
|
|
"num_tokens": 2677186.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.9653160572052,
|
|
"epoch": 0.08141454270766305,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004750468344541857,
|
|
"loss": 5.9105,
|
|
"mean_token_accuracy": 0.14514605104923248,
|
|
"num_tokens": 2686190.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.8910928726196286,
|
|
"epoch": 0.08169431776851412,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047450485753262525,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.14269855469465256,
|
|
"num_tokens": 2694934.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.835767793655395,
|
|
"epoch": 0.08197409282936519,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047395741108461633,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.14919260144233704,
|
|
"num_tokens": 2703279.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.912254762649536,
|
|
"epoch": 0.08225386789021627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047340451011867985,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.1445097081363201,
|
|
"num_tokens": 2712403.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.985236167907715,
|
|
"epoch": 0.08253364295106734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047284616979287515,
|
|
"loss": 5.8784,
|
|
"mean_token_accuracy": 0.14578445255756378,
|
|
"num_tokens": 2721136.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.843273448944092,
|
|
"epoch": 0.08281341801191842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047228240541438433,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.1495327726006508,
|
|
"num_tokens": 2730539.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.872775030136109,
|
|
"epoch": 0.0830931930727695,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047171323243909257,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.14278722032904625,
|
|
"num_tokens": 2740412.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.952418088912964,
|
|
"epoch": 0.08337296813362056,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047113866647116457,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.14550314098596573,
|
|
"num_tokens": 2749763.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.902268743515014,
|
|
"epoch": 0.08365274319447165,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004705587232626164,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.14427887573838233,
|
|
"num_tokens": 2758399.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.904958009719849,
|
|
"epoch": 0.08393251825532272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046997341871288424,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.14721864312887192,
|
|
"num_tokens": 2767806.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.940085363388062,
|
|
"epoch": 0.0842122933161738,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004693827688683879,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.14912354052066804,
|
|
"num_tokens": 2776697.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.986412858963012,
|
|
"epoch": 0.08449206837702487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004687867899220914,
|
|
"loss": 6.0513,
|
|
"mean_token_accuracy": 0.1391066186130047,
|
|
"num_tokens": 2786546.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.869002628326416,
|
|
"epoch": 0.08477184343787594,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046818549821305846,
|
|
"loss": 5.7888,
|
|
"mean_token_accuracy": 0.15096474960446357,
|
|
"num_tokens": 2794960.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.829828214645386,
|
|
"epoch": 0.08505161849872703,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046757891022600494,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.14856993556022643,
|
|
"num_tokens": 2804126.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.918961811065674,
|
|
"epoch": 0.0853313935595781,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004669670425908471,
|
|
"loss": 5.8175,
|
|
"mean_token_accuracy": 0.14590021967887878,
|
|
"num_tokens": 2812853.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.766618728637695,
|
|
"epoch": 0.08561116862042918,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004663499120822451,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.1575191080570221,
|
|
"num_tokens": 2821812.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.8912958145141605,
|
|
"epoch": 0.08589094368128025,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004657275356191437,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.1414273500442505,
|
|
"num_tokens": 2831657.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.941652011871338,
|
|
"epoch": 0.08617071874213132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046509993026430804,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.1418527767062187,
|
|
"num_tokens": 2841496.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.967176198959351,
|
|
"epoch": 0.0864504938029824,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004644671132238558,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.14426299482583999,
|
|
"num_tokens": 2850984.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.774064016342163,
|
|
"epoch": 0.08673026886383348,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046382910184678585,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.14789169430732726,
|
|
"num_tokens": 2859682.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.936661148071289,
|
|
"epoch": 0.08701004392468456,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004631859136245025,
|
|
"loss": 5.925,
|
|
"mean_token_accuracy": 0.14146076440811156,
|
|
"num_tokens": 2868652.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.8458904266357425,
|
|
"epoch": 0.08728981898553563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004625375661903357,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.1500212162733078,
|
|
"num_tokens": 2878151.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.714489269256592,
|
|
"epoch": 0.0875695940463867,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046188407731905787,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.1576072409749031,
|
|
"num_tokens": 2887171.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.947921180725098,
|
|
"epoch": 0.08784936910723778,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046122546492639643,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.14779970645904542,
|
|
"num_tokens": 2896217.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.8732991218566895,
|
|
"epoch": 0.08812914416808885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000460561747068543,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.14265499711036683,
|
|
"num_tokens": 2905272.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.916759490966797,
|
|
"epoch": 0.08840891922893994,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004598929419416578,
|
|
"loss": 5.8228,
|
|
"mean_token_accuracy": 0.14375049173831939,
|
|
"num_tokens": 2914297.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.826504182815552,
|
|
"epoch": 0.08868869428979101,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045921906788137123,
|
|
"loss": 5.8364,
|
|
"mean_token_accuracy": 0.147948782145977,
|
|
"num_tokens": 2922872.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.880048561096191,
|
|
"epoch": 0.08896846935064208,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045854014336228115,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.14824217110872268,
|
|
"num_tokens": 2932316.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.904519987106323,
|
|
"epoch": 0.08924824441149316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045785618699744615,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.14554950594902039,
|
|
"num_tokens": 2942041.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.872646474838257,
|
|
"epoch": 0.08952801947234423,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045716721753787543,
|
|
"loss": 5.8871,
|
|
"mean_token_accuracy": 0.14541386142373086,
|
|
"num_tokens": 2951726.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.891257953643799,
|
|
"epoch": 0.08980779453319532,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004564732538720148,
|
|
"loss": 5.8248,
|
|
"mean_token_accuracy": 0.1563461571931839,
|
|
"num_tokens": 2961008.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.745857095718383,
|
|
"epoch": 0.09008756959404639,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045577431502522877,
|
|
"loss": 5.7829,
|
|
"mean_token_accuracy": 0.15594240054488182,
|
|
"num_tokens": 2970007.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.933908319473266,
|
|
"epoch": 0.09036734465489746,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004550704201592787,
|
|
"loss": 5.9097,
|
|
"mean_token_accuracy": 0.14012961015105246,
|
|
"num_tokens": 2979060.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.837322330474853,
|
|
"epoch": 0.09064711971574854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004543615885717981,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.15124776661396028,
|
|
"num_tokens": 2987902.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.794670820236206,
|
|
"epoch": 0.09092689477659961,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045364783969576296,
|
|
"loss": 5.7841,
|
|
"mean_token_accuracy": 0.15281061828136444,
|
|
"num_tokens": 2996427.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.938097763061523,
|
|
"epoch": 0.0912066698374507,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004529291930989592,
|
|
"loss": 5.9298,
|
|
"mean_token_accuracy": 0.14550916701555253,
|
|
"num_tokens": 3005579.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.839151525497437,
|
|
"epoch": 0.09148644489830177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004522056684834464,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.14142662063241004,
|
|
"num_tokens": 3014625.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.845537948608398,
|
|
"epoch": 0.09176621995915284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004514772856850173,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.15203074961900712,
|
|
"num_tokens": 3023806.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.958638095855713,
|
|
"epoch": 0.09204599502000392,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004507440646726542,
|
|
"loss": 5.8805,
|
|
"mean_token_accuracy": 0.14775419160723685,
|
|
"num_tokens": 3033731.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.848289918899536,
|
|
"epoch": 0.09232577008085499,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004500060255479818,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.15215797871351242,
|
|
"num_tokens": 3042264.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.851382160186768,
|
|
"epoch": 0.09260554514170607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004492631885447151,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.1552473321557045,
|
|
"num_tokens": 3051400.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.8827508926391605,
|
|
"epoch": 0.09288532020255715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044851557402810616,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.14523063153028487,
|
|
"num_tokens": 3061509.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.831000280380249,
|
|
"epoch": 0.09316509526340822,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044776320249438444,
|
|
"loss": 5.7975,
|
|
"mean_token_accuracy": 0.1502298593521118,
|
|
"num_tokens": 3070318.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.940295314788818,
|
|
"epoch": 0.0934448703242593,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044700609457019565,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.14855741560459138,
|
|
"num_tokens": 3079429.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.8560706615448,
|
|
"epoch": 0.09372464538511037,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004462442710120359,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.14453537240624428,
|
|
"num_tokens": 3088500.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.8202159881591795,
|
|
"epoch": 0.09400442044596145,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000445477752705683,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.15873004794120787,
|
|
"num_tokens": 3096773.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.865380382537841,
|
|
"epoch": 0.09428419550681252,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044470656066562336,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.1546894833445549,
|
|
"num_tokens": 3105790.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.847274351119995,
|
|
"epoch": 0.0945639705676636,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004439307160344765,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.14811273217201232,
|
|
"num_tokens": 3114771.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.755411386489868,
|
|
"epoch": 0.09484374562851468,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044315024008241473,
|
|
"loss": 5.7518,
|
|
"mean_token_accuracy": 0.1524191528558731,
|
|
"num_tokens": 3123910.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.929304456710815,
|
|
"epoch": 0.09512352068936575,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004423651542065806,
|
|
"loss": 5.9395,
|
|
"mean_token_accuracy": 0.14688817262649537,
|
|
"num_tokens": 3132768.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.849935054779053,
|
|
"epoch": 0.09540329575021683,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044157547993050006,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.14470150023698808,
|
|
"num_tokens": 3142756.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.984419918060302,
|
|
"epoch": 0.0956830708110679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044078123890349227,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.13943962305784224,
|
|
"num_tokens": 3152669.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.865299320220947,
|
|
"epoch": 0.09596284587191897,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043998245290007606,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.1498618744313717,
|
|
"num_tokens": 3161543.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.7853340148925785,
|
|
"epoch": 0.09624262093277006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043917914381937323,
|
|
"loss": 5.7204,
|
|
"mean_token_accuracy": 0.15875888466835023,
|
|
"num_tokens": 3170005.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.8889477252960205,
|
|
"epoch": 0.09652239599362113,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043837133368450815,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.15774014294147493,
|
|
"num_tokens": 3178523.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.762332582473755,
|
|
"epoch": 0.09680217105447221,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004375590446420037,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.15568190366029738,
|
|
"num_tokens": 3186862.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.808806610107422,
|
|
"epoch": 0.09708194611532328,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004367422989611743,
|
|
"loss": 5.8177,
|
|
"mean_token_accuracy": 0.14879435077309608,
|
|
"num_tokens": 3195507.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.814892578125,
|
|
"epoch": 0.09736172117617435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004359211190335153,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.1576648697257042,
|
|
"num_tokens": 3205063.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.857382678985596,
|
|
"epoch": 0.09764149623702544,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043509552737208923,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.1520813412964344,
|
|
"num_tokens": 3214797.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.891229486465454,
|
|
"epoch": 0.0979212712978765,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043426554661090853,
|
|
"loss": 5.8293,
|
|
"mean_token_accuracy": 0.14855243861675263,
|
|
"num_tokens": 3223923.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.783728313446045,
|
|
"epoch": 0.09820104635872759,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043343119950431516,
|
|
"loss": 5.7031,
|
|
"mean_token_accuracy": 0.1542630076408386,
|
|
"num_tokens": 3232975.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.7834454536437985,
|
|
"epoch": 0.09848082141957866,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043259250892635644,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.15687773674726485,
|
|
"num_tokens": 3242196.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.874407386779785,
|
|
"epoch": 0.09876059648042973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004317494978701582,
|
|
"loss": 5.7765,
|
|
"mean_token_accuracy": 0.15025516897439956,
|
|
"num_tokens": 3251248.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.869711256027221,
|
|
"epoch": 0.09904037154128081,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004309021894472943,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14714980125427246,
|
|
"num_tokens": 3260195.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.891108465194702,
|
|
"epoch": 0.09932014660213188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004300506068871534,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.1442213699221611,
|
|
"num_tokens": 3270222.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.77832818031311,
|
|
"epoch": 0.09959992166298297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042919477353630135,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15076944306492807,
|
|
"num_tokens": 3278820.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.884161472320557,
|
|
"epoch": 0.09987969672383404,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000428334712857842,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.15692438632249833,
|
|
"num_tokens": 3288100.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.828272151947021,
|
|
"epoch": 0.10015947178468511,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042747044843077304,
|
|
"loss": 5.8622,
|
|
"mean_token_accuracy": 0.15525175929069518,
|
|
"num_tokens": 3297072.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.886663436889648,
|
|
"epoch": 0.10043924684553619,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00042660200394934047,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.15353555828332902,
|
|
"num_tokens": 3307118.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.896843290328979,
|
|
"epoch": 0.10071902190638726,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042572940322238844,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.15529625564813615,
|
|
"num_tokens": 3317168.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.82907190322876,
|
|
"epoch": 0.10099879696723835,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042485267017270664,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.15322525203227996,
|
|
"num_tokens": 3325997.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.7322102069854735,
|
|
"epoch": 0.10127857202808942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004239718288363745,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.15010084211826324,
|
|
"num_tokens": 3335911.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.804552745819092,
|
|
"epoch": 0.10155834708894049,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004230869033621023,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.14746056646108627,
|
|
"num_tokens": 3345910.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.685170221328735,
|
|
"epoch": 0.10183812214979157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004221979180105688,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.15606738328933717,
|
|
"num_tokens": 3355076.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.978805017471314,
|
|
"epoch": 0.10211789721064264,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042130489715375645,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.1493694469332695,
|
|
"num_tokens": 3364029.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.904508972167969,
|
|
"epoch": 0.10239767227149373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042040786527428335,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.15003095120191573,
|
|
"num_tokens": 3373010.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.8470189571380615,
|
|
"epoch": 0.1026774473323448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004195068469647315,
|
|
"loss": 5.7774,
|
|
"mean_token_accuracy": 0.15928260385990142,
|
|
"num_tokens": 3381690.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.757124423980713,
|
|
"epoch": 0.10295722239319587,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041860186692697297,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14969682320952415,
|
|
"num_tokens": 3392589.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.877426481246948,
|
|
"epoch": 0.10323699745404695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041769294997149264,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.1540641151368618,
|
|
"num_tokens": 3401099.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.998667240142822,
|
|
"epoch": 0.10351677251489802,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004167801210167081,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.14992498010396957,
|
|
"num_tokens": 3409802.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.82662444114685,
|
|
"epoch": 0.1037965475757491,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004158634050882861,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.15522693246603012,
|
|
"num_tokens": 3419189.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.671156597137451,
|
|
"epoch": 0.10407632263660017,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004149428273184569,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.15602488368749617,
|
|
"num_tokens": 3428867.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.9138130187988285,
|
|
"epoch": 0.10435609769745124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004140184129453253,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.15095819532871246,
|
|
"num_tokens": 3437739.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.779176378250122,
|
|
"epoch": 0.10463587275830233,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000413090187312178,
|
|
"loss": 5.7608,
|
|
"mean_token_accuracy": 0.1563764899969101,
|
|
"num_tokens": 3446673.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.898364496231079,
|
|
"epoch": 0.1049156478191534,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004121581758667898,
|
|
"loss": 5.8631,
|
|
"mean_token_accuracy": 0.14789247065782546,
|
|
"num_tokens": 3455877.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.761175918579101,
|
|
"epoch": 0.10519542288000448,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041122240416072533,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.15582992881536484,
|
|
"num_tokens": 3465306.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.758784818649292,
|
|
"epoch": 0.10547519794085555,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004102828978486385,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.1611683338880539,
|
|
"num_tokens": 3473784.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.922667503356934,
|
|
"epoch": 0.10575497300170662,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004093396826875695,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.15390021204948426,
|
|
"num_tokens": 3482843.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.8461333274841305,
|
|
"epoch": 0.10603474806255771,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040839278453623837,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.1522120788693428,
|
|
"num_tokens": 3491881.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.850742673873901,
|
|
"epoch": 0.10631452312340878,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004074422293543363,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.15194423794746398,
|
|
"num_tokens": 3500968.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.891610479354858,
|
|
"epoch": 0.10659429818425986,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004064880432018137,
|
|
"loss": 5.8654,
|
|
"mean_token_accuracy": 0.14877980351448059,
|
|
"num_tokens": 3510248.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.786740350723266,
|
|
"epoch": 0.10687407324511093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040553025223816615,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.1558419570326805,
|
|
"num_tokens": 3519750.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.762371587753296,
|
|
"epoch": 0.107153848305962,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040456888272171653,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.15853289812803267,
|
|
"num_tokens": 3527626.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.803076457977295,
|
|
"epoch": 0.10743362336681309,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040360396100889577,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.15330557376146317,
|
|
"num_tokens": 3537574.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.85295467376709,
|
|
"epoch": 0.10771339842766416,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004026355135535202,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1514697104692459,
|
|
"num_tokens": 3546305.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.8903913497924805,
|
|
"epoch": 0.10799317348851524,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000401663566906066,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.14438902512192725,
|
|
"num_tokens": 3556054.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.753151321411133,
|
|
"epoch": 0.10827294854936631,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040068814771294134,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15991320312023163,
|
|
"num_tokens": 3566156.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.640224361419678,
|
|
"epoch": 0.10855272361021738,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003997092827157562,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.1592881053686142,
|
|
"num_tokens": 3575176.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.9109299659729,
|
|
"epoch": 0.10883249867106846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000398726998750589,
|
|
"loss": 5.7892,
|
|
"mean_token_accuracy": 0.14814456030726433,
|
|
"num_tokens": 3585112.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.81527042388916,
|
|
"epoch": 0.10911227373191953,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039774132274725076,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.15033237636089325,
|
|
"num_tokens": 3594468.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.7505429744720455,
|
|
"epoch": 0.10939204879277062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039675228172854707,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.15946809947490692,
|
|
"num_tokens": 3603449.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.758810758590698,
|
|
"epoch": 0.10967182385362169,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003957599028095371,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.1498391680419445,
|
|
"num_tokens": 3612366.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.759896230697632,
|
|
"epoch": 0.10995159891447276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039476421319679017,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.1582018181681633,
|
|
"num_tokens": 3620466.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.775796556472779,
|
|
"epoch": 0.11023137397532384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039376524018764,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.15230363309383393,
|
|
"num_tokens": 3629424.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.776160955429077,
|
|
"epoch": 0.11051114903617491,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039276301116943616,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15213821083307266,
|
|
"num_tokens": 3638044.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.706624269485474,
|
|
"epoch": 0.110790924097026,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003917575536187936,
|
|
"loss": 5.73,
|
|
"mean_token_accuracy": 0.15515266135334968,
|
|
"num_tokens": 3647239.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.923574304580688,
|
|
"epoch": 0.11107069915787707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039074889510083894,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.15231991186738014,
|
|
"num_tokens": 3655729.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.84725513458252,
|
|
"epoch": 0.11135047421872814,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038973706326845495,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.150700543820858,
|
|
"num_tokens": 3665155.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.871934032440185,
|
|
"epoch": 0.11163024927957922,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003887220858615225,
|
|
"loss": 5.6854,
|
|
"mean_token_accuracy": 0.16067851781845094,
|
|
"num_tokens": 3673169.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.788043260574341,
|
|
"epoch": 0.11191002434043029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003877039907061597,
|
|
"loss": 5.814,
|
|
"mean_token_accuracy": 0.15419328063726426,
|
|
"num_tokens": 3683026.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.849886798858643,
|
|
"epoch": 0.11218979940128138,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003866828057139598,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.1491822436451912,
|
|
"num_tokens": 3692224.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.8027088165283205,
|
|
"epoch": 0.11246957446213245,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038565855888122503,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.15009186267852784,
|
|
"num_tokens": 3701326.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.8045741558074955,
|
|
"epoch": 0.11274934952298352,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038463127828819975,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.15352987349033356,
|
|
"num_tokens": 3710378.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.675677824020386,
|
|
"epoch": 0.1130291245838346,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038360099209830043,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.16326209753751755,
|
|
"num_tokens": 3719180.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.769056510925293,
|
|
"epoch": 0.11330889964468567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003825677285573433,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.15641107112169267,
|
|
"num_tokens": 3728197.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.89308614730835,
|
|
"epoch": 0.11358867470553675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038153151599277027,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.15505644381046296,
|
|
"num_tokens": 3737071.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.7944704532623295,
|
|
"epoch": 0.11386844976638782,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003804923828128723,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.1559743769466877,
|
|
"num_tokens": 3746103.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.84677095413208,
|
|
"epoch": 0.1141482248272389,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003794503575060104,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.15347915440797805,
|
|
"num_tokens": 3755377.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.6923786163330075,
|
|
"epoch": 0.11442799988808998,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037840546863983484,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.16136836856603623,
|
|
"num_tokens": 3763377.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.765568780899048,
|
|
"epoch": 0.11470777494894105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003773577448605015,
|
|
"loss": 5.6878,
|
|
"mean_token_accuracy": 0.1577932521700859,
|
|
"num_tokens": 3772927.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.8939320087432865,
|
|
"epoch": 0.11498755000979213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003763072148918872,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.1535826176404953,
|
|
"num_tokens": 3781809.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.765517473220825,
|
|
"epoch": 0.1152673250706432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003752539075348017,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.14945023581385614,
|
|
"num_tokens": 3791551.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.694364881515503,
|
|
"epoch": 0.11554710013149427,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037419785166619817,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.15597922652959822,
|
|
"num_tokens": 3799860.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.730410051345825,
|
|
"epoch": 0.11582687519234536,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003731390762383818,
|
|
"loss": 5.6196,
|
|
"mean_token_accuracy": 0.15803190171718598,
|
|
"num_tokens": 3808754.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.826288557052612,
|
|
"epoch": 0.11610665025319643,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003720776102782158,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.16269149631261826,
|
|
"num_tokens": 3817213.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.654380369186401,
|
|
"epoch": 0.11638642531404751,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037101348288632555,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.16024026721715928,
|
|
"num_tokens": 3826675.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.75474362373352,
|
|
"epoch": 0.11666620037489858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003699467232363012,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.15936376452445983,
|
|
"num_tokens": 3835127.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.769831371307373,
|
|
"epoch": 0.11694597543574965,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003688773605738973,
|
|
"loss": 5.8009,
|
|
"mean_token_accuracy": 0.14795432686805726,
|
|
"num_tokens": 3844467.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.769893980026245,
|
|
"epoch": 0.11722575049660074,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00036780542421623134,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.16054756790399552,
|
|
"num_tokens": 3853150.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.726003122329712,
|
|
"epoch": 0.1175055255574518,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003667309435509802,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.1651451990008354,
|
|
"num_tokens": 3861180.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.702756595611572,
|
|
"epoch": 0.11778530061830289,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003656539480355741,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.15809597373008727,
|
|
"num_tokens": 3870303.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.732271432876587,
|
|
"epoch": 0.11806507567915396,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003645744671963891,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.16051075458526612,
|
|
"num_tokens": 3879515.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.717753219604492,
|
|
"epoch": 0.11834485074000503,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003634925306279376,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.16357103139162063,
|
|
"num_tokens": 3887989.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.647048997879028,
|
|
"epoch": 0.11862462580085611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003624081679920574,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.1672131136059761,
|
|
"num_tokens": 3897071.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.666443967819214,
|
|
"epoch": 0.11890440086170719,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003613214090170977,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.1648178890347481,
|
|
"num_tokens": 3906058.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.802386808395386,
|
|
"epoch": 0.11918417592255827,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003602322834971048,
|
|
"loss": 5.6706,
|
|
"mean_token_accuracy": 0.15836320966482162,
|
|
"num_tokens": 3915027.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.6676342487335205,
|
|
"epoch": 0.11946395098340934,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003591408212910051,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.16593797653913497,
|
|
"num_tokens": 3924357.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.754116821289062,
|
|
"epoch": 0.11974372604426041,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003580470523217863,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.15829661935567857,
|
|
"num_tokens": 3933823.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.814476156234742,
|
|
"epoch": 0.1200235011051115,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003569510065756771,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.15345691293478012,
|
|
"num_tokens": 3942448.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.800265693664551,
|
|
"epoch": 0.12030327616596256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003558527141013254,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1527173787355423,
|
|
"num_tokens": 3952026.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.791549158096314,
|
|
"epoch": 0.12058305122681365,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003547522050089742,
|
|
"loss": 5.7546,
|
|
"mean_token_accuracy": 0.14622100368142127,
|
|
"num_tokens": 3963502.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.695604372024536,
|
|
"epoch": 0.12086282628766472,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00035364950946963606,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.16379044502973555,
|
|
"num_tokens": 3972080.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.683828544616699,
|
|
"epoch": 0.12114260134851579,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003525446577142663,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.154899001121521,
|
|
"num_tokens": 3981987.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.77276644706726,
|
|
"epoch": 0.12142237640936687,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00035143768003293395,
|
|
"loss": 5.6798,
|
|
"mean_token_accuracy": 0.15419003069400788,
|
|
"num_tokens": 3991165.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.69476056098938,
|
|
"epoch": 0.12170215147021794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003503286067739913,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.15938421711325645,
|
|
"num_tokens": 4001237.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.732597780227661,
|
|
"epoch": 0.12198192653106903,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00034921746834324193,
|
|
"loss": 5.6344,
|
|
"mean_token_accuracy": 0.16024436950683593,
|
|
"num_tokens": 4010457.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.731549692153931,
|
|
"epoch": 0.1222617015919201,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003481042952031072,
|
|
"loss": 5.6974,
|
|
"mean_token_accuracy": 0.1596264883875847,
|
|
"num_tokens": 4020211.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.731296968460083,
|
|
"epoch": 0.12254147665277117,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003469891178717911,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.16362568736076355,
|
|
"num_tokens": 4028790.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.76063027381897,
|
|
"epoch": 0.12282125171362225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003458719669224436,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.15336375832557678,
|
|
"num_tokens": 4038247.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.770486164093017,
|
|
"epoch": 0.12310102677447332,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003447528729823221,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.15302572548389434,
|
|
"num_tokens": 4047951.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.807470464706421,
|
|
"epoch": 0.1233808018353244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003436318667319525,
|
|
"loss": 5.7572,
|
|
"mean_token_accuracy": 0.1501487024128437,
|
|
"num_tokens": 4056481.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.852072525024414,
|
|
"epoch": 0.12366057689617548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034250897890428716,
|
|
"loss": 5.8096,
|
|
"mean_token_accuracy": 0.14974186569452286,
|
|
"num_tokens": 4066686.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.770815086364746,
|
|
"epoch": 0.12394035195702655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003413842402838633,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.1623397082090378,
|
|
"num_tokens": 4075606.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.671165132522583,
|
|
"epoch": 0.12422012701787763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00034025768170595834,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.1648730143904686,
|
|
"num_tokens": 4084659.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.734942007064819,
|
|
"epoch": 0.1244999020787287,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003391293340557446,
|
|
"loss": 5.6821,
|
|
"mean_token_accuracy": 0.15850546956062317,
|
|
"num_tokens": 4093253.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.746334218978882,
|
|
"epoch": 0.12477967713957978,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003379992282674431,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.15441933870315552,
|
|
"num_tokens": 4102448.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.706913709640503,
|
|
"epoch": 0.12505945220043085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003368673953234749,
|
|
"loss": 5.6194,
|
|
"mean_token_accuracy": 0.16242503076791764,
|
|
"num_tokens": 4110879.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.684977293014526,
|
|
"epoch": 0.12533922726128194,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00033573386625361176,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.1629284530878067,
|
|
"num_tokens": 4119701.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.652591848373413,
|
|
"epoch": 0.125619002322133,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00033459867213412567,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.1669366255402565,
|
|
"num_tokens": 4128479.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.686947345733643,
|
|
"epoch": 0.12589877738298408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000333461844086937,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.15521465092897416,
|
|
"num_tokens": 4137891.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.770881128311157,
|
|
"epoch": 0.12617855244383516,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033232341327876097,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.16292612105607987,
|
|
"num_tokens": 4146406.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.718049669265747,
|
|
"epoch": 0.12645832750468622,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003311834109202531,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.16526059061288834,
|
|
"num_tokens": 4154981.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.639597797393799,
|
|
"epoch": 0.1267381025655373,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033004186826515416,
|
|
"loss": 5.6191,
|
|
"mean_token_accuracy": 0.1598067045211792,
|
|
"num_tokens": 4164409.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.621099472045898,
|
|
"epoch": 0.1270178776263884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003288988166094324,
|
|
"loss": 5.5969,
|
|
"mean_token_accuracy": 0.1647018760442734,
|
|
"num_tokens": 4173276.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.787548160552978,
|
|
"epoch": 0.12729765268723947,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032775428729042656,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.16008727252483368,
|
|
"num_tokens": 4183043.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.719858312606812,
|
|
"epoch": 0.12757742774809053,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000326608311685986,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.15825727283954621,
|
|
"num_tokens": 4192129.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.743994855880738,
|
|
"epoch": 0.1278572028089416,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003254609212136108,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.16527171134948732,
|
|
"num_tokens": 4201834.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.649022054672241,
|
|
"epoch": 0.1281369778697927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032431214732959036,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.1635665476322174,
|
|
"num_tokens": 4211265.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.624596405029297,
|
|
"epoch": 0.12841675293064375,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000323162021528141,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.16614623963832856,
|
|
"num_tokens": 4220313.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.816921091079712,
|
|
"epoch": 0.12869652799149484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032201057534054264,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.14698631688952446,
|
|
"num_tokens": 4229240.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.762573146820069,
|
|
"epoch": 0.12897630305234592,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00032085784033427414,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.16257505863904953,
|
|
"num_tokens": 4238265.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.568354558944702,
|
|
"epoch": 0.12925607811319698,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003197038481121478,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.16731962859630584,
|
|
"num_tokens": 4246980.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.744292736053467,
|
|
"epoch": 0.12953585317404806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003185486303114436,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.1658761516213417,
|
|
"num_tokens": 4256314.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.784452104568482,
|
|
"epoch": 0.12981562823489914,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003173922186030409,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.15804459825158118,
|
|
"num_tokens": 4266830.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.655185604095459,
|
|
"epoch": 0.13009540329575023,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000316234644690551,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.16506769955158235,
|
|
"num_tokens": 4276234.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.7454390048980715,
|
|
"epoch": 0.13037517835660128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003150759403094473,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.17277702689170837,
|
|
"num_tokens": 4285911.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.573277139663697,
|
|
"epoch": 0.13065495341745237,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00031391613722619587,
|
|
"loss": 5.6363,
|
|
"mean_token_accuracy": 0.1597856506705284,
|
|
"num_tokens": 4295819.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.717997741699219,
|
|
"epoch": 0.13093472847830345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000312755267237384,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.16458401158452035,
|
|
"num_tokens": 4304586.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.666008996963501,
|
|
"epoch": 0.1312145035391545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003115933621688488,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.16213113367557525,
|
|
"num_tokens": 4314329.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.666855955123902,
|
|
"epoch": 0.1314942786000056,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00031043045387480487,
|
|
"loss": 5.569,
|
|
"mean_token_accuracy": 0.16828988641500472,
|
|
"num_tokens": 4323754.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.728784847259521,
|
|
"epoch": 0.13177405366085668,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003092665742369703,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.1563496008515358,
|
|
"num_tokens": 4332873.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.670199155807495,
|
|
"epoch": 0.13205382872170773,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00030810175516369343,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.15662863254547119,
|
|
"num_tokens": 4343046.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.74817271232605,
|
|
"epoch": 0.13233360378255882,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003069360285890775,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.16077424287796022,
|
|
"num_tokens": 4352562.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.742451953887939,
|
|
"epoch": 0.1326133788434099,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00030576942647210547,
|
|
"loss": 5.6831,
|
|
"mean_token_accuracy": 0.15817070752382278,
|
|
"num_tokens": 4360958.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.7430100440979,
|
|
"epoch": 0.13289315390426099,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00030460198079576355,
|
|
"loss": 5.6065,
|
|
"mean_token_accuracy": 0.1646000176668167,
|
|
"num_tokens": 4370600.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.711065340042114,
|
|
"epoch": 0.13317292896511204,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003034337235661648,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1629451483488083,
|
|
"num_tokens": 4380589.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.673133182525635,
|
|
"epoch": 0.13345270402596313,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003022646868116714,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.1685796022415161,
|
|
"num_tokens": 4389862.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.680800151824951,
|
|
"epoch": 0.1337324790868142,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003010949025820163,
|
|
"loss": 5.6181,
|
|
"mean_token_accuracy": 0.16437141895294188,
|
|
"num_tokens": 4399034.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.610961675643921,
|
|
"epoch": 0.13401225414766527,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002999244029474252,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.17609228193759918,
|
|
"num_tokens": 4408181.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.606054639816284,
|
|
"epoch": 0.13429202920851635,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00029875321999773684,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.1683323085308075,
|
|
"num_tokens": 4417003.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.652012586593628,
|
|
"epoch": 0.13457180426936743,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00029758138584152333,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.1592344120144844,
|
|
"num_tokens": 4426277.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.720648336410522,
|
|
"epoch": 0.1348515793302185,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0002964089326052102,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.17380728870630263,
|
|
"num_tokens": 4434737.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.576643753051758,
|
|
"epoch": 0.13513135439106957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002952358924321949,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.1740764170885086,
|
|
"num_tokens": 4444133.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.620946931838989,
|
|
"epoch": 0.13541112945192066,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00029406229748196657,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.16586569845676422,
|
|
"num_tokens": 4453012.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.720426464080811,
|
|
"epoch": 0.13569090451277174,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002928881799292235,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.1634717583656311,
|
|
"num_tokens": 4461179.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.718172025680542,
|
|
"epoch": 0.1359706795736228,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00029171357196299154,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.16303899735212327,
|
|
"num_tokens": 4470329.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.655877113342285,
|
|
"epoch": 0.13625045463447388,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0002905385057857414,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.157878540456295,
|
|
"num_tokens": 4480943.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.7620521068573,
|
|
"epoch": 0.13653022969532497,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002893630136125058,
|
|
"loss": 5.6514,
|
|
"mean_token_accuracy": 0.16541528105735778,
|
|
"num_tokens": 4490795.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.69360466003418,
|
|
"epoch": 0.13681000475617602,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002881871276699967,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.16737173348665238,
|
|
"num_tokens": 4500377.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.615415239334107,
|
|
"epoch": 0.1370897798170271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00028701088019572114,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16214984357357026,
|
|
"num_tokens": 4509414.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.716953706741333,
|
|
"epoch": 0.1373695548778782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002858343034370977,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.1594344422221184,
|
|
"num_tokens": 4519222.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.6767223358154295,
|
|
"epoch": 0.13764932993872925,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00028465742965057267,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.1654483899474144,
|
|
"num_tokens": 4528115.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.617089366912841,
|
|
"epoch": 0.13792910499958033,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00028348029110073533,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.15843377113342286,
|
|
"num_tokens": 4537330.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.6846363067626955,
|
|
"epoch": 0.13820888006043142,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00028230292005943365,
|
|
"loss": 5.6655,
|
|
"mean_token_accuracy": 0.15484083145856858,
|
|
"num_tokens": 4547427.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.620794153213501,
|
|
"epoch": 0.1384886551212825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00028112534880488945,
|
|
"loss": 5.4819,
|
|
"mean_token_accuracy": 0.16776254028081894,
|
|
"num_tokens": 4556148.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.639376163482666,
|
|
"epoch": 0.13876843018213356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002799476096208137,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.16475914269685746,
|
|
"num_tokens": 4565778.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.697155094146728,
|
|
"epoch": 0.13904820524298464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00027876973479552087,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.16957175135612487,
|
|
"num_tokens": 4574851.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.594253158569336,
|
|
"epoch": 0.13932798030383572,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00027759175662104424,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.15839396119117738,
|
|
"num_tokens": 4583664.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.7007721900939945,
|
|
"epoch": 0.13960775536468678,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002764137073922508,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.1772173210978508,
|
|
"num_tokens": 4592349.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.665040016174316,
|
|
"epoch": 0.13988753042553786,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00027523561940595505,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.16878434121608735,
|
|
"num_tokens": 4601242.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.693995475769043,
|
|
"epoch": 0.14016730548638895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002740575249600342,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.16639557778835296,
|
|
"num_tokens": 4610358.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.656335067749024,
|
|
"epoch": 0.14044708054724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00027287945635254263,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.15777888745069504,
|
|
"num_tokens": 4619660.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.658308792114258,
|
|
"epoch": 0.1407268556080911,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00027170144588082635,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.17469542175531388,
|
|
"num_tokens": 4628347.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.649258041381836,
|
|
"epoch": 0.14100663066894217,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00027052352584063763,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.1646207630634308,
|
|
"num_tokens": 4637160.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.64496340751648,
|
|
"epoch": 0.14128640572979326,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00026934572852524907,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.1644057348370552,
|
|
"num_tokens": 4646663.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.720569229125976,
|
|
"epoch": 0.1415661807906443,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00026816808622456937,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.15825680568814277,
|
|
"num_tokens": 4656259.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.6876654624938965,
|
|
"epoch": 0.1418459558514954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002669906312242569,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.1619700610637665,
|
|
"num_tokens": 4665867.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.709628009796143,
|
|
"epoch": 0.14212573091234648,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026581339580483525,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.16124948114156723,
|
|
"num_tokens": 4674451.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.770373058319092,
|
|
"epoch": 0.14240550597319754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002646364122408082,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.16295707672834397,
|
|
"num_tokens": 4684810.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.612470006942749,
|
|
"epoch": 0.14268528103404862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002634597127997749,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.16489555537700654,
|
|
"num_tokens": 4693461.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.6553059101104735,
|
|
"epoch": 0.1429650560948997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002622833297415445,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.16462549418210984,
|
|
"num_tokens": 4702147.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.719350719451905,
|
|
"epoch": 0.14324483115575076,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002611072953172531,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.1643210083246231,
|
|
"num_tokens": 4711208.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.636368227005005,
|
|
"epoch": 0.14352460621660185,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00025993164176847845,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.1598072439432144,
|
|
"num_tokens": 4720798.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.674344539642334,
|
|
"epoch": 0.14380438127745293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002587564013263564,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.16537421494722365,
|
|
"num_tokens": 4730119.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.676420974731445,
|
|
"epoch": 0.14408415633830401,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002575816062106974,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.1693610355257988,
|
|
"num_tokens": 4739615.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.661298561096191,
|
|
"epoch": 0.14436393139915507,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00025640728862910293,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.16640134602785112,
|
|
"num_tokens": 4749398.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.529336833953858,
|
|
"epoch": 0.14464370646000616,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00025523348077608285,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1767786294221878,
|
|
"num_tokens": 4757806.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.5426219463348385,
|
|
"epoch": 0.14492348152085724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00025406021483217225,
|
|
"loss": 5.5342,
|
|
"mean_token_accuracy": 0.16719046831130982,
|
|
"num_tokens": 4766484.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.6570676326751705,
|
|
"epoch": 0.1452032565817083,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00025288752296304963,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.17492833435535432,
|
|
"num_tokens": 4775143.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.601592588424682,
|
|
"epoch": 0.14548303164255938,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000251715437318655,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.1674225300550461,
|
|
"num_tokens": 4784225.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.626814222335815,
|
|
"epoch": 0.14576280670341046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002505439900323084,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.16674421429634095,
|
|
"num_tokens": 4793263.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.7088785648345945,
|
|
"epoch": 0.14604258176426155,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00024937321321982894,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.17084013521671296,
|
|
"num_tokens": 4801981.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.657845497131348,
|
|
"epoch": 0.1463223568251126,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00024820313897865433,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.17200833112001418,
|
|
"num_tokens": 4809883.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.543992948532105,
|
|
"epoch": 0.1466021318859637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00024703379938696105,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.16232667565345765,
|
|
"num_tokens": 4818368.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.675971984863281,
|
|
"epoch": 0.14688190694681477,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00024586522650278447,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.15936802327632904,
|
|
"num_tokens": 4826955.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.705751276016235,
|
|
"epoch": 0.14716168200766583,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00024469745236314064,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.16145253479480742,
|
|
"num_tokens": 4836051.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.6294593334198,
|
|
"epoch": 0.1474414570685169,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00024353050898314767,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.16890684217214585,
|
|
"num_tokens": 4845533.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.709641838073731,
|
|
"epoch": 0.147721232129368,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00024236442835514743,
|
|
"loss": 5.7324,
|
|
"mean_token_accuracy": 0.1559814289212227,
|
|
"num_tokens": 4853984.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.6191041469573975,
|
|
"epoch": 0.14800100719021905,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00024119924244782965,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.17112404853105545,
|
|
"num_tokens": 4862305.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.643775177001953,
|
|
"epoch": 0.14828078225107014,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00024003498320535462,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.15911641716957092,
|
|
"num_tokens": 4871273.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.69115948677063,
|
|
"epoch": 0.14856055731192122,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00023887168254647727,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.15700725466012955,
|
|
"num_tokens": 4880534.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.6965797424316404,
|
|
"epoch": 0.1488403323727723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00023770937236367308,
|
|
"loss": 5.6014,
|
|
"mean_token_accuracy": 0.16675964295864104,
|
|
"num_tokens": 4890022.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.756263971328735,
|
|
"epoch": 0.14912010743362336,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00023654808452226278,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.16924326568841935,
|
|
"num_tokens": 4899736.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.713470554351806,
|
|
"epoch": 0.14939988249447445,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00023538785085953912,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.174069944024086,
|
|
"num_tokens": 4908791.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.644090414047241,
|
|
"epoch": 0.14967965755532553,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00023422870318389404,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.16543931663036346,
|
|
"num_tokens": 4917670.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.617251539230347,
|
|
"epoch": 0.14995943261617659,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002330706732739468,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.16327330619096755,
|
|
"num_tokens": 4926453.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.676700305938721,
|
|
"epoch": 0.15023920767702767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023191379287767211,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.16559347808361052,
|
|
"num_tokens": 4936558.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.709424543380737,
|
|
"epoch": 0.15051898273787875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002307580937115305,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.17332152873277665,
|
|
"num_tokens": 4945210.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.687791967391968,
|
|
"epoch": 0.1507987577987298,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00022960360745959846,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.16581332087516784,
|
|
"num_tokens": 4954579.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.596445465087891,
|
|
"epoch": 0.1510785328595809,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00022845036577269972,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.16138702481985093,
|
|
"num_tokens": 4964027.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.75875768661499,
|
|
"epoch": 0.15135830792043198,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00022729840026753777,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.15999999195337294,
|
|
"num_tokens": 4973170.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.790727376937866,
|
|
"epoch": 0.15163808298128306,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002261477425258287,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1682533711194992,
|
|
"num_tokens": 4982510.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.60293984413147,
|
|
"epoch": 0.15191785804213412,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002249984240934358,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.18127554506063462,
|
|
"num_tokens": 4990992.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.539755964279175,
|
|
"epoch": 0.1521976331029852,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00022385047647950464,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.17619442641735078,
|
|
"num_tokens": 4999739.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.595760774612427,
|
|
"epoch": 0.1524774081638363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002227039311555986,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.17555348128080367,
|
|
"num_tokens": 5008957.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.665028190612793,
|
|
"epoch": 0.15275718322468734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002215588195548372,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.17178949415683747,
|
|
"num_tokens": 5018109.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.657345628738403,
|
|
"epoch": 0.15303695828553843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00022041517307103337,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.1844388633966446,
|
|
"num_tokens": 5026632.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.639189338684082,
|
|
"epoch": 0.1533167333463895,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002192730230578331,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.17115636616945268,
|
|
"num_tokens": 5036007.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.564154767990113,
|
|
"epoch": 0.15359650840724057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002181324008278559,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.16585114151239394,
|
|
"num_tokens": 5045295.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.579900121688842,
|
|
"epoch": 0.15387628346809165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00021699333765183655,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.1637026086449623,
|
|
"num_tokens": 5054359.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.649759721755982,
|
|
"epoch": 0.15415605852894274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002158558647577673,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.1742785319685936,
|
|
"num_tokens": 5063347.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.685994291305542,
|
|
"epoch": 0.15443583358979382,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00021472001333004215,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.16387508660554886,
|
|
"num_tokens": 5073010.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.640519618988037,
|
|
"epoch": 0.15471560865064488,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00021358581450860186,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.16307867914438248,
|
|
"num_tokens": 5082799.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.5817564010620115,
|
|
"epoch": 0.15499538371149596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002124532993880799,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.16812834441661834,
|
|
"num_tokens": 5092351.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.630770540237426,
|
|
"epoch": 0.15527515877234704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00021132249901695044,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.1700419917702675,
|
|
"num_tokens": 5101007.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.682374477386475,
|
|
"epoch": 0.1555549338331981,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00021019344439667705,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.1712168663740158,
|
|
"num_tokens": 5110786.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.665527725219727,
|
|
"epoch": 0.15583470889404918,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00020906616648086213,
|
|
"loss": 5.5688,
|
|
"mean_token_accuracy": 0.16651172041893006,
|
|
"num_tokens": 5120724.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.566106081008911,
|
|
"epoch": 0.15611448395490027,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00020794069617439942,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.17868822515010835,
|
|
"num_tokens": 5129249.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.686600589752198,
|
|
"epoch": 0.15639425901575132,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00020681706433262593,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.16322513818740844,
|
|
"num_tokens": 5138394.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.723010635375976,
|
|
"epoch": 0.1566740340766024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00020569530176047602,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.1688903585076332,
|
|
"num_tokens": 5148017.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.623873329162597,
|
|
"epoch": 0.1569538091374535,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002045754392116374,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.1765143245458603,
|
|
"num_tokens": 5156963.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.5810019969940186,
|
|
"epoch": 0.15723358419830458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00020345750738770757,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.17983626276254655,
|
|
"num_tokens": 5165393.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.594178247451782,
|
|
"epoch": 0.15751335925915563,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00020234153693735214,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.1695509746670723,
|
|
"num_tokens": 5174272.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.53258204460144,
|
|
"epoch": 0.15779313432000672,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002012275584554647,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.1848943293094635,
|
|
"num_tokens": 5182666.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.653265714645386,
|
|
"epoch": 0.1580729093808578,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00020011560248232803,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.17016485184431077,
|
|
"num_tokens": 5191400.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.657591819763184,
|
|
"epoch": 0.15835268444170886,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00019900569950277692,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.16682781875133515,
|
|
"num_tokens": 5201620.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.592450523376465,
|
|
"epoch": 0.15863245950255994,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00019789787994536228,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.1685665413737297,
|
|
"num_tokens": 5211180.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.6556089401245115,
|
|
"epoch": 0.15891223456341103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00019679217418151667,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.17167882174253463,
|
|
"num_tokens": 5220372.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.761126565933227,
|
|
"epoch": 0.15919200962426208,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00019568861252472236,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.16754570603370667,
|
|
"num_tokens": 5229525.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.6655580520629885,
|
|
"epoch": 0.15947178468511317,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00019458722522967952,
|
|
"loss": 5.4495,
|
|
"mean_token_accuracy": 0.17624941766262053,
|
|
"num_tokens": 5238373.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.625934648513794,
|
|
"epoch": 0.15975155974596425,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00019348804249147723,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.15897643938660622,
|
|
"num_tokens": 5247833.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.629451560974121,
|
|
"epoch": 0.16003133480681533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001923910944447655,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18059510737657547,
|
|
"num_tokens": 5256543.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.646956872940064,
|
|
"epoch": 0.1603111098676664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00019129641116292928,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.17094308286905288,
|
|
"num_tokens": 5265938.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.718534183502197,
|
|
"epoch": 0.16059088492851747,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00019020402265726343,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.16934689432382583,
|
|
"num_tokens": 5275634.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.613666296005249,
|
|
"epoch": 0.16087065998936856,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001891139588761509,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.17356483340263368,
|
|
"num_tokens": 5284351.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.606722688674926,
|
|
"epoch": 0.16115043505021961,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00018802624970424076,
|
|
"loss": 5.4375,
|
|
"mean_token_accuracy": 0.17815187126398085,
|
|
"num_tokens": 5293320.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.702021741867066,
|
|
"epoch": 0.1614302101110707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00018694092496162945,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.1652884900569916,
|
|
"num_tokens": 5303479.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.580821561813354,
|
|
"epoch": 0.16170998517192178,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00018585801440304306,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.174919730424881,
|
|
"num_tokens": 5311827.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.628740119934082,
|
|
"epoch": 0.16198976023277284,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00018477754771702165,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.1688842460513115,
|
|
"num_tokens": 5322024.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.567859077453614,
|
|
"epoch": 0.16226953529362392,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00018369955452510506,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.16756015866994858,
|
|
"num_tokens": 5331309.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.632315063476563,
|
|
"epoch": 0.162549310354475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001826240643810212,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.17050080597400666,
|
|
"num_tokens": 5341366.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.663816690444946,
|
|
"epoch": 0.1628290854153261,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001815511067698758,
|
|
"loss": 5.4376,
|
|
"mean_token_accuracy": 0.1785288631916046,
|
|
"num_tokens": 5350382.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.703562545776367,
|
|
"epoch": 0.16310886047617715,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001804807111073436,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.1669526293873787,
|
|
"num_tokens": 5359899.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.634199142456055,
|
|
"epoch": 0.16338863553702823,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001794129067388625,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.17441888451576232,
|
|
"num_tokens": 5368046.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.54944109916687,
|
|
"epoch": 0.16366841059787932,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00017834772293882868,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.16879914849996566,
|
|
"num_tokens": 5377511.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.519673824310303,
|
|
"epoch": 0.16394818565873037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000177285188909794,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16874182224273682,
|
|
"num_tokens": 5385860.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.587186479568482,
|
|
"epoch": 0.16422796071958146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001762253337816656,
|
|
"loss": 5.4292,
|
|
"mean_token_accuracy": 0.1739762544631958,
|
|
"num_tokens": 5395021.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.7044665813446045,
|
|
"epoch": 0.16450773578043254,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00017516818661090738,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.17277314364910126,
|
|
"num_tokens": 5404690.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.671811628341675,
|
|
"epoch": 0.1647875108412836,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001741137763797428,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.16848109662532806,
|
|
"num_tokens": 5413746.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.7029482364654545,
|
|
"epoch": 0.16506728590213468,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00017306213199536115,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.16972575336694717,
|
|
"num_tokens": 5423713.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.571771669387817,
|
|
"epoch": 0.16534706096298576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001720132822891243,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.17275784015655518,
|
|
"num_tokens": 5432801.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.615698909759521,
|
|
"epoch": 0.16562683602383685,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001709672560157769,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.17942357957363128,
|
|
"num_tokens": 5441785.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.617120027542114,
|
|
"epoch": 0.1659066110846879,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016992408185265758,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.16800451427698135,
|
|
"num_tokens": 5450829.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.6602719783782955,
|
|
"epoch": 0.166186386145539,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00016888378839891298,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.17843340784311296,
|
|
"num_tokens": 5459142.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.6811339378356935,
|
|
"epoch": 0.16646616120639007,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001678464041747137,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.17183150500059127,
|
|
"num_tokens": 5468813.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.6007122039794925,
|
|
"epoch": 0.16674593626724113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00016681195762047223,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.1756803125143051,
|
|
"num_tokens": 5478048.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.656706428527832,
|
|
"epoch": 0.1670257113280922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016578047709606337,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.16890244632959367,
|
|
"num_tokens": 5488136.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.625456476211548,
|
|
"epoch": 0.1673054863889433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00016475199088004678,
|
|
"loss": 5.4759,
|
|
"mean_token_accuracy": 0.17770687043666838,
|
|
"num_tokens": 5497712.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.605235433578491,
|
|
"epoch": 0.16758526144979435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00016372652716889163,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.17041922062635423,
|
|
"num_tokens": 5506884.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.598785877227783,
|
|
"epoch": 0.16786503651064544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001627041140762035,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.18399081379175186,
|
|
"num_tokens": 5515513.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.584302806854248,
|
|
"epoch": 0.16814481157149652,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00016168477963195382,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.1794687032699585,
|
|
"num_tokens": 5524888.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.622479820251465,
|
|
"epoch": 0.1684245866323476,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001606685517817114,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.16936913132667542,
|
|
"num_tokens": 5534599.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.607687520980835,
|
|
"epoch": 0.16870436169319866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00015965545838587592,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.1716221809387207,
|
|
"num_tokens": 5544184.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.766249799728394,
|
|
"epoch": 0.16898413675404975,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00015864552721891467,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1667330950498581,
|
|
"num_tokens": 5553644.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.6523150444030765,
|
|
"epoch": 0.16926391181490083,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00015763878596860076,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.17542214840650558,
|
|
"num_tokens": 5563368.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.622235679626465,
|
|
"epoch": 0.1695436868757519,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00015663526223525412,
|
|
"loss": 5.4899,
|
|
"mean_token_accuracy": 0.17377611696720124,
|
|
"num_tokens": 5573080.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.552012968063354,
|
|
"epoch": 0.16982346193660297,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0001556349835309848,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.17372677624225616,
|
|
"num_tokens": 5582412.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.678281641006469,
|
|
"epoch": 0.17010323699745405,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001546379772789389,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.16942847967147828,
|
|
"num_tokens": 5591429.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.698558568954468,
|
|
"epoch": 0.1703830120583051,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00015364427081254622,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.16547581553459167,
|
|
"num_tokens": 5600445.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.601873302459717,
|
|
"epoch": 0.1706627871191562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00015265389137477165,
|
|
"loss": 5.4346,
|
|
"mean_token_accuracy": 0.1758056551218033,
|
|
"num_tokens": 5608926.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.610825920104981,
|
|
"epoch": 0.17094256218000728,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00015166686611736786,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.1793224737048149,
|
|
"num_tokens": 5618008.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.642164087295532,
|
|
"epoch": 0.17122233724085836,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00015068322210013064,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.17616301774978638,
|
|
"num_tokens": 5626958.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.606994104385376,
|
|
"epoch": 0.17150211230170942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001497029862901578,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.17868903577327727,
|
|
"num_tokens": 5634734.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.573168659210205,
|
|
"epoch": 0.1717818873625605,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00014872618556110905,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.17912874817848207,
|
|
"num_tokens": 5644010.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.655603837966919,
|
|
"epoch": 0.1720616624234116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00014775284669246992,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.16634996682405473,
|
|
"num_tokens": 5653221.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.487155723571777,
|
|
"epoch": 0.17234143748426264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00014678299636881716,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.19824039340019226,
|
|
"num_tokens": 5661960.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.6791815757751465,
|
|
"epoch": 0.17262121254511373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001458166611790873,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.16622782945632936,
|
|
"num_tokens": 5672757.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.515874433517456,
|
|
"epoch": 0.1729009876059648,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00014485386761584773,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.1803530901670456,
|
|
"num_tokens": 5682053.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.737294340133667,
|
|
"epoch": 0.17318076266681587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00014389464207457042,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.17117608487606048,
|
|
"num_tokens": 5691956.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.607691431045533,
|
|
"epoch": 0.17346053772766695,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00014293901085290795,
|
|
"loss": 5.4438,
|
|
"mean_token_accuracy": 0.17209086418151856,
|
|
"num_tokens": 5700901.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.573616981506348,
|
|
"epoch": 0.17374031278851804,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00014198700014997307,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.18049017935991288,
|
|
"num_tokens": 5709636.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.601877307891845,
|
|
"epoch": 0.17402008784936912,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00014103863606562016,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.17868824452161788,
|
|
"num_tokens": 5718723.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.694384813308716,
|
|
"epoch": 0.17429986291022018,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00014009394459972964,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.16710951179265976,
|
|
"num_tokens": 5728737.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.67560920715332,
|
|
"epoch": 0.17457963797107126,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013915295165149513,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.17420278787612914,
|
|
"num_tokens": 5738191.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.708110570907593,
|
|
"epoch": 0.17485941303192234,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00013821568301871384,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.1669305220246315,
|
|
"num_tokens": 5748066.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.589784812927246,
|
|
"epoch": 0.1751391880927734,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00013728216439707862,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.16913450360298157,
|
|
"num_tokens": 5757090.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.598469066619873,
|
|
"epoch": 0.17541896315362449,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00013635242137947419,
|
|
"loss": 5.4305,
|
|
"mean_token_accuracy": 0.17707485109567642,
|
|
"num_tokens": 5766735.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.508171796798706,
|
|
"epoch": 0.17569873821447557,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00013542647945527498,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1711564466357231,
|
|
"num_tokens": 5776039.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.580328893661499,
|
|
"epoch": 0.17597851327532663,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001345043640096465,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1739375874400139,
|
|
"num_tokens": 5784839.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.609876394271851,
|
|
"epoch": 0.1762582883361777,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00013358610032284957,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.17852749079465866,
|
|
"num_tokens": 5794530.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.581386280059815,
|
|
"epoch": 0.1765380633970288,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000132671713569547,
|
|
"loss": 5.3647,
|
|
"mean_token_accuracy": 0.17578775435686111,
|
|
"num_tokens": 5804072.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.658695793151855,
|
|
"epoch": 0.17681783845787988,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0001317612288181136,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.171318656206131,
|
|
"num_tokens": 5812661.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.688057279586792,
|
|
"epoch": 0.17709761351873093,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00013085467102994864,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.16640610694885255,
|
|
"num_tokens": 5822261.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.6127800941467285,
|
|
"epoch": 0.17737738857958202,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00012995206505879198,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.1714189365506172,
|
|
"num_tokens": 5832365.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.609880971908569,
|
|
"epoch": 0.1776571636404331,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001290534356500421,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.1697823390364647,
|
|
"num_tokens": 5841332.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.7082414627075195,
|
|
"epoch": 0.17793693870128416,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00012815880744007827,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.17762261331081391,
|
|
"num_tokens": 5849922.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.620874452590942,
|
|
"epoch": 0.17821671376213524,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00012726820495558483,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1829085722565651,
|
|
"num_tokens": 5859193.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.5914360046386715,
|
|
"epoch": 0.17849648882298633,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00012638165261287868,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.17287297397851945,
|
|
"num_tokens": 5868946.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.645428943634033,
|
|
"epoch": 0.17877626388383738,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001254991747172402,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.1721863716840744,
|
|
"num_tokens": 5877497.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.62221884727478,
|
|
"epoch": 0.17905603894468847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00012462079546224662,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.17754752784967423,
|
|
"num_tokens": 5886334.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.568006992340088,
|
|
"epoch": 0.17933581400553955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00012374653892910896,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.17552449703216552,
|
|
"num_tokens": 5895397.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.581996488571167,
|
|
"epoch": 0.17961558906639064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00012287642908601166,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.17993669211864471,
|
|
"num_tokens": 5905161.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.6182807922363285,
|
|
"epoch": 0.1798953641272417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00012201048978745569,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.1701302170753479,
|
|
"num_tokens": 5914601.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.612086820602417,
|
|
"epoch": 0.18017513918809278,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00012114874477360427,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.16946762353181838,
|
|
"num_tokens": 5924184.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.543766927719116,
|
|
"epoch": 0.18045491424894386,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00012029121766963236,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.177339006960392,
|
|
"num_tokens": 5933774.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.545155239105225,
|
|
"epoch": 0.18073468930979492,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011943793198507858,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.17222069203853607,
|
|
"num_tokens": 5942839.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.623986101150512,
|
|
"epoch": 0.181014464370646,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00011858891111320104,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1789548322558403,
|
|
"num_tokens": 5951357.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.576654624938965,
|
|
"epoch": 0.18129423943149708,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001177441783303359,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.1734651431441307,
|
|
"num_tokens": 5961460.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.680444526672363,
|
|
"epoch": 0.18157401449234814,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00011690375679525896,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.1729705736041069,
|
|
"num_tokens": 5970673.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.587069511413574,
|
|
"epoch": 0.18185378955319922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00011606766954855124,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.17904770523309707,
|
|
"num_tokens": 5980033.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.630879497528076,
|
|
"epoch": 0.1821335646140503,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00011523593951196702,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.17140859067440034,
|
|
"num_tokens": 5990116.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.627670955657959,
|
|
"epoch": 0.1824133396749014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00011440858948780523,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.1717412829399109,
|
|
"num_tokens": 6000047.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.6528349876403805,
|
|
"epoch": 0.18269311473575245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00011358564215828484,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.17403859049081802,
|
|
"num_tokens": 6009184.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.512161207199097,
|
|
"epoch": 0.18297288979660353,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00011276712008492254,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.1847398176789284,
|
|
"num_tokens": 6018511.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.6321393013000485,
|
|
"epoch": 0.18325266485745462,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00011195304570791451,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.17535920292139054,
|
|
"num_tokens": 6027528.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.615204668045044,
|
|
"epoch": 0.18353243991830567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00011114344134552094,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1667225778102875,
|
|
"num_tokens": 6037111.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.589822387695312,
|
|
"epoch": 0.18381221497915676,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001103383291934545,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.18295225948095323,
|
|
"num_tokens": 6045629.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.6502279281616214,
|
|
"epoch": 0.18409199004000784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00010953773132427141,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.18252088576555253,
|
|
"num_tokens": 6055004.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.564513683319092,
|
|
"epoch": 0.1843717651008589,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00010874166968676677,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.17878872752189637,
|
|
"num_tokens": 6063784.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.621532917022705,
|
|
"epoch": 0.18465154016170998,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00010795016610537251,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.1786550909280777,
|
|
"num_tokens": 6073126.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.654560613632202,
|
|
"epoch": 0.18493131522256107,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00010716324227955904,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.17596739679574966,
|
|
"num_tokens": 6082775.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.691810417175293,
|
|
"epoch": 0.18521109028341215,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001063809197832406,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.17199649810791015,
|
|
"num_tokens": 6091862.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.677192831039429,
|
|
"epoch": 0.1854908653442632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00010560322006418368,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.1747978150844574,
|
|
"num_tokens": 6101182.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.605133962631226,
|
|
"epoch": 0.1857706404051143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00010483016444341887,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.17569668889045714,
|
|
"num_tokens": 6110342.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.487795066833496,
|
|
"epoch": 0.18605041546596537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00010406177411465654,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.1902581885457039,
|
|
"num_tokens": 6119092.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.561296606063843,
|
|
"epoch": 0.18633019052681643,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00010329807014370562,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18037820011377334,
|
|
"num_tokens": 6127735.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.532171154022217,
|
|
"epoch": 0.18660996558766751,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00010253907346789632,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.1823173612356186,
|
|
"num_tokens": 6136169.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.562611150741577,
|
|
"epoch": 0.1868897406485186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00010178480489550596,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.17173171490430833,
|
|
"num_tokens": 6145180.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.587430620193482,
|
|
"epoch": 0.18716951570936965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00010103528510518836,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.17749171257019042,
|
|
"num_tokens": 6154834.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.649193859100341,
|
|
"epoch": 0.18744929077022074,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001002905346454073,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.17826548367738723,
|
|
"num_tokens": 6164275.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.6086711406707765,
|
|
"epoch": 0.18772906583107182,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.955057393387285e-05,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.1744353786110878,
|
|
"num_tokens": 6172910.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.621222448348999,
|
|
"epoch": 0.1880088408919229,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 9.88154232569816e-05,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.17354301810264589,
|
|
"num_tokens": 6182552.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.628307771682739,
|
|
"epoch": 0.18828861595277396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 9.808510276926075e-05,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.177091084420681,
|
|
"num_tokens": 6191900.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.5591010570526125,
|
|
"epoch": 0.18856839101362505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 9.735963249281549e-05,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.1722171798348427,
|
|
"num_tokens": 6202143.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.601814126968383,
|
|
"epoch": 0.18884816607447613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 9.663903231677974e-05,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.17530256062746047,
|
|
"num_tokens": 6211793.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.615848636627197,
|
|
"epoch": 0.1891279411353272,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.592332199677145e-05,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17752578854560852,
|
|
"num_tokens": 6220384.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.527585649490357,
|
|
"epoch": 0.18940771619617827,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 9.521252115435061e-05,
|
|
"loss": 5.393,
|
|
"mean_token_accuracy": 0.18007893711328507,
|
|
"num_tokens": 6229131.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.575365877151489,
|
|
"epoch": 0.18968749125702936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 9.450664927648126e-05,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.17039853036403657,
|
|
"num_tokens": 6237698.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.622428274154663,
|
|
"epoch": 0.1899672663178804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.380572571499758e-05,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.16394446194171905,
|
|
"num_tokens": 6247889.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.6079741477966305,
|
|
"epoch": 0.1902470413787315,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.310976968607307e-05,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.18378451466560364,
|
|
"num_tokens": 6257115.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.645024538040161,
|
|
"epoch": 0.19052681643958258,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 9.241880026969381e-05,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.1730919063091278,
|
|
"num_tokens": 6266187.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.620902633666992,
|
|
"epoch": 0.19080659150043366,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 9.173283640913537e-05,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1766896903514862,
|
|
"num_tokens": 6275898.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.6087006568908695,
|
|
"epoch": 0.19108636656128472,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 9.10518969104436e-05,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.18197280317544937,
|
|
"num_tokens": 6284569.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.5508397102355955,
|
|
"epoch": 0.1913661416221358,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.037600044191868e-05,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.1812903180718422,
|
|
"num_tokens": 6292469.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.667384147644043,
|
|
"epoch": 0.1916459166829869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.970516553360383e-05,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.17423631399869918,
|
|
"num_tokens": 6301165.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.6062298774719235,
|
|
"epoch": 0.19192569174383795,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 8.903941057677692e-05,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.17572395503520966,
|
|
"num_tokens": 6309963.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.533150672912598,
|
|
"epoch": 0.19220546680468903,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.837875382344635e-05,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.1760173723101616,
|
|
"num_tokens": 6319138.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.599090099334717,
|
|
"epoch": 0.1924852418655401,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 8.772321338585076e-05,
|
|
"loss": 5.4534,
|
|
"mean_token_accuracy": 0.17400044500827788,
|
|
"num_tokens": 6328036.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.597335290908814,
|
|
"epoch": 0.19276501692639117,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.707280723596242e-05,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1772366374731064,
|
|
"num_tokens": 6336997.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.668742227554321,
|
|
"epoch": 0.19304479198724225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.64275532049944e-05,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.17442795485258103,
|
|
"num_tokens": 6346770.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.563310813903809,
|
|
"epoch": 0.19332456704809334,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 8.578746898291198e-05,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.1822229281067848,
|
|
"num_tokens": 6356313.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.700380897521972,
|
|
"epoch": 0.19360434210894442,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 8.515257211794742e-05,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.16822922676801683,
|
|
"num_tokens": 6365097.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.588365936279297,
|
|
"epoch": 0.19388411716979548,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.452288001611896e-05,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.1779933363199234,
|
|
"num_tokens": 6374523.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.608144235610962,
|
|
"epoch": 0.19416389223064656,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 8.389840994075379e-05,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.18702592998743056,
|
|
"num_tokens": 6383308.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.549237203598023,
|
|
"epoch": 0.19444366729149765,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 8.327917901201435e-05,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.17653237730264665,
|
|
"num_tokens": 6392431.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.574514770507813,
|
|
"epoch": 0.1947234423523487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 8.266520420642931e-05,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.18443700969219207,
|
|
"num_tokens": 6401532.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.625860643386841,
|
|
"epoch": 0.1950032174131998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.205650235642828e-05,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.1711268439888954,
|
|
"num_tokens": 6411307.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.629393529891968,
|
|
"epoch": 0.19528299247405087,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.145309014987978e-05,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.17319606840610505,
|
|
"num_tokens": 6420653.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.581476545333862,
|
|
"epoch": 0.19556276753490193,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.085498412963437e-05,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.18176741451025008,
|
|
"num_tokens": 6429006.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.669359922409058,
|
|
"epoch": 0.195842542595753,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 8.026220069307078e-05,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.17513497173786163,
|
|
"num_tokens": 6438128.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.621584272384643,
|
|
"epoch": 0.1961223176566041,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.967475609164621e-05,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.17944622039794922,
|
|
"num_tokens": 6447497.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.695060873031617,
|
|
"epoch": 0.19640209271745518,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 7.909266643045124e-05,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.16553999185562135,
|
|
"num_tokens": 6456954.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.654816484451294,
|
|
"epoch": 0.19668186777830624,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 7.851594766776802e-05,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.17642862498760223,
|
|
"num_tokens": 6466707.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.631994915008545,
|
|
"epoch": 0.19696164283915732,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 7.794461561463265e-05,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.17793382704257965,
|
|
"num_tokens": 6476444.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.691154146194458,
|
|
"epoch": 0.1972414179000084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 7.7378685934402e-05,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.17922268211841583,
|
|
"num_tokens": 6484953.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.535430145263672,
|
|
"epoch": 0.19752119296085946,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 7.68181741423242e-05,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.18314373642206191,
|
|
"num_tokens": 6493983.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.621595621109009,
|
|
"epoch": 0.19780096802171054,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 7.626309560511313e-05,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.1704625368118286,
|
|
"num_tokens": 6503286.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.6074666500091555,
|
|
"epoch": 0.19808074308256163,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.571346554052724e-05,
|
|
"loss": 5.4091,
|
|
"mean_token_accuracy": 0.17925854921340942,
|
|
"num_tokens": 6512540.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.572437047958374,
|
|
"epoch": 0.19836051814341268,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 7.516929901695249e-05,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.17335671186447144,
|
|
"num_tokens": 6522342.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.601689720153809,
|
|
"epoch": 0.19864029320426377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.463061095298893e-05,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.1684398591518402,
|
|
"num_tokens": 6531274.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.651219511032105,
|
|
"epoch": 0.19892006826511485,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.409741611704198e-05,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.17839524745941163,
|
|
"num_tokens": 6539938.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.588685083389282,
|
|
"epoch": 0.19919984332596594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 7.35697291269174e-05,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.17709300816059112,
|
|
"num_tokens": 6549196.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.644364643096924,
|
|
"epoch": 0.199479618386817,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.304756444942056e-05,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.1738071247935295,
|
|
"num_tokens": 6559444.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.624358224868774,
|
|
"epoch": 0.19975939344766808,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 7.253093639995994e-05,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.17749316096305848,
|
|
"num_tokens": 6570465.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.614028692245483,
|
|
"epoch": 0.20003916850851916,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 7.20198591421544e-05,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.1781265214085579,
|
|
"num_tokens": 6579306.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.528655862808227,
|
|
"epoch": 0.20031894356937022,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.151434668744517e-05,
|
|
"loss": 5.3422,
|
|
"mean_token_accuracy": 0.18188246488571166,
|
|
"num_tokens": 6588803.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.577136564254761,
|
|
"epoch": 0.2005987186302213,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 7.101441289471153e-05,
|
|
"loss": 5.3424,
|
|
"mean_token_accuracy": 0.18517076969146729,
|
|
"num_tokens": 6598541.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.621283054351807,
|
|
"epoch": 0.20087849369107239,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.052007146989098e-05,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.179257595539093,
|
|
"num_tokens": 6607611.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.6981030941009525,
|
|
"epoch": 0.20115826875192344,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.003133596560341e-05,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.1727484256029129,
|
|
"num_tokens": 6617504.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.5757803440094,
|
|
"epoch": 0.20143804381277453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.954821978077952e-05,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.18230992406606675,
|
|
"num_tokens": 6626195.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.706071949005127,
|
|
"epoch": 0.2017178188736256,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 6.907073616029356e-05,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.17243364006280898,
|
|
"num_tokens": 6635177.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.583072471618652,
|
|
"epoch": 0.2019975939344767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 6.85988981946002e-05,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18427297919988633,
|
|
"num_tokens": 6643724.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.6729576110839846,
|
|
"epoch": 0.20227736899532775,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 6.813271881937564e-05,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.1831071361899376,
|
|
"num_tokens": 6651589.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.595622730255127,
|
|
"epoch": 0.20255714405617883,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 6.767221081516286e-05,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.1843818962574005,
|
|
"num_tokens": 6660419.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.646933698654175,
|
|
"epoch": 0.20283691911702992,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 6.72173868070215e-05,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.1787369281053543,
|
|
"num_tokens": 6669662.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.64167160987854,
|
|
"epoch": 0.20311669417788097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.676825926418149e-05,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.17457474172115325,
|
|
"num_tokens": 6678263.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.591275215148926,
|
|
"epoch": 0.20339646923873206,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 6.632484049970122e-05,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.18070578575134277,
|
|
"num_tokens": 6687345.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.595158290863037,
|
|
"epoch": 0.20367624429958314,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.588714267013019e-05,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.17438464164733886,
|
|
"num_tokens": 6696781.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.624737119674682,
|
|
"epoch": 0.2039560193604342,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.545517777517544e-05,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.17891378849744796,
|
|
"num_tokens": 6705378.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.650308561325073,
|
|
"epoch": 0.20423579442128528,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.502895765737281e-05,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.17142409607768058,
|
|
"num_tokens": 6715556.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.548412942886353,
|
|
"epoch": 0.20451556948213637,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 6.460849400176212e-05,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.1816541686654091,
|
|
"num_tokens": 6725019.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.55108528137207,
|
|
"epoch": 0.20479534454298745,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.419379833556694e-05,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.18315638303756715,
|
|
"num_tokens": 6733442.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.610551261901856,
|
|
"epoch": 0.2050751196038385,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 6.378488202787835e-05,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.1792389079928398,
|
|
"num_tokens": 6742980.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.667132234573364,
|
|
"epoch": 0.2053548946646896,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 6.33817562893435e-05,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.1732276648283005,
|
|
"num_tokens": 6752716.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.495639228820801,
|
|
"epoch": 0.20563466972554068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.29844321718582e-05,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.18246687054634095,
|
|
"num_tokens": 6761374.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.626394605636596,
|
|
"epoch": 0.20591444478639173,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 6.259292056826383e-05,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.18038807064294815,
|
|
"num_tokens": 6770150.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.614890432357788,
|
|
"epoch": 0.20619421984724282,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 6.220723221204873e-05,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.16875952035188674,
|
|
"num_tokens": 6779109.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.638265705108642,
|
|
"epoch": 0.2064739949080939,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 6.182737767705406e-05,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.18429478853940964,
|
|
"num_tokens": 6787893.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.6633467197418215,
|
|
"epoch": 0.20675376996894496,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 6.145336737718375e-05,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.17447688281536103,
|
|
"num_tokens": 6797101.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.66504693031311,
|
|
"epoch": 0.20703354502979604,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 6.10852115661191e-05,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.17827175557613373,
|
|
"num_tokens": 6806099.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.650544166564941,
|
|
"epoch": 0.20731332009064712,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 6.072292033703766e-05,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.17720447480678558,
|
|
"num_tokens": 6815678.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.638128709793091,
|
|
"epoch": 0.2075930951514982,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 6.036650362233648e-05,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.1930965304374695,
|
|
"num_tokens": 6824326.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.602468633651734,
|
|
"epoch": 0.20787287021234926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 6.0015971193359824e-05,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.17990394234657286,
|
|
"num_tokens": 6833843.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.672366285324097,
|
|
"epoch": 0.20815264527320035,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.9671332660131306e-05,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.1642289564013481,
|
|
"num_tokens": 6844043.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.640067481994629,
|
|
"epoch": 0.20843242033405143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.933259747109042e-05,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.1859118789434433,
|
|
"num_tokens": 6853069.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.478939151763916,
|
|
"epoch": 0.2087121953949025,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.899977491283351e-05,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19511783719062806,
|
|
"num_tokens": 6861620.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.591347026824951,
|
|
"epoch": 0.20899197045575357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.867287410985908e-05,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.17653748393058777,
|
|
"num_tokens": 6871814.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.600829839706421,
|
|
"epoch": 0.20927174551660466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.835190402431779e-05,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.17183243334293366,
|
|
"num_tokens": 6881462.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.589510583877564,
|
|
"epoch": 0.2095515205774557,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.803687345576673e-05,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.1788550391793251,
|
|
"num_tokens": 6889918.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.541588211059571,
|
|
"epoch": 0.2098312956383068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.7727791040927977e-05,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.1864072635769844,
|
|
"num_tokens": 6898544.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.596061754226684,
|
|
"epoch": 0.21011107069915788,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 5.742466525345213e-05,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.17474737465381623,
|
|
"num_tokens": 6909036.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.588040542602539,
|
|
"epoch": 0.21039084576000897,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 5.7127504403685775e-05,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.17909753173589707,
|
|
"num_tokens": 6918539.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.574407577514648,
|
|
"epoch": 0.21067062082086002,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 5.6836316638443664e-05,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.182549324631691,
|
|
"num_tokens": 6927271.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.5319170475006105,
|
|
"epoch": 0.2109503958817111,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 5.655110994078553e-05,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.1819850981235504,
|
|
"num_tokens": 6935938.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.612181091308594,
|
|
"epoch": 0.2112301709425622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.6271892129797056e-05,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.17222869247198105,
|
|
"num_tokens": 6945429.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.517855548858643,
|
|
"epoch": 0.21150994600341325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.599867086037556e-05,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.18886305689811705,
|
|
"num_tokens": 6954165.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.619343662261963,
|
|
"epoch": 0.21178972106426433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.573145362302012e-05,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.17164421677589417,
|
|
"num_tokens": 6963748.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.547058820724487,
|
|
"epoch": 0.21206949612511541,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 5.5470247743626404e-05,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.1793201595544815,
|
|
"num_tokens": 6972778.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.657385778427124,
|
|
"epoch": 0.21234927118596647,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 5.5215060383285414e-05,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.17252370566129685,
|
|
"num_tokens": 6981860.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.585592794418335,
|
|
"epoch": 0.21262904624681755,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.496589853808759e-05,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.171404230594635,
|
|
"num_tokens": 6991767.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.6380256652832035,
|
|
"epoch": 0.21290882130766864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.47227690389308e-05,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.17931962758302689,
|
|
"num_tokens": 7000434.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.598411321640015,
|
|
"epoch": 0.21318859636851972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 5.448567855133306e-05,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.18587056994438172,
|
|
"num_tokens": 7009333.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.57962441444397,
|
|
"epoch": 0.21346837142937078,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 5.425463357524986e-05,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.1769099935889244,
|
|
"num_tokens": 7018622.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.65074725151062,
|
|
"epoch": 0.21374814649022186,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.402964044489591e-05,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.17731042206287384,
|
|
"num_tokens": 7028422.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.624558448791504,
|
|
"epoch": 0.21402792155107295,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.381070532857153e-05,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.18674263954162598,
|
|
"num_tokens": 7036454.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.6149290084838865,
|
|
"epoch": 0.214307696611924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 5.359783422849357e-05,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.18405462354421614,
|
|
"num_tokens": 7046432.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.634493970870972,
|
|
"epoch": 0.2145874716727751,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 5.3391032980630736e-05,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.17925070375204086,
|
|
"num_tokens": 7055763.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.650363922119141,
|
|
"epoch": 0.21486724673362617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.31903072545437e-05,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.17305445671081543,
|
|
"num_tokens": 7064861.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.637513494491577,
|
|
"epoch": 0.21514702179447723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.29956625532297e-05,
|
|
"loss": 5.417,
|
|
"mean_token_accuracy": 0.1744650647044182,
|
|
"num_tokens": 7074594.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.563904047012329,
|
|
"epoch": 0.2154267968553283,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.280710421297146e-05,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18140957355499268,
|
|
"num_tokens": 7082717.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.6917500495910645,
|
|
"epoch": 0.2157065719161794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.2624637403191165e-05,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.17346943616867067,
|
|
"num_tokens": 7092832.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.587896490097046,
|
|
"epoch": 0.21598634697703048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.2448267126308605e-05,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.18040136694908143,
|
|
"num_tokens": 7101920.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.547025346755982,
|
|
"epoch": 0.21626612203788154,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.2277998217603954e-05,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.18462412804365158,
|
|
"num_tokens": 7111023.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.569247531890869,
|
|
"epoch": 0.21654589709873262,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.211383534508541e-05,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.1729729026556015,
|
|
"num_tokens": 7120856.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.637767601013183,
|
|
"epoch": 0.2168256721595837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 5.1955783009361044e-05,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.17604185789823532,
|
|
"num_tokens": 7129825.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.4731988430023195,
|
|
"epoch": 0.21710544722043476,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.180384554351543e-05,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.19181579500436782,
|
|
"num_tokens": 7138513.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.575317478179931,
|
|
"epoch": 0.21738522228128584,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.1658027112990976e-05,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17580454796552658,
|
|
"num_tokens": 7147323.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.602580308914185,
|
|
"epoch": 0.21766499734213693,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.151833171547365e-05,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.17612906992435456,
|
|
"num_tokens": 7156151.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.605935668945312,
|
|
"epoch": 0.21794477240298799,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.1384763180783274e-05,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.17549584805965424,
|
|
"num_tokens": 7165129.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.674029302597046,
|
|
"epoch": 0.21822454746383907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.125732517076876e-05,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.1681998610496521,
|
|
"num_tokens": 7175752.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.6807276725769045,
|
|
"epoch": 0.21850432252469015,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 5.113602117920747e-05,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.16865825057029724,
|
|
"num_tokens": 7185616.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.657227516174316,
|
|
"epoch": 0.21878409758554124,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.102085453170966e-05,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.18109627813100815,
|
|
"num_tokens": 7195075.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.740746974945068,
|
|
"epoch": 0.2190638726463923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.091182838562709e-05,
|
|
"loss": 5.5102,
|
|
"mean_token_accuracy": 0.17352122962474822,
|
|
"num_tokens": 7203738.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.650801038742065,
|
|
"epoch": 0.21934364770724338,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 5.0808945729966716e-05,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.18014600425958632,
|
|
"num_tokens": 7213170.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.614649915695191,
|
|
"epoch": 0.21962342276809446,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.071220938530844e-05,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17581942081451415,
|
|
"num_tokens": 7222363.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.613489103317261,
|
|
"epoch": 0.21990319782894552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.0621622003728026e-05,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.17849222719669341,
|
|
"num_tokens": 7231711.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.577176856994629,
|
|
"epoch": 0.2201829728897966,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 5.053718606872433e-05,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1801558643579483,
|
|
"num_tokens": 7240602.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.625189542770386,
|
|
"epoch": 0.2204627479506477,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.0458903895151134e-05,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.1798821434378624,
|
|
"num_tokens": 7249936.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.57180643081665,
|
|
"epoch": 0.22074252301149874,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.038677762915381e-05,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.18012653440237045,
|
|
"num_tokens": 7259411.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.6547565937042235,
|
|
"epoch": 0.22102229807234983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 5.032080924811033e-05,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.17737533748149872,
|
|
"num_tokens": 7268328.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.623548126220703,
|
|
"epoch": 0.2213020731332009,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 5.026100056057718e-05,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.17397240102291106,
|
|
"num_tokens": 7278123.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.574464273452759,
|
|
"epoch": 0.221581848194052,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 5.0207353206239764e-05,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.1829357162117958,
|
|
"num_tokens": 7287746.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.655947828292847,
|
|
"epoch": 0.22186162325490305,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 5.0159868655867436e-05,
|
|
"loss": 5.4533,
|
|
"mean_token_accuracy": 0.17779434025287627,
|
|
"num_tokens": 7296579.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.639813661575317,
|
|
"epoch": 0.22214139831575413,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 5.011854821127305e-05,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.18081778138875962,
|
|
"num_tokens": 7305480.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.594654273986817,
|
|
"epoch": 0.22242117337660522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.008339300527755e-05,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.1819113403558731,
|
|
"num_tokens": 7314425.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.585033988952636,
|
|
"epoch": 0.22270094843745628,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 5.005440400167859e-05,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.1700441226363182,
|
|
"num_tokens": 7323351.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.577469778060913,
|
|
"epoch": 0.22298072349830736,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 5.003158199522442e-05,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.18047396838665009,
|
|
"num_tokens": 7332278.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.6406107425689695,
|
|
"epoch": 0.22326049855915844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 5.0014927611591806e-05,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.1764102905988693,
|
|
"num_tokens": 7341077.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.61423168182373,
|
|
"epoch": 0.2235402736200095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.000444130736916e-05,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18062103241682054,
|
|
"num_tokens": 7349920.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.608104133605957,
|
|
"epoch": 0.22382004868086058,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.0000123370043736e-05,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.17658718973398208,
|
|
"num_tokens": 7358966.0,
|
|
"step": 4000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 4000,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.0792397924352e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|