3035 lines
81 KiB
JSON
3035 lines
81 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.08393251825532272,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 1500,
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 4055064532992000.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|