6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 4.902761459350586,
|
||
|
|
"epoch": 0.00045355587808418,
|
||
|
|
"grad_norm": 15.0625,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 14.2424,
|
||
|
|
"mean_token_accuracy": 6.570302066393197e-05,
|
||
|
|
"num_tokens": 10827.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.906017255783081,
|
||
|
|
"epoch": 0.00090711175616836,
|
||
|
|
"grad_norm": 15.0625,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 14.1679,
|
||
|
|
"mean_token_accuracy": 0.00036321740481071174,
|
||
|
|
"num_tokens": 21025.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.919331836700439,
|
||
|
|
"epoch": 0.00136066763425254,
|
||
|
|
"grad_norm": 16.25,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 14.1379,
|
||
|
|
"mean_token_accuracy": 0.00018726952257566153,
|
||
|
|
"num_tokens": 31678.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.969941806793213,
|
||
|
|
"epoch": 0.00181422351233672,
|
||
|
|
"grad_norm": 17.75,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 13.9183,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 41025.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.119146680831909,
|
||
|
|
"epoch": 0.0022677793904208998,
|
||
|
|
"grad_norm": 21.875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 13.5438,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 51270.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.423425340652466,
|
||
|
|
"epoch": 0.00272133526850508,
|
||
|
|
"grad_norm": 26.625,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 13.082,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 62142.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.89132776260376,
|
||
|
|
"epoch": 0.00317489114658926,
|
||
|
|
"grad_norm": 25.625,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 11.989,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 72709.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.029912281036378,
|
||
|
|
"epoch": 0.00362844702467344,
|
||
|
|
"grad_norm": 3.671875,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.9002,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 82313.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.710572910308837,
|
||
|
|
"epoch": 0.00408200290275762,
|
||
|
|
"grad_norm": 3.59375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.6789,
|
||
|
|
"mean_token_accuracy": 0.001249837997602299,
|
||
|
|
"num_tokens": 92450.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.739872074127197,
|
||
|
|
"epoch": 0.0045355587808417995,
|
||
|
|
"grad_norm": 3.03125,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.5409,
|
||
|
|
"mean_token_accuracy": 0.010005939414259046,
|
||
|
|
"num_tokens": 103978.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.732357597351074,
|
||
|
|
"epoch": 0.00498911465892598,
|
||
|
|
"grad_norm": 2.140625,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 10.2901,
|
||
|
|
"mean_token_accuracy": 0.0165672049857676,
|
||
|
|
"num_tokens": 114134.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.688269710540771,
|
||
|
|
"epoch": 0.00544267053701016,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 10.1413,
|
||
|
|
"mean_token_accuracy": 0.015207256283611059,
|
||
|
|
"num_tokens": 125037.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.711676120758057,
|
||
|
|
"epoch": 0.00589622641509434,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.9497,
|
||
|
|
"mean_token_accuracy": 0.017865559458732604,
|
||
|
|
"num_tokens": 134721.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.7262864112854,
|
||
|
|
"epoch": 0.00634978229317852,
|
||
|
|
"grad_norm": 1.9765625,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.8497,
|
||
|
|
"mean_token_accuracy": 0.03912395965307951,
|
||
|
|
"num_tokens": 144448.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.72291088104248,
|
||
|
|
"epoch": 0.006803338171262699,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.7736,
|
||
|
|
"mean_token_accuracy": 0.0496896930038929,
|
||
|
|
"num_tokens": 154343.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.716559219360352,
|
||
|
|
"epoch": 0.00725689404934688,
|
||
|
|
"grad_norm": 1.953125,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.7443,
|
||
|
|
"mean_token_accuracy": 0.046880177780985834,
|
||
|
|
"num_tokens": 165650.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.707624149322509,
|
||
|
|
"epoch": 0.007710449927431059,
|
||
|
|
"grad_norm": 1.7734375,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.711,
|
||
|
|
"mean_token_accuracy": 0.04450351819396019,
|
||
|
|
"num_tokens": 177098.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.704974555969239,
|
||
|
|
"epoch": 0.00816400580551524,
|
||
|
|
"grad_norm": 1.96875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.4919,
|
||
|
|
"mean_token_accuracy": 0.05480348989367485,
|
||
|
|
"num_tokens": 187903.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.689633083343505,
|
||
|
|
"epoch": 0.00861756168359942,
|
||
|
|
"grad_norm": 1.8671875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.4033,
|
||
|
|
"mean_token_accuracy": 0.052090702950954436,
|
||
|
|
"num_tokens": 198077.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.674059963226318,
|
||
|
|
"epoch": 0.009071117561683599,
|
||
|
|
"grad_norm": 1.8046875,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.3565,
|
||
|
|
"mean_token_accuracy": 0.05150817483663559,
|
||
|
|
"num_tokens": 208641.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.649502754211426,
|
||
|
|
"epoch": 0.009524673439767779,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.1936,
|
||
|
|
"mean_token_accuracy": 0.05499474816024304,
|
||
|
|
"num_tokens": 218398.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.621120071411132,
|
||
|
|
"epoch": 0.00997822931785196,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.066,
|
||
|
|
"mean_token_accuracy": 0.05329935699701309,
|
||
|
|
"num_tokens": 229059.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.593021678924561,
|
||
|
|
"epoch": 0.01043178519593614,
|
||
|
|
"grad_norm": 1.7421875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.9831,
|
||
|
|
"mean_token_accuracy": 0.05141277946531773,
|
||
|
|
"num_tokens": 239775.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.551456928253174,
|
||
|
|
"epoch": 0.01088534107402032,
|
||
|
|
"grad_norm": 1.8515625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.842,
|
||
|
|
"mean_token_accuracy": 0.05272237621247768,
|
||
|
|
"num_tokens": 249954.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.502390956878662,
|
||
|
|
"epoch": 0.011338896952104499,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.7334,
|
||
|
|
"mean_token_accuracy": 0.05634862557053566,
|
||
|
|
"num_tokens": 260056.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.426200675964356,
|
||
|
|
"epoch": 0.01179245283018868,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.6347,
|
||
|
|
"mean_token_accuracy": 0.05641283132135868,
|
||
|
|
"num_tokens": 269904.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.35210132598877,
|
||
|
|
"epoch": 0.01224600870827286,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.5138,
|
||
|
|
"mean_token_accuracy": 0.05234182849526405,
|
||
|
|
"num_tokens": 280900.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.270804977416992,
|
||
|
|
"epoch": 0.01269956458635704,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.406,
|
||
|
|
"mean_token_accuracy": 0.05256233848631382,
|
||
|
|
"num_tokens": 290844.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.143964767456055,
|
||
|
|
"epoch": 0.013153120464441219,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.2834,
|
||
|
|
"mean_token_accuracy": 0.056692027300596234,
|
||
|
|
"num_tokens": 301345.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.030607223510742,
|
||
|
|
"epoch": 0.013606676342525399,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.1592,
|
||
|
|
"mean_token_accuracy": 0.05243662744760513,
|
||
|
|
"num_tokens": 312681.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.876211452484132,
|
||
|
|
"epoch": 0.01406023222060958,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.0357,
|
||
|
|
"mean_token_accuracy": 0.05974825695157051,
|
||
|
|
"num_tokens": 323492.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.703791522979737,
|
||
|
|
"epoch": 0.01451378809869376,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.9778,
|
||
|
|
"mean_token_accuracy": 0.05336504280567169,
|
||
|
|
"num_tokens": 334521.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.493086814880371,
|
||
|
|
"epoch": 0.014967343976777939,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.9038,
|
||
|
|
"mean_token_accuracy": 0.05283032245934009,
|
||
|
|
"num_tokens": 345468.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.287709426879882,
|
||
|
|
"epoch": 0.015420899854862119,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.7788,
|
||
|
|
"mean_token_accuracy": 0.055317680910229684,
|
||
|
|
"num_tokens": 355911.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.030819416046143,
|
||
|
|
"epoch": 0.0158744557329463,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.7522,
|
||
|
|
"mean_token_accuracy": 0.05364949442446232,
|
||
|
|
"num_tokens": 367537.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.806273078918457,
|
||
|
|
"epoch": 0.01632801161103048,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.8067,
|
||
|
|
"mean_token_accuracy": 0.05446445494890213,
|
||
|
|
"num_tokens": 377918.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.59828290939331,
|
||
|
|
"epoch": 0.01678156748911466,
|
||
|
|
"grad_norm": 0.703125,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.6514,
|
||
|
|
"mean_token_accuracy": 0.055352770164608954,
|
||
|
|
"num_tokens": 388461.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.414749145507812,
|
||
|
|
"epoch": 0.01723512336719884,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.6092,
|
||
|
|
"mean_token_accuracy": 0.06770730689167977,
|
||
|
|
"num_tokens": 399771.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.264602565765381,
|
||
|
|
"epoch": 0.01768867924528302,
|
||
|
|
"grad_norm": 0.6953125,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.4766,
|
||
|
|
"mean_token_accuracy": 0.07282306849956513,
|
||
|
|
"num_tokens": 410254.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.190978908538819,
|
||
|
|
"epoch": 0.018142235123367198,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.4886,
|
||
|
|
"mean_token_accuracy": 0.06817287020385265,
|
||
|
|
"num_tokens": 419792.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.113365936279298,
|
||
|
|
"epoch": 0.018595791001451378,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.4782,
|
||
|
|
"mean_token_accuracy": 0.07438576593995094,
|
||
|
|
"num_tokens": 429264.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.046414375305176,
|
||
|
|
"epoch": 0.019049346879535557,
|
||
|
|
"grad_norm": 0.69140625,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.4294,
|
||
|
|
"mean_token_accuracy": 0.0784988671541214,
|
||
|
|
"num_tokens": 439624.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.01142177581787,
|
||
|
|
"epoch": 0.01950290275761974,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.4206,
|
||
|
|
"mean_token_accuracy": 0.07665222510695457,
|
||
|
|
"num_tokens": 449556.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.982991123199463,
|
||
|
|
"epoch": 0.01995645863570392,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.4192,
|
||
|
|
"mean_token_accuracy": 0.07819079160690308,
|
||
|
|
"num_tokens": 460243.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.913471603393555,
|
||
|
|
"epoch": 0.0204100145137881,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.4682,
|
||
|
|
"mean_token_accuracy": 0.07565705217421055,
|
||
|
|
"num_tokens": 469767.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.974834537506103,
|
||
|
|
"epoch": 0.02086357039187228,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.3948,
|
||
|
|
"mean_token_accuracy": 0.07845633998513221,
|
||
|
|
"num_tokens": 480329.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.921621561050415,
|
||
|
|
"epoch": 0.02131712626995646,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.3597,
|
||
|
|
"mean_token_accuracy": 0.07565821185708047,
|
||
|
|
"num_tokens": 490096.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9462236881256105,
|
||
|
|
"epoch": 0.02177068214804064,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.404,
|
||
|
|
"mean_token_accuracy": 0.07110006958246232,
|
||
|
|
"num_tokens": 501231.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.90762996673584,
|
||
|
|
"epoch": 0.022224238026124818,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.3003,
|
||
|
|
"mean_token_accuracy": 0.07855217903852463,
|
||
|
|
"num_tokens": 510722.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.791062259674073,
|
||
|
|
"epoch": 0.022677793904208998,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.342,
|
||
|
|
"mean_token_accuracy": 0.0785796582698822,
|
||
|
|
"num_tokens": 521452.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.835426616668701,
|
||
|
|
"epoch": 0.023131349782293177,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.3275,
|
||
|
|
"mean_token_accuracy": 0.07848411723971367,
|
||
|
|
"num_tokens": 532397.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.834844970703125,
|
||
|
|
"epoch": 0.02358490566037736,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.3126,
|
||
|
|
"mean_token_accuracy": 0.08216355144977569,
|
||
|
|
"num_tokens": 542271.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.783105802536011,
|
||
|
|
"epoch": 0.02403846153846154,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.2852,
|
||
|
|
"mean_token_accuracy": 0.08326507434248924,
|
||
|
|
"num_tokens": 552411.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.789214849472046,
|
||
|
|
"epoch": 0.02449201741654572,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.2853,
|
||
|
|
"mean_token_accuracy": 0.07970908731222152,
|
||
|
|
"num_tokens": 561518.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8078306198120115,
|
||
|
|
"epoch": 0.0249455732946299,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.3048,
|
||
|
|
"mean_token_accuracy": 0.08076792433857918,
|
||
|
|
"num_tokens": 571361.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.704005384445191,
|
||
|
|
"epoch": 0.02539912917271408,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.2079,
|
||
|
|
"mean_token_accuracy": 0.08890472128987312,
|
||
|
|
"num_tokens": 580926.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.777441549301147,
|
||
|
|
"epoch": 0.025852685050798258,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.305,
|
||
|
|
"mean_token_accuracy": 0.07825151681900025,
|
||
|
|
"num_tokens": 592282.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.756225681304931,
|
||
|
|
"epoch": 0.026306240928882438,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.3123,
|
||
|
|
"mean_token_accuracy": 0.08080485239624977,
|
||
|
|
"num_tokens": 602767.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.716958808898926,
|
||
|
|
"epoch": 0.026759796806966617,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.2177,
|
||
|
|
"mean_token_accuracy": 0.08552644699811936,
|
||
|
|
"num_tokens": 612763.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.706277990341187,
|
||
|
|
"epoch": 0.027213352685050797,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.1737,
|
||
|
|
"mean_token_accuracy": 0.08685687705874442,
|
||
|
|
"num_tokens": 622796.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.668240880966186,
|
||
|
|
"epoch": 0.027666908563134977,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.1609,
|
||
|
|
"mean_token_accuracy": 0.08536986410617828,
|
||
|
|
"num_tokens": 633136.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.649664688110351,
|
||
|
|
"epoch": 0.02812046444121916,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.143,
|
||
|
|
"mean_token_accuracy": 0.08583157956600189,
|
||
|
|
"num_tokens": 643347.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.697743082046509,
|
||
|
|
"epoch": 0.02857402031930334,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.1414,
|
||
|
|
"mean_token_accuracy": 0.09304612576961517,
|
||
|
|
"num_tokens": 653096.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.587596750259399,
|
||
|
|
"epoch": 0.02902757619738752,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.1706,
|
||
|
|
"mean_token_accuracy": 0.08879687860608101,
|
||
|
|
"num_tokens": 663557.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.612160730361938,
|
||
|
|
"epoch": 0.0294811320754717,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.2254,
|
||
|
|
"mean_token_accuracy": 0.08831041827797889,
|
||
|
|
"num_tokens": 674395.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.695938348770142,
|
||
|
|
"epoch": 0.029934687953555878,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.1265,
|
||
|
|
"mean_token_accuracy": 0.09078574851155281,
|
||
|
|
"num_tokens": 684776.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.576247215270996,
|
||
|
|
"epoch": 0.030388243831640058,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.109,
|
||
|
|
"mean_token_accuracy": 0.08843011409044266,
|
||
|
|
"num_tokens": 694886.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.556908130645752,
|
||
|
|
"epoch": 0.030841799709724237,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.171,
|
||
|
|
"mean_token_accuracy": 0.09018958061933517,
|
||
|
|
"num_tokens": 705426.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.578840160369873,
|
||
|
|
"epoch": 0.03129535558780842,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.1594,
|
||
|
|
"mean_token_accuracy": 0.08782409057021141,
|
||
|
|
"num_tokens": 716271.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.638495922088623,
|
||
|
|
"epoch": 0.0317489114658926,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.1606,
|
||
|
|
"mean_token_accuracy": 0.09265835508704186,
|
||
|
|
"num_tokens": 726875.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.563690900802612,
|
||
|
|
"epoch": 0.032202467343976776,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.0773,
|
||
|
|
"mean_token_accuracy": 0.08827165514230728,
|
||
|
|
"num_tokens": 737825.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.58997654914856,
|
||
|
|
"epoch": 0.03265602322206096,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.089,
|
||
|
|
"mean_token_accuracy": 0.0890809178352356,
|
||
|
|
"num_tokens": 747424.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.506178569793701,
|
||
|
|
"epoch": 0.033109579100145135,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.0901,
|
||
|
|
"mean_token_accuracy": 0.09158140644431115,
|
||
|
|
"num_tokens": 757649.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.567615652084351,
|
||
|
|
"epoch": 0.03356313497822932,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.0671,
|
||
|
|
"mean_token_accuracy": 0.0931968331336975,
|
||
|
|
"num_tokens": 768556.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.400697326660156,
|
||
|
|
"epoch": 0.034016690856313495,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.0591,
|
||
|
|
"mean_token_accuracy": 0.09333095103502273,
|
||
|
|
"num_tokens": 778331.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.539828157424926,
|
||
|
|
"epoch": 0.03447024673439768,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.0387,
|
||
|
|
"mean_token_accuracy": 0.09365462064743042,
|
||
|
|
"num_tokens": 788065.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.495446348190308,
|
||
|
|
"epoch": 0.03492380261248186,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.0671,
|
||
|
|
"mean_token_accuracy": 0.09628497660160065,
|
||
|
|
"num_tokens": 798912.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.502418661117554,
|
||
|
|
"epoch": 0.03537735849056604,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.0166,
|
||
|
|
"mean_token_accuracy": 0.09867717772722244,
|
||
|
|
"num_tokens": 809580.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.49851360321045,
|
||
|
|
"epoch": 0.03583091436865022,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.1108,
|
||
|
|
"mean_token_accuracy": 0.09084957540035248,
|
||
|
|
"num_tokens": 820207.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.348110675811768,
|
||
|
|
"epoch": 0.036284470246734396,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.9336,
|
||
|
|
"mean_token_accuracy": 0.08944878205657006,
|
||
|
|
"num_tokens": 831038.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.545411586761475,
|
||
|
|
"epoch": 0.03673802612481858,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.0186,
|
||
|
|
"mean_token_accuracy": 0.09372441694140435,
|
||
|
|
"num_tokens": 842144.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.47612156867981,
|
||
|
|
"epoch": 0.037191582002902755,
|
||
|
|
"grad_norm": 1.609375,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.9989,
|
||
|
|
"mean_token_accuracy": 0.09804348424077033,
|
||
|
|
"num_tokens": 851315.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.322836017608642,
|
||
|
|
"epoch": 0.03764513788098694,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.0063,
|
||
|
|
"mean_token_accuracy": 0.09803526178002357,
|
||
|
|
"num_tokens": 861233.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.406570482254028,
|
||
|
|
"epoch": 0.038098693759071114,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.9994,
|
||
|
|
"mean_token_accuracy": 0.0946230135858059,
|
||
|
|
"num_tokens": 871131.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.391973686218262,
|
||
|
|
"epoch": 0.0385522496371553,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.975,
|
||
|
|
"mean_token_accuracy": 0.09175262376666068,
|
||
|
|
"num_tokens": 882195.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.452529048919677,
|
||
|
|
"epoch": 0.03900580551523948,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.9467,
|
||
|
|
"mean_token_accuracy": 0.09589996412396432,
|
||
|
|
"num_tokens": 891806.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.431856489181518,
|
||
|
|
"epoch": 0.03945936139332366,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.0087,
|
||
|
|
"mean_token_accuracy": 0.09551806971430779,
|
||
|
|
"num_tokens": 901350.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.414364910125732,
|
||
|
|
"epoch": 0.03991291727140784,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.9182,
|
||
|
|
"mean_token_accuracy": 0.09558806866407395,
|
||
|
|
"num_tokens": 912061.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.305682420730591,
|
||
|
|
"epoch": 0.040366473149492016,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.89,
|
||
|
|
"mean_token_accuracy": 0.09567090198397636,
|
||
|
|
"num_tokens": 922220.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.367461013793945,
|
||
|
|
"epoch": 0.0408200290275762,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.8992,
|
||
|
|
"mean_token_accuracy": 0.09762913659214974,
|
||
|
|
"num_tokens": 932319.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.292191886901856,
|
||
|
|
"epoch": 0.041273584905660375,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.9231,
|
||
|
|
"mean_token_accuracy": 0.09886682778596878,
|
||
|
|
"num_tokens": 943254.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.387064361572266,
|
||
|
|
"epoch": 0.04172714078374456,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.939,
|
||
|
|
"mean_token_accuracy": 0.09336472377181053,
|
||
|
|
"num_tokens": 953921.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.296272230148316,
|
||
|
|
"epoch": 0.042180696661828734,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.8498,
|
||
|
|
"mean_token_accuracy": 0.10429160594940186,
|
||
|
|
"num_tokens": 963832.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.304851102828979,
|
||
|
|
"epoch": 0.04263425253991292,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.9459,
|
||
|
|
"mean_token_accuracy": 0.09589096009731293,
|
||
|
|
"num_tokens": 974066.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.324310684204102,
|
||
|
|
"epoch": 0.0430878084179971,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.9353,
|
||
|
|
"mean_token_accuracy": 0.09945596382021904,
|
||
|
|
"num_tokens": 984402.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.312732458114624,
|
||
|
|
"epoch": 0.04354136429608128,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.8591,
|
||
|
|
"mean_token_accuracy": 0.09938167333602906,
|
||
|
|
"num_tokens": 993555.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334518146514893,
|
||
|
|
"epoch": 0.04399492017416546,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.8404,
|
||
|
|
"mean_token_accuracy": 0.10574882701039315,
|
||
|
|
"num_tokens": 1002920.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.289060401916504,
|
||
|
|
"epoch": 0.044448476052249636,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.907,
|
||
|
|
"mean_token_accuracy": 0.09448245465755463,
|
||
|
|
"num_tokens": 1013611.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.166425371170044,
|
||
|
|
"epoch": 0.04490203193033382,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.8012,
|
||
|
|
"mean_token_accuracy": 0.0957680583000183,
|
||
|
|
"num_tokens": 1024121.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.363502073287964,
|
||
|
|
"epoch": 0.045355587808417995,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.032,
|
||
|
|
"mean_token_accuracy": 0.1009724922478199,
|
||
|
|
"num_tokens": 1033845.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.24678144454956,
|
||
|
|
"epoch": 0.04580914368650218,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.831,
|
||
|
|
"mean_token_accuracy": 0.09820592999458314,
|
||
|
|
"num_tokens": 1044642.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.280577898025513,
|
||
|
|
"epoch": 0.046262699564586354,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.8867,
|
||
|
|
"mean_token_accuracy": 0.09730055406689644,
|
||
|
|
"num_tokens": 1054728.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.20595383644104,
|
||
|
|
"epoch": 0.04671625544267054,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.8504,
|
||
|
|
"mean_token_accuracy": 0.0942535676062107,
|
||
|
|
"num_tokens": 1065743.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1944211483001705,
|
||
|
|
"epoch": 0.04716981132075472,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.7719,
|
||
|
|
"mean_token_accuracy": 0.09884541779756546,
|
||
|
|
"num_tokens": 1076798.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.200849342346191,
|
||
|
|
"epoch": 0.047623367198838897,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.8921,
|
||
|
|
"mean_token_accuracy": 0.09789391681551933,
|
||
|
|
"num_tokens": 1087445.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216012907028198,
|
||
|
|
"epoch": 0.04807692307692308,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7985,
|
||
|
|
"mean_token_accuracy": 0.10271445363759994,
|
||
|
|
"num_tokens": 1098379.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.228269386291504,
|
||
|
|
"epoch": 0.048530478955007256,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.8866,
|
||
|
|
"mean_token_accuracy": 0.09828322008252144,
|
||
|
|
"num_tokens": 1108016.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.184875774383545,
|
||
|
|
"epoch": 0.04898403483309144,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.7837,
|
||
|
|
"mean_token_accuracy": 0.09823340401053429,
|
||
|
|
"num_tokens": 1117887.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.186046075820923,
|
||
|
|
"epoch": 0.049437590711175615,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.7773,
|
||
|
|
"mean_token_accuracy": 0.0981587328016758,
|
||
|
|
"num_tokens": 1128497.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1298119068145756,
|
||
|
|
"epoch": 0.0498911465892598,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.8017,
|
||
|
|
"mean_token_accuracy": 0.10637210011482238,
|
||
|
|
"num_tokens": 1138168.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.136086797714233,
|
||
|
|
"epoch": 0.050344702467343974,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.7618,
|
||
|
|
"mean_token_accuracy": 0.10049154385924339,
|
||
|
|
"num_tokens": 1148357.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1673754215240475,
|
||
|
|
"epoch": 0.05079825834542816,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.7907,
|
||
|
|
"mean_token_accuracy": 0.10017752796411514,
|
||
|
|
"num_tokens": 1159964.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.23973536491394,
|
||
|
|
"epoch": 0.05125181422351233,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.8508,
|
||
|
|
"mean_token_accuracy": 0.09828138649463654,
|
||
|
|
"num_tokens": 1170683.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.192407703399658,
|
||
|
|
"epoch": 0.051705370101596516,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.8052,
|
||
|
|
"mean_token_accuracy": 0.1006213940680027,
|
||
|
|
"num_tokens": 1181680.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.093324756622314,
|
||
|
|
"epoch": 0.0521589259796807,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.6997,
|
||
|
|
"mean_token_accuracy": 0.10036976039409637,
|
||
|
|
"num_tokens": 1191619.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.011592292785645,
|
||
|
|
"epoch": 0.052612481857764876,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.6916,
|
||
|
|
"mean_token_accuracy": 0.10292767509818077,
|
||
|
|
"num_tokens": 1202264.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.043795013427735,
|
||
|
|
"epoch": 0.05306603773584906,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.6999,
|
||
|
|
"mean_token_accuracy": 0.1045819990336895,
|
||
|
|
"num_tokens": 1212119.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.129189682006836,
|
||
|
|
"epoch": 0.053519593613933235,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.8212,
|
||
|
|
"mean_token_accuracy": 0.102519890666008,
|
||
|
|
"num_tokens": 1222317.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.168576860427857,
|
||
|
|
"epoch": 0.05397314949201742,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.7716,
|
||
|
|
"mean_token_accuracy": 0.10512009784579276,
|
||
|
|
"num_tokens": 1232914.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.968721580505371,
|
||
|
|
"epoch": 0.054426705370101594,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.6181,
|
||
|
|
"mean_token_accuracy": 0.10760264396667481,
|
||
|
|
"num_tokens": 1244214.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.105316591262818,
|
||
|
|
"epoch": 0.05488026124818578,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.7149,
|
||
|
|
"mean_token_accuracy": 0.10045301765203477,
|
||
|
|
"num_tokens": 1254626.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.98553991317749,
|
||
|
|
"epoch": 0.05533381712626995,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.8113,
|
||
|
|
"mean_token_accuracy": 0.10129074826836586,
|
||
|
|
"num_tokens": 1265461.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.082133436203003,
|
||
|
|
"epoch": 0.055787373004354136,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.6817,
|
||
|
|
"mean_token_accuracy": 0.11003390699625015,
|
||
|
|
"num_tokens": 1275810.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.964151763916016,
|
||
|
|
"epoch": 0.05624092888243832,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.6878,
|
||
|
|
"mean_token_accuracy": 0.11000289767980576,
|
||
|
|
"num_tokens": 1285170.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.021602058410645,
|
||
|
|
"epoch": 0.056694484760522496,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.6361,
|
||
|
|
"mean_token_accuracy": 0.10547553822398185,
|
||
|
|
"num_tokens": 1295460.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.010881614685059,
|
||
|
|
"epoch": 0.05714804063860668,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.7523,
|
||
|
|
"mean_token_accuracy": 0.10284495502710342,
|
||
|
|
"num_tokens": 1306656.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.070465517044068,
|
||
|
|
"epoch": 0.057601596516690855,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.7338,
|
||
|
|
"mean_token_accuracy": 0.1056830108165741,
|
||
|
|
"num_tokens": 1318019.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.88353590965271,
|
||
|
|
"epoch": 0.05805515239477504,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.6511,
|
||
|
|
"mean_token_accuracy": 0.10918820276856422,
|
||
|
|
"num_tokens": 1328120.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.09418797492981,
|
||
|
|
"epoch": 0.058508708272859214,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.7483,
|
||
|
|
"mean_token_accuracy": 0.10312345400452613,
|
||
|
|
"num_tokens": 1338354.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.009733867645264,
|
||
|
|
"epoch": 0.0589622641509434,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.7237,
|
||
|
|
"mean_token_accuracy": 0.1024971716105938,
|
||
|
|
"num_tokens": 1348666.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.047331762313843,
|
||
|
|
"epoch": 0.05941582002902757,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.7554,
|
||
|
|
"mean_token_accuracy": 0.10805487632751465,
|
||
|
|
"num_tokens": 1359713.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9947686195373535,
|
||
|
|
"epoch": 0.059869375907111756,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.6124,
|
||
|
|
"mean_token_accuracy": 0.10892275646328926,
|
||
|
|
"num_tokens": 1369507.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.998069620132446,
|
||
|
|
"epoch": 0.06032293178519594,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.768,
|
||
|
|
"mean_token_accuracy": 0.10034214109182357,
|
||
|
|
"num_tokens": 1380726.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.112451839447021,
|
||
|
|
"epoch": 0.060776487663280115,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.6933,
|
||
|
|
"mean_token_accuracy": 0.10579130649566651,
|
||
|
|
"num_tokens": 1391423.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.052730226516724,
|
||
|
|
"epoch": 0.0612300435413643,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.6678,
|
||
|
|
"mean_token_accuracy": 0.11295373067259788,
|
||
|
|
"num_tokens": 1402492.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.922665405273437,
|
||
|
|
"epoch": 0.061683599419448475,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.7161,
|
||
|
|
"mean_token_accuracy": 0.10829840004444122,
|
||
|
|
"num_tokens": 1412497.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.03723840713501,
|
||
|
|
"epoch": 0.06213715529753266,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.6772,
|
||
|
|
"mean_token_accuracy": 0.11061608865857124,
|
||
|
|
"num_tokens": 1423214.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.935256671905518,
|
||
|
|
"epoch": 0.06259071117561683,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.6745,
|
||
|
|
"mean_token_accuracy": 0.10797292739152908,
|
||
|
|
"num_tokens": 1434044.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918494129180909,
|
||
|
|
"epoch": 0.06304426705370102,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.6361,
|
||
|
|
"mean_token_accuracy": 0.10982377529144287,
|
||
|
|
"num_tokens": 1444387.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.957173490524292,
|
||
|
|
"epoch": 0.0634978229317852,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.5862,
|
||
|
|
"mean_token_accuracy": 0.10744345635175705,
|
||
|
|
"num_tokens": 1455157.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938698959350586,
|
||
|
|
"epoch": 0.06395137880986937,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.6693,
|
||
|
|
"mean_token_accuracy": 0.11478404849767684,
|
||
|
|
"num_tokens": 1466145.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.962664556503296,
|
||
|
|
"epoch": 0.06440493468795355,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.667,
|
||
|
|
"mean_token_accuracy": 0.10709880217909813,
|
||
|
|
"num_tokens": 1476713.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.92603645324707,
|
||
|
|
"epoch": 0.06485849056603774,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.671,
|
||
|
|
"mean_token_accuracy": 0.11409479826688766,
|
||
|
|
"num_tokens": 1486908.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899812459945679,
|
||
|
|
"epoch": 0.06531204644412192,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.5941,
|
||
|
|
"mean_token_accuracy": 0.11084994897246361,
|
||
|
|
"num_tokens": 1498185.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.901278781890869,
|
||
|
|
"epoch": 0.0657656023222061,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.6413,
|
||
|
|
"mean_token_accuracy": 0.1077586367726326,
|
||
|
|
"num_tokens": 1508376.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9933178424835205,
|
||
|
|
"epoch": 0.06621915820029027,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.7199,
|
||
|
|
"mean_token_accuracy": 0.10835012272000313,
|
||
|
|
"num_tokens": 1519953.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.853632211685181,
|
||
|
|
"epoch": 0.06667271407837445,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.592,
|
||
|
|
"mean_token_accuracy": 0.11243074238300324,
|
||
|
|
"num_tokens": 1529793.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.829979610443115,
|
||
|
|
"epoch": 0.06712626995645864,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.5882,
|
||
|
|
"mean_token_accuracy": 0.11395004838705063,
|
||
|
|
"num_tokens": 1540859.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.908363008499146,
|
||
|
|
"epoch": 0.06757982583454282,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.5104,
|
||
|
|
"mean_token_accuracy": 0.11262088865041733,
|
||
|
|
"num_tokens": 1549783.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84120545387268,
|
||
|
|
"epoch": 0.06803338171262699,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.5803,
|
||
|
|
"mean_token_accuracy": 0.10933975651860237,
|
||
|
|
"num_tokens": 1560522.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878204107284546,
|
||
|
|
"epoch": 0.06848693759071117,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.553,
|
||
|
|
"mean_token_accuracy": 0.11197188422083855,
|
||
|
|
"num_tokens": 1570668.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.856545925140381,
|
||
|
|
"epoch": 0.06894049346879536,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.669,
|
||
|
|
"mean_token_accuracy": 0.11744550019502639,
|
||
|
|
"num_tokens": 1581523.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84909029006958,
|
||
|
|
"epoch": 0.06939404934687954,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.5917,
|
||
|
|
"mean_token_accuracy": 0.1113414227962494,
|
||
|
|
"num_tokens": 1591356.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.83960976600647,
|
||
|
|
"epoch": 0.06984760522496372,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.5574,
|
||
|
|
"mean_token_accuracy": 0.11633669957518578,
|
||
|
|
"num_tokens": 1601779.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.888131904602051,
|
||
|
|
"epoch": 0.07030116110304789,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.5633,
|
||
|
|
"mean_token_accuracy": 0.1150720700621605,
|
||
|
|
"num_tokens": 1611995.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.856516313552857,
|
||
|
|
"epoch": 0.07075471698113207,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.586,
|
||
|
|
"mean_token_accuracy": 0.11050437688827515,
|
||
|
|
"num_tokens": 1621834.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.778967618942261,
|
||
|
|
"epoch": 0.07120827285921626,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.6288,
|
||
|
|
"mean_token_accuracy": 0.10744166076183319,
|
||
|
|
"num_tokens": 1632881.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7607427597045895,
|
||
|
|
"epoch": 0.07166182873730044,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.6028,
|
||
|
|
"mean_token_accuracy": 0.10911152362823487,
|
||
|
|
"num_tokens": 1642870.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8341546058654785,
|
||
|
|
"epoch": 0.07211538461538461,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.484,
|
||
|
|
"mean_token_accuracy": 0.11779236048460007,
|
||
|
|
"num_tokens": 1653390.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802682399749756,
|
||
|
|
"epoch": 0.07256894049346879,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.6078,
|
||
|
|
"mean_token_accuracy": 0.11580143421888352,
|
||
|
|
"num_tokens": 1663382.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889751863479614,
|
||
|
|
"epoch": 0.07302249637155298,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.6263,
|
||
|
|
"mean_token_accuracy": 0.10960384383797646,
|
||
|
|
"num_tokens": 1673601.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.744623231887817,
|
||
|
|
"epoch": 0.07347605224963716,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.5301,
|
||
|
|
"mean_token_accuracy": 0.1178050920367241,
|
||
|
|
"num_tokens": 1683565.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.720245599746704,
|
||
|
|
"epoch": 0.07392960812772134,
|
||
|
|
"grad_norm": 1.9140625,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.4975,
|
||
|
|
"mean_token_accuracy": 0.1157220259308815,
|
||
|
|
"num_tokens": 1693636.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.888108444213867,
|
||
|
|
"epoch": 0.07438316400580551,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.6028,
|
||
|
|
"mean_token_accuracy": 0.11490728184580803,
|
||
|
|
"num_tokens": 1703415.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8595898151397705,
|
||
|
|
"epoch": 0.0748367198838897,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.5759,
|
||
|
|
"mean_token_accuracy": 0.11677221283316612,
|
||
|
|
"num_tokens": 1713579.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7610352516174315,
|
||
|
|
"epoch": 0.07529027576197388,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.5869,
|
||
|
|
"mean_token_accuracy": 0.11174456626176835,
|
||
|
|
"num_tokens": 1724583.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.793128204345703,
|
||
|
|
"epoch": 0.07574383164005806,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.4998,
|
||
|
|
"mean_token_accuracy": 0.12149128615856171,
|
||
|
|
"num_tokens": 1735293.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784815979003906,
|
||
|
|
"epoch": 0.07619738751814223,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.5285,
|
||
|
|
"mean_token_accuracy": 0.11545130759477615,
|
||
|
|
"num_tokens": 1745623.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.785441732406616,
|
||
|
|
"epoch": 0.07665094339622641,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.5589,
|
||
|
|
"mean_token_accuracy": 0.11196033582091332,
|
||
|
|
"num_tokens": 1755713.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844113492965699,
|
||
|
|
"epoch": 0.0771044992743106,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.5448,
|
||
|
|
"mean_token_accuracy": 0.11228399202227593,
|
||
|
|
"num_tokens": 1765264.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.778715133666992,
|
||
|
|
"epoch": 0.07755805515239478,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.5551,
|
||
|
|
"mean_token_accuracy": 0.11371968314051628,
|
||
|
|
"num_tokens": 1775769.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.709914636611939,
|
||
|
|
"epoch": 0.07801161103047896,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.4821,
|
||
|
|
"mean_token_accuracy": 0.11689155176281929,
|
||
|
|
"num_tokens": 1786245.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.716907548904419,
|
||
|
|
"epoch": 0.07846516690856313,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.5182,
|
||
|
|
"mean_token_accuracy": 0.12198375314474105,
|
||
|
|
"num_tokens": 1796040.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.72428708076477,
|
||
|
|
"epoch": 0.07891872278664731,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.5268,
|
||
|
|
"mean_token_accuracy": 0.11597820520401,
|
||
|
|
"num_tokens": 1806007.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.862047719955444,
|
||
|
|
"epoch": 0.0793722786647315,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.6034,
|
||
|
|
"mean_token_accuracy": 0.11016635000705718,
|
||
|
|
"num_tokens": 1816935.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7226348400115965,
|
||
|
|
"epoch": 0.07982583454281568,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.4647,
|
||
|
|
"mean_token_accuracy": 0.11464838534593583,
|
||
|
|
"num_tokens": 1827419.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.80533652305603,
|
||
|
|
"epoch": 0.08027939042089985,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.5762,
|
||
|
|
"mean_token_accuracy": 0.11279575228691101,
|
||
|
|
"num_tokens": 1837933.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.692126846313476,
|
||
|
|
"epoch": 0.08073294629898403,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.6181,
|
||
|
|
"mean_token_accuracy": 0.11968202516436577,
|
||
|
|
"num_tokens": 1848551.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.773914003372193,
|
||
|
|
"epoch": 0.08118650217706821,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.4874,
|
||
|
|
"mean_token_accuracy": 0.11803188994526863,
|
||
|
|
"num_tokens": 1858380.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64626522064209,
|
||
|
|
"epoch": 0.0816400580551524,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.4255,
|
||
|
|
"mean_token_accuracy": 0.11616697832942009,
|
||
|
|
"num_tokens": 1868291.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.739772891998291,
|
||
|
|
"epoch": 0.08209361393323658,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.5222,
|
||
|
|
"mean_token_accuracy": 0.11596911773085594,
|
||
|
|
"num_tokens": 1879219.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701965379714966,
|
||
|
|
"epoch": 0.08254716981132075,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.5064,
|
||
|
|
"mean_token_accuracy": 0.1169955737888813,
|
||
|
|
"num_tokens": 1889809.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.736312532424927,
|
||
|
|
"epoch": 0.08300072568940493,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.4667,
|
||
|
|
"mean_token_accuracy": 0.11598963215947151,
|
||
|
|
"num_tokens": 1899986.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.627064943313599,
|
||
|
|
"epoch": 0.08345428156748912,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.4631,
|
||
|
|
"mean_token_accuracy": 0.11359920203685761,
|
||
|
|
"num_tokens": 1909314.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.714141511917115,
|
||
|
|
"epoch": 0.0839078374455733,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.4954,
|
||
|
|
"mean_token_accuracy": 0.1206825278699398,
|
||
|
|
"num_tokens": 1918443.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.711059856414795,
|
||
|
|
"epoch": 0.08436139332365747,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.4599,
|
||
|
|
"mean_token_accuracy": 0.11760578602552414,
|
||
|
|
"num_tokens": 1928683.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563105583190918,
|
||
|
|
"epoch": 0.08481494920174165,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.3733,
|
||
|
|
"mean_token_accuracy": 0.11783806160092354,
|
||
|
|
"num_tokens": 1938293.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.621684551239014,
|
||
|
|
"epoch": 0.08526850507982583,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.4649,
|
||
|
|
"mean_token_accuracy": 0.1159488506615162,
|
||
|
|
"num_tokens": 1948233.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.703399705886841,
|
||
|
|
"epoch": 0.08572206095791002,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.3795,
|
||
|
|
"mean_token_accuracy": 0.12225733622908593,
|
||
|
|
"num_tokens": 1958611.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.67765588760376,
|
||
|
|
"epoch": 0.0861756168359942,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.5279,
|
||
|
|
"mean_token_accuracy": 0.12170163914561272,
|
||
|
|
"num_tokens": 1968957.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.721297121047973,
|
||
|
|
"epoch": 0.08662917271407837,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.4022,
|
||
|
|
"mean_token_accuracy": 0.12271194607019424,
|
||
|
|
"num_tokens": 1978503.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51479959487915,
|
||
|
|
"epoch": 0.08708272859216255,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.3838,
|
||
|
|
"mean_token_accuracy": 0.12056222185492516,
|
||
|
|
"num_tokens": 1988458.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.663824939727784,
|
||
|
|
"epoch": 0.08753628447024674,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.5235,
|
||
|
|
"mean_token_accuracy": 0.1133016251027584,
|
||
|
|
"num_tokens": 1999984.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.534238243103028,
|
||
|
|
"epoch": 0.08798984034833092,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.38,
|
||
|
|
"mean_token_accuracy": 0.12614745199680327,
|
||
|
|
"num_tokens": 2010645.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.69314603805542,
|
||
|
|
"epoch": 0.08844339622641509,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.4879,
|
||
|
|
"mean_token_accuracy": 0.11517181396484374,
|
||
|
|
"num_tokens": 2020196.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.586405944824219,
|
||
|
|
"epoch": 0.08889695210449927,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.3749,
|
||
|
|
"mean_token_accuracy": 0.12108265981078148,
|
||
|
|
"num_tokens": 2030101.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620171546936035,
|
||
|
|
"epoch": 0.08935050798258345,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.4594,
|
||
|
|
"mean_token_accuracy": 0.1197955846786499,
|
||
|
|
"num_tokens": 2040454.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.581764078140258,
|
||
|
|
"epoch": 0.08980406386066764,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.402,
|
||
|
|
"mean_token_accuracy": 0.1192368857562542,
|
||
|
|
"num_tokens": 2050378.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651663303375244,
|
||
|
|
"epoch": 0.09025761973875182,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.4549,
|
||
|
|
"mean_token_accuracy": 0.11869885623455048,
|
||
|
|
"num_tokens": 2060282.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589950847625732,
|
||
|
|
"epoch": 0.09071117561683599,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.4433,
|
||
|
|
"mean_token_accuracy": 0.12011284530162811,
|
||
|
|
"num_tokens": 2070563.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.661682939529419,
|
||
|
|
"epoch": 0.09116473149492017,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999999985110217,
|
||
|
|
"loss": 6.5128,
|
||
|
|
"mean_token_accuracy": 0.11984694451093673,
|
||
|
|
"num_tokens": 2080153.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546395254135132,
|
||
|
|
"epoch": 0.09161828737300436,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999999924620471,
|
||
|
|
"loss": 6.3602,
|
||
|
|
"mean_token_accuracy": 0.12557145729660987,
|
||
|
|
"num_tokens": 2090590.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653158855438233,
|
||
|
|
"epoch": 0.09207184325108854,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999999817600155,
|
||
|
|
"loss": 6.4314,
|
||
|
|
"mean_token_accuracy": 0.11608105525374413,
|
||
|
|
"num_tokens": 2101945.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.635874509811401,
|
||
|
|
"epoch": 0.09252539912917271,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999999664049268,
|
||
|
|
"loss": 6.4312,
|
||
|
|
"mean_token_accuracy": 0.12001314610242844,
|
||
|
|
"num_tokens": 2112514.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546846055984497,
|
||
|
|
"epoch": 0.09297895500725689,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004999999463967816,
|
||
|
|
"loss": 6.3852,
|
||
|
|
"mean_token_accuracy": 0.11658050194382667,
|
||
|
|
"num_tokens": 2122296.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.713669490814209,
|
||
|
|
"epoch": 0.09343251088534107,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00049999992173558,
|
||
|
|
"loss": 6.5311,
|
||
|
|
"mean_token_accuracy": 0.10938856825232506,
|
||
|
|
"num_tokens": 2134512.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649443817138672,
|
||
|
|
"epoch": 0.09388606676342526,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004999998924213228,
|
||
|
|
"loss": 6.4339,
|
||
|
|
"mean_token_accuracy": 0.12238849774003029,
|
||
|
|
"num_tokens": 2143934.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488268947601318,
|
||
|
|
"epoch": 0.09433962264150944,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999998584540105,
|
||
|
|
"loss": 6.3351,
|
||
|
|
"mean_token_accuracy": 0.11762306764721871,
|
||
|
|
"num_tokens": 2155730.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.570074510574341,
|
||
|
|
"epoch": 0.09479317851959361,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999998198336437,
|
||
|
|
"loss": 6.3681,
|
||
|
|
"mean_token_accuracy": 0.11555026769638062,
|
||
|
|
"num_tokens": 2166422.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646327686309815,
|
||
|
|
"epoch": 0.09524673439767779,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999997765602233,
|
||
|
|
"loss": 6.469,
|
||
|
|
"mean_token_accuracy": 0.11361956149339676,
|
||
|
|
"num_tokens": 2177842.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.617121315002441,
|
||
|
|
"epoch": 0.09570029027576198,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999997286337502,
|
||
|
|
"loss": 6.5398,
|
||
|
|
"mean_token_accuracy": 0.11744040250778198,
|
||
|
|
"num_tokens": 2188614.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.604910278320313,
|
||
|
|
"epoch": 0.09615384615384616,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999996760542254,
|
||
|
|
"loss": 6.3246,
|
||
|
|
"mean_token_accuracy": 0.12567146718502045,
|
||
|
|
"num_tokens": 2197886.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.525793075561523,
|
||
|
|
"epoch": 0.09660740203193033,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00049999961882165,
|
||
|
|
"loss": 6.3772,
|
||
|
|
"mean_token_accuracy": 0.12232817932963372,
|
||
|
|
"num_tokens": 2209930.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564913749694824,
|
||
|
|
"epoch": 0.09706095791001451,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999995569360251,
|
||
|
|
"loss": 6.3959,
|
||
|
|
"mean_token_accuracy": 0.11825868040323258,
|
||
|
|
"num_tokens": 2219767.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.555662298202515,
|
||
|
|
"epoch": 0.0975145137880987,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000499999490397352,
|
||
|
|
"loss": 6.3192,
|
||
|
|
"mean_token_accuracy": 0.121416836977005,
|
||
|
|
"num_tokens": 2230082.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495458173751831,
|
||
|
|
"epoch": 0.09796806966618288,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999994192056321,
|
||
|
|
"loss": 6.3673,
|
||
|
|
"mean_token_accuracy": 0.12748734578490256,
|
||
|
|
"num_tokens": 2240066.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.524483871459961,
|
||
|
|
"epoch": 0.09842162554426705,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999993433608669,
|
||
|
|
"loss": 6.3942,
|
||
|
|
"mean_token_accuracy": 0.11839633882045746,
|
||
|
|
"num_tokens": 2250732.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.593288707733154,
|
||
|
|
"epoch": 0.09887518142235123,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999992628630579,
|
||
|
|
"loss": 6.2797,
|
||
|
|
"mean_token_accuracy": 0.12327790930867195,
|
||
|
|
"num_tokens": 2261452.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.485133695602417,
|
||
|
|
"epoch": 0.09932873730043541,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999991777122069,
|
||
|
|
"loss": 6.3782,
|
||
|
|
"mean_token_accuracy": 0.12279095351696015,
|
||
|
|
"num_tokens": 2271929.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531335401535034,
|
||
|
|
"epoch": 0.0997822931785196,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999990879083156,
|
||
|
|
"loss": 6.3604,
|
||
|
|
"mean_token_accuracy": 0.12319791615009308,
|
||
|
|
"num_tokens": 2282987.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.444648933410645,
|
||
|
|
"epoch": 0.10023584905660378,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999989934513857,
|
||
|
|
"loss": 6.3295,
|
||
|
|
"mean_token_accuracy": 0.12565099447965622,
|
||
|
|
"num_tokens": 2292796.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598123359680176,
|
||
|
|
"epoch": 0.10068940493468795,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999988943414193,
|
||
|
|
"loss": 6.3766,
|
||
|
|
"mean_token_accuracy": 0.12076297253370286,
|
||
|
|
"num_tokens": 2303057.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4050017356872555,
|
||
|
|
"epoch": 0.10114296081277213,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999987905784184,
|
||
|
|
"loss": 6.3638,
|
||
|
|
"mean_token_accuracy": 0.12473835423588753,
|
||
|
|
"num_tokens": 2314168.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.548490381240844,
|
||
|
|
"epoch": 0.10159651669085631,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999986821623853,
|
||
|
|
"loss": 6.335,
|
||
|
|
"mean_token_accuracy": 0.12088372111320496,
|
||
|
|
"num_tokens": 2325241.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.579931640625,
|
||
|
|
"epoch": 0.1020500725689405,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999985690933219,
|
||
|
|
"loss": 6.3584,
|
||
|
|
"mean_token_accuracy": 0.12107386961579322,
|
||
|
|
"num_tokens": 2334866.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416501808166504,
|
||
|
|
"epoch": 0.10250362844702467,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004999984513712311,
|
||
|
|
"loss": 6.366,
|
||
|
|
"mean_token_accuracy": 0.12216197848320007,
|
||
|
|
"num_tokens": 2345422.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.573203802108765,
|
||
|
|
"epoch": 0.10295718432510885,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004999983289961146,
|
||
|
|
"loss": 6.3667,
|
||
|
|
"mean_token_accuracy": 0.12462597936391831,
|
||
|
|
"num_tokens": 2356285.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.414275217056274,
|
||
|
|
"epoch": 0.10341074020319303,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999982019679755,
|
||
|
|
"loss": 6.2962,
|
||
|
|
"mean_token_accuracy": 0.12918335497379302,
|
||
|
|
"num_tokens": 2366861.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546162033081055,
|
||
|
|
"epoch": 0.10386429608127722,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999980702868164,
|
||
|
|
"loss": 6.3186,
|
||
|
|
"mean_token_accuracy": 0.12778222039341927,
|
||
|
|
"num_tokens": 2376851.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468019723892212,
|
||
|
|
"epoch": 0.1043178519593614,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999979339526396,
|
||
|
|
"loss": 6.3967,
|
||
|
|
"mean_token_accuracy": 0.12601374089717865,
|
||
|
|
"num_tokens": 2386857.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.512000989913941,
|
||
|
|
"epoch": 0.10477140783744557,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999977929654484,
|
||
|
|
"loss": 6.3197,
|
||
|
|
"mean_token_accuracy": 0.12597798183560371,
|
||
|
|
"num_tokens": 2397035.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.556376361846924,
|
||
|
|
"epoch": 0.10522496371552975,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004999976473252453,
|
||
|
|
"loss": 6.3936,
|
||
|
|
"mean_token_accuracy": 0.12374778017401696,
|
||
|
|
"num_tokens": 2408177.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.569843435287476,
|
||
|
|
"epoch": 0.10567851959361393,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999974970320338,
|
||
|
|
"loss": 6.342,
|
||
|
|
"mean_token_accuracy": 0.12336181774735451,
|
||
|
|
"num_tokens": 2418445.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446996784210205,
|
||
|
|
"epoch": 0.10613207547169812,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999973420858165,
|
||
|
|
"loss": 6.3375,
|
||
|
|
"mean_token_accuracy": 0.12320749461650848,
|
||
|
|
"num_tokens": 2428990.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.456551933288575,
|
||
|
|
"epoch": 0.10658563134978229,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999971824865968,
|
||
|
|
"loss": 6.3706,
|
||
|
|
"mean_token_accuracy": 0.11951386407017708,
|
||
|
|
"num_tokens": 2439643.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.636844635009766,
|
||
|
|
"epoch": 0.10703918722786647,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999970182343782,
|
||
|
|
"loss": 6.4152,
|
||
|
|
"mean_token_accuracy": 0.12312159314751625,
|
||
|
|
"num_tokens": 2450691.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.513713598251343,
|
||
|
|
"epoch": 0.10749274310595065,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999968493291638,
|
||
|
|
"loss": 6.3519,
|
||
|
|
"mean_token_accuracy": 0.12444976568222046,
|
||
|
|
"num_tokens": 2460706.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332309865951538,
|
||
|
|
"epoch": 0.10794629898403484,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999966757709573,
|
||
|
|
"loss": 6.2426,
|
||
|
|
"mean_token_accuracy": 0.13491440415382386,
|
||
|
|
"num_tokens": 2470947.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.500934410095215,
|
||
|
|
"epoch": 0.10839985486211902,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999964975597622,
|
||
|
|
"loss": 6.2077,
|
||
|
|
"mean_token_accuracy": 0.12923589274287223,
|
||
|
|
"num_tokens": 2481132.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5095055103302,
|
||
|
|
"epoch": 0.10885341074020319,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999963146955821,
|
||
|
|
"loss": 6.2492,
|
||
|
|
"mean_token_accuracy": 0.12882558181881903,
|
||
|
|
"num_tokens": 2491701.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.308234691619873,
|
||
|
|
"epoch": 0.10930696661828737,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499996127178421,
|
||
|
|
"loss": 6.3173,
|
||
|
|
"mean_token_accuracy": 0.1222999058663845,
|
||
|
|
"num_tokens": 2502360.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526607275009155,
|
||
|
|
"epoch": 0.10976052249637155,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999959350082825,
|
||
|
|
"loss": 6.2211,
|
||
|
|
"mean_token_accuracy": 0.1294765926897526,
|
||
|
|
"num_tokens": 2512140.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4609130859375,
|
||
|
|
"epoch": 0.11021407837445574,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999957381851709,
|
||
|
|
"loss": 6.3314,
|
||
|
|
"mean_token_accuracy": 0.12224320769309997,
|
||
|
|
"num_tokens": 2522721.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3936292171478275,
|
||
|
|
"epoch": 0.1106676342525399,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999955367090901,
|
||
|
|
"loss": 6.1999,
|
||
|
|
"mean_token_accuracy": 0.1303488314151764,
|
||
|
|
"num_tokens": 2531786.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.481017780303955,
|
||
|
|
"epoch": 0.11112119013062409,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999953305800441,
|
||
|
|
"loss": 6.3062,
|
||
|
|
"mean_token_accuracy": 0.12003768384456634,
|
||
|
|
"num_tokens": 2542895.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.442375755310058,
|
||
|
|
"epoch": 0.11157474600870827,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999951197980374,
|
||
|
|
"loss": 6.305,
|
||
|
|
"mean_token_accuracy": 0.12665605992078782,
|
||
|
|
"num_tokens": 2554120.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.489529991149903,
|
||
|
|
"epoch": 0.11202830188679246,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999949043630744,
|
||
|
|
"loss": 6.3339,
|
||
|
|
"mean_token_accuracy": 0.12409112006425857,
|
||
|
|
"num_tokens": 2563935.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3626786231994625,
|
||
|
|
"epoch": 0.11248185776487664,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999946842751593,
|
||
|
|
"loss": 6.2477,
|
||
|
|
"mean_token_accuracy": 0.1251929335296154,
|
||
|
|
"num_tokens": 2574465.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.431154251098633,
|
||
|
|
"epoch": 0.11293541364296081,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999944595342968,
|
||
|
|
"loss": 6.2144,
|
||
|
|
"mean_token_accuracy": 0.12585682272911072,
|
||
|
|
"num_tokens": 2584694.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.402558374404907,
|
||
|
|
"epoch": 0.11338896952104499,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999942301404916,
|
||
|
|
"loss": 6.1836,
|
||
|
|
"mean_token_accuracy": 0.1319870851933956,
|
||
|
|
"num_tokens": 2594540.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334234380722046,
|
||
|
|
"epoch": 0.11384252539912917,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004999939960937484,
|
||
|
|
"loss": 6.1343,
|
||
|
|
"mean_token_accuracy": 0.1355540633201599,
|
||
|
|
"num_tokens": 2604896.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.494117069244385,
|
||
|
|
"epoch": 0.11429608127721336,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999937573940721,
|
||
|
|
"loss": 6.2886,
|
||
|
|
"mean_token_accuracy": 0.1345356211066246,
|
||
|
|
"num_tokens": 2614143.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274349880218506,
|
||
|
|
"epoch": 0.11474963715529753,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999935140414674,
|
||
|
|
"loss": 6.1951,
|
||
|
|
"mean_token_accuracy": 0.12857473343610765,
|
||
|
|
"num_tokens": 2623999.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.511336469650269,
|
||
|
|
"epoch": 0.11520319303338171,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999932660359395,
|
||
|
|
"loss": 6.4052,
|
||
|
|
"mean_token_accuracy": 0.12467710450291633,
|
||
|
|
"num_tokens": 2636208.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.449693775177002,
|
||
|
|
"epoch": 0.11565674891146589,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999930133774936,
|
||
|
|
"loss": 6.2795,
|
||
|
|
"mean_token_accuracy": 0.13579537123441696,
|
||
|
|
"num_tokens": 2645854.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.469302797317505,
|
||
|
|
"epoch": 0.11611030478955008,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999927560661348,
|
||
|
|
"loss": 6.2593,
|
||
|
|
"mean_token_accuracy": 0.1359974443912506,
|
||
|
|
"num_tokens": 2655877.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.474381637573242,
|
||
|
|
"epoch": 0.11656386066763426,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999924941018685,
|
||
|
|
"loss": 6.2797,
|
||
|
|
"mean_token_accuracy": 0.1305759347975254,
|
||
|
|
"num_tokens": 2666157.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2998865127563475,
|
||
|
|
"epoch": 0.11701741654571843,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999922274847,
|
||
|
|
"loss": 6.1961,
|
||
|
|
"mean_token_accuracy": 0.13332010209560394,
|
||
|
|
"num_tokens": 2676647.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.388902854919434,
|
||
|
|
"epoch": 0.11747097242380261,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499991956214635,
|
||
|
|
"loss": 6.2308,
|
||
|
|
"mean_token_accuracy": 0.14106824845075608,
|
||
|
|
"num_tokens": 2686417.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.417198610305786,
|
||
|
|
"epoch": 0.1179245283018868,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499991680291679,
|
||
|
|
"loss": 6.2281,
|
||
|
|
"mean_token_accuracy": 0.12554471418261529,
|
||
|
|
"num_tokens": 2697540.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.371242427825928,
|
||
|
|
"epoch": 0.11837808417997098,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999913997158378,
|
||
|
|
"loss": 6.2766,
|
||
|
|
"mean_token_accuracy": 0.12081151455640793,
|
||
|
|
"num_tokens": 2709397.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.381704521179199,
|
||
|
|
"epoch": 0.11883164005805515,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999911144871169,
|
||
|
|
"loss": 6.2198,
|
||
|
|
"mean_token_accuracy": 0.12881449088454247,
|
||
|
|
"num_tokens": 2720430.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3669020652771,
|
||
|
|
"epoch": 0.11928519593613933,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999908246055226,
|
||
|
|
"loss": 6.1855,
|
||
|
|
"mean_token_accuracy": 0.1260046534240246,
|
||
|
|
"num_tokens": 2730648.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3640461444854735,
|
||
|
|
"epoch": 0.11973875181422351,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999905300710607,
|
||
|
|
"loss": 6.1767,
|
||
|
|
"mean_token_accuracy": 0.12971787378191948,
|
||
|
|
"num_tokens": 2739979.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.467068099975586,
|
||
|
|
"epoch": 0.1201923076923077,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999902308837373,
|
||
|
|
"loss": 6.3039,
|
||
|
|
"mean_token_accuracy": 0.12591902986168862,
|
||
|
|
"num_tokens": 2750329.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.297173976898193,
|
||
|
|
"epoch": 0.12064586357039188,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999899270435584,
|
||
|
|
"loss": 6.1752,
|
||
|
|
"mean_token_accuracy": 0.1377357542514801,
|
||
|
|
"num_tokens": 2760535.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.402283620834351,
|
||
|
|
"epoch": 0.12109941944847605,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999896185505307,
|
||
|
|
"loss": 6.2099,
|
||
|
|
"mean_token_accuracy": 0.1282433770596981,
|
||
|
|
"num_tokens": 2770470.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.357119464874268,
|
||
|
|
"epoch": 0.12155297532656023,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999893054046603,
|
||
|
|
"loss": 6.2395,
|
||
|
|
"mean_token_accuracy": 0.12727272063493728,
|
||
|
|
"num_tokens": 2781506.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.281704378128052,
|
||
|
|
"epoch": 0.12200653120464441,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999889876059537,
|
||
|
|
"loss": 6.0945,
|
||
|
|
"mean_token_accuracy": 0.1367440052330494,
|
||
|
|
"num_tokens": 2791245.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.390601301193238,
|
||
|
|
"epoch": 0.1224600870827286,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999886651544176,
|
||
|
|
"loss": 6.1272,
|
||
|
|
"mean_token_accuracy": 0.13428937569260596,
|
||
|
|
"num_tokens": 2801680.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.298570585250855,
|
||
|
|
"epoch": 0.12291364296081277,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999883380500584,
|
||
|
|
"loss": 6.2077,
|
||
|
|
"mean_token_accuracy": 0.13555841743946076,
|
||
|
|
"num_tokens": 2812805.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.452785491943359,
|
||
|
|
"epoch": 0.12336719883889695,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999880062928831,
|
||
|
|
"loss": 6.2401,
|
||
|
|
"mean_token_accuracy": 0.12772336453199387,
|
||
|
|
"num_tokens": 2822834.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322773456573486,
|
||
|
|
"epoch": 0.12382075471698113,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999876698828985,
|
||
|
|
"loss": 6.1829,
|
||
|
|
"mean_token_accuracy": 0.1308009184896946,
|
||
|
|
"num_tokens": 2832312.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.387462949752807,
|
||
|
|
"epoch": 0.12427431059506532,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999873288201116,
|
||
|
|
"loss": 6.1993,
|
||
|
|
"mean_token_accuracy": 0.13682973608374596,
|
||
|
|
"num_tokens": 2842998.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.381214332580567,
|
||
|
|
"epoch": 0.1247278664731495,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004999869831045294,
|
||
|
|
"loss": 6.2182,
|
||
|
|
"mean_token_accuracy": 0.1281896151602268,
|
||
|
|
"num_tokens": 2854218.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274281024932861,
|
||
|
|
"epoch": 0.12518142235123367,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999866327361589,
|
||
|
|
"loss": 6.1073,
|
||
|
|
"mean_token_accuracy": 0.13887619599699974,
|
||
|
|
"num_tokens": 2864484.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.392649173736572,
|
||
|
|
"epoch": 0.12563497822931785,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999862777150077,
|
||
|
|
"loss": 6.2187,
|
||
|
|
"mean_token_accuracy": 0.13294630274176597,
|
||
|
|
"num_tokens": 2873800.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.378524923324585,
|
||
|
|
"epoch": 0.12608853410740203,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999859180410829,
|
||
|
|
"loss": 6.2196,
|
||
|
|
"mean_token_accuracy": 0.12941672652959824,
|
||
|
|
"num_tokens": 2884247.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3022987842559814,
|
||
|
|
"epoch": 0.12654208998548622,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999855537143919,
|
||
|
|
"loss": 6.1277,
|
||
|
|
"mean_token_accuracy": 0.13321435153484346,
|
||
|
|
"num_tokens": 2894739.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330821084976196,
|
||
|
|
"epoch": 0.1269956458635704,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999851847349425,
|
||
|
|
"loss": 6.2018,
|
||
|
|
"mean_token_accuracy": 0.13309190422296524,
|
||
|
|
"num_tokens": 2904376.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41134204864502,
|
||
|
|
"epoch": 0.12744920174165458,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999848111027419,
|
||
|
|
"loss": 6.2438,
|
||
|
|
"mean_token_accuracy": 0.12967129945755004,
|
||
|
|
"num_tokens": 2914304.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346340560913086,
|
||
|
|
"epoch": 0.12790275761973874,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999844328177983,
|
||
|
|
"loss": 6.1142,
|
||
|
|
"mean_token_accuracy": 0.13302754908800124,
|
||
|
|
"num_tokens": 2924400.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468166971206665,
|
||
|
|
"epoch": 0.12835631349782292,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999840498801191,
|
||
|
|
"loss": 6.3637,
|
||
|
|
"mean_token_accuracy": 0.13450959250330924,
|
||
|
|
"num_tokens": 2935040.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.250949144363403,
|
||
|
|
"epoch": 0.1288098693759071,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999836622897126,
|
||
|
|
"loss": 6.139,
|
||
|
|
"mean_token_accuracy": 0.13291264548897744,
|
||
|
|
"num_tokens": 2945536.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.240394401550293,
|
||
|
|
"epoch": 0.1292634252539913,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999832700465865,
|
||
|
|
"loss": 6.0631,
|
||
|
|
"mean_token_accuracy": 0.13600366339087486,
|
||
|
|
"num_tokens": 2954969.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372559261322022,
|
||
|
|
"epoch": 0.12971698113207547,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999828731507491,
|
||
|
|
"loss": 6.1846,
|
||
|
|
"mean_token_accuracy": 0.13019020035862922,
|
||
|
|
"num_tokens": 2966218.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348944854736328,
|
||
|
|
"epoch": 0.13017053701015965,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999824716022085,
|
||
|
|
"loss": 6.2124,
|
||
|
|
"mean_token_accuracy": 0.12568282783031465,
|
||
|
|
"num_tokens": 2976640.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.317825126647949,
|
||
|
|
"epoch": 0.13062409288824384,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999820654009731,
|
||
|
|
"loss": 6.1754,
|
||
|
|
"mean_token_accuracy": 0.13333930373191832,
|
||
|
|
"num_tokens": 2985883.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.33205885887146,
|
||
|
|
"epoch": 0.13107764876632802,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004999816545470513,
|
||
|
|
"loss": 6.1738,
|
||
|
|
"mean_token_accuracy": 0.1286979652941227,
|
||
|
|
"num_tokens": 2996695.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.338008069992066,
|
||
|
|
"epoch": 0.1315312046444122,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999812390404514,
|
||
|
|
"loss": 6.1786,
|
||
|
|
"mean_token_accuracy": 0.13488187193870543,
|
||
|
|
"num_tokens": 3007500.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171080303192139,
|
||
|
|
"epoch": 0.13198476052249636,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999808188811823,
|
||
|
|
"loss": 6.0426,
|
||
|
|
"mean_token_accuracy": 0.13422525823116302,
|
||
|
|
"num_tokens": 3017299.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42709584236145,
|
||
|
|
"epoch": 0.13243831640058054,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999803940692524,
|
||
|
|
"loss": 6.3248,
|
||
|
|
"mean_token_accuracy": 0.12495478615164757,
|
||
|
|
"num_tokens": 3028389.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.34055233001709,
|
||
|
|
"epoch": 0.13289187227866472,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999799646046707,
|
||
|
|
"loss": 6.1313,
|
||
|
|
"mean_token_accuracy": 0.13551339507102966,
|
||
|
|
"num_tokens": 3038883.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.360403776168823,
|
||
|
|
"epoch": 0.1333454281567489,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999795304874461,
|
||
|
|
"loss": 6.2634,
|
||
|
|
"mean_token_accuracy": 0.13484074100852012,
|
||
|
|
"num_tokens": 3049904.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292270040512085,
|
||
|
|
"epoch": 0.1337989840348331,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999790917175873,
|
||
|
|
"loss": 6.0954,
|
||
|
|
"mean_token_accuracy": 0.13213692530989646,
|
||
|
|
"num_tokens": 3059788.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332358312606812,
|
||
|
|
"epoch": 0.13425253991291727,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999786482951036,
|
||
|
|
"loss": 6.0914,
|
||
|
|
"mean_token_accuracy": 0.13121994063258172,
|
||
|
|
"num_tokens": 3070413.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2656394958496096,
|
||
|
|
"epoch": 0.13470609579100146,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004999782002200041,
|
||
|
|
"loss": 6.2047,
|
||
|
|
"mean_token_accuracy": 0.1304186299443245,
|
||
|
|
"num_tokens": 3081093.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334182834625244,
|
||
|
|
"epoch": 0.13515965166908564,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999777474922982,
|
||
|
|
"loss": 6.1612,
|
||
|
|
"mean_token_accuracy": 0.12822958827018738,
|
||
|
|
"num_tokens": 3090594.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.352655935287475,
|
||
|
|
"epoch": 0.13561320754716982,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999772901119951,
|
||
|
|
"loss": 6.2409,
|
||
|
|
"mean_token_accuracy": 0.13285785242915155,
|
||
|
|
"num_tokens": 3101061.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28689432144165,
|
||
|
|
"epoch": 0.13606676342525398,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999768280791043,
|
||
|
|
"loss": 6.1627,
|
||
|
|
"mean_token_accuracy": 0.13513913974165917,
|
||
|
|
"num_tokens": 3111715.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.282320547103882,
|
||
|
|
"epoch": 0.13652031930333816,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999763613936352,
|
||
|
|
"loss": 6.0892,
|
||
|
|
"mean_token_accuracy": 0.13638533875346184,
|
||
|
|
"num_tokens": 3121378.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252392864227295,
|
||
|
|
"epoch": 0.13697387518142234,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999758900555979,
|
||
|
|
"loss": 6.0183,
|
||
|
|
"mean_token_accuracy": 0.13862146139144899,
|
||
|
|
"num_tokens": 3131229.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241233825683594,
|
||
|
|
"epoch": 0.13742743105950653,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999754140650017,
|
||
|
|
"loss": 6.1025,
|
||
|
|
"mean_token_accuracy": 0.13484096452593802,
|
||
|
|
"num_tokens": 3140859.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.310092401504517,
|
||
|
|
"epoch": 0.1378809869375907,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999749334218567,
|
||
|
|
"loss": 6.1048,
|
||
|
|
"mean_token_accuracy": 0.13604142144322395,
|
||
|
|
"num_tokens": 3151692.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2527360916137695,
|
||
|
|
"epoch": 0.1383345428156749,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999744481261726,
|
||
|
|
"loss": 6.1801,
|
||
|
|
"mean_token_accuracy": 0.13370710536837577,
|
||
|
|
"num_tokens": 3161879.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248764514923096,
|
||
|
|
"epoch": 0.13878809869375908,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999739581779597,
|
||
|
|
"loss": 6.0456,
|
||
|
|
"mean_token_accuracy": 0.1446085900068283,
|
||
|
|
"num_tokens": 3171282.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270263290405273,
|
||
|
|
"epoch": 0.13924165457184326,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499973463577228,
|
||
|
|
"loss": 6.1068,
|
||
|
|
"mean_token_accuracy": 0.1418723337352276,
|
||
|
|
"num_tokens": 3181398.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2894738674163815,
|
||
|
|
"epoch": 0.13969521044992744,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999729643239877,
|
||
|
|
"loss": 6.2273,
|
||
|
|
"mean_token_accuracy": 0.1322890356183052,
|
||
|
|
"num_tokens": 3191431.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347840642929077,
|
||
|
|
"epoch": 0.1401487663280116,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999724604182492,
|
||
|
|
"loss": 6.2145,
|
||
|
|
"mean_token_accuracy": 0.12926804050803184,
|
||
|
|
"num_tokens": 3202147.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323010873794556,
|
||
|
|
"epoch": 0.14060232220609578,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999719518600229,
|
||
|
|
"loss": 6.0864,
|
||
|
|
"mean_token_accuracy": 0.13912193179130555,
|
||
|
|
"num_tokens": 3212428.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.246621894836426,
|
||
|
|
"epoch": 0.14105587808417996,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999714386493192,
|
||
|
|
"loss": 6.1409,
|
||
|
|
"mean_token_accuracy": 0.1369505174458027,
|
||
|
|
"num_tokens": 3222099.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.316340351104737,
|
||
|
|
"epoch": 0.14150943396226415,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999709207861489,
|
||
|
|
"loss": 6.0828,
|
||
|
|
"mean_token_accuracy": 0.13749494701623916,
|
||
|
|
"num_tokens": 3232079.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204212045669555,
|
||
|
|
"epoch": 0.14196298984034833,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999703982705227,
|
||
|
|
"loss": 6.005,
|
||
|
|
"mean_token_accuracy": 0.14854954034090043,
|
||
|
|
"num_tokens": 3241762.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180720520019531,
|
||
|
|
"epoch": 0.1424165457184325,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999698711024513,
|
||
|
|
"loss": 6.0869,
|
||
|
|
"mean_token_accuracy": 0.13718333020806311,
|
||
|
|
"num_tokens": 3252571.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.293680715560913,
|
||
|
|
"epoch": 0.1428701015965167,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999693392819456,
|
||
|
|
"loss": 6.1328,
|
||
|
|
"mean_token_accuracy": 0.1329519271850586,
|
||
|
|
"num_tokens": 3263542.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.287594938278199,
|
||
|
|
"epoch": 0.14332365747460088,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999688028090166,
|
||
|
|
"loss": 6.1936,
|
||
|
|
"mean_token_accuracy": 0.13597823828458785,
|
||
|
|
"num_tokens": 3273295.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.440543842315674,
|
||
|
|
"epoch": 0.14377721335268506,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999682616836755,
|
||
|
|
"loss": 6.2261,
|
||
|
|
"mean_token_accuracy": 0.1362229973077774,
|
||
|
|
"num_tokens": 3283605.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.197280740737915,
|
||
|
|
"epoch": 0.14423076923076922,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999677159059334,
|
||
|
|
"loss": 6.0532,
|
||
|
|
"mean_token_accuracy": 0.14048462361097336,
|
||
|
|
"num_tokens": 3293837.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.210299730300903,
|
||
|
|
"epoch": 0.1446843251088534,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999671654758016,
|
||
|
|
"loss": 6.0692,
|
||
|
|
"mean_token_accuracy": 0.14433105364441873,
|
||
|
|
"num_tokens": 3304131.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.238543367385864,
|
||
|
|
"epoch": 0.14513788098693758,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999666103932915,
|
||
|
|
"loss": 6.1103,
|
||
|
|
"mean_token_accuracy": 0.13127385154366494,
|
||
|
|
"num_tokens": 3313543.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.23192195892334,
|
||
|
|
"epoch": 0.14559143686502177,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999660506584145,
|
||
|
|
"loss": 6.0745,
|
||
|
|
"mean_token_accuracy": 0.1385864198207855,
|
||
|
|
"num_tokens": 3324487.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.296097135543823,
|
||
|
|
"epoch": 0.14604499274310595,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999654862711823,
|
||
|
|
"loss": 6.1001,
|
||
|
|
"mean_token_accuracy": 0.13781747072935105,
|
||
|
|
"num_tokens": 3335094.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.208214139938354,
|
||
|
|
"epoch": 0.14649854862119013,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999649172316065,
|
||
|
|
"loss": 6.04,
|
||
|
|
"mean_token_accuracy": 0.13336168527603148,
|
||
|
|
"num_tokens": 3344252.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.273281383514404,
|
||
|
|
"epoch": 0.14695210449927432,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499964343539699,
|
||
|
|
"loss": 6.1072,
|
||
|
|
"mean_token_accuracy": 0.1359778583049774,
|
||
|
|
"num_tokens": 3354265.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.312763309478759,
|
||
|
|
"epoch": 0.1474056603773585,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999637651954714,
|
||
|
|
"loss": 6.2133,
|
||
|
|
"mean_token_accuracy": 0.13838177993893624,
|
||
|
|
"num_tokens": 3364616.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.300515222549438,
|
||
|
|
"epoch": 0.14785921625544268,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999631821989358,
|
||
|
|
"loss": 6.1601,
|
||
|
|
"mean_token_accuracy": 0.13766503930091858,
|
||
|
|
"num_tokens": 3373650.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221302127838134,
|
||
|
|
"epoch": 0.14831277213352684,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999625945501043,
|
||
|
|
"loss": 6.0573,
|
||
|
|
"mean_token_accuracy": 0.1438056230545044,
|
||
|
|
"num_tokens": 3384590.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.271721410751343,
|
||
|
|
"epoch": 0.14876632801161102,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000499962002248989,
|
||
|
|
"loss": 6.0793,
|
||
|
|
"mean_token_accuracy": 0.13807034716010094,
|
||
|
|
"num_tokens": 3395616.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2336437702178955,
|
||
|
|
"epoch": 0.1492198838896952,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999614052956024,
|
||
|
|
"loss": 6.0885,
|
||
|
|
"mean_token_accuracy": 0.13720295056700707,
|
||
|
|
"num_tokens": 3405810.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2871723651885985,
|
||
|
|
"epoch": 0.1496734397677794,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999608036899563,
|
||
|
|
"loss": 6.1248,
|
||
|
|
"mean_token_accuracy": 0.13411571234464645,
|
||
|
|
"num_tokens": 3415932.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227649116516114,
|
||
|
|
"epoch": 0.15012699564586357,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999601974320636,
|
||
|
|
"loss": 6.0773,
|
||
|
|
"mean_token_accuracy": 0.13326597362756729,
|
||
|
|
"num_tokens": 3425626.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198207044601441,
|
||
|
|
"epoch": 0.15058055152394775,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999595865219367,
|
||
|
|
"loss": 6.098,
|
||
|
|
"mean_token_accuracy": 0.13101402595639228,
|
||
|
|
"num_tokens": 3434837.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.252737283706665,
|
||
|
|
"epoch": 0.15103410740203194,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999589709595881,
|
||
|
|
"loss": 6.0898,
|
||
|
|
"mean_token_accuracy": 0.14350827634334565,
|
||
|
|
"num_tokens": 3445238.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.187345504760742,
|
||
|
|
"epoch": 0.15148766328011612,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999583507450308,
|
||
|
|
"loss": 6.0692,
|
||
|
|
"mean_token_accuracy": 0.13529428243637084,
|
||
|
|
"num_tokens": 3456738.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133850383758545,
|
||
|
|
"epoch": 0.1519412191582003,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999577258782774,
|
||
|
|
"loss": 5.9664,
|
||
|
|
"mean_token_accuracy": 0.13891834691166877,
|
||
|
|
"num_tokens": 3466296.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328598546981811,
|
||
|
|
"epoch": 0.15239477503628446,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000499957096359341,
|
||
|
|
"loss": 6.1502,
|
||
|
|
"mean_token_accuracy": 0.13001871183514596,
|
||
|
|
"num_tokens": 3476989.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21191725730896,
|
||
|
|
"epoch": 0.15284833091436864,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999564621882343,
|
||
|
|
"loss": 5.9815,
|
||
|
|
"mean_token_accuracy": 0.14194255620241164,
|
||
|
|
"num_tokens": 3487050.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.256222677230835,
|
||
|
|
"epoch": 0.15330188679245282,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999558233649708,
|
||
|
|
"loss": 6.2052,
|
||
|
|
"mean_token_accuracy": 0.1338474340736866,
|
||
|
|
"num_tokens": 3497777.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257563257217408,
|
||
|
|
"epoch": 0.153755442670537,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999551798895636,
|
||
|
|
"loss": 6.1012,
|
||
|
|
"mean_token_accuracy": 0.13192513063549996,
|
||
|
|
"num_tokens": 3509066.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.171849775314331,
|
||
|
|
"epoch": 0.1542089985486212,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999545317620258,
|
||
|
|
"loss": 6.0377,
|
||
|
|
"mean_token_accuracy": 0.13509414941072465,
|
||
|
|
"num_tokens": 3519567.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180337810516358,
|
||
|
|
"epoch": 0.15466255442670537,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999538789823711,
|
||
|
|
"loss": 6.0677,
|
||
|
|
"mean_token_accuracy": 0.1376472532749176,
|
||
|
|
"num_tokens": 3529402.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.29026083946228,
|
||
|
|
"epoch": 0.15511611030478956,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999532215506127,
|
||
|
|
"loss": 6.0768,
|
||
|
|
"mean_token_accuracy": 0.14445007145404815,
|
||
|
|
"num_tokens": 3539805.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146165990829468,
|
||
|
|
"epoch": 0.15556966618287374,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999525594667645,
|
||
|
|
"loss": 5.9557,
|
||
|
|
"mean_token_accuracy": 0.1396943673491478,
|
||
|
|
"num_tokens": 3550477.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.103784704208374,
|
||
|
|
"epoch": 0.15602322206095792,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00049995189273084,
|
||
|
|
"loss": 6.0572,
|
||
|
|
"mean_token_accuracy": 0.13744304925203324,
|
||
|
|
"num_tokens": 3560729.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.271568822860718,
|
||
|
|
"epoch": 0.15647677793904208,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499951221342853,
|
||
|
|
"loss": 6.1321,
|
||
|
|
"mean_token_accuracy": 0.1289873942732811,
|
||
|
|
"num_tokens": 3571538.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223130464553833,
|
||
|
|
"epoch": 0.15693033381712626,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999505453028174,
|
||
|
|
"loss": 6.1212,
|
||
|
|
"mean_token_accuracy": 0.1351299576461315,
|
||
|
|
"num_tokens": 3583128.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263720464706421,
|
||
|
|
"epoch": 0.15738388969521044,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999498646107472,
|
||
|
|
"loss": 6.0628,
|
||
|
|
"mean_token_accuracy": 0.13980068638920784,
|
||
|
|
"num_tokens": 3594358.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227974891662598,
|
||
|
|
"epoch": 0.15783744557329463,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999491792666566,
|
||
|
|
"loss": 5.9844,
|
||
|
|
"mean_token_accuracy": 0.14432255774736405,
|
||
|
|
"num_tokens": 3604345.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122195100784301,
|
||
|
|
"epoch": 0.1582910014513788,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999484892705597,
|
||
|
|
"loss": 6.0287,
|
||
|
|
"mean_token_accuracy": 0.13807731494307518,
|
||
|
|
"num_tokens": 3616129.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.275023746490478,
|
||
|
|
"epoch": 0.158744557329463,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999477946224705,
|
||
|
|
"loss": 6.0836,
|
||
|
|
"mean_token_accuracy": 0.14040916562080383,
|
||
|
|
"num_tokens": 3627458.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181599187850952,
|
||
|
|
"epoch": 0.15919811320754718,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999470953224037,
|
||
|
|
"loss": 5.9586,
|
||
|
|
"mean_token_accuracy": 0.1387786313891411,
|
||
|
|
"num_tokens": 3636047.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1431786060333256,
|
||
|
|
"epoch": 0.15965166908563136,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999463913703735,
|
||
|
|
"loss": 5.9542,
|
||
|
|
"mean_token_accuracy": 0.13981650844216348,
|
||
|
|
"num_tokens": 3646930.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141822052001953,
|
||
|
|
"epoch": 0.16010522496371554,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999456827663948,
|
||
|
|
"loss": 6.0495,
|
||
|
|
"mean_token_accuracy": 0.1432150684297085,
|
||
|
|
"num_tokens": 3657279.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173039388656616,
|
||
|
|
"epoch": 0.1605587808417997,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499944969510482,
|
||
|
|
"loss": 5.9656,
|
||
|
|
"mean_token_accuracy": 0.141604046523571,
|
||
|
|
"num_tokens": 3667070.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.148836374282837,
|
||
|
|
"epoch": 0.16101233671988388,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999442516026498,
|
||
|
|
"loss": 5.9909,
|
||
|
|
"mean_token_accuracy": 0.13877027854323387,
|
||
|
|
"num_tokens": 3677560.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135176277160644,
|
||
|
|
"epoch": 0.16146589259796806,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999435290429133,
|
||
|
|
"loss": 5.951,
|
||
|
|
"mean_token_accuracy": 0.14585819393396376,
|
||
|
|
"num_tokens": 3686701.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194845485687256,
|
||
|
|
"epoch": 0.16191944847605225,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999428018312872,
|
||
|
|
"loss": 6.0453,
|
||
|
|
"mean_token_accuracy": 0.14197150394320487,
|
||
|
|
"num_tokens": 3696338.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213848018646241,
|
||
|
|
"epoch": 0.16237300435413643,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999420699677867,
|
||
|
|
"loss": 6.0178,
|
||
|
|
"mean_token_accuracy": 0.13948137164115906,
|
||
|
|
"num_tokens": 3705752.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173350286483765,
|
||
|
|
"epoch": 0.1628265602322206,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999413334524269,
|
||
|
|
"loss": 6.1086,
|
||
|
|
"mean_token_accuracy": 0.13366367369890214,
|
||
|
|
"num_tokens": 3716225.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1766557693481445,
|
||
|
|
"epoch": 0.1632801161103048,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999405922852229,
|
||
|
|
"loss": 5.9812,
|
||
|
|
"mean_token_accuracy": 0.1403820961713791,
|
||
|
|
"num_tokens": 3726593.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1498106002807615,
|
||
|
|
"epoch": 0.16373367198838898,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999398464661901,
|
||
|
|
"loss": 6.0292,
|
||
|
|
"mean_token_accuracy": 0.13524944633245467,
|
||
|
|
"num_tokens": 3737563.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278463888168335,
|
||
|
|
"epoch": 0.16418722786647316,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999390959953441,
|
||
|
|
"loss": 6.0868,
|
||
|
|
"mean_token_accuracy": 0.13811569064855575,
|
||
|
|
"num_tokens": 3747752.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.124238109588623,
|
||
|
|
"epoch": 0.16464078374455732,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999383408727002,
|
||
|
|
"loss": 6.0109,
|
||
|
|
"mean_token_accuracy": 0.13542224168777467,
|
||
|
|
"num_tokens": 3758795.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21006441116333,
|
||
|
|
"epoch": 0.1650943396226415,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999375810982741,
|
||
|
|
"loss": 6.0051,
|
||
|
|
"mean_token_accuracy": 0.14309126287698745,
|
||
|
|
"num_tokens": 3768690.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147620582580567,
|
||
|
|
"epoch": 0.16554789550072568,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999368166720815,
|
||
|
|
"loss": 6.0588,
|
||
|
|
"mean_token_accuracy": 0.137413576990366,
|
||
|
|
"num_tokens": 3779018.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.241029739379883,
|
||
|
|
"epoch": 0.16600145137880987,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999360475941382,
|
||
|
|
"loss": 5.9743,
|
||
|
|
"mean_token_accuracy": 0.14609253406524658,
|
||
|
|
"num_tokens": 3788985.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181500005722046,
|
||
|
|
"epoch": 0.16645500725689405,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00049993527386446,
|
||
|
|
"loss": 6.0916,
|
||
|
|
"mean_token_accuracy": 0.13334065973758696,
|
||
|
|
"num_tokens": 3800787.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.164537858963013,
|
||
|
|
"epoch": 0.16690856313497823,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999344954830633,
|
||
|
|
"loss": 5.9801,
|
||
|
|
"mean_token_accuracy": 0.1378617025911808,
|
||
|
|
"num_tokens": 3811381.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.188645315170288,
|
||
|
|
"epoch": 0.16736211901306242,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999337124499638,
|
||
|
|
"loss": 6.0844,
|
||
|
|
"mean_token_accuracy": 0.14289560168981552,
|
||
|
|
"num_tokens": 3822055.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152506732940674,
|
||
|
|
"epoch": 0.1678156748911466,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999329247651777,
|
||
|
|
"loss": 6.0558,
|
||
|
|
"mean_token_accuracy": 0.13555024489760398,
|
||
|
|
"num_tokens": 3831900.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.184814882278443,
|
||
|
|
"epoch": 0.16826923076923078,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999321324287213,
|
||
|
|
"loss": 6.0046,
|
||
|
|
"mean_token_accuracy": 0.1400987111032009,
|
||
|
|
"num_tokens": 3842702.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.251664876937866,
|
||
|
|
"epoch": 0.16872278664731494,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999313354406114,
|
||
|
|
"loss": 5.986,
|
||
|
|
"mean_token_accuracy": 0.1382150486111641,
|
||
|
|
"num_tokens": 3852690.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014293146133423,
|
||
|
|
"epoch": 0.16917634252539912,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499930533800864,
|
||
|
|
"loss": 5.9598,
|
||
|
|
"mean_token_accuracy": 0.15227705091238022,
|
||
|
|
"num_tokens": 3863040.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.209018230438232,
|
||
|
|
"epoch": 0.1696298984034833,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999297275094958,
|
||
|
|
"loss": 6.065,
|
||
|
|
"mean_token_accuracy": 0.13639552444219588,
|
||
|
|
"num_tokens": 3873613.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046637344360351,
|
||
|
|
"epoch": 0.1700834542815675,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999289165665235,
|
||
|
|
"loss": 5.8751,
|
||
|
|
"mean_token_accuracy": 0.14939435720443725,
|
||
|
|
"num_tokens": 3883936.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090919876098633,
|
||
|
|
"epoch": 0.17053701015965167,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999281009719639,
|
||
|
|
"loss": 5.8273,
|
||
|
|
"mean_token_accuracy": 0.15036647394299507,
|
||
|
|
"num_tokens": 3893788.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0542162418365475,
|
||
|
|
"epoch": 0.17099056603773585,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999272807258339,
|
||
|
|
"loss": 5.912,
|
||
|
|
"mean_token_accuracy": 0.14638229012489318,
|
||
|
|
"num_tokens": 3903434.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.142886686325073,
|
||
|
|
"epoch": 0.17144412191582004,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999264558281504,
|
||
|
|
"loss": 5.9101,
|
||
|
|
"mean_token_accuracy": 0.14875417798757554,
|
||
|
|
"num_tokens": 3913476.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993232488632202,
|
||
|
|
"epoch": 0.17189767779390422,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999256262789305,
|
||
|
|
"loss": 5.8601,
|
||
|
|
"mean_token_accuracy": 0.14939367920160293,
|
||
|
|
"num_tokens": 3923301.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073164653778076,
|
||
|
|
"epoch": 0.1723512336719884,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999247920781913,
|
||
|
|
"loss": 6.0334,
|
||
|
|
"mean_token_accuracy": 0.13975203409790993,
|
||
|
|
"num_tokens": 3933335.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.233634042739868,
|
||
|
|
"epoch": 0.17280478955007256,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999239532259502,
|
||
|
|
"loss": 6.037,
|
||
|
|
"mean_token_accuracy": 0.13394607827067376,
|
||
|
|
"num_tokens": 3944171.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.214393186569214,
|
||
|
|
"epoch": 0.17325834542815674,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999231097222244,
|
||
|
|
"loss": 6.1071,
|
||
|
|
"mean_token_accuracy": 0.14265160858631135,
|
||
|
|
"num_tokens": 3954160.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173836088180542,
|
||
|
|
"epoch": 0.17371190130624092,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999222615670312,
|
||
|
|
"loss": 5.9094,
|
||
|
|
"mean_token_accuracy": 0.14953405708074569,
|
||
|
|
"num_tokens": 3964110.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1780534267425535,
|
||
|
|
"epoch": 0.1741654571843251,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999214087603885,
|
||
|
|
"loss": 6.0034,
|
||
|
|
"mean_token_accuracy": 0.14108952656388282,
|
||
|
|
"num_tokens": 3974293.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1007123470306395,
|
||
|
|
"epoch": 0.1746190130624093,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999205513023135,
|
||
|
|
"loss": 5.9491,
|
||
|
|
"mean_token_accuracy": 0.1505696728825569,
|
||
|
|
"num_tokens": 3984346.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014599132537842,
|
||
|
|
"epoch": 0.17507256894049347,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999196891928245,
|
||
|
|
"loss": 5.8944,
|
||
|
|
"mean_token_accuracy": 0.1506063535809517,
|
||
|
|
"num_tokens": 3992897.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1384530544281,
|
||
|
|
"epoch": 0.17552612481857766,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999188224319388,
|
||
|
|
"loss": 5.929,
|
||
|
|
"mean_token_accuracy": 0.1495840311050415,
|
||
|
|
"num_tokens": 4002575.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0449896335601805,
|
||
|
|
"epoch": 0.17597968069666184,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999179510196746,
|
||
|
|
"loss": 6.0023,
|
||
|
|
"mean_token_accuracy": 0.1404266342520714,
|
||
|
|
"num_tokens": 4013752.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181995582580567,
|
||
|
|
"epoch": 0.17643323657474602,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999170749560498,
|
||
|
|
"loss": 5.8891,
|
||
|
|
"mean_token_accuracy": 0.14904519468545913,
|
||
|
|
"num_tokens": 4023718.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080067110061646,
|
||
|
|
"epoch": 0.17688679245283018,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999161942410827,
|
||
|
|
"loss": 5.9877,
|
||
|
|
"mean_token_accuracy": 0.13862392008304597,
|
||
|
|
"num_tokens": 4034210.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.194681644439697,
|
||
|
|
"epoch": 0.17734034833091436,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999153088747913,
|
||
|
|
"loss": 5.9752,
|
||
|
|
"mean_token_accuracy": 0.14118978679180144,
|
||
|
|
"num_tokens": 4044868.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.018691873550415,
|
||
|
|
"epoch": 0.17779390420899854,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000499914418857194,
|
||
|
|
"loss": 5.9759,
|
||
|
|
"mean_token_accuracy": 0.14467088282108306,
|
||
|
|
"num_tokens": 4055049.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.195721387863159,
|
||
|
|
"epoch": 0.17824746008708273,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999135241883092,
|
||
|
|
"loss": 6.0328,
|
||
|
|
"mean_token_accuracy": 0.13953902348876,
|
||
|
|
"num_tokens": 4065889.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.124079751968384,
|
||
|
|
"epoch": 0.1787010159651669,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999126248681555,
|
||
|
|
"loss": 6.0438,
|
||
|
|
"mean_token_accuracy": 0.13967278376221656,
|
||
|
|
"num_tokens": 4077288.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1740796089172365,
|
||
|
|
"epoch": 0.1791545718432511,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999117208967513,
|
||
|
|
"loss": 5.9939,
|
||
|
|
"mean_token_accuracy": 0.14228827133774757,
|
||
|
|
"num_tokens": 4087402.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.136812305450439,
|
||
|
|
"epoch": 0.17960812772133528,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999108122741154,
|
||
|
|
"loss": 6.0412,
|
||
|
|
"mean_token_accuracy": 0.13958762884140014,
|
||
|
|
"num_tokens": 4098150.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085280323028565,
|
||
|
|
"epoch": 0.18006168359941946,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999098990002666,
|
||
|
|
"loss": 5.9088,
|
||
|
|
"mean_token_accuracy": 0.14206465110182762,
|
||
|
|
"num_tokens": 4108134.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.158121109008789,
|
||
|
|
"epoch": 0.18051523947750364,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999089810752237,
|
||
|
|
"loss": 6.0448,
|
||
|
|
"mean_token_accuracy": 0.13666467741131783,
|
||
|
|
"num_tokens": 4118251.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.078621101379395,
|
||
|
|
"epoch": 0.1809687953555878,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499908058499006,
|
||
|
|
"loss": 5.8876,
|
||
|
|
"mean_token_accuracy": 0.14455655217170715,
|
||
|
|
"num_tokens": 4129228.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047148942947388,
|
||
|
|
"epoch": 0.18142235123367198,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999071312716321,
|
||
|
|
"loss": 5.9426,
|
||
|
|
"mean_token_accuracy": 0.15172967463731765,
|
||
|
|
"num_tokens": 4139391.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093998432159424,
|
||
|
|
"epoch": 0.18187590711175616,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999061993931215,
|
||
|
|
"loss": 5.88,
|
||
|
|
"mean_token_accuracy": 0.15255183577537537,
|
||
|
|
"num_tokens": 4148891.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.305850887298584,
|
||
|
|
"epoch": 0.18232946298984035,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999052628634934,
|
||
|
|
"loss": 6.2083,
|
||
|
|
"mean_token_accuracy": 0.13769319280982018,
|
||
|
|
"num_tokens": 4159551.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18409833908081,
|
||
|
|
"epoch": 0.18278301886792453,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999043216827671,
|
||
|
|
"loss": 6.0219,
|
||
|
|
"mean_token_accuracy": 0.1419105350971222,
|
||
|
|
"num_tokens": 4170055.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019263553619385,
|
||
|
|
"epoch": 0.1832365747460087,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004999033758509621,
|
||
|
|
"loss": 5.8725,
|
||
|
|
"mean_token_accuracy": 0.142510387301445,
|
||
|
|
"num_tokens": 4180767.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1171001434326175,
|
||
|
|
"epoch": 0.1836901306240929,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000499902425368098,
|
||
|
|
"loss": 5.99,
|
||
|
|
"mean_token_accuracy": 0.1484679900109768,
|
||
|
|
"num_tokens": 4190654.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084097576141358,
|
||
|
|
"epoch": 0.18414368650217708,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999014702341944,
|
||
|
|
"loss": 5.9217,
|
||
|
|
"mean_token_accuracy": 0.14448753595352173,
|
||
|
|
"num_tokens": 4200753.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.135722398757935,
|
||
|
|
"epoch": 0.18459724238026126,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999005104492712,
|
||
|
|
"loss": 5.9985,
|
||
|
|
"mean_token_accuracy": 0.14054833576083184,
|
||
|
|
"num_tokens": 4210994.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.120487928390503,
|
||
|
|
"epoch": 0.18505079825834542,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998995460133481,
|
||
|
|
"loss": 5.9412,
|
||
|
|
"mean_token_accuracy": 0.14108474180102348,
|
||
|
|
"num_tokens": 4220883.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127297973632812,
|
||
|
|
"epoch": 0.1855043541364296,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004998985769264451,
|
||
|
|
"loss": 5.977,
|
||
|
|
"mean_token_accuracy": 0.13780092522501947,
|
||
|
|
"num_tokens": 4231269.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101497316360474,
|
||
|
|
"epoch": 0.18595791001451378,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998976031885821,
|
||
|
|
"loss": 5.9776,
|
||
|
|
"mean_token_accuracy": 0.1418766401708126,
|
||
|
|
"num_tokens": 4241559.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.121247720718384,
|
||
|
|
"epoch": 0.18641146589259797,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998966247997794,
|
||
|
|
"loss": 5.8733,
|
||
|
|
"mean_token_accuracy": 0.14405595809221267,
|
||
|
|
"num_tokens": 4250870.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.015826034545898,
|
||
|
|
"epoch": 0.18686502177068215,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998956417600572,
|
||
|
|
"loss": 5.8246,
|
||
|
|
"mean_token_accuracy": 0.15058073103427888,
|
||
|
|
"num_tokens": 4260848.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.08300142288208,
|
||
|
|
"epoch": 0.18731857764876633,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998946540694358,
|
||
|
|
"loss": 5.9464,
|
||
|
|
"mean_token_accuracy": 0.1485067129135132,
|
||
|
|
"num_tokens": 4270973.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14107756614685,
|
||
|
|
"epoch": 0.18777213352685052,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998936617279357,
|
||
|
|
"loss": 6.0361,
|
||
|
|
"mean_token_accuracy": 0.14370361119508743,
|
||
|
|
"num_tokens": 4281211.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.045505952835083,
|
||
|
|
"epoch": 0.1882256894049347,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004998926647355773,
|
||
|
|
"loss": 5.8954,
|
||
|
|
"mean_token_accuracy": 0.14735701233148574,
|
||
|
|
"num_tokens": 4291425.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1746431350708,
|
||
|
|
"epoch": 0.18867924528301888,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998916630923813,
|
||
|
|
"loss": 5.9993,
|
||
|
|
"mean_token_accuracy": 0.14234295561909677,
|
||
|
|
"num_tokens": 4301079.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0917683124542235,
|
||
|
|
"epoch": 0.18913280116110304,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998906567983685,
|
||
|
|
"loss": 5.9599,
|
||
|
|
"mean_token_accuracy": 0.14310015216469765,
|
||
|
|
"num_tokens": 4312374.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10637731552124,
|
||
|
|
"epoch": 0.18958635703918722,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998896458535595,
|
||
|
|
"loss": 5.8884,
|
||
|
|
"mean_token_accuracy": 0.15468773394823074,
|
||
|
|
"num_tokens": 4322810.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0409440994262695,
|
||
|
|
"epoch": 0.1900399129172714,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998886302579752,
|
||
|
|
"loss": 5.888,
|
||
|
|
"mean_token_accuracy": 0.14332466721534728,
|
||
|
|
"num_tokens": 4332082.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.115694570541382,
|
||
|
|
"epoch": 0.19049346879535559,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499887610011637,
|
||
|
|
"loss": 5.9771,
|
||
|
|
"mean_token_accuracy": 0.14411457404494285,
|
||
|
|
"num_tokens": 4342632.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025098752975464,
|
||
|
|
"epoch": 0.19094702467343977,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998865851145656,
|
||
|
|
"loss": 5.9079,
|
||
|
|
"mean_token_accuracy": 0.14562978297472,
|
||
|
|
"num_tokens": 4353544.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080524492263794,
|
||
|
|
"epoch": 0.19140058055152395,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998855555667822,
|
||
|
|
"loss": 6.0337,
|
||
|
|
"mean_token_accuracy": 0.13668391555547715,
|
||
|
|
"num_tokens": 4363636.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174575281143189,
|
||
|
|
"epoch": 0.19185413642960814,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998845213683084,
|
||
|
|
"loss": 5.91,
|
||
|
|
"mean_token_accuracy": 0.14217197224497796,
|
||
|
|
"num_tokens": 4373672.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952403831481933,
|
||
|
|
"epoch": 0.19230769230769232,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998834825191652,
|
||
|
|
"loss": 5.8609,
|
||
|
|
"mean_token_accuracy": 0.14928537905216216,
|
||
|
|
"num_tokens": 4383199.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0944489479064945,
|
||
|
|
"epoch": 0.1927612481857765,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998824390193743,
|
||
|
|
"loss": 5.9295,
|
||
|
|
"mean_token_accuracy": 0.14216511845588684,
|
||
|
|
"num_tokens": 4394446.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.156260538101196,
|
||
|
|
"epoch": 0.19321480406386066,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998813908689573,
|
||
|
|
"loss": 5.9814,
|
||
|
|
"mean_token_accuracy": 0.14446035400032997,
|
||
|
|
"num_tokens": 4405882.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021085166931153,
|
||
|
|
"epoch": 0.19366835994194484,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004998803380679359,
|
||
|
|
"loss": 5.8395,
|
||
|
|
"mean_token_accuracy": 0.15445481687784196,
|
||
|
|
"num_tokens": 4415280.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026923942565918,
|
||
|
|
"epoch": 0.19412191582002902,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998792806163317,
|
||
|
|
"loss": 6.0418,
|
||
|
|
"mean_token_accuracy": 0.1423596292734146,
|
||
|
|
"num_tokens": 4425755.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0691611766815186,
|
||
|
|
"epoch": 0.1945754716981132,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998782185141667,
|
||
|
|
"loss": 5.899,
|
||
|
|
"mean_token_accuracy": 0.1436906062066555,
|
||
|
|
"num_tokens": 4436259.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100642156600952,
|
||
|
|
"epoch": 0.1950290275761974,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998771517614629,
|
||
|
|
"loss": 5.9354,
|
||
|
|
"mean_token_accuracy": 0.14032572209835054,
|
||
|
|
"num_tokens": 4446423.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079388666152954,
|
||
|
|
"epoch": 0.19548258345428157,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998760803582422,
|
||
|
|
"loss": 5.8765,
|
||
|
|
"mean_token_accuracy": 0.15558486431837082,
|
||
|
|
"num_tokens": 4456678.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.038434076309204,
|
||
|
|
"epoch": 0.19593613933236576,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998750043045269,
|
||
|
|
"loss": 5.88,
|
||
|
|
"mean_token_accuracy": 0.1474220186471939,
|
||
|
|
"num_tokens": 4467031.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084740686416626,
|
||
|
|
"epoch": 0.19638969521044994,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998739236003392,
|
||
|
|
"loss": 5.9457,
|
||
|
|
"mean_token_accuracy": 0.13701039925217628,
|
||
|
|
"num_tokens": 4477771.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058000755310059,
|
||
|
|
"epoch": 0.1968432510885341,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998728382457014,
|
||
|
|
"loss": 5.9724,
|
||
|
|
"mean_token_accuracy": 0.14374302327632904,
|
||
|
|
"num_tokens": 4488426.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157823610305786,
|
||
|
|
"epoch": 0.19729680696661828,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004998717482406362,
|
||
|
|
"loss": 5.9512,
|
||
|
|
"mean_token_accuracy": 0.14008950740098952,
|
||
|
|
"num_tokens": 4499735.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.083208417892456,
|
||
|
|
"epoch": 0.19775036284470246,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998706535851657,
|
||
|
|
"loss": 5.9067,
|
||
|
|
"mean_token_accuracy": 0.1461469426751137,
|
||
|
|
"num_tokens": 4509500.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037715578079224,
|
||
|
|
"epoch": 0.19820391872278664,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004998695542793129,
|
||
|
|
"loss": 5.9079,
|
||
|
|
"mean_token_accuracy": 0.14525417983531952,
|
||
|
|
"num_tokens": 4520431.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.084038925170899,
|
||
|
|
"epoch": 0.19865747460087083,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998684503231003,
|
||
|
|
"loss": 5.9846,
|
||
|
|
"mean_token_accuracy": 0.14418850764632224,
|
||
|
|
"num_tokens": 4532294.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.027761554718017,
|
||
|
|
"epoch": 0.199111030478955,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000499867341716551,
|
||
|
|
"loss": 5.8985,
|
||
|
|
"mean_token_accuracy": 0.1443702645599842,
|
||
|
|
"num_tokens": 4542488.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043829488754272,
|
||
|
|
"epoch": 0.1995645863570392,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998662284596878,
|
||
|
|
"loss": 5.8528,
|
||
|
|
"mean_token_accuracy": 0.1418704494833946,
|
||
|
|
"num_tokens": 4552933.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060906505584716,
|
||
|
|
"epoch": 0.20001814223512338,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004998651105525335,
|
||
|
|
"loss": 5.8336,
|
||
|
|
"mean_token_accuracy": 0.15473553836345671,
|
||
|
|
"num_tokens": 4562373.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9967522621154785,
|
||
|
|
"epoch": 0.20047169811320756,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004998639879951115,
|
||
|
|
"loss": 5.9557,
|
||
|
|
"mean_token_accuracy": 0.14503294080495835,
|
||
|
|
"num_tokens": 4572715.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131484937667847,
|
||
|
|
"epoch": 0.2009252539912917,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499862860787445,
|
||
|
|
"loss": 5.8461,
|
||
|
|
"mean_token_accuracy": 0.1420556351542473,
|
||
|
|
"num_tokens": 4582782.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036686944961548,
|
||
|
|
"epoch": 0.2013788098693759,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004998617289295571,
|
||
|
|
"loss": 5.9439,
|
||
|
|
"mean_token_accuracy": 0.14234896376729012,
|
||
|
|
"num_tokens": 4594108.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102933645248413,
|
||
|
|
"epoch": 0.20183236574746008,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998605924214714,
|
||
|
|
"loss": 5.9103,
|
||
|
|
"mean_token_accuracy": 0.14780050218105317,
|
||
|
|
"num_tokens": 4604732.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049504566192627,
|
||
|
|
"epoch": 0.20228592162554426,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998594512632114,
|
||
|
|
"loss": 6.0456,
|
||
|
|
"mean_token_accuracy": 0.13591379299759865,
|
||
|
|
"num_tokens": 4614998.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057260751724243,
|
||
|
|
"epoch": 0.20273947750362845,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004998583054548006,
|
||
|
|
"loss": 5.8648,
|
||
|
|
"mean_token_accuracy": 0.14422834739089013,
|
||
|
|
"num_tokens": 4624665.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085105228424072,
|
||
|
|
"epoch": 0.20319303338171263,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004998571549962628,
|
||
|
|
"loss": 5.8612,
|
||
|
|
"mean_token_accuracy": 0.15319595485925674,
|
||
|
|
"num_tokens": 4633731.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046474456787109,
|
||
|
|
"epoch": 0.2036465892597968,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998559998876216,
|
||
|
|
"loss": 5.8897,
|
||
|
|
"mean_token_accuracy": 0.14516430646181105,
|
||
|
|
"num_tokens": 4643421.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105594730377197,
|
||
|
|
"epoch": 0.204100145137881,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998548401289012,
|
||
|
|
"loss": 5.9729,
|
||
|
|
"mean_token_accuracy": 0.14359490424394608,
|
||
|
|
"num_tokens": 4653795.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111778020858765,
|
||
|
|
"epoch": 0.20455370101596518,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998536757201253,
|
||
|
|
"loss": 5.9528,
|
||
|
|
"mean_token_accuracy": 0.14500485807657243,
|
||
|
|
"num_tokens": 4664840.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.058202457427979,
|
||
|
|
"epoch": 0.20500725689404933,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998525066613181,
|
||
|
|
"loss": 5.9537,
|
||
|
|
"mean_token_accuracy": 0.14941285997629167,
|
||
|
|
"num_tokens": 4675508.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049920320510864,
|
||
|
|
"epoch": 0.20546081277213352,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998513329525038,
|
||
|
|
"loss": 5.8734,
|
||
|
|
"mean_token_accuracy": 0.15032386034727097,
|
||
|
|
"num_tokens": 4685995.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.082958173751831,
|
||
|
|
"epoch": 0.2059143686502177,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998501545937066,
|
||
|
|
"loss": 5.9052,
|
||
|
|
"mean_token_accuracy": 0.14433911442756653,
|
||
|
|
"num_tokens": 4696659.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0467150688171385,
|
||
|
|
"epoch": 0.20636792452830188,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000499848971584951,
|
||
|
|
"loss": 5.8595,
|
||
|
|
"mean_token_accuracy": 0.15614939630031585,
|
||
|
|
"num_tokens": 4706438.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930180215835572,
|
||
|
|
"epoch": 0.20682148040638607,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998477839262611,
|
||
|
|
"loss": 5.8678,
|
||
|
|
"mean_token_accuracy": 0.1469499036669731,
|
||
|
|
"num_tokens": 4716402.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050282192230225,
|
||
|
|
"epoch": 0.20727503628447025,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.000499846591617662,
|
||
|
|
"loss": 5.9457,
|
||
|
|
"mean_token_accuracy": 0.1466635584831238,
|
||
|
|
"num_tokens": 4728488.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.057934761047363,
|
||
|
|
"epoch": 0.20772859216255443,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998453946591779,
|
||
|
|
"loss": 5.976,
|
||
|
|
"mean_token_accuracy": 0.14741047471761703,
|
||
|
|
"num_tokens": 4738693.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.034505462646484,
|
||
|
|
"epoch": 0.20818214804063861,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998441930508339,
|
||
|
|
"loss": 5.8617,
|
||
|
|
"mean_token_accuracy": 0.149900358915329,
|
||
|
|
"num_tokens": 4748895.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12192120552063,
|
||
|
|
"epoch": 0.2086357039187228,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998429867926547,
|
||
|
|
"loss": 5.9731,
|
||
|
|
"mean_token_accuracy": 0.1417195826768875,
|
||
|
|
"num_tokens": 4760135.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1114363193511965,
|
||
|
|
"epoch": 0.20908925979680695,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998417758846651,
|
||
|
|
"loss": 6.0106,
|
||
|
|
"mean_token_accuracy": 0.1492314174771309,
|
||
|
|
"num_tokens": 4769935.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163050842285156,
|
||
|
|
"epoch": 0.20954281567489114,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998405603268903,
|
||
|
|
"loss": 5.9454,
|
||
|
|
"mean_token_accuracy": 0.14845321476459503,
|
||
|
|
"num_tokens": 4779520.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973990440368652,
|
||
|
|
"epoch": 0.20999637155297532,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998393401193554,
|
||
|
|
"loss": 5.8416,
|
||
|
|
"mean_token_accuracy": 0.15259672403335572,
|
||
|
|
"num_tokens": 4791256.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966838359832764,
|
||
|
|
"epoch": 0.2104499274310595,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998381152620857,
|
||
|
|
"loss": 5.811,
|
||
|
|
"mean_token_accuracy": 0.15300733894109725,
|
||
|
|
"num_tokens": 4801334.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96552734375,
|
||
|
|
"epoch": 0.21090348330914369,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998368857551067,
|
||
|
|
"loss": 5.7882,
|
||
|
|
"mean_token_accuracy": 0.15469710677862167,
|
||
|
|
"num_tokens": 4811361.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016611623764038,
|
||
|
|
"epoch": 0.21135703918722787,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004998356515984433,
|
||
|
|
"loss": 5.85,
|
||
|
|
"mean_token_accuracy": 0.1501396507024765,
|
||
|
|
"num_tokens": 4821190.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.041166496276856,
|
||
|
|
"epoch": 0.21181059506531205,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998344127921213,
|
||
|
|
"loss": 5.8821,
|
||
|
|
"mean_token_accuracy": 0.1504140943288803,
|
||
|
|
"num_tokens": 4830694.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997649621963501,
|
||
|
|
"epoch": 0.21226415094339623,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004998331693361666,
|
||
|
|
"loss": 5.8687,
|
||
|
|
"mean_token_accuracy": 0.1483940526843071,
|
||
|
|
"num_tokens": 4841344.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003773546218872,
|
||
|
|
"epoch": 0.21271770682148042,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998319212306046,
|
||
|
|
"loss": 5.8398,
|
||
|
|
"mean_token_accuracy": 0.14764055758714675,
|
||
|
|
"num_tokens": 4851161.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979840612411499,
|
||
|
|
"epoch": 0.21317126269956457,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000499830668475461,
|
||
|
|
"loss": 5.831,
|
||
|
|
"mean_token_accuracy": 0.1507522940635681,
|
||
|
|
"num_tokens": 4860740.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.029822587966919,
|
||
|
|
"epoch": 0.21362481857764876,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499829411070762,
|
||
|
|
"loss": 5.856,
|
||
|
|
"mean_token_accuracy": 0.147916804254055,
|
||
|
|
"num_tokens": 4871733.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999858570098877,
|
||
|
|
"epoch": 0.21407837445573294,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998281490165335,
|
||
|
|
"loss": 5.9117,
|
||
|
|
"mean_token_accuracy": 0.14421676099300385,
|
||
|
|
"num_tokens": 4883617.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.043055486679077,
|
||
|
|
"epoch": 0.21453193033381712,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004998268823128016,
|
||
|
|
"loss": 5.8607,
|
||
|
|
"mean_token_accuracy": 0.14836216866970062,
|
||
|
|
"num_tokens": 4894519.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004064750671387,
|
||
|
|
"epoch": 0.2149854862119013,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004998256109595923,
|
||
|
|
"loss": 5.8134,
|
||
|
|
"mean_token_accuracy": 0.14691278859972953,
|
||
|
|
"num_tokens": 4904965.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955627918243408,
|
||
|
|
"epoch": 0.2154390420899855,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998243349569323,
|
||
|
|
"loss": 5.7279,
|
||
|
|
"mean_token_accuracy": 0.157587631046772,
|
||
|
|
"num_tokens": 4914618.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92179274559021,
|
||
|
|
"epoch": 0.21589259796806967,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998230543048477,
|
||
|
|
"loss": 5.7896,
|
||
|
|
"mean_token_accuracy": 0.15410214364528657,
|
||
|
|
"num_tokens": 4924341.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918932485580444,
|
||
|
|
"epoch": 0.21634615384615385,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499821769003365,
|
||
|
|
"loss": 5.7633,
|
||
|
|
"mean_token_accuracy": 0.15452138409018518,
|
||
|
|
"num_tokens": 4934231.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887126874923706,
|
||
|
|
"epoch": 0.21679970972423804,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998204790525109,
|
||
|
|
"loss": 5.7905,
|
||
|
|
"mean_token_accuracy": 0.1511450305581093,
|
||
|
|
"num_tokens": 4944303.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001142930984497,
|
||
|
|
"epoch": 0.2172532656023222,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998191844523119,
|
||
|
|
"loss": 5.8693,
|
||
|
|
"mean_token_accuracy": 0.15268588662147523,
|
||
|
|
"num_tokens": 4954571.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.987411212921143,
|
||
|
|
"epoch": 0.21770682148040638,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000499817885202795,
|
||
|
|
"loss": 5.848,
|
||
|
|
"mean_token_accuracy": 0.14666955098509787,
|
||
|
|
"num_tokens": 4964418.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03399133682251,
|
||
|
|
"epoch": 0.21816037735849056,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998165813039869,
|
||
|
|
"loss": 5.8291,
|
||
|
|
"mean_token_accuracy": 0.1442165307700634,
|
||
|
|
"num_tokens": 4975036.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994223356246948,
|
||
|
|
"epoch": 0.21861393323657474,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004998152727559145,
|
||
|
|
"loss": 5.9302,
|
||
|
|
"mean_token_accuracy": 0.14429473355412484,
|
||
|
|
"num_tokens": 4985272.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.091732931137085,
|
||
|
|
"epoch": 0.21906748911465893,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000499813959558605,
|
||
|
|
"loss": 5.8548,
|
||
|
|
"mean_token_accuracy": 0.15049488544464112,
|
||
|
|
"num_tokens": 4995187.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026802444458008,
|
||
|
|
"epoch": 0.2195210449927431,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004998126417120856,
|
||
|
|
"loss": 5.9175,
|
||
|
|
"mean_token_accuracy": 0.15209949463605882,
|
||
|
|
"num_tokens": 5005013.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094258975982666,
|
||
|
|
"epoch": 0.2199746008708273,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004998113192163835,
|
||
|
|
"loss": 5.9259,
|
||
|
|
"mean_token_accuracy": 0.14370185285806655,
|
||
|
|
"num_tokens": 5016789.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985634708404541,
|
||
|
|
"epoch": 0.22042815674891147,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499809992071526,
|
||
|
|
"loss": 5.8749,
|
||
|
|
"mean_token_accuracy": 0.15012458711862564,
|
||
|
|
"num_tokens": 5026913.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017763757705689,
|
||
|
|
"epoch": 0.22088171262699566,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998086602775406,
|
||
|
|
"loss": 5.9623,
|
||
|
|
"mean_token_accuracy": 0.1502877563238144,
|
||
|
|
"num_tokens": 5037501.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990037059783935,
|
||
|
|
"epoch": 0.2213352685050798,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004998073238344547,
|
||
|
|
"loss": 5.8105,
|
||
|
|
"mean_token_accuracy": 0.144505974650383,
|
||
|
|
"num_tokens": 5048478.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0197502136230465,
|
||
|
|
"epoch": 0.221788824383164,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004998059827422962,
|
||
|
|
"loss": 5.8716,
|
||
|
|
"mean_token_accuracy": 0.13962874338030815,
|
||
|
|
"num_tokens": 5059118.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010491847991943,
|
||
|
|
"epoch": 0.22224238026124818,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998046370010926,
|
||
|
|
"loss": 5.8321,
|
||
|
|
"mean_token_accuracy": 0.15523343831300734,
|
||
|
|
"num_tokens": 5070180.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002876043319702,
|
||
|
|
"epoch": 0.22269593613933236,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998032866108718,
|
||
|
|
"loss": 5.8404,
|
||
|
|
"mean_token_accuracy": 0.15497579723596572,
|
||
|
|
"num_tokens": 5079912.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.074828386306763,
|
||
|
|
"epoch": 0.22314949201741655,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998019315716618,
|
||
|
|
"loss": 5.9112,
|
||
|
|
"mean_token_accuracy": 0.15170105695724487,
|
||
|
|
"num_tokens": 5090549.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936306381225586,
|
||
|
|
"epoch": 0.22360304789550073,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998005718834905,
|
||
|
|
"loss": 5.767,
|
||
|
|
"mean_token_accuracy": 0.15424081236124038,
|
||
|
|
"num_tokens": 5100880.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983072996139526,
|
||
|
|
"epoch": 0.2240566037735849,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997992075463862,
|
||
|
|
"loss": 5.8865,
|
||
|
|
"mean_token_accuracy": 0.1511937439441681,
|
||
|
|
"num_tokens": 5111796.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071778011322022,
|
||
|
|
"epoch": 0.2245101596516691,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997978385603769,
|
||
|
|
"loss": 5.8722,
|
||
|
|
"mean_token_accuracy": 0.14768328070640563,
|
||
|
|
"num_tokens": 5123468.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959640073776245,
|
||
|
|
"epoch": 0.22496371552975328,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004997964649254911,
|
||
|
|
"loss": 5.8051,
|
||
|
|
"mean_token_accuracy": 0.15414749532938005,
|
||
|
|
"num_tokens": 5132925.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989591789245606,
|
||
|
|
"epoch": 0.22541727140783743,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997950866417572,
|
||
|
|
"loss": 5.8777,
|
||
|
|
"mean_token_accuracy": 0.1485254153609276,
|
||
|
|
"num_tokens": 5143445.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.993931770324707,
|
||
|
|
"epoch": 0.22587082728592162,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004997937037092034,
|
||
|
|
"loss": 5.8058,
|
||
|
|
"mean_token_accuracy": 0.14833374321460724,
|
||
|
|
"num_tokens": 5153176.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067162322998047,
|
||
|
|
"epoch": 0.2263243831640058,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004997923161278587,
|
||
|
|
"loss": 5.8445,
|
||
|
|
"mean_token_accuracy": 0.14823048263788224,
|
||
|
|
"num_tokens": 5162765.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973460483551025,
|
||
|
|
"epoch": 0.22677793904208998,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997909238977514,
|
||
|
|
"loss": 5.8977,
|
||
|
|
"mean_token_accuracy": 0.150830414891243,
|
||
|
|
"num_tokens": 5173390.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978850793838501,
|
||
|
|
"epoch": 0.22723149492017417,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004997895270189108,
|
||
|
|
"loss": 5.8062,
|
||
|
|
"mean_token_accuracy": 0.1472632072865963,
|
||
|
|
"num_tokens": 5184212.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894932794570923,
|
||
|
|
"epoch": 0.22768505079825835,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997881254913653,
|
||
|
|
"loss": 5.7866,
|
||
|
|
"mean_token_accuracy": 0.14934516549110413,
|
||
|
|
"num_tokens": 5194311.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951768064498902,
|
||
|
|
"epoch": 0.22813860667634253,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997867193151441,
|
||
|
|
"loss": 5.7758,
|
||
|
|
"mean_token_accuracy": 0.1520687684416771,
|
||
|
|
"num_tokens": 5204708.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.913540315628052,
|
||
|
|
"epoch": 0.22859216255442671,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004997853084902763,
|
||
|
|
"loss": 5.7608,
|
||
|
|
"mean_token_accuracy": 0.15067852139472962,
|
||
|
|
"num_tokens": 5214566.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952923536300659,
|
||
|
|
"epoch": 0.2290457184325109,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004997838930167911,
|
||
|
|
"loss": 5.8035,
|
||
|
|
"mean_token_accuracy": 0.15393685698509216,
|
||
|
|
"num_tokens": 5224762.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007725048065185,
|
||
|
|
"epoch": 0.22949927431059505,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997824728947176,
|
||
|
|
"loss": 5.8629,
|
||
|
|
"mean_token_accuracy": 0.14823582395911217,
|
||
|
|
"num_tokens": 5235146.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064925336837769,
|
||
|
|
"epoch": 0.22995283018867924,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997810481240853,
|
||
|
|
"loss": 5.8276,
|
||
|
|
"mean_token_accuracy": 0.1468263030052185,
|
||
|
|
"num_tokens": 5243867.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916410827636719,
|
||
|
|
"epoch": 0.23040638606676342,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004997796187049238,
|
||
|
|
"loss": 5.7346,
|
||
|
|
"mean_token_accuracy": 0.1514027461409569,
|
||
|
|
"num_tokens": 5254279.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060354948043823,
|
||
|
|
"epoch": 0.2308599419448476,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997781846372623,
|
||
|
|
"loss": 5.8574,
|
||
|
|
"mean_token_accuracy": 0.14669395685195924,
|
||
|
|
"num_tokens": 5264769.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961148881912232,
|
||
|
|
"epoch": 0.23131349782293179,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004997767459211307,
|
||
|
|
"loss": 5.8023,
|
||
|
|
"mean_token_accuracy": 0.14596094489097594,
|
||
|
|
"num_tokens": 5274291.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.973608541488647,
|
||
|
|
"epoch": 0.23176705370101597,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997753025565587,
|
||
|
|
"loss": 5.751,
|
||
|
|
"mean_token_accuracy": 0.15511572808027269,
|
||
|
|
"num_tokens": 5284366.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983015012741089,
|
||
|
|
"epoch": 0.23222060957910015,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004997738545435763,
|
||
|
|
"loss": 5.8651,
|
||
|
|
"mean_token_accuracy": 0.14840636104345323,
|
||
|
|
"num_tokens": 5294494.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.955273532867432,
|
||
|
|
"epoch": 0.23267416545718433,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997724018822133,
|
||
|
|
"loss": 5.8663,
|
||
|
|
"mean_token_accuracy": 0.14921268746256827,
|
||
|
|
"num_tokens": 5305606.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.970898771286011,
|
||
|
|
"epoch": 0.23312772133526852,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004997709445724996,
|
||
|
|
"loss": 5.856,
|
||
|
|
"mean_token_accuracy": 0.1487169645726681,
|
||
|
|
"num_tokens": 5315677.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.037318992614746,
|
||
|
|
"epoch": 0.23358127721335267,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997694826144656,
|
||
|
|
"loss": 5.9139,
|
||
|
|
"mean_token_accuracy": 0.14366162866353988,
|
||
|
|
"num_tokens": 5326453.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969986534118652,
|
||
|
|
"epoch": 0.23403483309143686,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004997680160081414,
|
||
|
|
"loss": 5.805,
|
||
|
|
"mean_token_accuracy": 0.15401693433523178,
|
||
|
|
"num_tokens": 5337591.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923111820220948,
|
||
|
|
"epoch": 0.23448838896952104,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004997665447535573,
|
||
|
|
"loss": 5.798,
|
||
|
|
"mean_token_accuracy": 0.15265310406684876,
|
||
|
|
"num_tokens": 5349400.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.048951911926269,
|
||
|
|
"epoch": 0.23494194484760522,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997650688507438,
|
||
|
|
"loss": 5.7909,
|
||
|
|
"mean_token_accuracy": 0.1504625990986824,
|
||
|
|
"num_tokens": 5359984.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.95233383178711,
|
||
|
|
"epoch": 0.2353955007256894,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997635882997314,
|
||
|
|
"loss": 5.8509,
|
||
|
|
"mean_token_accuracy": 0.15640779882669448,
|
||
|
|
"num_tokens": 5369254.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96616530418396,
|
||
|
|
"epoch": 0.2358490566037736,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997621031005507,
|
||
|
|
"loss": 5.7868,
|
||
|
|
"mean_token_accuracy": 0.15061139017343522,
|
||
|
|
"num_tokens": 5379648.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9050251007080075,
|
||
|
|
"epoch": 0.23630261248185777,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004997606132532325,
|
||
|
|
"loss": 5.7438,
|
||
|
|
"mean_token_accuracy": 0.1579679898917675,
|
||
|
|
"num_tokens": 5390321.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978159952163696,
|
||
|
|
"epoch": 0.23675616835994195,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004997591187578075,
|
||
|
|
"loss": 5.7975,
|
||
|
|
"mean_token_accuracy": 0.15755213797092438,
|
||
|
|
"num_tokens": 5401078.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922601938247681,
|
||
|
|
"epoch": 0.23720972423802614,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004997576196143067,
|
||
|
|
"loss": 5.7705,
|
||
|
|
"mean_token_accuracy": 0.15626103281974793,
|
||
|
|
"num_tokens": 5411977.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.919599151611328,
|
||
|
|
"epoch": 0.2376632801161103,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499756115822761,
|
||
|
|
"loss": 5.7429,
|
||
|
|
"mean_token_accuracy": 0.14914836585521699,
|
||
|
|
"num_tokens": 5422967.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0454573154449465,
|
||
|
|
"epoch": 0.23811683599419448,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997546073832015,
|
||
|
|
"loss": 5.7987,
|
||
|
|
"mean_token_accuracy": 0.16146147549152373,
|
||
|
|
"num_tokens": 5432260.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874481344223023,
|
||
|
|
"epoch": 0.23857039187227866,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004997530942956595,
|
||
|
|
"loss": 5.7685,
|
||
|
|
"mean_token_accuracy": 0.15337550789117813,
|
||
|
|
"num_tokens": 5441706.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.954086065292358,
|
||
|
|
"epoch": 0.23902394775036284,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997515765601662,
|
||
|
|
"loss": 5.7734,
|
||
|
|
"mean_token_accuracy": 0.16176194995641707,
|
||
|
|
"num_tokens": 5452397.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8905235767364506,
|
||
|
|
"epoch": 0.23947750362844702,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004997500541767531,
|
||
|
|
"loss": 5.732,
|
||
|
|
"mean_token_accuracy": 0.15274471640586854,
|
||
|
|
"num_tokens": 5463762.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96301908493042,
|
||
|
|
"epoch": 0.2399310595065312,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004997485271454516,
|
||
|
|
"loss": 5.8042,
|
||
|
|
"mean_token_accuracy": 0.14668141603469848,
|
||
|
|
"num_tokens": 5474622.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9286675453186035,
|
||
|
|
"epoch": 0.2403846153846154,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004997469954662933,
|
||
|
|
"loss": 5.7846,
|
||
|
|
"mean_token_accuracy": 0.1540173590183258,
|
||
|
|
"num_tokens": 5484697.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.917514657974243,
|
||
|
|
"epoch": 0.24083817126269957,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997454591393097,
|
||
|
|
"loss": 5.7995,
|
||
|
|
"mean_token_accuracy": 0.15156363248825072,
|
||
|
|
"num_tokens": 5496433.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03740963935852,
|
||
|
|
"epoch": 0.24129172714078376,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004997439181645329,
|
||
|
|
"loss": 5.9087,
|
||
|
|
"mean_token_accuracy": 0.14503674134612082,
|
||
|
|
"num_tokens": 5507917.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.060143232345581,
|
||
|
|
"epoch": 0.2417452830188679,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997423725419945,
|
||
|
|
"loss": 5.8745,
|
||
|
|
"mean_token_accuracy": 0.14898139089345933,
|
||
|
|
"num_tokens": 5519159.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.990707302093506,
|
||
|
|
"epoch": 0.2421988388969521,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997408222717267,
|
||
|
|
"loss": 5.8503,
|
||
|
|
"mean_token_accuracy": 0.15473444908857345,
|
||
|
|
"num_tokens": 5529180.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912744617462158,
|
||
|
|
"epoch": 0.24265239477503628,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004997392673537612,
|
||
|
|
"loss": 5.7518,
|
||
|
|
"mean_token_accuracy": 0.1590703994035721,
|
||
|
|
"num_tokens": 5539363.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.91375207901001,
|
||
|
|
"epoch": 0.24310595065312046,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004997377077881306,
|
||
|
|
"loss": 5.8534,
|
||
|
|
"mean_token_accuracy": 0.15084453225135802,
|
||
|
|
"num_tokens": 5549841.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941425514221192,
|
||
|
|
"epoch": 0.24355950653120464,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004997361435748668,
|
||
|
|
"loss": 5.7527,
|
||
|
|
"mean_token_accuracy": 0.1558105766773224,
|
||
|
|
"num_tokens": 5560299.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983996868133545,
|
||
|
|
"epoch": 0.24401306240928883,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004997345747140024,
|
||
|
|
"loss": 5.818,
|
||
|
|
"mean_token_accuracy": 0.1520366132259369,
|
||
|
|
"num_tokens": 5571081.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.893987655639648,
|
||
|
|
"epoch": 0.244466618287373,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004997330012055695,
|
||
|
|
"loss": 5.7623,
|
||
|
|
"mean_token_accuracy": 0.1579376369714737,
|
||
|
|
"num_tokens": 5581389.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.951496028900147,
|
||
|
|
"epoch": 0.2449201741654572,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997314230496011,
|
||
|
|
"loss": 5.7861,
|
||
|
|
"mean_token_accuracy": 0.14917654246091844,
|
||
|
|
"num_tokens": 5592347.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928359746932983,
|
||
|
|
"epoch": 0.24537373004354138,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004997298402461296,
|
||
|
|
"loss": 5.7622,
|
||
|
|
"mean_token_accuracy": 0.1548761934041977,
|
||
|
|
"num_tokens": 5603411.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997703504562378,
|
||
|
|
"epoch": 0.24582728592162553,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004997282527951876,
|
||
|
|
"loss": 5.7484,
|
||
|
|
"mean_token_accuracy": 0.1618112340569496,
|
||
|
|
"num_tokens": 5614615.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.855966997146607,
|
||
|
|
"epoch": 0.24628084179970972,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997266606968081,
|
||
|
|
"loss": 5.7219,
|
||
|
|
"mean_token_accuracy": 0.1555338978767395,
|
||
|
|
"num_tokens": 5624582.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.882028532028198,
|
||
|
|
"epoch": 0.2467343976777939,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004997250639510241,
|
||
|
|
"loss": 5.7521,
|
||
|
|
"mean_token_accuracy": 0.1485395088791847,
|
||
|
|
"num_tokens": 5634310.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959417104721069,
|
||
|
|
"epoch": 0.24718795355587808,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997234625578684,
|
||
|
|
"loss": 5.8284,
|
||
|
|
"mean_token_accuracy": 0.1493539556860924,
|
||
|
|
"num_tokens": 5644018.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905500411987305,
|
||
|
|
"epoch": 0.24764150943396226,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004997218565173742,
|
||
|
|
"loss": 5.7685,
|
||
|
|
"mean_token_accuracy": 0.15543410778045655,
|
||
|
|
"num_tokens": 5653592.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.994117975234985,
|
||
|
|
"epoch": 0.24809506531204645,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997202458295748,
|
||
|
|
"loss": 5.829,
|
||
|
|
"mean_token_accuracy": 0.15618719160556793,
|
||
|
|
"num_tokens": 5662812.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947774648666382,
|
||
|
|
"epoch": 0.24854862119013063,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997186304945034,
|
||
|
|
"loss": 5.7997,
|
||
|
|
"mean_token_accuracy": 0.15028751492500306,
|
||
|
|
"num_tokens": 5672939.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8947399139404295,
|
||
|
|
"epoch": 0.24900217706821481,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004997170105121935,
|
||
|
|
"loss": 5.7789,
|
||
|
|
"mean_token_accuracy": 0.15528277158737183,
|
||
|
|
"num_tokens": 5683350.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.005437898635864,
|
||
|
|
"epoch": 0.249455732946299,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004997153858826786,
|
||
|
|
"loss": 5.8528,
|
||
|
|
"mean_token_accuracy": 0.1439196802675724,
|
||
|
|
"num_tokens": 5694516.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938060188293457,
|
||
|
|
"epoch": 0.24990928882438315,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997137566059922,
|
||
|
|
"loss": 5.6847,
|
||
|
|
"mean_token_accuracy": 0.15682510733604432,
|
||
|
|
"num_tokens": 5705443.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872813892364502,
|
||
|
|
"epoch": 0.25036284470246734,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997121226821681,
|
||
|
|
"loss": 5.7821,
|
||
|
|
"mean_token_accuracy": 0.15022583901882172,
|
||
|
|
"num_tokens": 5715933.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.941016101837159,
|
||
|
|
"epoch": 0.25081640058055155,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00049971048411124,
|
||
|
|
"loss": 5.8439,
|
||
|
|
"mean_token_accuracy": 0.14352803230285643,
|
||
|
|
"num_tokens": 5726630.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003946161270141,
|
||
|
|
"epoch": 0.2512699564586357,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997088408932418,
|
||
|
|
"loss": 5.7792,
|
||
|
|
"mean_token_accuracy": 0.1525881379842758,
|
||
|
|
"num_tokens": 5736890.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.804270029067993,
|
||
|
|
"epoch": 0.25172351233671986,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997071930282076,
|
||
|
|
"loss": 5.6826,
|
||
|
|
"mean_token_accuracy": 0.16186858713626862,
|
||
|
|
"num_tokens": 5747042.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935064744949341,
|
||
|
|
"epoch": 0.25217706821480407,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997055405161712,
|
||
|
|
"loss": 5.7996,
|
||
|
|
"mean_token_accuracy": 0.1525806337594986,
|
||
|
|
"num_tokens": 5757367.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97401123046875,
|
||
|
|
"epoch": 0.2526306240928882,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997038833571671,
|
||
|
|
"loss": 5.8662,
|
||
|
|
"mean_token_accuracy": 0.1486934617161751,
|
||
|
|
"num_tokens": 5769557.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932326173782348,
|
||
|
|
"epoch": 0.25308417997097243,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004997022215512295,
|
||
|
|
"loss": 5.7594,
|
||
|
|
"mean_token_accuracy": 0.1602458581328392,
|
||
|
|
"num_tokens": 5780615.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959806776046753,
|
||
|
|
"epoch": 0.2535377358490566,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004997005550983925,
|
||
|
|
"loss": 5.737,
|
||
|
|
"mean_token_accuracy": 0.15268604904413224,
|
||
|
|
"num_tokens": 5791271.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.863793230056762,
|
||
|
|
"epoch": 0.2539912917271408,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499698883998691,
|
||
|
|
"loss": 5.6886,
|
||
|
|
"mean_token_accuracy": 0.15530947148799895,
|
||
|
|
"num_tokens": 5801117.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.88543930053711,
|
||
|
|
"epoch": 0.25444484760522496,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004996972082521591,
|
||
|
|
"loss": 5.7122,
|
||
|
|
"mean_token_accuracy": 0.1563066676259041,
|
||
|
|
"num_tokens": 5811696.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911672639846802,
|
||
|
|
"epoch": 0.25489840348330917,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996955278588319,
|
||
|
|
"loss": 5.738,
|
||
|
|
"mean_token_accuracy": 0.16307492852210997,
|
||
|
|
"num_tokens": 5822207.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.838271713256836,
|
||
|
|
"epoch": 0.2553519593613933,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004996938428187437,
|
||
|
|
"loss": 5.7025,
|
||
|
|
"mean_token_accuracy": 0.15967562049627304,
|
||
|
|
"num_tokens": 5831927.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887790107727051,
|
||
|
|
"epoch": 0.2558055152394775,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996921531319297,
|
||
|
|
"loss": 5.7578,
|
||
|
|
"mean_token_accuracy": 0.15641293302178383,
|
||
|
|
"num_tokens": 5842093.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887936401367187,
|
||
|
|
"epoch": 0.2562590711175617,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004996904587984246,
|
||
|
|
"loss": 5.704,
|
||
|
|
"mean_token_accuracy": 0.16297227442264556,
|
||
|
|
"num_tokens": 5850551.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.81576018333435,
|
||
|
|
"epoch": 0.25671262699564584,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004996887598182636,
|
||
|
|
"loss": 5.6901,
|
||
|
|
"mean_token_accuracy": 0.15636582523584366,
|
||
|
|
"num_tokens": 5860651.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827975130081176,
|
||
|
|
"epoch": 0.25716618287373005,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996870561914819,
|
||
|
|
"loss": 5.6698,
|
||
|
|
"mean_token_accuracy": 0.15702708512544633,
|
||
|
|
"num_tokens": 5871500.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.840231275558471,
|
||
|
|
"epoch": 0.2576197387518142,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996853479181145,
|
||
|
|
"loss": 5.6725,
|
||
|
|
"mean_token_accuracy": 0.15341195613145828,
|
||
|
|
"num_tokens": 5881523.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9528480052948,
|
||
|
|
"epoch": 0.2580732946298984,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004996836349981969,
|
||
|
|
"loss": 5.8174,
|
||
|
|
"mean_token_accuracy": 0.15260155200958253,
|
||
|
|
"num_tokens": 5891162.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902073764801026,
|
||
|
|
"epoch": 0.2585268505079826,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004996819174317645,
|
||
|
|
"loss": 5.7173,
|
||
|
|
"mean_token_accuracy": 0.1552115336060524,
|
||
|
|
"num_tokens": 5901818.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874346494674683,
|
||
|
|
"epoch": 0.2589804063860668,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004996801952188528,
|
||
|
|
"loss": 5.79,
|
||
|
|
"mean_token_accuracy": 0.15259438008069992,
|
||
|
|
"num_tokens": 5913889.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9258890628814695,
|
||
|
|
"epoch": 0.25943396226415094,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996784683594973,
|
||
|
|
"loss": 5.7571,
|
||
|
|
"mean_token_accuracy": 0.156342051923275,
|
||
|
|
"num_tokens": 5923429.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998136568069458,
|
||
|
|
"epoch": 0.2598875181422351,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996767368537338,
|
||
|
|
"loss": 5.7779,
|
||
|
|
"mean_token_accuracy": 0.15545209050178527,
|
||
|
|
"num_tokens": 5933847.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.854821443557739,
|
||
|
|
"epoch": 0.2603410740203193,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996750007015983,
|
||
|
|
"loss": 5.6677,
|
||
|
|
"mean_token_accuracy": 0.15953482687473297,
|
||
|
|
"num_tokens": 5943874.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.930334520339966,
|
||
|
|
"epoch": 0.26079462989840346,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996732599031264,
|
||
|
|
"loss": 5.7357,
|
||
|
|
"mean_token_accuracy": 0.1538098156452179,
|
||
|
|
"num_tokens": 5953653.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.918991279602051,
|
||
|
|
"epoch": 0.2612481857764877,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004996715144583543,
|
||
|
|
"loss": 5.6866,
|
||
|
|
"mean_token_accuracy": 0.15937823802232742,
|
||
|
|
"num_tokens": 5964039.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940640115737915,
|
||
|
|
"epoch": 0.26170174165457183,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000499669764367318,
|
||
|
|
"loss": 5.8108,
|
||
|
|
"mean_token_accuracy": 0.15168801695108414,
|
||
|
|
"num_tokens": 5974083.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8325118064880375,
|
||
|
|
"epoch": 0.26215529753265604,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004996680096300537,
|
||
|
|
"loss": 5.7435,
|
||
|
|
"mean_token_accuracy": 0.15367064327001573,
|
||
|
|
"num_tokens": 5984629.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8481368064880375,
|
||
|
|
"epoch": 0.2626088534107402,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996662502465978,
|
||
|
|
"loss": 5.6702,
|
||
|
|
"mean_token_accuracy": 0.1644247755408287,
|
||
|
|
"num_tokens": 5994295.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873128223419189,
|
||
|
|
"epoch": 0.2630624092888244,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004996644862169864,
|
||
|
|
"loss": 5.7046,
|
||
|
|
"mean_token_accuracy": 0.15299894511699677,
|
||
|
|
"num_tokens": 6004156.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.876518249511719,
|
||
|
|
"epoch": 0.26351596516690856,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004996627175412563,
|
||
|
|
"loss": 5.7805,
|
||
|
|
"mean_token_accuracy": 0.15570748448371888,
|
||
|
|
"num_tokens": 6014188.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.96129150390625,
|
||
|
|
"epoch": 0.2639695210449927,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000499660944219444,
|
||
|
|
"loss": 5.8435,
|
||
|
|
"mean_token_accuracy": 0.1530625268816948,
|
||
|
|
"num_tokens": 6024879.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.983526945114136,
|
||
|
|
"epoch": 0.2644230769230769,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004996591662515861,
|
||
|
|
"loss": 5.8974,
|
||
|
|
"mean_token_accuracy": 0.15041209682822226,
|
||
|
|
"num_tokens": 6036374.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.880353546142578,
|
||
|
|
"epoch": 0.2648766328011611,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996573836377193,
|
||
|
|
"loss": 5.7655,
|
||
|
|
"mean_token_accuracy": 0.1547638565301895,
|
||
|
|
"num_tokens": 6046432.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.962761545181275,
|
||
|
|
"epoch": 0.2653301886792453,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004996555963778806,
|
||
|
|
"loss": 5.763,
|
||
|
|
"mean_token_accuracy": 0.15179126113653182,
|
||
|
|
"num_tokens": 6056864.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006943416595459,
|
||
|
|
"epoch": 0.26578374455732945,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499653804472107,
|
||
|
|
"loss": 5.7827,
|
||
|
|
"mean_token_accuracy": 0.15777789205312728,
|
||
|
|
"num_tokens": 6067294.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.932409477233887,
|
||
|
|
"epoch": 0.26623730043541366,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996520079204353,
|
||
|
|
"loss": 5.7948,
|
||
|
|
"mean_token_accuracy": 0.15130407512187957,
|
||
|
|
"num_tokens": 6077587.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947808265686035,
|
||
|
|
"epoch": 0.2666908563134978,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000499650206722903,
|
||
|
|
"loss": 5.7315,
|
||
|
|
"mean_token_accuracy": 0.1543162226676941,
|
||
|
|
"num_tokens": 6089306.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.866966199874878,
|
||
|
|
"epoch": 0.267144412191582,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996484008795471,
|
||
|
|
"loss": 5.6891,
|
||
|
|
"mean_token_accuracy": 0.15265745371580125,
|
||
|
|
"num_tokens": 6099651.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.864347743988037,
|
||
|
|
"epoch": 0.2675979680696662,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000499646590390405,
|
||
|
|
"loss": 5.688,
|
||
|
|
"mean_token_accuracy": 0.1571669578552246,
|
||
|
|
"num_tokens": 6110063.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.873627424240112,
|
||
|
|
"epoch": 0.26805152394775034,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004996447752555142,
|
||
|
|
"loss": 5.7144,
|
||
|
|
"mean_token_accuracy": 0.15664682239294053,
|
||
|
|
"num_tokens": 6120031.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.848915719985962,
|
||
|
|
"epoch": 0.26850507982583455,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004996429554749122,
|
||
|
|
"loss": 5.7616,
|
||
|
|
"mean_token_accuracy": 0.15996424555778505,
|
||
|
|
"num_tokens": 6131274.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9580456733703615,
|
||
|
|
"epoch": 0.2689586357039187,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996411310486367,
|
||
|
|
"loss": 5.8021,
|
||
|
|
"mean_token_accuracy": 0.1580547109246254,
|
||
|
|
"num_tokens": 6140878.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.900578355789184,
|
||
|
|
"epoch": 0.2694121915820029,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004996393019767253,
|
||
|
|
"loss": 5.7986,
|
||
|
|
"mean_token_accuracy": 0.15211150646209717,
|
||
|
|
"num_tokens": 6152229.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.871568775177002,
|
||
|
|
"epoch": 0.26986574746008707,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004996374682592158,
|
||
|
|
"loss": 5.6994,
|
||
|
|
"mean_token_accuracy": 0.15565146058797835,
|
||
|
|
"num_tokens": 6162311.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.939528369903565,
|
||
|
|
"epoch": 0.2703193033381713,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996356298961463,
|
||
|
|
"loss": 5.8077,
|
||
|
|
"mean_token_accuracy": 0.15412216633558273,
|
||
|
|
"num_tokens": 6172806.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.916967105865479,
|
||
|
|
"epoch": 0.27077285921625543,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004996337868875549,
|
||
|
|
"loss": 5.774,
|
||
|
|
"mean_token_accuracy": 0.15645444989204407,
|
||
|
|
"num_tokens": 6183479.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928597736358642,
|
||
|
|
"epoch": 0.27122641509433965,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004996319392334792,
|
||
|
|
"loss": 5.7363,
|
||
|
|
"mean_token_accuracy": 0.1543424740433693,
|
||
|
|
"num_tokens": 6194201.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853014802932739,
|
||
|
|
"epoch": 0.2716799709724238,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000499630086933958,
|
||
|
|
"loss": 5.6793,
|
||
|
|
"mean_token_accuracy": 0.15483027845621108,
|
||
|
|
"num_tokens": 6204774.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.876689767837524,
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004996282299890292,
|
||
|
|
"loss": 5.6781,
|
||
|
|
"mean_token_accuracy": 0.15287237316370011,
|
||
|
|
"num_tokens": 6215056.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27213352685050796,
|
||
|
|
"eval_entropy": 5.712364828856282,
|
||
|
|
"eval_loss": 5.759267330169678,
|
||
|
|
"eval_mean_token_accuracy": 0.1617233954799863,
|
||
|
|
"eval_num_tokens": 6215056.0,
|
||
|
|
"eval_runtime": 21.065,
|
||
|
|
"eval_samples_per_second": 1678.618,
|
||
|
|
"eval_steps_per_second": 209.827,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 110230,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1338598636093440.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|