{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 2000.0,
"global_step": 40511,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 6.16979269496545e-06,
"loss": 1.3917,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.23395853899309e-05,
"loss": 1.0351,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 1.8509378084896346e-05,
"loss": 0.9747,
"step": 1500
},
{
"epoch": 0.05,
"learning_rate": 2.46791707798618e-05,
"loss": 0.9373,
"step": 2000
},
{
"epoch": 0.06,
"learning_rate": 3.084896347482725e-05,
"loss": 0.9124,
"step": 2500
},
{
"epoch": 0.07,
"learning_rate": 3.701875616979269e-05,
"loss": 0.8946,
"step": 3000
},
{
"epoch": 0.09,
"learning_rate": 4.318854886475814e-05,
"loss": 0.8819,
"step": 3500
},
{
"epoch": 0.1,
"learning_rate": 4.93583415597236e-05,
"loss": 0.8723,
"step": 4000
},
{
"epoch": 0.11,
"learning_rate": 4.9385611234537426e-05,
"loss": 0.8615,
"step": 4500
},
{
"epoch": 0.12,
"learning_rate": 4.869990948736938e-05,
"loss": 0.8553,
"step": 5000
},
{
"epoch": 0.14,
"learning_rate": 4.801420774020132e-05,
"loss": 0.8466,
"step": 5500
},
{
"epoch": 0.15,
"learning_rate": 4.732850599303327e-05,
"loss": 0.8412,
"step": 6000
},
{
"epoch": 0.16,
"learning_rate": 4.6642804245865215e-05,
"loss": 0.8331,
"step": 6500
},
{
"epoch": 0.17,
"learning_rate": 4.5957102498697166e-05,
"loss": 0.8252,
"step": 7000
},
{
"epoch": 0.19,
"learning_rate": 4.527140075152912e-05,
"loss": 0.8164,
"step": 7500
},
{
"epoch": 0.2,
"learning_rate": 4.458569900436107e-05,
"loss": 0.8139,
"step": 8000
},
{
"epoch": 0.21,
"learning_rate": 4.389999725719302e-05,
"loss": 0.8072,
"step": 8500
},
{
"epoch": 0.22,
"learning_rate": 4.321429551002496e-05,
"loss": 0.8096,
"step": 9000
},
{
"epoch": 0.23,
"learning_rate": 4.252859376285691e-05,
"loss": 0.8026,
"step": 9500
},
{
"epoch": 0.25,
"learning_rate": 4.1842892015688856e-05,
"loss": 0.8027,
"step": 10000
},
{
"epoch": 0.26,
"learning_rate": 4.115719026852081e-05,
"loss": 0.7952,
"step": 10500
},
{
"epoch": 0.27,
"learning_rate": 4.047148852135275e-05,
"loss": 0.7936,
"step": 11000
},
{
"epoch": 0.28,
"learning_rate": 3.97857867741847e-05,
"loss": 0.7913,
"step": 11500
},
{
"epoch": 0.3,
"learning_rate": 3.910008502701665e-05,
"loss": 0.7896,
"step": 12000
},
{
"epoch": 0.31,
"learning_rate": 3.8414383279848596e-05,
"loss": 0.7857,
"step": 12500
},
{
"epoch": 0.32,
"learning_rate": 3.7728681532680547e-05,
"loss": 0.7842,
"step": 13000
},
{
"epoch": 0.33,
"learning_rate": 3.70429797855125e-05,
"loss": 0.7813,
"step": 13500
},
{
"epoch": 0.35,
"learning_rate": 3.635727803834445e-05,
"loss": 0.7812,
"step": 14000
},
{
"epoch": 0.36,
"learning_rate": 3.567157629117639e-05,
"loss": 0.7793,
"step": 14500
},
{
"epoch": 0.37,
"learning_rate": 3.498587454400834e-05,
"loss": 0.7721,
"step": 15000
},
{
"epoch": 0.38,
"learning_rate": 3.4300172796840286e-05,
"loss": 0.7726,
"step": 15500
},
{
"epoch": 0.39,
"learning_rate": 3.361447104967224e-05,
"loss": 0.7714,
"step": 16000
},
{
"epoch": 0.41,
"learning_rate": 3.292876930250419e-05,
"loss": 0.7737,
"step": 16500
},
{
"epoch": 0.42,
"learning_rate": 3.224306755533613e-05,
"loss": 0.7661,
"step": 17000
},
{
"epoch": 0.43,
"learning_rate": 3.155736580816808e-05,
"loss": 0.7675,
"step": 17500
},
{
"epoch": 0.44,
"learning_rate": 3.0871664061000026e-05,
"loss": 0.7688,
"step": 18000
},
{
"epoch": 0.46,
"learning_rate": 3.0185962313831976e-05,
"loss": 0.7637,
"step": 18500
},
{
"epoch": 0.47,
"learning_rate": 2.9500260566663924e-05,
"loss": 0.7644,
"step": 19000
},
{
"epoch": 0.48,
"learning_rate": 2.8814558819495874e-05,
"loss": 0.7632,
"step": 19500
},
{
"epoch": 0.49,
"learning_rate": 2.8128857072327825e-05,
"loss": 0.7607,
"step": 20000
},
{
"epoch": 0.51,
"learning_rate": 2.744315532515977e-05,
"loss": 0.7614,
"step": 20500
},
{
"epoch": 0.52,
"learning_rate": 2.675745357799172e-05,
"loss": 0.7602,
"step": 21000
},
{
"epoch": 0.53,
"learning_rate": 2.6071751830823667e-05,
"loss": 0.7564,
"step": 21500
},
{
"epoch": 0.54,
"learning_rate": 2.5386050083655617e-05,
"loss": 0.7574,
"step": 22000
},
{
"epoch": 0.56,
"learning_rate": 2.4700348336487565e-05,
"loss": 0.7534,
"step": 22500
},
{
"epoch": 0.57,
"learning_rate": 2.4014646589319512e-05,
"loss": 0.7567,
"step": 23000
},
{
"epoch": 0.58,
"learning_rate": 2.332894484215146e-05,
"loss": 0.7534,
"step": 23500
},
{
"epoch": 0.59,
"learning_rate": 2.2643243094983406e-05,
"loss": 0.7555,
"step": 24000
},
{
"epoch": 0.6,
"learning_rate": 2.1957541347815357e-05,
"loss": 0.7534,
"step": 24500
},
{
"epoch": 0.62,
"learning_rate": 2.1271839600647304e-05,
"loss": 0.7475,
"step": 25000
},
{
"epoch": 0.63,
"learning_rate": 2.058613785347925e-05,
"loss": 0.7482,
"step": 25500
},
{
"epoch": 0.64,
"learning_rate": 1.99004361063112e-05,
"loss": 0.7475,
"step": 26000
},
{
"epoch": 0.65,
"learning_rate": 1.9214734359143146e-05,
"loss": 0.7479,
"step": 26500
},
{
"epoch": 0.67,
"learning_rate": 1.8529032611975096e-05,
"loss": 0.7433,
"step": 27000
},
{
"epoch": 0.68,
"learning_rate": 1.7843330864807044e-05,
"loss": 0.7473,
"step": 27500
},
{
"epoch": 0.69,
"learning_rate": 1.7157629117638994e-05,
"loss": 0.7439,
"step": 28000
},
{
"epoch": 0.7,
"learning_rate": 1.647192737047094e-05,
"loss": 0.7423,
"step": 28500
},
{
"epoch": 0.72,
"learning_rate": 1.578622562330289e-05,
"loss": 0.7429,
"step": 29000
},
{
"epoch": 0.73,
"learning_rate": 1.5100523876134836e-05,
"loss": 0.7424,
"step": 29500
},
{
"epoch": 0.74,
"learning_rate": 1.4414822128966785e-05,
"loss": 0.7408,
"step": 30000
},
{
"epoch": 0.75,
"learning_rate": 1.3729120381798732e-05,
"loss": 0.7402,
"step": 30500
},
{
"epoch": 0.77,
"learning_rate": 1.3043418634630683e-05,
"loss": 0.7376,
"step": 31000
},
{
"epoch": 0.78,
"learning_rate": 1.235771688746263e-05,
"loss": 0.7371,
"step": 31500
},
{
"epoch": 0.79,
"learning_rate": 1.1672015140294577e-05,
"loss": 0.741,
"step": 32000
},
{
"epoch": 0.8,
"learning_rate": 1.0986313393126526e-05,
"loss": 0.7354,
"step": 32500
},
{
"epoch": 0.81,
"learning_rate": 1.0300611645958475e-05,
"loss": 0.7343,
"step": 33000
},
{
"epoch": 0.83,
"learning_rate": 9.614909898790423e-06,
"loss": 0.7357,
"step": 33500
},
{
"epoch": 0.84,
"learning_rate": 8.92920815162237e-06,
"loss": 0.7319,
"step": 34000
},
{
"epoch": 0.85,
"learning_rate": 8.243506404454319e-06,
"loss": 0.7339,
"step": 34500
},
{
"epoch": 0.86,
"learning_rate": 7.557804657286268e-06,
"loss": 0.732,
"step": 35000
},
{
"epoch": 0.88,
"learning_rate": 6.872102910118215e-06,
"loss": 0.7352,
"step": 35500
},
{
"epoch": 0.89,
"learning_rate": 6.186401162950164e-06,
"loss": 0.7364,
"step": 36000
},
{
"epoch": 0.9,
"learning_rate": 5.500699415782112e-06,
"loss": 0.733,
"step": 36500
},
{
"epoch": 0.91,
"learning_rate": 4.814997668614059e-06,
"loss": 0.7318,
"step": 37000
},
{
"epoch": 0.93,
"learning_rate": 4.129295921446008e-06,
"loss": 0.7333,
"step": 37500
},
{
"epoch": 0.94,
"learning_rate": 3.4435941742779558e-06,
"loss": 0.7358,
"step": 38000
},
{
"epoch": 0.95,
"learning_rate": 2.7578924271099047e-06,
"loss": 0.7332,
"step": 38500
},
{
"epoch": 0.96,
"learning_rate": 2.0721906799418528e-06,
"loss": 0.7325,
"step": 39000
},
{
"epoch": 0.98,
"learning_rate": 1.3864889327738007e-06,
"loss": 0.7282,
"step": 39500
},
{
"epoch": 0.99,
"learning_rate": 7.00787185605749e-07,
"loss": 0.731,
"step": 40000
},
{
"epoch": 1.0,
"learning_rate": 1.508543843769714e-08,
"loss": 0.7318,
"step": 40500
},
{
"epoch": 1.0,
"step": 40511,
"total_flos": 1.9760674493693952e+17,
"train_loss": 0.787189019458772,
"train_runtime": 32945.1529,
"train_samples_per_second": 19.674,
"train_steps_per_second": 1.23
}
],
"logging_steps": 500,
"max_steps": 40511,
"num_train_epochs": 1,
"save_steps": 2000,
"total_flos": 1.9760674493693952e+17,
"trial_name": null,
"trial_params": null
}