|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 13.215859030837004, |
|
"eval_steps": 500, |
|
"global_step": 300, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001958997722095672, |
|
"loss": 2.0853, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00019134396355353076, |
|
"loss": 1.3615, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00018678815489749431, |
|
"loss": 0.9669, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00018223234624145787, |
|
"loss": 0.812, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00017767653758542142, |
|
"loss": 0.5919, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.00017312072892938497, |
|
"loss": 0.3963, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 0.00016856492027334853, |
|
"loss": 0.3623, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.00016400911161731208, |
|
"loss": 0.2111, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.00015945330296127563, |
|
"loss": 0.2065, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 0.0001548974943052392, |
|
"loss": 0.1298, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 0.00015034168564920274, |
|
"loss": 0.1439, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 0.0001457858769931663, |
|
"loss": 0.1188, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"learning_rate": 0.00014123006833712985, |
|
"loss": 0.1068, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 6.17, |
|
"learning_rate": 0.0001366742596810934, |
|
"loss": 0.1007, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 6.61, |
|
"learning_rate": 0.00013211845102505695, |
|
"loss": 0.0901, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 0.0001275626423690205, |
|
"loss": 0.0886, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 7.49, |
|
"learning_rate": 0.00012300683371298406, |
|
"loss": 0.0746, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 7.93, |
|
"learning_rate": 0.0001184510250569476, |
|
"loss": 0.0798, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 8.37, |
|
"learning_rate": 0.00011389521640091117, |
|
"loss": 0.0655, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 8.81, |
|
"learning_rate": 0.00010933940774487472, |
|
"loss": 0.068, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 9.25, |
|
"learning_rate": 0.00010478359908883827, |
|
"loss": 0.0633, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 9.69, |
|
"learning_rate": 0.00010022779043280184, |
|
"loss": 0.0604, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 10.13, |
|
"learning_rate": 9.567198177676538e-05, |
|
"loss": 0.0642, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 10.57, |
|
"learning_rate": 9.111617312072893e-05, |
|
"loss": 0.0566, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 11.01, |
|
"learning_rate": 8.656036446469249e-05, |
|
"loss": 0.0578, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 11.45, |
|
"learning_rate": 8.200455580865604e-05, |
|
"loss": 0.0504, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 11.89, |
|
"learning_rate": 7.74487471526196e-05, |
|
"loss": 0.0606, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 12.33, |
|
"learning_rate": 7.289293849658315e-05, |
|
"loss": 0.0497, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 12.78, |
|
"learning_rate": 6.83371298405467e-05, |
|
"loss": 0.0524, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 13.22, |
|
"learning_rate": 6.378132118451025e-05, |
|
"loss": 0.057, |
|
"step": 300 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 440, |
|
"num_train_epochs": 20, |
|
"save_steps": 100, |
|
"total_flos": 2.630622497248051e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|