|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0621348911311737, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9393939393939395e-05, |
|
"loss": 1.9406, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.8585858585858588e-05, |
|
"loss": 1.9925, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 1.7777777777777777e-05, |
|
"loss": 1.9952, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1.6969696969696972e-05, |
|
"loss": 1.9616, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 1.616161616161616e-05, |
|
"loss": 2.0246, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.5353535353535354e-05, |
|
"loss": 1.9661, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.4545454545454546e-05, |
|
"loss": 1.9318, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.3737373737373739e-05, |
|
"loss": 1.9104, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.2929292929292931e-05, |
|
"loss": 1.9786, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.2121212121212122e-05, |
|
"loss": 1.9611, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.1313131313131314e-05, |
|
"loss": 1.9473, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.0505050505050507e-05, |
|
"loss": 1.9428, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 9.696969696969698e-06, |
|
"loss": 1.899, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.888888888888888e-06, |
|
"loss": 1.9273, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 8.08080808080808e-06, |
|
"loss": 1.9628, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 7.272727272727273e-06, |
|
"loss": 1.9621, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 6.464646464646466e-06, |
|
"loss": 1.949, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 5.656565656565657e-06, |
|
"loss": 1.9522, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.848484848484849e-06, |
|
"loss": 1.9618, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.04040404040404e-06, |
|
"loss": 1.9464, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.232323232323233e-06, |
|
"loss": 1.9332, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 2.4242424242424244e-06, |
|
"loss": 1.9209, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 1.6161616161616164e-06, |
|
"loss": 1.9663, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 8.080808080808082e-07, |
|
"loss": 1.9469, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0, |
|
"loss": 1.947, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 500, |
|
"num_train_epochs": 2, |
|
"save_steps": 20, |
|
"total_flos": 1.89836833062912e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|