|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 15.0, |
|
"global_step": 77325, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 4.3533785968315555e-05, |
|
"loss": 2.2903, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 3.706757193663111e-05, |
|
"loss": 2.0218, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 3.0601357904946654e-05, |
|
"loss": 1.9077, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 7.76, |
|
"learning_rate": 2.4135143873262206e-05, |
|
"loss": 1.8285, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 9.7, |
|
"learning_rate": 1.766892984157776e-05, |
|
"loss": 1.7738, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 11.64, |
|
"learning_rate": 1.1202715809893308e-05, |
|
"loss": 1.7327, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 13.58, |
|
"learning_rate": 4.736501778208859e-06, |
|
"loss": 1.7067, |
|
"step": 70000 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"step": 77325, |
|
"total_flos": 4.04095424790528e+16, |
|
"train_loss": 1.875084553326059, |
|
"train_runtime": 7135.6528, |
|
"train_samples_per_second": 21.673, |
|
"train_steps_per_second": 10.836 |
|
} |
|
], |
|
"max_steps": 77325, |
|
"num_train_epochs": 15, |
|
"total_flos": 4.04095424790528e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|