|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.09280033341437155, |
|
"global_step": 8016, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.9999768462241983e-05, |
|
"loss": 1.7563, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9884694196506097e-05, |
|
"loss": 1.6983, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.9768925317496153e-05, |
|
"loss": 1.6678, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9537387559476264e-05, |
|
"loss": 1.6488, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9306081339214394e-05, |
|
"loss": 1.6092, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.9074775118952524e-05, |
|
"loss": 1.6189, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.8843237360932635e-05, |
|
"loss": 1.603, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.8611699602912747e-05, |
|
"loss": 1.5877, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.8380161844892858e-05, |
|
"loss": 1.5702, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.8148855624630988e-05, |
|
"loss": 1.5832, |
|
"step": 8000 |
|
} |
|
], |
|
"max_steps": 86379, |
|
"num_train_epochs": 1, |
|
"total_flos": 1.4927762414370816e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|