|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.999322340185227, |
|
"global_step": 2212, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 4.311557788944724e-05, |
|
"loss": 1.8701, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"exact_match": 79.49858088930937, |
|
"f1": 87.56398459706838, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 3.057788944723618e-05, |
|
"loss": 0.9835, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"exact_match": 82.90444654683066, |
|
"f1": 89.73526941390388, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 1.801507537688442e-05, |
|
"loss": 0.7131, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"exact_match": 83.78429517502366, |
|
"f1": 90.6613951393689, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 5.452261306532663e-06, |
|
"loss": 0.6276, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"exact_match": 84.1438032166509, |
|
"f1": 90.984962516233, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"step": 2212, |
|
"total_flos": 1.36249422804523e+17, |
|
"train_runtime": 3222.535, |
|
"train_samples_per_second": 0.686 |
|
} |
|
], |
|
"max_steps": 2212, |
|
"num_train_epochs": 2, |
|
"total_flos": 1.36249422804523e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|