|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.015384615384615385, |
|
"eval_steps": 10, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.006153846153846154, |
|
"eval_loss": 1.4845428466796875, |
|
"eval_runtime": 1.2728, |
|
"eval_samples_per_second": 89.569, |
|
"eval_steps_per_second": 4.714, |
|
"step": 2 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 325, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 5, |
|
"total_flos": 321671273644032.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|