|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0016355287161099578, |
|
"eval_steps": 10, |
|
"global_step": 13, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00012580990123922753, |
|
"eval_loss": 1.046350121498108, |
|
"eval_runtime": 460.9411, |
|
"eval_samples_per_second": 7.261, |
|
"eval_steps_per_second": 3.632, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0006290495061961376, |
|
"grad_norm": 3.190112829208374, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9941, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0012580990123922753, |
|
"grad_norm": 0.6102684140205383, |
|
"learning_rate": 0.0001, |
|
"loss": 0.8414, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0012580990123922753, |
|
"eval_loss": 1.001396894454956, |
|
"eval_runtime": 474.1232, |
|
"eval_samples_per_second": 7.059, |
|
"eval_steps_per_second": 3.531, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 13, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3652889390088192.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|