|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 5, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.106128215789795, |
|
"eval_runtime": 3.7637, |
|
"eval_samples_per_second": 1.328, |
|
"eval_steps_per_second": 0.531, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.106128215789795, |
|
"eval_runtime": 3.8052, |
|
"eval_samples_per_second": 1.314, |
|
"eval_steps_per_second": 0.526, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 1.106128215789795, |
|
"eval_runtime": 3.7193, |
|
"eval_samples_per_second": 1.344, |
|
"eval_steps_per_second": 0.538, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.106128215789795, |
|
"eval_runtime": 3.7501, |
|
"eval_samples_per_second": 1.333, |
|
"eval_steps_per_second": 0.533, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.106128215789795, |
|
"eval_runtime": 3.7785, |
|
"eval_samples_per_second": 1.323, |
|
"eval_steps_per_second": 0.529, |
|
"step": 5 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 7, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 7, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 72683520000.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|