|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9976905311778291, |
|
"eval_steps": 100, |
|
"global_step": 297, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.33592273777031284, |
|
"eval_accuracy": 0.30284854622865065, |
|
"eval_loss": 4.374380111694336, |
|
"eval_runtime": 59.2892, |
|
"eval_samples_per_second": 16.883, |
|
"eval_steps_per_second": 8.45, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.6718454755406257, |
|
"eval_accuracy": 0.3460089712594723, |
|
"eval_loss": 4.067607879638672, |
|
"eval_runtime": 59.2586, |
|
"eval_samples_per_second": 16.892, |
|
"eval_steps_per_second": 8.454, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.9976905311778291, |
|
"step": 297, |
|
"total_flos": 4.406810464349061e+17, |
|
"train_loss": 4.514452385179924, |
|
"train_runtime": 3834.9386, |
|
"train_samples_per_second": 4.967, |
|
"train_steps_per_second": 0.077 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 297, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 200, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.406810464349061e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|