|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 75, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.5416666666666666, |
|
"eval_loss": 0.6833394169807434, |
|
"eval_runtime": 1.6468, |
|
"eval_samples_per_second": 58.294, |
|
"eval_steps_per_second": 14.574, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.5625, |
|
"eval_loss": 1.2481266260147095, |
|
"eval_runtime": 1.672, |
|
"eval_samples_per_second": 57.415, |
|
"eval_steps_per_second": 14.354, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.6041666666666666, |
|
"eval_loss": 1.7170292139053345, |
|
"eval_runtime": 1.7763, |
|
"eval_samples_per_second": 54.045, |
|
"eval_steps_per_second": 13.511, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 75, |
|
"total_flos": 0.0, |
|
"train_loss": 0.5482939656575521, |
|
"train_runtime": 190.4657, |
|
"train_samples_per_second": 1.575, |
|
"train_steps_per_second": 0.394 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 75, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 0.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|