| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1203, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.41562759767248547, | |
| "grad_norm": 368394.84375, | |
| "learning_rate": 1.833748960931006e-05, | |
| "loss": 0.7077, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8312551953449709, | |
| "grad_norm": 38091.30078125, | |
| "learning_rate": 1.6674979218620116e-05, | |
| "loss": 0.4632, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.3516891300678253, | |
| "eval_runtime": 35.1495, | |
| "eval_samples_per_second": 14.054, | |
| "eval_steps_per_second": 1.764, | |
| "step": 1203 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6015, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 5860001780858880.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |