| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.6994049549102783, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.8261, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.021863408386707306, | |
| "eval_runtime": 14.7955, | |
| "eval_samples_per_second": 40.553, | |
| "eval_steps_per_second": 10.138, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.3775118589401245, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0428, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.010692029260098934, | |
| "eval_runtime": 22.0677, | |
| "eval_samples_per_second": 27.189, | |
| "eval_steps_per_second": 6.797, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.30723807215690613, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0259, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.01044970378279686, | |
| "eval_runtime": 24.6966, | |
| "eval_samples_per_second": 24.295, | |
| "eval_steps_per_second": 6.074, | |
| "step": 1800 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3000, | |
| "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": 1101016439193600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |