| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011409013120365089, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022818026240730175, | |
| "grad_norm": 2.3938968181610107, | |
| "learning_rate": 1e-05, | |
| "loss": 2.7759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022818026240730175, | |
| "eval_loss": 3.1060092449188232, | |
| "eval_runtime": 183.4111, | |
| "eval_samples_per_second": 4.029, | |
| "eval_steps_per_second": 2.017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004563605248146035, | |
| "grad_norm": 1.942126750946045, | |
| "learning_rate": 2e-05, | |
| "loss": 2.686, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004563605248146035, | |
| "eval_loss": 3.057384490966797, | |
| "eval_runtime": 20.5146, | |
| "eval_samples_per_second": 36.023, | |
| "eval_steps_per_second": 18.036, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0068454078722190535, | |
| "grad_norm": 1.8215091228485107, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00912721049629207, | |
| "grad_norm": 1.2940646409988403, | |
| "learning_rate": 4e-05, | |
| "loss": 2.139, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00912721049629207, | |
| "eval_loss": 2.9904003143310547, | |
| "eval_runtime": 21.0621, | |
| "eval_samples_per_second": 35.087, | |
| "eval_steps_per_second": 17.567, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011409013120365089, | |
| "grad_norm": 2.6347923278808594, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3303, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 802638189821952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |