| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005184705119896306, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010369410239792613, | |
| "grad_norm": 6.6360368728637695, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010369410239792613, | |
| "eval_loss": 0.848354697227478, | |
| "eval_runtime": 94.818, | |
| "eval_samples_per_second": 17.138, | |
| "eval_steps_per_second": 8.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020738820479585226, | |
| "grad_norm": 5.302432060241699, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8162, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020738820479585226, | |
| "eval_loss": 0.7812278866767883, | |
| "eval_runtime": 19.6903, | |
| "eval_samples_per_second": 82.528, | |
| "eval_steps_per_second": 41.289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031108230719377834, | |
| "grad_norm": 3.5102508068084717, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7571, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004147764095917045, | |
| "grad_norm": 3.6251587867736816, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7907, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004147764095917045, | |
| "eval_loss": 0.6997274160385132, | |
| "eval_runtime": 19.6009, | |
| "eval_samples_per_second": 82.904, | |
| "eval_steps_per_second": 41.478, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005184705119896306, | |
| "grad_norm": 2.5546457767486572, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7225, | |
| "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": 306895210414080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |