| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010294685368678419, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002058937073735684, | |
| "grad_norm": 1.33009934425354, | |
| "learning_rate": 1e-05, | |
| "loss": 39.0267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002058937073735684, | |
| "eval_loss": 2.536212682723999, | |
| "eval_runtime": 104.9222, | |
| "eval_samples_per_second": 7.796, | |
| "eval_steps_per_second": 3.898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004117874147471368, | |
| "grad_norm": 1.3979864120483398, | |
| "learning_rate": 2e-05, | |
| "loss": 40.9222, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004117874147471368, | |
| "eval_loss": 2.534588575363159, | |
| "eval_runtime": 29.3576, | |
| "eval_samples_per_second": 27.863, | |
| "eval_steps_per_second": 13.932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006176811221207052, | |
| "grad_norm": 1.4818819761276245, | |
| "learning_rate": 3e-05, | |
| "loss": 40.1928, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008235748294942736, | |
| "grad_norm": 1.505240559577942, | |
| "learning_rate": 4e-05, | |
| "loss": 38.817, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008235748294942736, | |
| "eval_loss": 2.5333926677703857, | |
| "eval_runtime": 29.4792, | |
| "eval_samples_per_second": 27.748, | |
| "eval_steps_per_second": 13.874, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010294685368678419, | |
| "grad_norm": 1.3221640586853027, | |
| "learning_rate": 5e-05, | |
| "loss": 40.167, | |
| "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": 5537747422937088.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |