| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2551440329218107, | |
| "eval_steps": 500, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9996629653035128e-05, | |
| "loss": 1.3337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9915854864676665e-05, | |
| "loss": 1.5296, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.966483553946637e-05, | |
| "loss": 1.3001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9251166435386837e-05, | |
| "loss": 1.1836, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.868180920098644e-05, | |
| "loss": 1.1287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.796634556457236e-05, | |
| "loss": 1.093, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.7116816083045603e-05, | |
| "loss": 1.0771, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.0666340589523315, | |
| "eval_runtime": 6.8061, | |
| "eval_samples_per_second": 146.926, | |
| "eval_steps_per_second": 1.175, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "step": 31, | |
| "total_flos": 50905428787200.0, | |
| "train_loss": 1.2071462215915802, | |
| "train_runtime": 1490.1678, | |
| "train_samples_per_second": 41.583, | |
| "train_steps_per_second": 0.081 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 121, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 50905428787200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |