| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012, | |
| "loss": 12.7445, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019555555555555556, | |
| "loss": 11.2951, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 9.9077, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00016888888888888889, | |
| "loss": 8.6537, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 7.7628, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00014222222222222224, | |
| "loss": 7.0578, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00012888888888888892, | |
| "loss": 6.7923, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 6.4867, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00010222222222222222, | |
| "loss": 6.4616, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 6.278, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 6.2509, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 6.1527, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 6.1656, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 6.0661, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 6.0176, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 6.0408, | |
| "step": 144 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 150, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 281424942858240.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |